kevin/deepseek-harness
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into rfc/interactive-side-sessions

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-13 22:16:01 +08:00
committed by GitHub
parent cecc4c82c3 b3e1a4154b
commit 522a570cc7
386 changed files with 27063 additions and 5050 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/dsh-find-simplifications/SKILL.md
+9 -1
View File
@@ -41,6 +41,14 @@ Use parallel subagents when the user asks for breadth or many candidates. Give e
If subagents are unavailable, simulate the same breadth yourself. Do not let the first good candidate stop the survey.
Start with the largest production-code deltas. A broad simplification audit that stops after obvious unused symbols can miss the files where duplicated lifecycle or defensive machinery carries most of the cost.
## Audit Trust And Lifecycle Boundaries
Classify every defensive copy, freeze, validator, and callback capture by the boundary it crosses. Same-process typed service/plugin calls ordinarily borrow readonly values; parser/config, queue, model/tool JSON, durable/file, worker, process, and wire boundaries own or validate data. Tests built around hostile getters, fake typed objects, callback replacement, or mutation after a same-process handoff are evidence of a potentially speculative contract, not automatic justification for keeping it.
For complex asynchronous code, draw the ownership graph and map each sentinel, readiness promise, cancellation path, disposer, and state flag to a distinct owner or transition. When several mechanisms mirror the same liveness or settlement fact, propose one transaction or lifecycle controller instead. Preserve separate machinery where it protects a real boundary: synchronous publication and rollback, callback containment, first-terminal-outcome arbitration, worker/process ownership, or dispose-to-quiescence.
## Prove Or Reject Each Candidate
For every symbol or behavior, classify consumers before writing:
@@ -60,7 +68,7 @@ Reject or downgrade a candidate when:
## Write The RFC
Create one file per durable proposal under `docs/rfc/proposed/yyyy-mm-dd-topic.md` and add it to the Proposed table in `docs/rfc/README.md`. Keep prose paragraphs on one physical line and use relative Markdown links.
Create one file per durable proposal under `docs/rfc/<lifecycle>/<class>/yyyy-mm-dd-topic.md`, following the lifecycle/classification contract in `docs/rfc/README.md`. Regenerate `docs/rfc/INDEX.md`; never add a manual RFC table to the README. Keep prose paragraphs on one physical line and use relative Markdown links.
Prefer this shape, adjusting when the idea needs it:
.github/workflows/ci.yml
+14
View File
@@ -82,6 +82,20 @@ jobs:
- name: Install (immutable)
run: pnpm install --frozen-lockfile
# The snapshot lane REPLAYS the sandbox example's recorded scenarios,
# re-executing their bash calls under a real runner. ubuntu-latest has
# no bubblewrap preinstalled and no built Landlock launcher, so without
# this the confined executions fail closed (SANDBOX_UNAVAILABLE). Same
# install as sandbox.yml's bwrap leg (incl. the Ubuntu 24.04 AppArmor
# userns knob).
- name: Install bubblewrap (unrestrict userns)
if: matrix.lane == 'snapshot'
run: |
sudo apt-get update -q
sudo apt-get install -yq bubblewrap
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
|| echo "apparmor userns knob absent — the functional probe decides"
- uses: actions/cache@v4
if: matrix.lane == 'lint'
with:
.github/workflows/e2e.yml
+14
View File
@@ -82,6 +82,20 @@ jobs:
- name: Install (immutable)
run: pnpm install --frozen-lockfile
# The with-key escalation e2e (examples/sandbox-acp-agent/tests/
# escalation.e2e.ts) self-skips without a usable runner — without this
# step it would never actually execute anywhere (CI had no bwrap, dev
# macs run Seatbelt instead), which is exactly how a broken harness
# composition once survived unseen. Same recipe as ci.yml's bwrap
# steps; the userns knob is best-effort (absent on pre-24.04 kernels,
# the probe decides).
- name: Install bubblewrap (unrestrict userns)
run: |
sudo apt-get update -q
sudo apt-get install -yq bubblewrap
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
|| echo "apparmor userns knob absent — the functional probe decides"
# Guard against a false green: the e2e suites self-skip when the key is
# absent, so a missing/misconfigured secret would otherwise pass as
# "all skipped". This job only runs on trusted events (the `if:` above
.github/workflows/sandbox.yml
+124
View File
@@ -0,0 +1,124 @@
# Sandbox CI: the keyless real-kernel confinement proofs. A separate workflow
# from ci.yml because the axis is different — these jobs fan out over
# OS×runner (kernel capabilities), not node versions. The Landlock launcher
# arrives from the registry with `pnpm install` (the npm package family
# `node-addon-landlock-run`, built and released from its own repository), so
# these legs exercise the true consumer path — nothing is compiled here.
name: Sandbox
on:
push:
branches: [main, master]
pull_request:
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
jobs:
# Keyless real-kernel sandbox proofs (sandbox RFC § Testing): each ladder
# rung is only provable on a host where it enforces, so this job fans out
# an OS×runner matrix — bwrap and Landlock on Linux (separate legs: the
# Landlock files force the bwrap rung off, so each leg proves exactly one
# rung; Landlock twice, once per architecture, each confining through the
# registry-installed launcher), Seatbelt on macOS (sandbox-exec ships with
# the OS). One node
# version only: kernel confinement does not vary by node, and ci.yml's
# node matrix already covers the node axis.
#
# The e2e files self-skip where their runner is absent, so a leg that lost
# its runner (no bwrap, kernel without Landlock, macOS without
# sandbox-exec) would otherwise pass as a false green — the same trap
# e2e.yml's key preflight guards against. Each leg therefore asserts BOTH
# its platform files actually ran: `Test Files 2 passed (2)`, no skips.
sandbox-e2e:
strategy:
fail-fast: false
matrix:
include:
- os: ubuntu-latest
runner: bwrap
- os: ubuntu-24.04
runner: landlock
- os: ubuntu-24.04-arm
runner: landlock
- os: macos-latest
runner: seatbelt
name: sandbox e2e (${{ matrix.runner }}, ${{ matrix.os }})
runs-on: ${{ matrix.os }}
timeout-minutes: 20
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
with:
node-version: 24
- name: Enable corepack (pnpm)
run: corepack enable
- name: Install (immutable)
run: pnpm install --frozen-lockfile
# The bwrap rung needs bubblewrap on PATH and unprivileged user
# namespaces. Ubuntu 24.04 gates the latter behind an AppArmor knob;
# lift it best-effort — on images where the knob is absent the
# functional probe (and the run-guard below) is the arbiter anyway.
- name: Install bubblewrap (unrestrict userns)
if: matrix.runner == 'bwrap'
run: |
sudo apt-get update -q
sudo apt-get install -yq bubblewrap
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
|| echo "apparmor userns knob absent — the functional probe decides"
# The unit suite runs on ubuntu in `checks`; this is the one darwin leg
# in the workflow, so run it here too — the platform-dependent unit
# expectations (Seatbelt path canonicalization: /tmp IS /private/tmp)
# take their darwin branch only on this runner.
- name: Unit tests (darwin parity)
if: matrix.runner == 'seatbelt'
run: pnpm run test
- name: Sandbox e2e (real kernel confinement, world-verified)
# NO_COLOR: vitest force-enables ANSI color under GITHUB_ACTIONS even
# without a TTY, which would thread escape codes through the summary
# line the run-guard greps.
env:
NO_COLOR: 1
run: |
set -u +e -o pipefail
out=$(pnpm exec vitest run --config vitest.e2e.config.ts \
packages/sandbox/sandbox-local/tests/${{ matrix.runner }}.e2e.ts \
packages/bash/bash-sandbox/tests/${{ matrix.runner }}.e2e.ts 2>&1); status=$?
echo "$out"
[ "$status" -eq 0 ]
# Both platform files must have RUN — a self-skip (runner missing on
# the very platform that exists to prove it) is a failure, not a pass.
echo "$out" | grep -qE 'Test Files[[:space:]]+2 passed \(2\)'
# Publish-path rehearsal, Landlock legs only (the pack gates need built
# lib/). The e2e packs the workspace closure, installs the tarballs
# into a throwaway consumer — npm pulling `node-addon-landlock-run`
# and its platform package from the registry, the true consumer path —
# and confines through the INSTALLED launcher, asserting it executable
# apart (a mode-stripped binary must not masquerade as a non-enforcing
# kernel). Same no-silent-skip guard as above.
- name: Build packages (lib/ for the pack rehearsal)
if: matrix.runner == 'landlock'
run: pnpm run build
- name: Packed-distribution e2e (pack → install → confine)
if: matrix.runner == 'landlock'
env:
NO_COLOR: 1
run: |
set -u +e -o pipefail
out=$(pnpm exec vitest run --config vitest.e2e.config.ts \
packages/sandbox/sandbox-local/tests/packed-install.e2e.ts 2>&1); status=$?
echo "$out"
[ "$status" -eq 0 ]
echo "$out" | grep -qE 'Test Files[[:space:]]+1 passed \(1\)'
AGENTS.md
+3 -2
View File
@@ -15,6 +15,7 @@ packages/ Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai
llm/ LLM seam + the DeepSeek adapters (hand-rolled + pi-ai design twin)
bash/ bash executor seam + local impl + model-facing bash tools
fs/ filesystem seam + local impl + policy gate + read/write/edit tools
skill/ skill provider registry + local impl + catalog/loader tool
web/ web seam + search/fetch providers + model-facing web tools
compact/ compaction seam + basic backend
subagent/ subagent seam + spawn/fork/ACP backends + delegation tool
@@ -24,7 +25,7 @@ packages/ Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai
cordis/ self-referential toolset: the agent inspects/mounts plugins in its own runtime
hooks/ Claude Code / Codex hook bridges + shared wire-protocol library
session-persistence/ persistence seam + JSONL/SQLite backends
ui/ ACP bridge, app-boot glue, stdio/ACP app bins, user-interaction seam, ask-user tool
ui/ ACP bridge, app-boot glue, stdio/ACP app bins, user-approval and user-interaction seams, ask-user tool
support/ dev/test infrastructure packages
util/ zero-dependency utilities
examples/ Runnable demos: thin cordis.yml leaves over the app packages (see examples/AGENTS.md)
@@ -71,7 +72,7 @@ pnpm run hygiene
out=$(printf 'echo ci smoke\n' | pnpm run demo:echo 2>&1)
printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})'
printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE'
ls .sessions/_no-cwd/main-session-*.jsonl >/dev/null
test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)"
rm -rf .sessions
pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts
```
docs/agent-lifecycle.md
+1
View File
@@ -39,6 +39,7 @@ sequenceDiagram
Tools-->>Session: tool-owned events when applicable
Driver->>Session: <code>tool/result</code> and <code>step/end</code>
Driver->>Hooks: <code>agent/turn-continuation</code> waterfall
Driver->>Hooks: <code>agent/turn-stop</code> serial terminal checkpoint
Driver->>Session: <code>turn/end</code>
Driver->>Persistence: <code>session/flush</code> parallel checkpoint
Driver-->>SDK: <code>agent/status</code> idle
docs/architecture.md
+28 -19
View File
@@ -1,19 +1,18 @@
# DeepSeek Harness Architecture
The project is an SDK for building agent harnesses. The idea is to have **everything as a plugin**. For example, the agent loop is just one plugin shipped by default.
The **DeepSeek Harness SDK** builds agent harnesses on Cordis. The principle is simple: **everything is a plugin**. The shipped loop is one plugin, not a privileged kernel.
## Overview
The project is based on [Cordis](cordis-primer.md).
A harness is one [Cordis](cordis-primer.md) context. Packages contribute service keys, typed events, and disposable registrations: services expose stable calls (`ctx.llm`, `ctx.tools`, `ctx.sessions`), events provide interception and notifications (`agent/request`, `tools/pre-execute`, `session/event`), and registrations install prompt sections, tools, providers, adapters, or listeners.
A running harness is one Cordis context. Packages contribute service keys, typed events, and disposable registrations to that context. Services provides stable call signatures (`ctx.llm`, `ctx.tools`, `ctx.sessions`); events are interception and notification points (`agent/request`, `tools/pre-execute`, `session/event`); registrations install prompt sections, tool schemas, providers, adapters, and listeners.
Composition is preferred over inheritance. `packages/core/` is a repository grouping for the default agent flow; capability around it are equally first-class plugins from a Cordis perspective.
`packages/core/` groups the default agent flow; surrounding capabilities are equally first-class Cordis plugins.
### Default Services
| ctx key | Package | Role |
|---|---|---|
| — | [`dsh-scope`](../packages/core/scope/README.md) | scoped-context registration primitive (library) |
| `ctx.sessions` | `dsh-session` | in-memory event-sourced sessions |
| `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables |
| `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) |
@@ -26,8 +25,10 @@ Composition is preferred over inheritance. `packages/core/` is a repository grou
|---|---|---|
| `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls |
| `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution |
| `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) |
| `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution |
| `ctx.fs` | [`fs/`](../packages/fs/README.md) | filesystem provider primitives and policy events |
| `ctx.skills` | [`skill/`](../packages/skill/README.md) | skill provider registry and progressive disclosure |
| `ctx.web` | [`web/`](../packages/web/README.md) | search/fetch provider registries |
| `ctx.compact` | [`compact/`](../packages/compact/README.md) | session-log compaction |
| `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers |
@@ -36,12 +37,10 @@ Composition is preferred over inheritance. `packages/core/` is a repository grou
## Event
Events are the harness extension API used by Service. The generated [events catalog](cordis-catalog/events.md) is the exhaustive reference. The [producer/consumer map](event-producer-consumer.md) shows which packages emit or listen to each event.
Events form the service extension API; see the exhaustive [events catalog](cordis-catalog/events.md) and [producer/consumer map](event-producer-consumer.md).
### Event Domains
Pick the event domain for new behavior:
- **Session events** are durable, replayable facts. Turn and step boundaries, user input, assistant output, tool calls, tool results, steering, compaction records, and tool-owned durable facts append to the session log and flow through `session/event`.
- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, call-config shaping, result validation, and continuation policy.
- **Capability events** belong to the seam that owns the action. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` let policy and adapters attach without importing the loop.
@@ -52,14 +51,16 @@ Waterfall events behave like around-middleware: a listener delegates by calling
## Default Loop Lifecycle
The shipped loop drains queued work, assembles a request, streams a model answer, executes tools, decides whether to continue, and checkpoints durable state. The important part is where it pauses: each pause is a documented service call or event that another plugin can use.
The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins.
A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points.
### Turn Flow
```text
create agent -> emit agent/session-start(source)
prepare private session + agent.ctx -> await unpublished setup
-> enter session + agent -> session/created -> agent/created
-> enable driving -> agent/session-start(source) -> start driver
forever:
wait for queued messages
emit agent/status(running)
@@ -81,19 +82,20 @@ forever:
'assistant/message'
each tool call:
'tool/call'
tools/pre-execute -> tools/execute -> tools/post-execute
tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result
'tool/result'
append post-tool context and steering
'step/end'
agent/turn-continuation
agent/turn-stop (terminal policy)
stop unless tools or continuation policy ask for another step
'turn/end'
checkpoint persistence and notify idle/running status
```
Prompt assembly is single-path: `renderPrompt(assemble({ agent }))` IS the system prompt sent to the model. Plugins contribute ordered sections (static or computed from the per-call `AssembleContext`), tool schemas, and named variables interpolated as `{{name}}` at render — strictly, so an unknown or valueless reference fails the turn instead of shipping a hole. `dsh-system-prompt` owns the openers — the static `harness:identity` section (order −100) and the deployment's persona (order 0, its `persona` config, shared context-wide) — while the shipped loop registers the `model`/`cwd` variables; prompt-fact ownership is pinned by the [prompt-variables RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
Prompt assembly is single-path: the loop sends `renderPrompt(await assemble(assembleContextFor(agent)))`; the helper couples the explicit agent and scope. Plugins contribute ordered sections, tool schemas, and named variables interpolated as `{{name}}` at render — strictly, so an unknown or valueless reference fails the turn instead of shipping a hole. `dsh-system-prompt` owns the openers — the static `harness:identity` section (order −100) and the deployment's global default persona (order 0, shadowable by a same-named agent-scoped section) — while the loop registers the `model`/`cwd` variables; prompt-fact ownership is pinned by the [prompt-variables RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; leftover steering after a turn is re-queued as ordinary input.
Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved.
### Failure Boundaries
@@ -103,7 +105,11 @@ Every session event is turn-enclosed. Reloading a crashed session preserves the
### Agent Handles
`ctx.agents` owns live agents and returns an `AgentHandle { agent, dispose() }`. `Agent` is the API other plugins drive: `send()` queues work, `steer()` injects mid-turn content, `inject()` appends context and opens a one-shot injection turn when idle, `cancel()` is the public stop primitive, and `whenIdle()` observes quiescence. Lifecycle owners tear down with `await dispose()`.
`ctx.agents` owns live agents and returns an `AgentHandle { agent, dispose() }`. `Agent` is the API other plugins drive: `send()` queues work, `steer()` injects mid-turn content, `inject()` appends context and opens a one-shot injection turn when idle, `cancel()` is the public stop primitive, and `whenIdle()` observes quiescence. The caller fiber and concrete factory provider structurally co-own programmatic lifecycles; a consumer handle is the only non-structural teardown capability, and every owner reaches the same awaited disposer.
### Agent Scope
Every live agent owns `agent.ctx` ([`dsh-scope`](../packages/core/scope/README.md), keyed by the agent). Its registrations are visible only to that agent, shadow same-named globals, and unwind with it. Its listeners hear only that agent's dispatches; an opaque carrier routes while the real subject stays explicit. `CreateAgentOptions.setup(agentCtx)` composes this world before publication and does not drive. Dev invariants and `verify-scoped-dispatch` keep carrier/subject identity aligned with event declarations. Rationale: [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent `persona`, `toolFilter`, and `maxDepth` are the separate [composition-controls feature](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md).
## State
@@ -125,13 +131,13 @@ Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAs
### Capability Pattern
A swappable capability usually splits into **interface / implementation / consumer**: the interface owns the `ctx` key and event names; an implementation registers a backend; a consumer exposes model-facing behavior through `ctx.tools` or prompt assembly. The bash trio is the reference shape, and the [capability graph](capability-seams.md) shows the current package families.
A swappable capability usually splits into **interface / implementation / consumer**: the interface owns its `ctx` key and events, an implementation registers a backend, and a consumer exposes model behavior through tools or prompts. Bash is the reference; the [capability graph](capability-seams.md) shows every family.
Some cases bend the template deliberately. LLM keeps interface and consumer event names together because adapters are the implementations. Filesystem adds policy checks around provider primitives. Web is one service with search and fetch provider registries, so provider swaps do not rename model tools. Subagents use a named provider registry because multiple delegation backends can coexist; `spawn` starts fresh, `fork` seeds from the parent's completed-turn prefix, and ACP can drive an out-of-process child ([subagent.md](core-data-structures/subagent.md)).
Some seams bend the template deliberately. LLM keeps interface and consumer vocabulary together because adapters are the implementations. Filesystem adds policy gates around provider primitives. Web is one service with search and fetch provider registries, so provider swaps do not rename model tools. Skills and subagents use named provider registries; local skills scan project/user roots, and other providers can add embedded or remote catalogs without registry/tool changes. Subagents spawn fresh, fork from the parent's completed-turn prefix, or use ACP children ([subagent.md](core-data-structures/subagent.md)).
### Bundles And Apps
`dsh-agent-core` is the default bundle: one plugin loading the agent loop ([README](../packages/core/agent-core/README.md)). App packages compose it with a front end and own the entrypoint `bin`: `dsh-stdio-agent` for the terminal REPL, and `dsh-acp-agent` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
`dsh-agent-core` is the default composition bundle: one plugin loading the shared spine ([README](../packages/core/agent-core/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-agent` for terminal REPL, and `dsh-acp-agent` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)).
### Where New Behavior Goes
@@ -143,17 +149,20 @@ New behavior should attach to a documented extension point; changing the shipped
| Add a model-facing capability | register a tool on `ctx.tools`; schemas flow into prompt assembly |
| Add command execution | implement and register a `ctx.bash` backend |
| Add filesystem access or policy | implement a `ctx.fs` provider or listen on `fs/*` policy events |
| Intercept prompts, requests, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` waterfall |
| Confine spawned processes | a `ctx.sandbox` backend; consumers wrap their argv before spawning |
| Intercept prompts, requests, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` waterfall; use serial `agent/turn-stop` for a monotonic terminal stop |
| Add a session-stable request prefix outside history | compose it on `agent/session-prefix`, once per loop instance; logged on the request header |
| Add UI or editor integration | drive `ctx.agents` and render from `session/event` |
| Add durable session state | add a `SessionEventMap` member and render/replay from the log |
| Fork a live session | use `ctx.sessions.fork(source, boundary?, childSessionId?)` |
| Scope a tool, prompt section, or listener to ONE agent | register it through that agent's `agent.ctx` (see Agent Scope) |
The [extension cookbook](cookbook/extension-cookbook.md) carries plugin skeletons and the feature-to-seam map; step-by-step guides cover [packages](cookbook/adding-a-package.md), [tools](cookbook/adding-a-tool.md), [LLM adapters](cookbook/adding-an-llm-adapter.md), and [vendored packages](cookbook/adding-a-vendored-package.md).
## Quick Reference
- Domain terms in the [glossary](glossary.md)
- Type definitions in [core-data-structures/](core-data-structures/core.md)
- Exact event and service signatures in [events](cordis-catalog/events.md)
- [services](cordis-catalog/services.md) catalogs
- package contracts in the [package map](../packages/README.md)
- [RFCs](rfc/README.md)
- [RFCs](rfc/README.md)
docs/capability-seams.md
+28 -3
View File
@@ -29,23 +29,33 @@ flowchart LR
pkg_tools["tools"]
pkg_tool_fs["tool-fs"]
pkg_tool_web["tool-web"]
svc_tools["ctx.tools<br/>Tool registry and execution waterfall"]
svc_tools["ctx.tools<br/>Tool registry and guarded execution pipeline"]
pkg_tool_ask_user["tool-ask-user"]
pkg_tool_bash["tool-bash"]
pkg_tool_cordis["tool-cordis"]
pkg_tool_skill["tool-skill"]
pkg_tool_subagent["tool-subagent"]
pkg_tool_todo["tool-todo"]
pkg_user_interaction["user-interaction"]
svc_userInteraction["ctx.userInteraction<br/>Human question/answer seam"]
pkg_stdio_agent["stdio-agent"]
pkg_skill["skill"]
svc_skills["ctx.skills<br/>Skill provider registry"]
pkg_skill_local["skill-local"]
svc_agents["ctx.agents<br/>Agent registry"]
svc_agentLoop["ctx.agentLoop<br/>Concrete loop driver"]
pkg_agent_core["agent-core"]
pkg_bash["bash"]
svc_bash["ctx.bash<br/>Bash executor seam"]
pkg_bash_local["bash-local"]
pkg_bash_sandbox["bash-sandbox"]
pkg_hooks_claude["hooks-claude"]
pkg_hooks_codex["hooks-codex"]
pkg_sandbox["sandbox"]
svc_sandbox["ctx.sandbox<br/>Process-sandbox seam"]
pkg_sandbox_local["sandbox-local"]
pkg_approval["approval"]
svc_approval["ctx.approval<br/>Approval seam"]
pkg_code_runtime["code-runtime"]
svc_codeRuntime["ctx.codeRuntime<br/>Code-execution seam"]
pkg_code_runtime_worker["code-runtime-worker"]
@@ -71,11 +81,14 @@ flowchart LR
svc_workflows["ctx.workflows<br/>Workflow script engine"]
pkg_workflow_workerthread["workflow-workerthread"]
pkg_tool_workflow["tool-workflow"]
pkg_acp --> svc_approval
pkg_acp --> svc_userInteraction
pkg_agent --> svc_agents
pkg_agent_loop --> svc_agentLoop
pkg_approval --> svc_approval
pkg_bash --> svc_bash
pkg_bash_local --> svc_bash
pkg_bash_sandbox --> svc_bash
pkg_code_runtime --> svc_codeRuntime
pkg_code_runtime_worker --> svc_codeRuntime
pkg_compact --> svc_compact
@@ -86,10 +99,14 @@ flowchart LR
pkg_llm_deepseek --> svc_llm
pkg_llm_pi_ai --> svc_llm
pkg_llm_replay --> svc_llm
pkg_sandbox --> svc_sandbox
pkg_sandbox_local --> svc_sandbox
pkg_session --> svc_sessions
pkg_session_persistence --> svc_sessionPersistence
pkg_session_persistence_jsonl --> svc_sessionPersistence
pkg_session_persistence_sqlite --> svc_sessionPersistence
pkg_skill --> svc_skills
pkg_skill_local --> svc_skills
pkg_stdio_agent --> svc_userInteraction
pkg_subagent --> svc_subagents
pkg_subagent_acp --> svc_subagents
@@ -112,6 +129,8 @@ flowchart LR
svc_agents --> pkg_invariants
svc_agents --> pkg_stdio_agent
svc_agents --> pkg_subagent_inprocess
svc_approval --> pkg_tool_bash
svc_approval --> pkg_tools
svc_bash --> pkg_hooks_claude
svc_bash --> pkg_hooks_codex
svc_bash --> pkg_tool_bash
@@ -120,6 +139,7 @@ flowchart LR
svc_fs --> pkg_tool_fs
svc_llm --> pkg_agent_loop
svc_llm --> pkg_compact_basic
svc_sandbox --> pkg_bash_sandbox
svc_sessionPersistence --> pkg_acp
svc_sessionPersistence --> pkg_agent_loop
svc_sessions --> pkg_agent
@@ -127,6 +147,7 @@ flowchart LR
svc_sessions --> pkg_invariants
svc_sessions --> pkg_session_persistence
svc_sessions --> pkg_subagent_inprocess
svc_skills --> pkg_tool_skill
svc_subagents --> pkg_tool_subagent
svc_systemPrompt --> pkg_agent_loop
svc_systemPrompt --> pkg_tool_fs
@@ -138,6 +159,7 @@ flowchart LR
svc_tools --> pkg_tool_bash
svc_tools --> pkg_tool_cordis
svc_tools --> pkg_tool_fs
svc_tools --> pkg_tool_skill
svc_tools --> pkg_tool_subagent
svc_tools --> pkg_tool_todo
svc_tools --> pkg_tool_web
@@ -155,11 +177,14 @@ flowchart LR
| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. |
| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
| `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. |
| `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers tool definitions, exposes schemas to the prompt, and routes calls through tools/pre-execute and tools/post-execute. |
| `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. |
| `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. |
| `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. |
| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-agent`](../packages/ui/stdio-agent), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. |
| `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-core`](../packages/core/agent-core) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
| `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors can replace bash-local. |
| `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. |
| `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. |
| `ctx.approval` | `seam` | `approval` | [`acp`](../packages/ui/acp) | [`tools`](../packages/core/tools), [`tool-bash`](../packages/bash/tool-bash) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. |
| `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). |
| `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. |
| `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. |
docs/config-catalog.md
+242 -68
View File
@@ -31,7 +31,7 @@ export interface AcpConfig {
Depends on: `Stream` (`@agentclientprotocol/sdk`)
Source: [`packages/ui/acp/src/index.ts:236`](../packages/ui/acp/src/index.ts)
Source: [`packages/ui/acp/src/index.ts:248`](../packages/ui/acp/src/index.ts)
## `@deepseek-ai/dsh-acp-agent`
@@ -56,10 +56,12 @@ export interface Config {
tools?: ToolsConfig
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
persistenceRoot?: string
/** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */
skills?: agentCore.SkillConfig
}
```
Depends on: [`ToolsConfig`](#deepseek-aidsh-tools)
Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
Source: [`packages/ui/acp-agent/src/index.ts:52`](../packages/ui/acp-agent/src/index.ts)
@@ -71,12 +73,12 @@ Source: [`packages/ui/acp-agent/src/index.ts:52`](../packages/ui/acp-agent/src/i
* `agents` to the agent loop (an app that pre-creates no agents, like the ACP
* bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
* plugin (the deployment's persona section and the explicit model-facing tool
* order), the `tools` object to the tool registry (its presentation `mode`).
* Every field is optional INPUT here because each owner's schema
* supplies the default (`[]` / `''` / absent — lexicographic / `native`); the
* schema is the INTERSECTION of the owners' own schemas (the registry's
* nested under its `tools` key), so validation and defaulting can never
* drift from them.
* order), the `tools` object to the tool registry (its presentation `mode`),
* and `skills` to the skill registry/local provider/tool consumer. Every field
* is optional INPUT here because each owner's schema supplies the default;
* the schema is the INTERSECTION of the owners' own schemas (with registry
* schemas nested under their bundle keys), so validation and defaulting can
* never drift from them.
*/
export interface Config {
/** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
@@ -87,40 +89,39 @@ export interface Config {
toolOrder?: SystemPromptConfig['toolOrder']
/** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
tools?: ToolsConfig
/** Skill registry, local provider, and model-facing consumer config. */
skills?: SkillConfig
}
/** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
export interface SkillConfig {
/** Registry-level discovery cache settings. */
registry?: SkillRegistryConfig
/** Local filesystem skill provider settings. */
local?: SkillLocal.Config
/** Model-facing skill catalog and tool settings. */
tool?: toolSkill.Config
}
```
Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`ToolsConfig`](#deepseek-aidsh-tools)
Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts)
Source: [`packages/core/agent-core/src/index.ts:71`](../packages/core/agent-core/src/index.ts)
Source: [`packages/core/agent-core/src/index.ts:87`](../packages/core/agent-core/src/index.ts)
## `@deepseek-ai/dsh-agent-loop`
Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt`
```ts config-catalog
/**
* Plugin config: the agents to create — or resume, via `resumeSessionId` —
* declaratively at startup, so a cordis.yml deployment needs no code.
*/
/** Plugin configuration for declarative startup agents. */
export interface Config {
/** Agents created from configuration at startup. */
/** Agents created or resumed at plugin startup. */
agents: (AgentOptions & {
/** Agent id to register under; also seeds the fresh per-run session id (`${id}-session-<uuid>`). */
/** Registry identity for the live agent. */
id: AgentId
/**
* If set, the config agent RESUMES this persisted session id instead of
* starting a fresh `${id}-session-<uuid>`. Sourced from an env var in
* cordis.yml (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`), so a
* demo can continue a prior conversation without code changes. Requires a
* `dsh-session-persistence` backend; the resume is deferred until that
* service is available (via `ctx.inject`) and the loaded session's events
* seed the live session so history continues.
*
* The schema accepts a plain string at runtime (cordis.yml values are
* untyped); the brand is compile-time only — the config format is the
* boundary where an id enters, so the TYPE declares the brand here.
*/
/** Optional workspace for a fresh session. */
cwd?: string
/** Persisted session to resume instead of creating a fresh session. */
resumeSessionId?: SessionId
})[]
}
@@ -128,7 +129,7 @@ export interface Config {
Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:36`](../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:325`](../packages/core/agent-loop/src/index.ts)
## `@deepseek-ai/dsh-bash-local`
@@ -150,6 +151,33 @@ export interface Config {
Source: [`packages/bash/bash-local/src/index.ts:29`](../packages/bash/bash-local/src/index.ts)
## `@deepseek-ai/dsh-bash-sandbox`
Requires: `sandbox`
```ts config-catalog
/**
* Plugin config: the local executor's knobs plus the sandbox policy. All
* optional — `static Config` supplies the defaults (`mode: 'read-only'` is the
* fail-safe default; an example that wants a workspace-writable agent opts in
* explicitly). The runner choice is NOT configured here: which platform
* backend confines the command is the `ctx.sandbox` provider's config.
*/
export interface Config extends LocalConfig {
/** File-sandbox mode commands run under (default: `read-only`). */
mode?: SandboxMode
/**
* Root directory `workspace-write` mode may write under (default: the
* executor's default working directory — `cwd`, else `process.cwd()`).
*/
workspaceRoot?: string
}
```
Depends on: [`LocalConfig`](#deepseek-aidsh-bash-local) · [`SandboxMode`](core-data-structures/sandbox.md)
Source: [`packages/bash/bash-sandbox/src/index.ts:60`](../packages/bash/bash-sandbox/src/index.ts)
## `@deepseek-ai/dsh-code-runtime-worker`
```ts config-catalog
@@ -300,24 +328,6 @@ export interface Config {
Source: [`packages/hooks/hooks-codex/src/index.ts:43`](../packages/hooks/hooks-codex/src/index.ts)
## `@deepseek-ai/dsh-invariants`
Requires: `sessions`
```ts config-catalog
/** Plugin config. */
export interface Config {
/**
* Deep-freeze logged session-event data so mutating a logged event throws.
* Default true — this plugin only runs in dev/test, where freezing is the
* point. Set false to assert the event contract without freezing.
*/
freeze?: boolean
}
```
Source: [`packages/support/invariants/src/index.ts:45`](../packages/support/invariants/src/index.ts)
## `@deepseek-ai/dsh-llm-deepseek`
Requires: `llm`
@@ -430,6 +440,53 @@ export interface Config {
Source: [`packages/guard/repeat-tool-guard/src/index.ts:55`](../packages/guard/repeat-tool-guard/src/index.ts)
## `@deepseek-ai/dsh-sandbox-local`
```ts config-catalog
/** Plugin config. All optional — `static Config` supplies the defaults. */
export interface Config {
/**
* Override the sandbox runner argv (the bwrap-shaped profile arguments are
* appended). A NON-EMPTY argv is the operator's assertion that this runner
* exists and FULLY enforces the profile (confinement reports
* `enforcement: 'full'`, and — the runner's kernel mechanism being unknown
* — carries both Linux file-denial dialects as its denial signatures) —
* the runner chain and its probes are skipped,
* and a broken runner fails loudly at execution time. The operator also
* supplies {@link runnerFailureSignatures}, which distinguish the runner
* refusing its profile from the wrapped command failing normally.
* Absent (or empty — the schema normalizes an omitted array to `[]`): the
* built-in platform chains — Linux `bwrap` then the Landlock launcher
* (probed in that order), darwin `sandbox-exec` (the sole candidate,
* selected without a probe). Used for custom/alternative runners and
* for deterministic fake runners in keyless test tiers.
*/
runnerCommand?: string[]
/**
* Case-insensitive stderr substrings emitted when a configured
* {@link runnerCommand} refuses its profile before executing the wrapped
* command. Required and non-empty with `runnerCommand`; rejected without
* it. Missing/unexecutable runner errors are added automatically from
* `runnerCommand[0]`, while these signatures cover an executable runner's
* own failure dialect.
*/
runnerFailureSignatures?: string[]
/**
* Per-probe timeout in milliseconds for the chain's functional probes
* (default: 5000; must be a positive finite number — Node treats a 0
* `spawnSync` timeout as UNBOUNDED, so 0 is rejected at construction). A
* probe that exceeds it reads as an unusable rung, so a
* host slow enough to trip the default — cold NFS mounts, heavily loaded
* CI — would otherwise be misclassified `SANDBOX_UNAVAILABLE` with no
* config escape. Bounds ONE probe, and the chain walk runs each at most once
* per provider lifetime.
*/
probeTimeoutMs?: number
}
```
Source: [`packages/sandbox/sandbox-local/src/index.ts:36`](../packages/sandbox/sandbox-local/src/index.ts)
## `@deepseek-ai/dsh-session-persistence-jsonl`
Requires: `sessions`
@@ -483,6 +540,36 @@ export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:50`](../packages/session-persistence/session-persistence-sqlite/src/index.ts)
## `@deepseek-ai/dsh-skill`
```ts config-catalog
/** Skill registry configuration. */
export interface Config {
/** Maximum number of completed cwd/provider catalogs kept in memory. */
readonly collectCacheMaxEntries?: number
}
```
Source: [`packages/skill/skill/src/index.ts:113`](../packages/skill/skill/src/index.ts)
## `@deepseek-ai/dsh-skill-local`
Requires: `skills`
```ts config-catalog
/** Local filesystem skill provider configuration. */
export interface Config {
/** DeepSeek Harness config root. Defaults to `$DSH_HOME` or `~/.dsh`. */
dshHome?: string
/** Shared agent config root. Defaults to `$DSH_AGENTS_HOME` or `~/.agents`. */
agentsHome?: string
/** Additional skill roots scanned after project roots and before user roots. */
customSkillDirs?: string[]
}
```
Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-local/src/index.ts)
## `@deepseek-ai/dsh-stdio-agent`
```ts config-catalog
@@ -492,7 +579,9 @@ Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:5
* {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is
* the deployment persona (forwarded to the system-prompt plugin); `toolOrder`
* is the explicit model-facing tool order (forwarded to the system-prompt plugin);
* `persistenceRoot` is the JSONL backend's directory; `welcome` is the UI banner.
* fresh sessions use `process.cwd()` as their workspace cwd; resumed sessions
* keep their persisted cwd. `persistenceRoot` is the JSONL backend's directory;
* `welcome` is the UI banner.
*/
export interface Config {
/** Model name for the `main` agent (must have a registered adapter). */
@@ -507,6 +596,8 @@ export interface Config {
persistenceRoot?: string
/** stdin-chat banner printed once on start. Defaults to `'ready.'`. */
welcome?: string
/** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */
skills?: agentCore.SkillConfig
/**
* If set, the `main` agent RESUMES this persisted session id instead of
* starting fresh. Sourced from an env var in the leaf `cordis.yml`
@@ -516,9 +607,9 @@ export interface Config {
}
```
Depends on: [`ToolsConfig`](#deepseek-aidsh-tools)
Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools)
Source: [`packages/ui/stdio-agent/src/index.ts:63`](../packages/ui/stdio-agent/src/index.ts)
Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts)
## `@deepseek-ai/dsh-subagent-acp`
@@ -578,7 +669,7 @@ Source: [`packages/subagent/subagent-acp/src/index.ts:30`](../packages/subagent/
## `@deepseek-ai/dsh-subagent-fork`
Requires: `subagents` · `agents`
Requires: `subagents`
```ts config-catalog
/** Config: the registry name to register the provider under. */
@@ -606,9 +697,11 @@ export interface Config {
/** Which start-time capabilities to advertise (default: all `true`). */
capabilities?: Partial<SubagentCapabilities>
/**
* The context contract to declare ({@link SubagentProvider.inheritsParentContext});
* default `false` (spawn-like). Set `true` to exercise the fork-shaped tool
* wording in consumer tests.
* The conversation-history descriptor to declare
* ({@link SubagentProvider.inheritsParentContext}); default `false` (fresh
* conversation). Set `true` to exercise seeded/fork wording in consumer
* tests. This flag says nothing about tool, service, scope, or authority
* inheritance.
*/
inheritsParentContext?: boolean
/**
@@ -621,11 +714,11 @@ export interface Config {
Depends on: [`SubagentCapabilities`](../packages/subagent/subagent/src/index.ts) · [`SubagentStopReason`](../packages/subagent/subagent/src/index.ts)
Source: [`packages/support/subagent-mock/src/index.ts:84`](../packages/support/subagent-mock/src/index.ts)
Source: [`packages/support/subagent-mock/src/index.ts:97`](../packages/support/subagent-mock/src/index.ts)
## `@deepseek-ai/dsh-subagent-spawn`
Requires: `subagents` · `agents`
Requires: `subagents`
```ts config-catalog
/** Config: the registry name to register the provider under. */
@@ -635,7 +728,7 @@ export interface Config {
}
```
Source: [`packages/subagent/subagent-spawn/src/index.ts:36`](../packages/subagent/subagent-spawn/src/index.ts)
Source: [`packages/subagent/subagent-spawn/src/index.ts:35`](../packages/subagent/subagent-spawn/src/index.ts)
## `@deepseek-ai/dsh-system-prompt`
@@ -646,7 +739,10 @@ export interface Config {
* The deployment's persona — the ONE deployment-authored fragment of the
* system prompt, rendered as the order-0 `deployment:persona` section
* (after the harness identity, before all tool guidance). Every agent in
* the context shares it, subagents included. Template, not free-form text:
* the context shares it by default; a per-agent persona is a SCOPED section
* of the same name registered through that agent's `agent.ctx` (it shadows
* this one for that agent — the subagent seam's `persona` request field does
* exactly that). Template, not free-form text:
* every complete `{{…}}` group is interpreted strictly against the
* registered prompt variables (the shipped agent loop registers `{{model}}`
* and `{{cwd}}`), and there is no escape syntax for literal `{{…}}` prose
@@ -681,7 +777,7 @@ export interface Config {
}
```
Source: [`packages/core/system-prompt/src/index.ts:179`](../packages/core/system-prompt/src/index.ts)
Source: [`packages/core/system-prompt/src/index.ts:225`](../packages/core/system-prompt/src/index.ts)
## `@deepseek-ai/dsh-tool-cordis`
@@ -721,6 +817,20 @@ export interface Config {
Source: [`packages/fs/tool-fs/src/index.ts:48`](../packages/fs/tool-fs/src/index.ts)
## `@deepseek-ai/dsh-tool-skill`
Requires: `tools` · `skills`
```ts config-catalog
/** Model-facing skill catalog configuration. */
export interface Config {
/** Maximum normalized description length rendered in the session catalog; minimum 3. */
catalogDescriptionMaxLength?: number
}
```
Source: [`packages/skill/tool-skill/src/index.ts:19`](../packages/skill/tool-skill/src/index.ts)
## `@deepseek-ai/dsh-tool-subagent`
Requires: `tools` · `subagents`
@@ -740,17 +850,47 @@ export interface Config {
toolName?: string
/**
* Default per-child agent options (model) applied to every spawned child.
* Omitted fields fall back to the child loop's own defaults. There is no
* per-child persona: the deployment persona (the system-prompt plugin's
* `persona` config) is a context-wide section every agent shares.
* Omitted fields fall back to the child loop's own defaults.
*/
agentOptions?: AgentOptions
/**
* Per-child persona applied to every child this tool spawns: a scoped
* `deployment:persona` section shadowing the deployment's persona for the
* child alone. Requires the bound provider's `persona` capability
* (in-process backends support it; a request against one that doesn't is
* rejected at start). Omitted ⇒ the child renders the deployment persona.
*/
persona?: string
/**
* Tool scoping applied to every child this tool spawns (see
* `SubagentStartRequest.toolFilter`): the named global tools vanish from
* the child's prompt AND refuse to execute. Requires the provider's
* `toolFilter` capability. Unknown names fail the spawn loudly. Note the
* child otherwise sees every global tool — including this delegation tool
* itself; `deny`-listing it (or setting `maxDepth`) is how a deployment
* bounds recursion.
*/
toolFilter?: {
/** Global tool names the child keeps; everything else is removed. */
allow?: string[]
/** Global tool names removed from the child. */
deny?: string[]
}
/**
* Recursion cap applied to every child this tool spawns (see
* `SubagentStartRequest.maxDepth`): a spawn whose child would sit deeper
* than this in the delegation tree is rejected. Requires the provider's
* `depthLimit` capability. Must be a non-negative safe integer and is
* validated when the plugin loads. Omitted ⇒ unbounded (bound it in
* deployments that expose this tool to children).
*/
maxDepth?: number
}
```
Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts)
Source: [`packages/subagent/tool-subagent/src/index.ts:44`](../packages/subagent/tool-subagent/src/index.ts)
Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts)
## `@deepseek-ai/dsh-tool-web`
@@ -799,9 +939,9 @@ Requires: `systemPrompt`
export interface Config {
/**
* The presentation mode. `'native'` (the default) contributes every
* registered tool as a wire function definition — byte-for-byte today's
* behavior. `'code'` contributes exactly ONE wire tool, `run_code`, plus
* the generated `tools:sdk` prompt section declaring every other tool as a
* visible end capability as a native wire function definition. Under
* `'code'` this registry contributes exactly ONE wire tool,
* `run_code`, plus the generated `tools:sdk` prompt section declaring every other tool as a
* TypeScript API the program calls. `'both'` contributes every native
* definition AND `run_code` + the SDK section. Non-native modes require a
* loaded `ctx.codeRuntime` whose `language` is `'typescript'` — a missing
@@ -818,7 +958,38 @@ export interface Config {
export type ToolPresentationMode = 'native' | 'code' | 'both'
```
Source: [`packages/core/tools/src/index.ts:319`](../packages/core/tools/src/index.ts)
Source: [`packages/core/tools/src/index.ts:401`](../packages/core/tools/src/index.ts)
## `@deepseek-ai/dsh-user-approval`
```ts config-catalog
/** Plugin config. All optional — `static Config` supplies the defaults. */
export interface Config {
/**
* The deployment's default {@link ApprovalPolicy} for sessions without an
* `approval/policy` override — `'ask'` delegates to the composed answerers
* (fail-closed with none); `'never'` auto-rejects every ask without
* prompting (the deterministic CI/unattended stance).
*/
readonly policy?: ApprovalPolicy
}
/**
* A session's approval policy — what happens to an {@link ApprovalService}
* ask BEFORE any interactive answerer sees it:
*
* - `'ask'` (the default) — delegate to the composed answerers; with none
* composed the chain falls through to the fail-closed `'unavailable'`
* (exactly today's behavior).
* - `'never'` — never prompt anyone: every ask resolves `'rejected'`
* deterministically. The strict headless stance (CI, unattended runs) and
* the only policy value stated in the system prompt — unlike `'ask'`, its
* outcome is knowable without asking, so stating it cannot overclaim.
*/
export type ApprovalPolicy = 'ask' | 'never'
```
Source: [`packages/ui/user-approval/src/index.ts:270`](../packages/ui/user-approval/src/index.ts)
## `@deepseek-ai/dsh-web`
@@ -967,6 +1138,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
- `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts))
- `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts))
- `@deepseek-ai/dsh-invariants` — requires `sessions` ([`packages/support/invariants/src/index.ts`](../packages/support/invariants/src/index.ts))
- `@deepseek-ai/dsh-llm` ([`packages/llm/llm/src/index.ts`](../packages/llm/llm/src/index.ts))
- `@deepseek-ai/dsh-session` ([`packages/core/session/src/index.ts`](../packages/core/session/src/index.ts))
- `@deepseek-ai/dsh-subagent` ([`packages/subagent/subagent/src/index.ts`](../packages/subagent/subagent/src/index.ts))
@@ -984,6 +1156,7 @@ Abstract service classes — a deployment loads a concrete implementation packag
- `@deepseek-ai/dsh-code-runtime` — abstract `CodeRuntime` ([`packages/code-runtime/code-runtime/src/index.ts`](../packages/code-runtime/code-runtime/src/index.ts))
- `@deepseek-ai/dsh-compact` — abstract `CompactService` ([`packages/compact/compact/src/index.ts`](../packages/compact/compact/src/index.ts))
- `@deepseek-ai/dsh-fs` — abstract `FileSystem` ([`packages/fs/fs/src/index.ts`](../packages/fs/fs/src/index.ts))
- `@deepseek-ai/dsh-sandbox` — abstract `SandboxProvider` ([`packages/sandbox/sandbox/src/index.ts`](../packages/sandbox/sandbox/src/index.ts))
- `@deepseek-ai/dsh-session-persistence` — abstract `SessionPersistence` ([`packages/session-persistence/session-persistence/src/index.ts`](../packages/session-persistence/session-persistence/src/index.ts))
- `@deepseek-ai/dsh-workflow` — abstract `WorkflowService` ([`packages/workflow/workflow/src/index.ts`](../packages/workflow/workflow/src/index.ts))
@@ -995,6 +1168,7 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them.
- `@deepseek-ai/dsh-app-boot` ([`packages/ui/app-boot/src/index.ts`](../packages/ui/app-boot/src/index.ts))
- `@deepseek-ai/dsh-brand` ([`packages/util/brand/src/index.ts`](../packages/util/brand/src/index.ts))
- `@deepseek-ai/dsh-hook-protocol` ([`packages/hooks/hook-protocol/src/index.ts`](../packages/hooks/hook-protocol/src/index.ts))
- `@deepseek-ai/dsh-scope` ([`packages/core/scope/src/index.ts`](../packages/core/scope/src/index.ts))
- `@deepseek-ai/dsh-subagent-inprocess` ([`packages/subagent/subagent-inprocess/src/index.ts`](../packages/subagent/subagent-inprocess/src/index.ts))
- `@deepseek-ai/dsh-subagent-subprocess` ([`packages/subagent/subagent-subprocess/src/index.ts`](../packages/subagent/subagent-subprocess/src/index.ts))
- `@deepseek-ai/dsh-timeout` ([`packages/util/timeout/src/index.ts`](../packages/util/timeout/src/index.ts))
docs/cookbook/adding-a-tool.md
+7 -5
View File
@@ -22,7 +22,7 @@ export function apply(ctx: Context) {
},
async execute(args, exec) {
// args is TYPED from the schema: { path: string; limit?: number }
// exec carries { callId, name, arguments, agent?, signal? }
// exec carries immutable identity + token; signal is the operational field
return [{ type: 'text', text: await readFile(args.path, 'utf8') }]
},
}))
@@ -34,7 +34,9 @@ Registration is effect-based: disposing the plugin fiber unregisters the tool (w
## Rules of the execute() contract
- **Args are validated for you.** `defineTool` validates the model-generated `arguments` against the `SchemaSpec` before `execute` runs (type, required keys, enum membership, nested objects/arrays — [runtime arg validation](../rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md)), so inside `execute` the args already match `InferArgs`. You still hand-check value constraints the DSL can't express (non-empty strings, positive numbers, cross-field rules); throw a descriptive Error for those. Raw JSON-Schema tools registered directly (MCP) are NOT validated by the harness — they validate their own input.
- **Throwing means isError.** The registry catches anything `execute()` throws and returns `{isError: true}` to the model. Use that for infrastructure failures (bad input, spawn errors, aborts) — but REPORT domain failures in the result text instead (e.g. tool-bash returns `[exit code: 9]` with `isError: false`: the model decides what a failing command means).
- **Registration borrows your readonly definition.** A typed same-process contribution is not a serialization boundary; do not mutate its schema or replace callbacks after registration. `schemas()` materializes only the explicit model-facing projection. To hot-swap a tool, dispose its owning effect and register the replacement; mutable state inside the callback's closure remains ordinary plugin state.
- **Execution identity is protected.** The registry materializes `arguments` as detached lossless JSON in one recursive pass, freezes that value before policy starts, and assigns an opaque `exec.token`; `callId`, `name`, `arguments`, `agent`, `token`, and an optional enclosing-transport `parent` token stay immutable through dispatch. `parent` is identity-only and exposes no live outer execution. Treat `args` as readonly input. An around-dispatch wrapper may add, replace, or remove only `exec.signal` to impose cancellation or a deadline.
- **Throwing or returning non-JSON data means isError.** The registry catches anything `execute()` throws and materializes the complete post-policy result as lossless JSON before final observers run. A throw, malformed result, or non-JSON content/context/meta becomes `{isError: true}` so the live outcome cannot succeed and then fail at the durable log. Use errors for infrastructure failures (bad input, spawn errors, aborts), but report domain failures in the result text instead (for example, tool-bash returns `[exit code: 9]` with `isError: false` because the model decides what a failing command means).
- **Honor `exec.signal`.** Cancel in-flight work when it fires.
- **Attach durable card data with `meta` (optional).** `execute` may return `{ content, meta }` instead of a bare `ContentBlock[]` — `meta` is a JSON-serializable payload the core treats as opaque, persisted on the `tool/result` event and handed back to your `presentResult` (so a card that needs more than `args`, like `write`/`edit`'s applied-hunk diff, survives a session replay). Keep UI-only data here, never in the model-facing `content`.
- **Use `exec.agent` for async notifications.** `agent.inject(content, {source: {kind: 'plugin', plugin: '<name>'}})` appends durable context the NEXT model request sees — it is not a wake-up (an idle agent stays idle). Guard against disposed agents (try/catch).
@@ -45,13 +47,13 @@ Follow tool-bash's background pattern: a `run_in_background` flag returns a task
> TODO: each tool reimplements this background pattern by hand today. At some point we need a generic long-running-tool layer that handles task ids, incremental polling, kill, and completion notices uniformly.
## Permissions / sandboxing
## Execution policy and observation
Prefer not to build policy into the tool. The seam is the `tools/pre-execute` gate (deny/ask — see the permission-gate example in [extension-cookbook.md](./extension-cookbook.md)) and the `tools/post-execute` inspect/transform seam, or a sandboxing implementation behind the tool's executor seam.
Prefer not to build deployment policy into the tool. Use `tools/pre-execute` for extensible allow/deny/ask policy (the [permission-gate example](./extension-cookbook.md#a-hook-plugin-permission-gate)), `ctx.tools.guard()` for a final monotonic deny that later listeners cannot undo, `tools/execute` to wrap core dispatch with a deadline/retry/metrics scope, `tools/post-execute` to transform or attach model-facing context, and `tools/result` to observe the immutable normalized outcome without changing it. A sandboxing implementation can also sit behind the tool's executor capability seam; the exact contracts are in the [`dsh-tools` README](../../packages/core/tools/README.md#extension-points).
## Code Mode reaches your tool for free
Under the registry's non-native `mode` ([Code Mode](../../packages/core/tools/README.md)), a registered tool is ALSO callable from a `run_code` program as `await tools.<name>(args)` — nothing to add. The generated SDK declares your parameters from the same JSON Schema `defineTool` emits (constructs outside that subset degrade to `unknown`), each program call re-enters `execute()` through both waterfalls, and a failed call rejects the program-side promise with your error text. Two consequences worth designing for: your `description` and parameter `description`s become JSDoc a model reads while WRITING CODE, and non-text result blocks reach programs as placeholders (text is the lingua franca of the bridge).
Under the registry's non-native `mode` ([Code Mode](../../packages/core/tools/README.md)), each visible registered capability is callable from a `run_code` program as `await tools.<name>(args)` — nothing to add. The registry keeps `run_code` itself as reserved, unfilterable presentation infrastructure while restrictions still control which end capabilities appear in the scoped SDK and bindings. The generated SDK declares parameters from the same JSON Schema `defineTool` emits (constructs outside that subset degrade to `unknown`); each program call receives its own immutable execution whose `parent` is the enclosing `run_code` token, then re-enters the complete pre/guard/around/post/result pipeline. A failed call rejects the program-side promise with your error text. Design `description` and parameter `description`s as JSDoc a model reads while writing code, and remember that non-text result blocks reach programs as placeholders (text is the bridge's lingua franca).
## How your tool renders in an editor (ACP presentation)
docs/cookbook/extension-cookbook.md
+14 -7
View File
@@ -28,6 +28,8 @@ export function apply(ctx: Context) {
}
```
This waterfall is the reorderable policy layer. Use `ctx.tools.guard()` when an invariant needs a monotonic final denial, `tools/execute` when a plugin must wrap the actual dispatch lifetime (timeouts/retries/metrics; only `exec.signal` is replaceable), `tools/post-execute` for explicit result transformation, and `tools/result` for contained observation of the immutable final outcome. The [adding-a-tool guide](./adding-a-tool.md#execution-policy-and-observation) gives the selection rule.
## A UI plugin
A UI plugin renders from the `session/event` feed (the assistant token stream as `assistant/chunk`, plus turn/step boundaries and tool activity), and drives input back in via `agent.send()` / `agent.steer()`.
@@ -54,9 +56,9 @@ export function apply(ctx: Context) {
## A client-driver plugin (external protocol bridge)
A *client driver* is a UI plugin whose "user" is another program speaking a wire protocol rather than a human at a terminal. It owns the process's stdio (so it must run with **no stdout logger** — every non-protocol byte corrupts the stream), creates/resumes agents on demand through the `dsh-agent` factory seam, translates harness events (`session/event`, `agent/*`) into outbound protocol messages, and translates inbound requests back into `agent.send()` / `agent.cancel()`. Two harness-specific contracts make it correct: resolve each request exactly once off a settle signal (settle from the durable `turn/end` session event — the boundary is a session event, not an `agent/*` mirror — with `agent/status` as the fallback if a peer listener starved yours), and tear each agent down through its `AgentHandle.dispose()` (which stops the loop, `await`s its exit, and unregisters), not just `cancel()` — disposal must *reach* quiescence, not merely request it.
A *client driver* is a UI plugin whose "user" is another program speaking a wire protocol rather than a human at a terminal. It owns the process's stdio (so it must run with **no stdout logger** — every non-protocol byte corrupts the stream), creates/resumes agents on demand through the `dsh-agent` factory seam, translates harness events (`session/event`, `agent/*`) into outbound protocol messages, and translates inbound requests back into `agent.send()` / `agent.cancel()`. Two harness-specific contracts make it correct: correlate and settle each request exactly once from the durable `turn/end` session event even if rendering fails, and tear each agent down through its `AgentHandle.dispose()` (which stops the loop, `await`s its exit, and unregisters), not just `cancel()` — disposal must *reach* quiescence, not merely request it.
`packages/ui/acp` is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the deferred-permission-gate note.
`packages/ui/acp` is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the permission-prompt answerer it registers on the approval seam.
```ts
import type { Context } from 'cordis'
@@ -87,21 +89,26 @@ Three complete examples load their plugin trees from `cordis.yml`: [`examples/ec
Every product feature maps to a listener on a documented extension seam — the microkernel claim made checkable ([microkernel RFC](../rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)). No row modifies the loop.
`system-prompt/assemble` is an expert cooperative whole-assembly transform: its returned assembly is authoritative, so listener authors own preserving active Code Mode and structured-output protocol contributions. Prefer `ctx.tools.restrict()` for tool filtering that must stay aligned across presentation, lookup, and execution.
| Product feature | Plugin mechanism |
|---|---|
| Hook system (user + project level) | listeners on `agent/session-start`, `agent/prompt-submit`, `agent/request`, `agent/step-result`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation` — each interception waterfall returns a typed Decision; the `dsh-hooks-claude` / `dsh-hooks-codex` bridges map hook config files onto these seams |
| `/goal` | force-continue via `agent/turn-continuation` + `steer()` reminders |
| `/loop` | on the `turn/end` session event, `send()` the next iteration; or force-continue |
| Dynamic workflow | orchestrator plugin on `turn/end` (or `step/end`) driving `send`/`steer` + subagents |
| Dynamic workflow | `ctx.workflows` + the worker-thread engine + the `workflow` tool; structured in-process children enforce output with scoped prompt/tool registrations, a monotonic tool guard, final `tools/result` commit (including enclosing `run_code`), and terminal `agent/turn-stop` |
| Queued + steering messages | core `Agent.send()` / `Agent.steer()` |
| Context compaction (auto + manual) | the `ctx.compact` seam + a backend (`dsh-compact-basic`) on the serial `agent/pre-step` seam; auto = token-pressure check before each step; a manual trigger invokes the same `ctx.compact` routine ([compaction RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) |
| System prompt configurability | `ctx.systemPrompt.section()` with ordering |
| System prompt configurability | `ctx.systemPrompt.section()` with ordering and scope-local shadowing |
| AGENTS.md (root) | a section provider reading the file |
| AGENTS.md (subdir, on-touch) + file-change notices | `agent.inject()` from a watcher / tool-result listener |
| Built-in tools | `ctx.tools.register()`; schemas flow into the assembly automatically — the `dsh-tool-*` families (bash, fs, web, subagent, todo) are the shipped examples |
| ToolSearch / progressive disclosure | filter tools at `system-prompt/assemble` (the assembly carries the schemas; the loop logs the result as the request header, so disclosure stays reconstructable) |
| Tool sandbox (landlock / sandbox-exec) | `tools/pre-execute` (deny), or a sandboxing `BashExecutor` on the `dsh-bash` seam |
| Permission system / AskUserQuestion | `tools/pre-execute` (deny/ask); register an ask tool |
| ToolSearch / progressive disclosure | replace a scoped `ctx.tools.restrict()` registration as the visible set changes; the registry keeps presentation, lookup, and execution aligned |
| Tool deadline / retry / metrics | wrap core dispatch with `tools/execute`; a wrapper may replace `exec.signal`, delegate, and inspect the normalized result in one lexical lifetime |
| Final tool-result metrics / audit / capture | observe immutable authoritative outcomes with `tools/result`; use `tools/post-execute` instead only when the plugin must transform the result or attach context |
| Monotonic terminal turn policy | return `{ action: 'stop' }` from serial `agent/turn-stop`, after continuation and steering have already been folded |
| Subprocess sandbox (landlock / sandbox-exec) | use a `ctx.sandbox` backend through `dsh-bash-sandbox`; use `tools/pre-execute` for capability-level denial |
| Permission system / AskUserQuestion | return `ask` from `tools/pre-execute` and answer through `ctx.approval`; register a separate model-facing ask tool for ordinary user questions |
| Plan mode | `tools/pre-execute` (deny writes) + a mode prompt section via `ctx.systemPrompt.section()` or `agent.inject()` (model-visible ⟺ logged: `agent/request` shapes call config only) |
| Sub-agent delegation | the `ctx.subagents` provider registry (`dsh-subagent-spawn`/`-fork`/`-acp`) + `dsh-tool-subagent` exposing one configured provider to the model |
| MCP | one plugin per server: discover tools → `ctx.tools.register()` |
docs/cordis-catalog/events.md
+143 -69
View File
@@ -15,89 +15,89 @@ Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `n
### `agent/created` — emit
An agent was registered in the AgentRegistry and is ready to receive messages.
An agent's fully composed scoped world was published in the AgentRegistry. Its session is already live in the session store. Setup is composition-only by contract; the subsequent `agent/session-start` boundary is the first supported place to inject or queue startup work. A synchronous listener throw vetoes publication and rollback emits the matching disposal edges; returned-promise rejection is observed and logged but cannot retroactively veto this synchronous boundary. A synchronous listener that requests the advanced registry detach does not remove the entry immediately: removal and the paired `agent/disposed` edge wait until the creation dispatch unwinds, so no later creation listener observes a disposal that preceded its own creation callback.
```ts cordis-catalog
'agent/created'(agent: Agent): void
'agent/created'(this: Scoped<Agent>, agent: Agent): void
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:265`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts)
### `agent/disposed` — emit
An agent was disposed and removed from the registry; its fiber and any in-flight turn have been torn down.
An agent was removed from the registry. The concrete AgentLoop lifecycle emits this only after its driver and any in-flight turn reach quiescence; a custom agent registered through the public registry owns its own driver contract, which the registry cannot infer. Ordered teardown may still be detaching the session and unwinding scoped registrations when this runs.
```ts cordis-catalog
'agent/disposed'(agent: Agent): void
'agent/disposed'(this: Scoped<Agent>, agent: Agent): void
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:272`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts)
### `agent/error` — emit
A step or turn errored. The loop reports a failure here (plus the logger) even when the error has no in-turn position for a session `error` event.
```ts cordis-catalog
'agent/error'(agent: Agent, turn: number, step: number, error: Error): void
'agent/error'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, error: Error): void
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:476`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts)
### `agent/pre-step` — serial
Awaited pre-step surface-mutation checkpoint, fired once per step AFTER `turn/start` (and after the prior step closed) but BEFORE this step's `step/start` — so anything a listener appends lands OUTSIDE the step, between `turn/start`/`step/end` and the upcoming `step/start`. `step` is the number of the step about to start. The loop awaits `ctx.serial('agent/pre-step', …)` after assembling the system prompt, then opens the step and derives the request history ONCE from whatever the surface now holds. This is where compaction belongs: it mutates the session surface in place (shadowing an older range with a summary node) with its log-only `compact/*` records cleanly outside any step, and the single subsequent derive reflects the mutation — so there is no double-derive and no listener can see (or be expected to act on) an assembled `messages` array that does not exist yet.
Serial (awaited in registration order), not a waterfall: a listener mutates the surface as a side effect; there is nothing to transform, but the loop must wait for the mutation to complete before opening the step and deriving. Cordis `serial` bails early if a listener returns a bail value; this event is typed and documented as `void`, so listeners must not return a semantic veto value. `fullSystemPrompt` is the assembled prompt a listener needs to measure pressure (the system prompt counts toward the budget), and `sessionPrefix` is the instance's composed agent/session-prefix product for the same reason — every request carries it in front of the derived history, and it is composed BEFORE this seam fires precisely so a pressure gate counts the prefix the request will actually send (never a stale logged one). `signal` cancels any in-flight work a listener starts (e.g. a summarization model call).
Serial (awaited in registration order), not a waterfall: a listener mutates the surface as a side effect; there is nothing to transform, but the loop must wait for the mutation to complete before opening the step and deriving. Cordis `serial` bails early if a listener returns a bail value; this event is typed and documented as `void`, so listeners must not return a semantic veto value. `fullSystemPrompt` is the assembled prompt a listener needs to measure pressure (the system prompt counts toward the budget), and `sessionPrefix` is the instance's composed agent/session-prefix product for the same reason — every request carries it in front of the derived history, and it is composed BEFORE this seam fires precisely so a pressure gate counts the prefix the request will actually send (never a stale logged one). `signal` cancels any in-flight work a listener starts (e.g. a summarization model call). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered through `agent.ctx` fires only for that agent's dispatches; a listener on a plain plugin context fires for every agent. The dispatch `this` is the scope carrier (`Scoped<Agent>`), built by the emitting side via `scopeTarget`/`agentEvents`.
```ts cordis-catalog
'agent/pre-step'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise<void> | void
'agent/pre-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise<void> | void
```
Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:357`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts)
### `agent/prompt-submit` — waterfall
Waterfall: decide what happens to ONE drained queued message before it becomes a `user/message` — allow (optionally rewriting the prompt bytes or attaching `additionalContext`) or block it. Fires inside the already-open turn, per drained message. Maps onto Claude Code's `UserPromptSubmit` hook. Call `next()` to delegate to the default (allow unchanged), or return a PromptDecision without calling `next()` to short-circuit.
```ts cordis-catalog
'agent/prompt-submit'(agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>
'agent/prompt-submit'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>
```
Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:370`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts)
### `agent/queued` — emit
A message entered the agent's inbox (queued or steering). `source` is the resolved source (defaults applied), not the caller's raw options.
A message entered the agent's inbox (queued or steering). Content and the resolved source are the detached, deeply-frozen values retained by the inbox. `source` has defaults applied and is not the caller's raw options.
```ts cordis-catalog
'agent/queued'(agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void
'agent/queued'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void
```
Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:290`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts)
### `agent/request` — waterfall
Waterfall: shape the step's call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use). Config is ALL a listener shapes here: every request is a pure function of the session log (the reconstructability RFC), so model-visible content flows through the log channels — `inject()`, steering, prompt-submit `additionalContext`, prompt sections via `system-prompt/assemble`, or the header-logged session prefix via agent/session-prefix — never through request mutation, and the loop records whatever config the request actually uses as a `request/header*` event before dispatch. The step's messages are already snapshotted when this fires (the `step/start` boundary): an `inject()` from a listener here lands in the log but joins the NEXT request. For surface mutation that must precede the snapshot (compaction), use agent/pre-step. Call `next()` to delegate, or return an LlmCallConfig without it to short-circuit.
```ts cordis-catalog
'agent/request'(agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>
'agent/request'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>
```
Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:394`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts)
### `agent/session-prefix` — waterfall
@@ -105,63 +105,89 @@ Waterfall: compose the SESSION PREFIX — request-only messages placed in front
This is the home for session-stable openers the model must always see but that must NOT become durable history — a skills catalog, an AGENTS.md digest, a workspace baseline: `Session.deriveMessages()` never returns the prefix, and the header events are its only durable record, so the request stays reconstructable from the log. Content that CHANGES mid-session belongs in the append-only history channels instead — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter.
The seed is a frozen empty list; a contributing listener returns a NEW array — never an in-place push. The canonical contribution is a PREPEND, `[mine, ...await next()]`: the waterfall unwinds innermost-first (the LAST-registered listener's `next()` resolves first), so prepending yields registration order on the wire, and every plugin using it composes deterministically. The append form `[...await next(), mine]` is legal but places a contribution AFTER every later-registered plugin's — reverse registration order when all contributors append. Call `next()` to delegate, or return a list without it to short-circuit.
The seed is a frozen empty list; a contributing listener returns a NEW array — never an in-place push. The canonical contribution is a PREPEND, `[mine, ...await next()]`: the waterfall unwinds innermost-first (the LAST-registered listener's `next()` resolves first), so prepending yields registration order on the wire, and every plugin using it composes deterministically. The append form `[...await next(), mine]` is legal but places a contribution AFTER every later-registered plugin's — reverse registration order when all contributors append. Call `next()` to delegate, or return a list without it to short-circuit. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered through `agent.ctx` fires only for that agent's dispatches; a listener on a plain plugin context fires for every agent. The dispatch `this` is the scope carrier (`Scoped<Agent>`), built by the emitting side via `scopeTarget`/`agentEvents`.
```ts cordis-catalog
'agent/session-prefix'(agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise<Message[]>): Promise<Message[]>
'agent/session-prefix'(this: Scoped<Agent>, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise<Message[]>): Promise<Message[]>
```
Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:441`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts)
### `agent/session-start` — emit
The agent's session lifecycle began, fired once before its first turn. `source` says why (SessionStartSource: fresh startup, a resumed persisted session, …). A pure NOTIFICATION (emit, not waterfall): it carries no veto — a session-start listener that wants to seed context does so via `agent.inject()` (a `context/message` the first request sees), not by returning a decision. Cannot block the session from starting; that gap is deliberate (a bridge logs/injects, it does not gate startup).
The agent's session lifecycle began, fired once before its first turn. `source` says why (SessionStartSource: fresh startup, a resumed persisted session, …). A pure NOTIFICATION (emit, not waterfall): a listener cannot veto by returning a decision or throwing. A listener that wants to seed context does so via `agent.inject()` (a `context/message` the first request sees). A lifecycle owner can still dispose its structural ownership edge during this notification; publication rechecks liveness and then aborts before the driver starts.
```ts cordis-catalog
'agent/session-start'(agent: Agent, source: SessionStartSource): void
'agent/session-start'(this: Scoped<Agent>, agent: Agent, source: SessionStartSource): void
```
Types: [Agent](../core-data-structures/core.md)
Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:305`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts)
### `agent/status` — emit
Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle off this transition, never off a status you just requested — `send()` does not flip status to `running` before it returns.
```ts cordis-catalog
'agent/status'(agent: Agent, status: AgentStatus): void
'agent/status'(this: Scoped<Agent>, agent: Agent, status: AgentStatus): void
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:281`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts)
### `agent/step-result` — waterfall
Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …).
```ts cordis-catalog
'agent/step-result'(agent: Agent, turn: number, step: number, message: Message, next: () => Promise<Message>): Promise<Message>
'agent/step-result'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, message: Message, next: () => Promise<Message>): Promise<Message>
```
Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:451`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts)
### `agent/turn-continuation` — waterfall
Waterfall: override the turn-continuation decision via a typed ContinuationDecision. The loop's `defaultDecision` is `continue` when the step had tool calls or steering was injected, else `stop`. Listeners force-continue (`/goal`, `/loop` — optionally attaching a `reason` recorded as next-step steering) or force-stop (budget guards). Call `next()` to delegate to the default, or return a decision to override.
```ts cordis-catalog
'agent/turn-continuation'(agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>
'agent/turn-continuation'(this: Scoped<Agent>, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:464`](../../packages/core/agent/src/types.ts)
Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts)
### `agent/turn-stop` — serial
Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` waterfall, any `continue.reason`, and the pending-steering continuation override have been folded. A listener returns `{ action: 'stop' }` to make this turn terminal, or `undefined` to abstain. Terminal stop is monotonic: listener order and steering cannot resume the turn, and pending steering is discarded rather than becoming another step or turn.
```ts cordis-catalog
'agent/turn-stop'(this: Scoped<Agent>, agent: Agent, turn: number): ContinuationStop | undefined
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts)
## `approval/*`
### `approval/request` — waterfall
Waterfall asking the composed answerers to decide one approval request. Dispatched only from ApprovalService.request — callers go through the service (which owns cancellation and the audit events), never through `ctx.waterfall` directly. A listener that can answer for this request's agent returns an outcome WITHOUT calling `next()` (the decision slot is single-occupancy, first listener to answer wins); a listener that does not recognize the agent MUST call `next()` so another answerer — or the fail-closed default `'unavailable'` — gets the question. Throwing is contained by the service and yields `'unavailable'`. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) keys the carrier by `req.agent`: a listener registered through `agent.ctx` receives only that agent's questions, while a plain-context listener receives every agent's. `req` is a readonly same-process value borrowed from the caller.
```ts cordis-catalog
'approval/request'(this: Scoped<ApprovalService>, req: ApprovalRequest, next: () => Promise<ApprovalOutcome>): Promise<ApprovalOutcome>
```
Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalRequest](../core-data-structures/approval.md)
Source: [`packages/ui/user-approval/src/index.ts:70`](../../packages/ui/user-approval/src/index.ts)
## `fs/*`
@@ -219,77 +245,109 @@ Source: [`packages/llm/llm/src/index.ts:39`](../../packages/llm/llm/src/index.ts
### `session/created` — emit
A session was created in the store.
A session was created in the store. A synchronous listener throw vetoes publication and rollback emits the matching `session/disposed` edge; returned-promise rejection is observed and logged but cannot retroactively veto this synchronous boundary. A synchronous listener that requests the advanced detach does not remove the entry immediately: removal and the paired `session/disposed` edge wait until the creation dispatch unwinds. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the session's owner scope, captured when the session was ENTERED (an agent's session is entered through `agent.ctx`, so its events dispatch in that agent's scope; a bare `sessions.create()` from a plain plugin dispatches subject-less). A listener registered through `agent.ctx` hears only that agent's sessions; a plain plugin listener hears every session.
```ts cordis-catalog
'session/created'(session: Session): void
'session/created'(this: Scoped<Session>, session: Session): void
```
Source: [`packages/core/session/src/index.ts:39`](../../packages/core/session/src/index.ts)
Source: [`packages/core/session/src/index.ts:52`](../../packages/core/session/src/index.ts)
### `session/disposed` — emit
A previously announced session left the store. Emitted exactly once on normal detach or publication rollback, and never for a prepared/entered session whose `session/created` announcement did not begin. Listener failures (including returned-promise rejections) are logged and contained per listener so teardown always reaches quiescence. Scope-filtered dispatch uses the same owner carrier captured at entry; agent-scoped listeners hear only their own session's teardown.
```ts cordis-catalog
'session/disposed'(this: Scoped<Session>, session: Session): void
```
Source: [`packages/core/session/src/index.ts:64`](../../packages/core/session/src/index.ts)
### `session/event` — emit
An event was appended to a session log (sync, fire-and-forget). This is the per-append feed a UI or invariant plugin tails.
An event was appended to a session log (sync, fire-and-forget). This is the per-append feed a UI or invariant plugin tails. The log push is the commit point; synchronous throws and returned-promise rejections from observers are logged and contained per listener, so they cannot make a committed append appear to fail or starve later listeners. The exact callback list and Cordis internal-dispatch checks resolve before the push; callbacks themselves run only after it. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the session's owner scope, captured when the session was ENTERED (an agent's session is entered through `agent.ctx`, so its events dispatch in that agent's scope; a bare `sessions.create()` from a plain plugin dispatches subject-less). A listener registered through `agent.ctx` hears only that agent's sessions; a plain plugin listener hears every session.
```ts cordis-catalog
'session/event'(session: Session, event: SessionEvent): void
'session/event'(this: Scoped<Session>, session: Session, event: SessionEvent): void
```
Types: [SessionEvent](../core-data-structures/core.md)
Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/src/index.ts)
Source: [`packages/core/session/src/index.ts:83`](../../packages/core/session/src/index.ts)
### `session/flush` — parallel
Awaited durability checkpoint. The agent loop awaits `ctx.parallel('session/flush', session)` at every turn end; persistence plugins (JSONL, SQLite) drain their write-behind buffers here and on fiber dispose. Awaited (parallel), not a waterfall: every listener runs and the loop waits for all of them, but none can veto.
Awaited durability checkpoint. The agent loop awaits `ctx.sessions.flush(session)` at every turn end; persistence plugins (JSONL, SQLite) drain their write-behind buffers here and on fiber dispose. Awaited (parallel), not a waterfall: every listener runs and the caller waits for all of them, but none can veto. Dispatch it through SessionStore.flush — the store owns the carrier — never via a raw `ctx.parallel`. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the session's owner scope, captured when the session was ENTERED (an agent's session is entered through `agent.ctx`, so its events dispatch in that agent's scope; a bare `sessions.create()` from a plain plugin dispatches subject-less). A listener registered through `agent.ctx` hears only that agent's sessions; a plain plugin listener hears every session.
```ts cordis-catalog
'session/flush'(session: Session): Promise<void> | void
'session/flush'(this: Scoped<Session>, session: Session): Promise<void> | void
```
Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts)
Source: [`packages/core/session/src/index.ts:101`](../../packages/core/session/src/index.ts)
## `skill/*`
### `skill/provider-added` — emit
A skill provider became resolvable in the `ctx.skills` registry. Consumers can observe this instead of depending on Cordis plugin load order, which is concurrent for sibling plugins.
```ts cordis-catalog
'skill/provider-added'(provider: SkillProvider): void
```
Source: [`packages/skill/skill/src/index.ts:131`](../../packages/skill/skill/src/index.ts)
### `skill/provider-removed` — emit
A skill provider left the registry because its plugin fiber was disposed.
```ts cordis-catalog
'skill/provider-removed'(name: string): void
```
Source: [`packages/skill/skill/src/index.ts:137`](../../packages/skill/skill/src/index.ts)
## `subagent/*`
### `subagent/end` — emit
A subagent run settled — emitted when SubagentRun.result resolves (any stop reason). Paired with Events['subagent/start'].
A ready child settled. Scope-filtered dispatch uses the same delegating parent carrier as `subagent/start`, so the lifecycle pair reaches the same scoped audience.
```ts cordis-catalog
'subagent/end'(info: SubagentRunEndInfo): void
'subagent/end'(this: Scoped<SubagentService>, info: SubagentRunEndInfo): void
```
Source: [`packages/subagent/subagent/src/index.ts:98`](../../packages/subagent/subagent/src/index.ts)
Source: [`packages/subagent/subagent/src/index.ts:90`](../../packages/subagent/subagent/src/index.ts)
### `subagent/provider-added` — emit
A provider became resolvable in the SubagentService registry. Consumers that derive state from a named provider (e.g. the model-facing tool wording in `dsh-tool-subagent`) react HERE instead of assuming load order — the cordis Loader starts sibling plugins concurrently, so "listed earlier in cordis.yml" does not mean "registered earlier".
A provider became resolvable in the registry.
```ts cordis-catalog
'subagent/provider-added'(provider: SubagentProvider): void
```
Source: [`packages/subagent/subagent/src/index.ts:72`](../../packages/subagent/subagent/src/index.ts)
Source: [`packages/subagent/subagent/src/index.ts:66`](../../packages/subagent/subagent/src/index.ts)
### `subagent/provider-removed` — emit
A provider left the registry (its plugin's fiber was disposed — an unload or an HMR reload). Consumers holding provider-derived state drop it here; a reload re-fires `subagent/provider-added` with the fresh provider. Delivered with per-listener containment: a throwing subscriber is logged, never starves later subscribers, and never disrupts the provider's teardown.
A provider left the registry. Accepted runs remain holder-owned.
```ts cordis-catalog
'subagent/provider-removed'(name: string): void
```
Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts)
Source: [`packages/subagent/subagent/src/index.ts:72`](../../packages/subagent/subagent/src/index.ts)
### `subagent/start` — emit
A subagent run started — emitted after the provider is resolved and its capabilities validated, as the child run begins. Paired with Events['subagent/end'].
A provider established a ready child. For in-process providers, `ctx.agents.get(info.id)` resolves during this notification. Scope-filtered dispatch keys the carrier by the delegating parent, so a parent-scoped listener observes only its own delegations. Paired with `subagent/end`.
```ts cordis-catalog
'subagent/start'(info: SubagentRunInfo): void
'subagent/start'(this: Scoped<SubagentService>, info: SubagentRunInfo): void
```
Source: [`packages/subagent/subagent/src/index.ts:91`](../../packages/subagent/subagent/src/index.ts)
Source: [`packages/subagent/subagent/src/index.ts:82`](../../packages/subagent/subagent/src/index.ts)
## `system-prompt/*`
@@ -297,69 +355,85 @@ Source: [`packages/subagent/subagent/src/index.ts:91`](../../packages/subagent/s
Waterfall around prompt assembly — mutate or extend the PromptAssembly (sections + tools + variables) before it is rendered. Bound to the SystemPrompt service; call `next()` to delegate.
Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is keyed by `context.scope` — a listener registered through `agent.ctx` fires only for that agent's assemblies; a plain plugin listener fires for every assembly (scope-less ones included, dispatched subject-less).
The returned assembly is authoritative. This is an expert composition seam: a listener that removes or replaces another plugin's protocol contribution owns preserving that protocol's invariants.
```ts cordis-catalog
'system-prompt/assemble'(this: SystemPrompt, assembly: PromptAssembly, context: AssembleContext, next: () => Promise<PromptAssembly>): Promise<PromptAssembly>
'system-prompt/assemble'(this: Scoped<SystemPrompt>, assembly: PromptAssembly, context: AssembleContext, next: () => Promise<PromptAssembly>): Promise<PromptAssembly>
```
Source: [`packages/core/system-prompt/src/index.ts:38`](../../packages/core/system-prompt/src/index.ts)
Source: [`packages/core/system-prompt/src/index.ts:49`](../../packages/core/system-prompt/src/index.ts)
### `system-prompt/change` — emit
A section, tool provider, or variable provider was registered or unregistered (the assembly inputs changed).
A section, tool provider, or variable provider was registered or unregistered (the assembly inputs changed — possibly for one scope only). An UNFILTERED registry-subject notification, deliberately not scope-filtered dispatch: a global change concerns every agent's next assembly, so a scoped listener subscribing here sees every change, not just its own scope's.
```ts cordis-catalog
'system-prompt/change'(): void
```
Source: [`packages/core/system-prompt/src/index.ts:44`](../../packages/core/system-prompt/src/index.ts)
Source: [`packages/core/system-prompt/src/index.ts:59`](../../packages/core/system-prompt/src/index.ts)
## `tools/*`
### `tools/change` — emit
A tool was registered or unregistered (the available tool set changed).
A tool was registered or unregistered, or a scoped restriction changed (the available tool set changed — possibly for one scope only). An UNFILTERED registry-subject notification, deliberately not scope-filtered dispatch: a global change concerns every agent's next assembly, so a scoped listener subscribing here sees every change, not just its own scope's.
```ts cordis-catalog
'tools/change'(): void
```
Source: [`packages/core/tools/src/index.ts:132`](../../packages/core/tools/src/index.ts)
Source: [`packages/core/tools/src/index.ts:173`](../../packages/core/tools/src/index.ts)
### `tools/execute` — waterfall
Around-dispatch waterfall wrapping the registry's core tool dispatch, between the `tools/pre-execute` gate and the `tools/post-execute` seam. A listener receives `(exec, next)`: call `next()` to delegate to dispatch (returning its ToolExecutionResult, optionally wrapped), or return a replacement result without calling `next()` to short-circuit dispatch. The base `next()` IS the dispatch-with-normalization thunk — a thrown tool (or unknown tool) is already normalized to an `isError` result by the time a listener's `await next()` returns, so a wrapper never sees a raw throw from the tool body. This is the seam a timeout/retry/metrics plugin wraps: it can mutate `exec` (e.g. replace `exec.signal` with a per-call deadline) BEFORE `next()` and inspect the result AFTER. (Cordis `next()` ignores any passed arguments and re-invokes downstream with the shared payload, so a wrapper mutates `exec` in place rather than passing a new object to `next()`.) Multiple listeners compose by registration order — an outer one wraps the inner ones plus dispatch.
Around-dispatch waterfall wrapping the registry's core tool dispatch, between the `tools/pre-execute` gate and the `tools/post-execute` seam. A listener receives `(exec, next)`: call `next()` to delegate to dispatch (returning its ToolExecutionResult, optionally wrapped), or return a replacement result without calling `next()` to short-circuit dispatch. The base `next()` IS the dispatch-with-normalization thunk — a thrown tool (or unknown tool) is already normalized to an `isError` result by the time a listener's `await next()` returns, so a wrapper never sees a raw throw from the tool body. This is the seam a timeout/retry/metrics plugin wraps: it can set or replace the one mutable field, `exec.signal` (e.g. with a per-call deadline), BEFORE `next()`, restore/delete it afterward, and inspect the result AFTER. Call identity (`token`, `callId`, `name`, `arguments`, `agent`, and `parent`) is immutable throughout the pipeline so a wrapper cannot change which tool and scope the pipeline accepted. (Cordis `next()` ignores passed arguments and re-invokes downstream with the shared payload, so a wrapper changes `exec.signal` in place rather than passing a new object to `next()`.) Multiple listeners compose by registration order — an outer one wraps the inner ones plus dispatch. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is keyed by `exec.agent` — a listener registered through `agent.ctx` wraps only that agent's calls; a plain plugin listener wraps every call (including agent-less ones, which dispatch subject-less).
```ts cordis-catalog
'tools/execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
'tools/execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
```
Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
Source: [`packages/core/tools/src/index.ts:111`](../../packages/core/tools/src/index.ts)
Source: [`packages/core/tools/src/index.ts:128`](../../packages/core/tools/src/index.ts)
### `tools/post-execute` — waterfall
Waterfall AFTER a tool runs — where hook plugins inspect the result and accept it (optionally REPLACING the model-facing content, and/or attaching `additionalContext` for the next request) or block it with corrective `feedback` (Claude Code's `PostToolUse`). Listeners receive `(exec, result, next)`: call `next()` to delegate to the default (accept unchanged), or return a PostToolDecision to override. Core tool dispatch runs earlier as the base `next()` of the `tools/execute` waterfall, all inside `execute`'s outer try/catch (and the tool body keeps its own inner try/catch, so a thrown tool still reaches `post-execute` as an `isError` result).
Waterfall AFTER a tool runs — where hook plugins inspect the result and accept it (optionally REPLACING the model-facing content, and/or attaching `additionalContext` for the next request) or block it with corrective `feedback` (Claude Code's `PostToolUse`). Listeners receive `(exec, result, next)`: call `next()` to delegate to the default (accept unchanged), or return a PostToolDecision to override. Core tool dispatch runs earlier as the base `next()` of the `tools/execute` waterfall, all inside `execute`'s outer try/catch (and the tool body keeps its own inner try/catch, so a thrown tool still reaches `post-execute` as an `isError` result). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is keyed by `exec.agent` — a listener registered through `agent.ctx` fires only for that agent's calls; a plain plugin listener fires for every call (including agent-less ones, which dispatch subject-less).
```ts cordis-catalog
'tools/post-execute'(this: ToolRegistry, exec: ToolExecution, result: ToolExecutionResult, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>
'tools/post-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, result: Readonly<ToolExecutionResult>, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>
```
Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
Source: [`packages/core/tools/src/index.ts:127`](../../packages/core/tools/src/index.ts)
Source: [`packages/core/tools/src/index.ts:148`](../../packages/core/tools/src/index.ts)
### `tools/pre-execute` — waterfall
Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code's `PreToolUse`). Listeners receive `(exec, next)`: call `next()` to delegate to the default (allow), or return a PreToolDecision without calling `next()` to short-circuit. A `deny` skips dispatch and yields an `isError` result; the tool body never runs. Input rewrite is deliberately NOT offered here (see PreToolDecision); `ask` degrades to deny until the permission system lands (`FIXME(permissions)`).
Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code's `PreToolUse`). Listeners receive `(exec, next)`: call `next()` to delegate to the default (allow), or return a PreToolDecision without calling `next()` to short-circuit. A `deny` skips dispatch and yields an `isError` result; the tool body never runs. Input rewrite is deliberately NOT offered here (see PreToolDecision); `ask` is serviced by the `ctx.approval` seam when one is mounted, and degrades to deny otherwise. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) keys the carrier by `exec.agent`: a listener registered through `agent.ctx` fires only for that agent's calls, while a plain plugin listener fires for every call (including agent-less ones, which dispatch subject-less).
```ts cordis-catalog
'tools/pre-execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
```
Types: [ToolExecution](../core-data-structures/tools.md)
Source: [`packages/core/tools/src/index.ts:91`](../../packages/core/tools/src/index.ts)
Source: [`packages/core/tools/src/index.ts:101`](../../packages/core/tools/src/index.ts)
### `tools/result` — emit
Synchronous notification of the authoritative FINAL tool outcome, after the complete pre/execute/post pipeline, final lossless-JSON validation, and outer error normalization. Unlike the three waterfalls, this seam cannot transform the result: each listener receives the now-frozen execution object and a deep-frozen result snapshot; listener failures are contained and logged, and ToolRegistry.execute still returns the outcome. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`, using the same carrier as the pipeline.
```ts cordis-catalog
'tools/result'(this: Scoped<ToolRegistry>, exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): undefined
```
Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
Source: [`packages/core/tools/src/index.ts:163`](../../packages/core/tools/src/index.ts)
## `workflow/*`
@@ -375,7 +449,7 @@ Source: [`packages/workflow/workflow/src/index.ts:96`](../../packages/workflow/w
### `workflow/agent-start` — emit
One `agent()` call started a child run. Paired with Events['workflow/agent-end'] by `agent.seq`.
One `agent()` call established a ready child run. Paired with Events['workflow/agent-end'] by `agent.seq`. A call that never receives a ready run from the provider emits neither event in this pair.
```ts cordis-catalog
'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void
@@ -401,7 +475,7 @@ The script emitted a narration line (a `log(message)` call).
'workflow/log'(info: WorkflowRunInfo, message: string): void
```
Source: [`packages/workflow/workflow/src/index.ts:77`](../../packages/workflow/workflow/src/index.ts)
Source: [`packages/workflow/workflow/src/index.ts:75`](../../packages/workflow/workflow/src/index.ts)
### `workflow/phase` — emit
@@ -411,7 +485,7 @@ The script entered a phase (a `phase(title)` call) — progress grouping for obs
'workflow/phase'(info: WorkflowRunInfo, title: string): void
```
Source: [`packages/workflow/workflow/src/index.ts:70`](../../packages/workflow/workflow/src/index.ts)
Source: [`packages/workflow/workflow/src/index.ts:68`](../../packages/workflow/workflow/src/index.ts)
### `workflow/start` — emit
@@ -421,7 +495,7 @@ A workflow run started — the script's meta block validated, the body about to
'workflow/start'(info: WorkflowRunInfo): void
```
Source: [`packages/workflow/workflow/src/index.ts:62`](../../packages/workflow/workflow/src/index.ts)
Source: [`packages/workflow/workflow/src/index.ts:60`](../../packages/workflow/workflow/src/index.ts)
## Inherited events (cordis core + loader/hmr/timer)
docs/cordis-catalog/services.md
+76 -26
View File
@@ -11,34 +11,48 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary
## `ctx.agentLoop` — `AgentLoop`
The agent-loop plugin (`ctx.agentLoop`): creates ReactLoopAgents, runs their loops, and registers them in `ctx.agents`. Also implements the AgentFactory seam, so plugins create/resume agents through `ctx.agents` (the interface) without depending on this concrete package.
The loop itself is deliberately thin — every behavior beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy declared in @deepseek-ai/dsh-agent.
Concrete ReactLoopAgent factory and driver service.
```ts cordis-catalog
create(id: AgentId, options: AgentOptions = {}): ReactLoopAgent
createAgent(options: CreateAgentOptions): AgentHandle
async resume(options: ResumeAgentOptions): Promise<AgentHandle>
create(id: AgentId, options: AgentOptions = {}, meta: Pick<SessionHeader, 'cwd'> = {}): ReactLoopAgent
async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise<AgentHandle>
async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise<AgentHandle>
```
Source: [`packages/core/agent-loop/src/index.ts:68`](../../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:338`](../../packages/core/agent-loop/src/index.ts)
## `ctx.agents` — `AgentRegistry`
Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (phase 1: `@deepseek-ai/dsh-agent-loop`), registered via setFactory.
Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory.
```ts cordis-catalog
setFactory(factory: AgentFactory): () => void
create(options: CreateAgentOptions): AgentHandle
async create(options: CreateAgentOptions): Promise<AgentHandle>
async resume(options: ResumeAgentOptions): Promise<AgentHandle>
register(agent: Agent): () => void
enter(agent: Agent): () => void
announce(agent: Agent): void
get(id: AgentId): Agent | undefined
list(): Agent[]
```
Types: [Agent](../core-data-structures/core.md)
Source: [`packages/core/agent/src/index.ts:117`](../../packages/core/agent/src/index.ts)
Source: [`packages/core/agent/src/index.ts:203`](../../packages/core/agent/src/index.ts)
## `ctx.approval` — `ApprovalService`
The `ctx.approval` service: dispatches ApprovalRequests to the `approval/request` waterfall and audits every ask/outcome pair to the requesting agent's session log. Stateless between requests — grants are returned to the caller, never stored here.
Owns the policy tier too (`effective = fold(the session's 'approval/policy' events) ?? config.policy`): `request()` resolves `'never'` to `'rejected'` before dispatching any interactive answerer, a per-agent prompt section states a `'never'` policy (and only that one in prose — an `'ask'` promise could overclaim an answerer that headless compositions do not have), and an `agent/pre-step` narrator injects at most one coalesced notice when a session's effective policy moved past what the model was last told.
```ts cordis-catalog
async request(req: ApprovalRequest): Promise<ApprovalOutcome>
```
Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalRequest](../core-data-structures/approval.md)
Source: [`packages/ui/user-approval/src/index.ts:294`](../../packages/ui/user-approval/src/index.ts)
## `ctx.bash` — `BashExecutor` (abstract seam)
@@ -65,7 +79,7 @@ onTaskDone(listener: BashTaskListener): () => void
Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) · [BashTask](../core-data-structures/bash.md) · [BashTaskRead](../core-data-structures/bash.md)
Source: [`packages/bash/bash/src/index.ts:59`](../../packages/bash/bash/src/index.ts)
Source: [`packages/bash/bash/src/index.ts:62`](../../packages/bash/bash/src/index.ts)
## `ctx.codeRuntime` — `CodeRuntime` (abstract seam)
@@ -147,6 +161,24 @@ Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../co
Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts)
## `ctx.sandbox` — `SandboxProvider` (abstract seam)
Abstract process-sandbox service. Subclass, implement confine, and load the subclass as a plugin — it registers as `ctx.sandbox` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).
Semantics every implementation must honor:
- confine either returns an argv whose runner ENFORCES the policy or fails closed — at `confine` time with SandboxUnavailableError (no backend for this host), or at EXECUTION time by the runner itself refusing to run the command (exiting without exec'ing it, identified by ConfinedArgv.runnerFailureSignatures). A silent unconfined passthrough is never a legal outcome on either path.
- Probing exists to ARBITRATE between multiple candidate backends and may be skipped when a platform has exactly one: the sole candidate is selected directly and the runner's exec-time fail-closed refusal carries the safety property. When probing does run, it is functional (actually enforcing a profile, not a version check), at most once per provider lifetime; `confine` itself spawns nothing beyond that one-time probing.
- The returned ConfinedArgv.enforcement states the backend's actual completeness for THIS host; `partial` is reported, never silently upgraded to `full`.
```ts cordis-catalog
abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv
```
Types: [ConfinedArgv](../core-data-structures/sandbox.md) · [SandboxPolicy](../core-data-structures/sandbox.md)
Source: [`packages/sandbox/sandbox/src/index.ts:180`](../../packages/sandbox/sandbox/src/index.ts)
## `ctx.sessionPersistence` — `SessionPersistence` (abstract seam)
Abstract durable session-persistence service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as `ctx.sessionPersistence` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).
@@ -155,7 +187,7 @@ Contracts every implementation MUST honor (a DB backend asserts them inside a tr
- **Append-only; a crashed turn is closed, not truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. A crash can leave an unclosed final turn whose events are real (and possibly large); load preserves them and closes the orphaned turn with synthetic boundary events (see load). Only a never-fully-written torn tail fragment is discarded.
- **Contiguous seq.** A persisted log is contiguous: `events[i].seq === i`. load rejects a parse error or a `seq` gap in the COMMITTED region (unloadable); append's first event `seq` MUST equal the backend's stored next-seq (after `load` has balanced any interrupted turn).
- **JSON-serializable data.** `SessionEventMap` is merge-extensible and `event.data` is typed only as `SessionEventMap[K]`, so append REJECTS non-JSON-serializable data with an error naming the offending event type. A backend snapshots (serializes/clones) each event when it buffers, since `session.events` hands out the live mutable object.
- **JSON-serializable events.** `SessionEventMap` is merge-extensible, so append materializes each complete batch through the shared lossless-JSON boundary before buffering it. The public `session.events` view is immutable, but persistence still snapshots direct/replay callers at this independent trust boundary.
- **Durability.** append returns only once the batch is durable (the file backend fsyncs; a DB commits). create MAY defer the physical write until the first append (lazy materialization).
```ts cordis-catalog
@@ -180,25 +212,39 @@ create(id?: SessionId, options?: CreateSessionOptions): Session
prepare(id?: SessionId, options?: CreateSessionOptions): Session
enter(session: Session): () => void
announce(session: Session): void
async flush(session: Session): Promise<void>
get(id: SessionId): Session | undefined
list(): Session[]
fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session
```
Source: [`packages/core/session/src/index.ts:405`](../../packages/core/session/src/index.ts)
Source: [`packages/core/session/src/index.ts:590`](../../packages/core/session/src/index.ts)
## `ctx.skills` — `SkillService`
Registry of skill providers. It merges provider catalogs with stable first-wins duplicate handling, exposes sorted model-visible summaries, and loads full skill bodies on demand.
```ts cordis-catalog
registerProvider(provider: SkillProvider): () => void
register(skill: SkillRegistration): () => void
async list(options: SkillLookupOptions = {}): Promise<SkillSummary[]>
async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefinition | undefined>
```
Source: [`packages/skill/skill/src/index.ts:158`](../../packages/skill/skill/src/index.ts)
## `ctx.subagents` — `SubagentService`
The `subagents` service: a registry of named SubagentProviders and a capability-checked start surface.
Named provider registry and capability-checked start surface.
```ts cordis-catalog
registerProvider(provider: SubagentProvider): () => void
getProvider(name: string): SubagentProvider | undefined
list(): string[]
start(name: string, request: SubagentStartRequest): SubagentRun
async start(name: string, request: SubagentStartRequest): Promise<SubagentRun>
```
Source: [`packages/subagent/subagent/src/index.ts:144`](../../packages/subagent/subagent/src/index.ts)
Source: [`packages/subagent/subagent/src/index.ts:123`](../../packages/subagent/subagent/src/index.ts)
## `ctx.systemPrompt` — `SystemPrompt`
@@ -206,27 +252,31 @@ Registry service (`ctx.systemPrompt`): plugins contribute ordered text sections,
```ts cordis-catalog
section(section: PromptSection): () => void
tools(provider: () => ToolSchema[]): () => void
tools(provider: (context: AssembleContext) => ToolProviderResult): () => void
variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void
async assemble(context: AssembleContext = {}): Promise<PromptAssembly>
```
Source: [`packages/core/system-prompt/src/index.ts:291`](../../packages/core/system-prompt/src/index.ts)
Source: [`packages/core/system-prompt/src/index.ts:340`](../../packages/core/system-prompt/src/index.ts)
## `ctx.tools` — `ToolRegistry`
Tool registry (`ctx.tools`): tool plugins register definitions; the agent loop executes calls through the `tools/pre-execute` → `tools/execute` → `tools/post-execute` pipeline. The registry contributes its schemas into the system-prompt assembly — WHICH schemas is governed by its `mode` config (see Config.mode); under a non-native mode it also registers the `run_code` tool and the `tools:sdk` prompt section itself.
Tool registry (`ctx.tools`): tool plugins register definitions; the agent loop executes calls through the `tools/pre-execute` → guards → `tools/execute` → `tools/post-execute` → `tools/result` pipeline. The registry contributes its schemas into the system-prompt assembly — WHICH schemas is governed by its `mode` config (see Config.mode); under a non-native mode it also owns the reserved `run_code` presentation transport and the `tools:sdk` prompt section.
Two registration layers (`@deepseek-ai/dsh-scope`): a registration through a plain plugin context is GLOBAL (visible to every agent); one through a scoped context (`agent.ctx`) is filed in that scope's layer — visible to that agent alone, disposed with the scope, and SHADOWING a global tool of the same name for that agent (most-specific-wins; within one layer a duplicate name still throws). restrict masks the global layer per scope. One private visibility resolver feeds the registry's prompt contribution, get, and execute — and, under a non-native mode, the SDK section and `run_code`'s bindings — so those registry-owned presentation and dispatch paths agree. An expert `system-prompt/assemble` listener may deliberately replace the final wire composition and owns any resulting divergence.
```ts cordis-catalog
register(definition: ToolDefinition): () => void
get(name: string): ToolDefinition | undefined
schemas(): ToolSchema[]
async execute(exec: ToolExecution): Promise<ToolExecutionResult>
restrict(filter: ToolRestriction): () => void
guard(guard: ToolGuard): () => void
get(name: string, scope?: ScopeKey): ToolDefinition | undefined
schemas(scope?: ScopeKey): ToolSchema[]
async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
```
Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
Source: [`packages/core/tools/src/index.ts:345`](../../packages/core/tools/src/index.ts)
Source: [`packages/core/tools/src/index.ts:493`](../../packages/core/tools/src/index.ts)
## `ctx.userInteraction` — `UserInteractionService`
@@ -268,7 +318,7 @@ Abstract workflow execution service. Subclass, implement start, and load the sub
Semantics every implementation must honor:
- start throws synchronously for a request that cannot begin (an unparseable script, an invalid meta block). Once it returns a WorkflowRun, `result` NEVER rejects — every failure resolves with `stopReason: 'error'` (or `'cancelled'`) — and once the run is cancelled, `result` SETTLES within the implementation's bounded grace even if the script itself never settles (a consumer awaiting `result` must never be wedged past a cancellation).
- The `workflow/*` events fire through emitWorkflowEvent (data snapshots, per-listener containment); `workflow/end` fires exactly once per started run, after `result` is settled or as it settles.
- The `workflow/*` events fire through emitWorkflowEvent (borrowed immutable data, per-listener containment); `workflow/end` fires exactly once per started run, after `result` is settled or as it settles.
- `dispose()` reaches quiescence within a bounded grace: it cancels, waits for the script to settle AND its started children to finish disposing, and abandons whatever is left rather than hanging its caller (the engine documents what abandonment leaves behind).
- Runs are HOLDER-OWNED: the engine hands control (`cancel`/`dispose`) to the `start()` caller and does not track its live runs — disposing the engine's own fiber mid-run deliberately leaves those runs to their holders' teardown, so an engine reload cannot yank a run out from under the consumer awaiting it.
@@ -276,7 +326,7 @@ Semantics every implementation must honor:
abstract start(request: WorkflowStartRequest): WorkflowRun
```
Source: [`packages/workflow/workflow/src/index.ts:210`](../../packages/workflow/workflow/src/index.ts)
Source: [`packages/workflow/workflow/src/index.ts:211`](../../packages/workflow/workflow/src/index.ts)
## Inherited `ctx` members (cordis core + loader/hmr/timer)
docs/cordis-primer.md
+1 -1
View File
@@ -27,7 +27,7 @@ The mode is part of the event's public contract. New harness events document it
`ctx.waterfall` is around-middleware. A listener receives `(...args, next)`. Call `next()` to delegate the possibly wrapped result to the next service; return without `next()` to short-circuit. Values propagate through `next()`'s return value.
Cooperative listeners usually mutate a shared request or decision object and then delegate. A listener can also choose to repalce the result entirely and downstream listeners will only see the result after replacement. Use `prepend: true` only when the listener must run before ordinary registrations.
Cooperative listeners usually mutate a shared request or decision object and then delegate. A listener can also choose to replace the result entirely and downstream listeners will only see the result after replacement. Use `prepend: true` only when the listener must run before ordinary registrations.
For single-decision events, short-circuiting is the design. A policy listener can return without `next()` when it owns the decision, while a listener that only annotates or observes must delegate.
docs/core-data-structures/approval.md
+64
View File
@@ -0,0 +1,64 @@
# User Approval
The user-approval seam of [dsh-user-approval](../../packages/ui/user-approval) answers one question: may this specific action proceed? It owns the shared request/outcome vocabulary, the `ctx.approval` dispatch service, the `approval/request` answerer waterfall, the log-only audit pair, and the per-session `ask`/`never` policy. UI channels such as [dsh-acp](../../packages/ui/acp) provide answerers; callers such as [dsh-tools](../../packages/core/tools) and [dsh-tool-bash](../../packages/bash/tool-bash) consume the closed outcome and fail closed unless it is `allowed-once`.
Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approval/src/index.ts)
## Identity and outcome
Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call, session, or agent ids.
```ts type-equiv
type ApprovalRequestId = Branded<'ApprovalRequestId'>
```
`ApprovalOutcome` is closed and fail-closed. `allowed-once` grants only the asked-about action; callers deny on `rejected`, `cancelled`, and `unavailable`. A missing, non-owning, throwing, or non-conforming answerer becomes `unavailable` rather than opening the gate.
```ts type-equiv
type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable'
```
## Per-session policy
`ApprovalPolicy` determines what happens before interactive answerers run. `ask` delegates to the composed answerer chain, whose no-answer default is `unavailable`; `never` deterministically returns `rejected` without dispatching any answerer. The effective value is the last `approval/policy` event in the session log, falling back to the service config. `setApprovalPolicy(session, policy)` is the single write path, so replay reconstructs the override.
```ts type-equiv
type ApprovalPolicy = 'ask' | 'never'
```
The prompt section states the deterministic `never` behavior and records either policy with a source-owned marker. The pre-step narrator reads that marker from the logged request header after restart; it does not infer state from deployment persona prose. An idle ACP switch is held in the bridge until the next `turn/start`, because approval audit and policy events must remain turn-enclosed for durable replay.
## Approval request
`ApprovalRequest` identifies the agent and tool action closely enough to route and audit the question. It deliberately omits tool arguments: an answerer attaches the prompt to the already-streamed tool call through `callId` instead of rendering a second copy that could drift.
```ts type-equiv
interface ApprovalRequest {
/**
* The agent on whose behalf the question is asked. Routes the question (a
* UI answerer only answers for agents it owns) and receives the audit
* events on its session log.
*/
readonly agent: Agent
/** The tool the question is about (presentation and audit). */
readonly toolName: string
/**
* The exact tool call being decided, when the asker has one — lets a UI
* attach the prompt to the tool call it already streamed.
*/
readonly callId?: CallId
/** The asker's human-readable explanation of WHY it is asking. */
readonly reason?: string
/**
* Aborting withdraws the question: the request settles `'cancelled'`
* immediately and a late answer from a still-pending answerer is discarded.
*/
readonly signal?: AbortSignal
}
```
## Dispatch and audit
`ctx.approval.request(req)` requires the requesting session to be inside an open turn. It appends `approval/asked`, obtains one outcome, appends the matching `approval/decided`, and resolves with that outcome. The `never` policy is enforced inside the service before waterfall dispatch, so even an answerer registered later with `prepend` cannot bypass it. Answerers return an outcome when they own the request or call `next()` to delegate; the first answer occupies the single decision slot.
The audit events are log-only and do not enter the model transcript. Model-visible behavior is the caller's derived tool result, while the request header records the prompt policy that the model actually saw. Service disposal removes its prompt section and pre-step narrator together; answerer listeners are independently effect-bound to their owning plugins.
docs/core-data-structures/bash.md
+84 -1
View File
@@ -44,6 +44,20 @@ interface BashExecRequest {
* ownerless background start (a non-agent caller).
*/
owner?: OwnerToken | undefined
/**
* Explicit per-call sandbox-policy input, overriding the executor's
* configured default mode for THIS call. Never a silent default: a
* consumer sets it only from an explicit policy source — an
* `'allowed-once'` grant a human just issued through `ctx.approval` (the
* escalation flow in the sandbox RFC § Escalation, which outranks), or the
* session's standing override folded from its own `bash/sandbox-mode`
* events (the sandbox RFC § Per-session mode switching — the user's recorded per-session
* choice). A sandboxing executor confines THIS call under the given mode;
* a non-sandboxing executor carries the field and confines nothing (the
* tool layer stamps neither escalation nor overrides without a sandboxing
* executor — see {@link BashExecutor.sandboxMode}).
*/
sandboxMode?: SandboxMode | undefined
}
```
@@ -79,6 +93,16 @@ interface BashExecSpec {
* task. `start()` stores it; `run()` (foreground) ignores it.
*/
owner: OwnerToken | undefined
/**
* The sandbox mode this call executes under, REQUIRED-but-nullable for the
* same visibility reason as `owner`. A sandboxing executor's `resolve()`
* stamps the effective mode (the request's explicit override, else its
* configured default) so `run()`/`start()` read the spec, never the config;
* a non-sandboxing executor carries the request value through verbatim and
* ignores it (`undefined` under such an executor means what its README says:
* unconfined execution).
*/
sandboxMode: SandboxMode | undefined
}
```
@@ -106,6 +130,12 @@ interface BashRunResult {
timeoutMs: number
stdout: CollectedOutput
stderr: CollectedOutput
/**
* Sandbox facts, present iff a sandboxing executor ran the command — an
* unsandboxed executor (e.g. `dsh-bash-local`) never sets it. See
* {@link BashSandboxInfo} for the `denied` classification semantics.
*/
sandbox?: BashSandboxInfo
}
```
@@ -122,9 +152,52 @@ interface CollectedOutput {
}
```
## File sandbox: `BashSandboxInfo`
A sandbox-consuming executor (`dsh-bash-sandbox`) exposes its configured fallback through `BashExecutor.sandboxMode`. The tool layer folds each agent session's durable `bash/sandbox-mode` override, stamps the effective mode onto the request, states it in the per-agent prompt, and may replace it for one user-approved strictly wider call. The mode/enforcement vocabulary is owned and cataloged by the [`@deepseek-ai/dsh-sandbox` seam](sandbox.md), whose provider wraps the executor's argv; modes govern FILE effects only, not network or process visibility.
A sandboxed run always reports the facts it executed under on `BashRunResult.sandbox`: `denied` is the executor's conservative classification of a failure as sandbox-caused (a failed exit whose stderr carries a filesystem-permission signature — never a clean exit or a signal kill), read from the collected stderr tail; `enforcement` reports how completely the selected backend governs the mode's file effects (`SandboxEnforcement = 'full' | 'partial'` — `partial` when an older Landlock ABI governs only a subset of the requested accesses; absent under `danger-full-access`, where nothing is confined); `runnerFailed` marks the opposite of a denial — the sandbox RUNNER itself failed and the command never ran (stamped only on settled background tasks; a foreground run surfaces the same condition as the thrown `SANDBOX_UNAVAILABLE` error):
```ts type-equiv
interface BashSandboxInfo {
/** The mode the command actually ran under. */
mode: SandboxMode
/**
* True when the executor classifies this run's failure as the sandbox
* denying a file operation. The classification is CONSERVATIVE (a failed
* exit whose stderr carries a filesystem-permission signature) and reads
* the COLLECTED stderr — the bounded in-memory tail per
* {@link CollectedOutput} semantics, so a signature that survives only in a
* spill file is missed toward `denied: false`. A plain command failure
* keeps `denied: false` even under a sandboxed mode.
*/
denied: boolean
/**
* How completely the runner enforced `mode`'s file effects — see
* {@link SandboxEnforcement}. Absent exactly when `mode` is
* `danger-full-access`: nothing is confined, so there is no enforcement to
* report.
*/
enforcement?: SandboxEnforcement
/**
* True when the executor classifies this failure as the SANDBOX RUNNER
* itself failing (missing binary, refused profile, fail-closed refusal
* before exec) — the command NEVER RAN; this is a sandbox failure, not a
* task failure, and it outranks `denied` (a runner's own error text can
* contain denial words). Only ever stamped on settled BACKGROUND tasks: a
* foreground run surfaces the same condition as the thrown
* `SANDBOX_UNAVAILABLE` error instead (the foreground path has an error
* channel; a settled task's facts are its only channel).
*/
runnerFailed?: boolean
}
```
One more piece completes the vocabulary: the `SANDBOX_UNAVAILABLE` error code (owned by the [sandbox seam](sandbox.md)) is what the `ctx.sandbox` provider throws — and the executor propagates — when a confined mode has no usable backend. A selected runner refusing its profile reaches the same fail-closed foreground error; a settled background task records `runnerFailed`. The model sees the current effective mode in the prompt, receives denial/runner facts in results, and can request a one-shot strictly wider retry through `sandbox_permissions` plus `justification`; `ctx.approval` must grant that exact call before anything executes. The complete policy and switching design is the [sandbox RFC](../rfc/implemented/feature/2026-07-06-sandbox.md).
## Background tasks: `BashTask`
A long-running command started with `start()` is tracked as a `BashTask`. `BashTaskStatus` is `'running' | 'completed' | 'killed'`; `done` resolves when the underlying process closes and never rejects.
A long-running command started with `start()` is tracked as a `BashTask`. `BashTaskStatus` is `'running' | 'completed' | 'killed'`; `done` resolves when the underlying process closes and never rejects. A sandboxing executor stamps `sandbox` once the task settles — classification runs against the settled task's collected stderr — so the field is absent while running and under an unsandboxed executor.
```ts type-equiv
interface BashTask {
@@ -137,6 +210,16 @@ interface BashTask {
signal: NodeJS.Signals | null
/** Resolves when the underlying process closes (never rejects). */
readonly done: Promise<void>
/**
* Sandbox facts for this task's execution, stamped by a sandboxing executor
* once the task settles and BEFORE completion listeners are notified — an
* `onTaskDone` consumer and a `done` awaiter both see it. Denial
* classification runs against the settled task's collected stderr, so the
* field cannot exist earlier: absent while the task is running and under an
* executor that does not sandbox. See {@link BashSandboxInfo} for the
* `denied` semantics.
*/
sandbox?: BashSandboxInfo
}
```
docs/core-data-structures/core.md
+33 -5
View File
@@ -16,13 +16,18 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
| Sub-page | Owns |
|---|---|
| [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam |
| [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context |
| [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant |
| [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
| [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, the `tools/pre-execute`/`tools/post-execute` pipeline |
| [system-prompt.md](system-prompt.md) | per-assembly context, tool-provider results, prompt sections, and cooperative assembly |
| [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, and the guarded execution pipeline |
| [user-interaction.md](user-interaction.md) | the UI-backed human question/answer seam: `AskUserQuestionRequest`, answer/options vocabulary, provider API, error taxonomy |
| [approval.md](approval.md) | the one-shot user-approval seam: `ApprovalRequest`, `ApprovalOutcome`, per-session policy, audit and answerer contracts |
| [bash.md](bash.md) | the bash executor seam: `BashExecRequest`/`Spec`, `BashRunResult`, background `BashTask`s |
| [sandbox.md](sandbox.md) | the process-confinement seam: file-effect modes, `SandboxPolicy`, `ConfinedArgv`, enforcement and fail-closed errors |
| [code-runtime.md](code-runtime.md) | the code-execution seam: `CodeRunRequest`/`Result`, binding namespaces, captured logs, the `CodeRunFailure` taxonomy |
| [filesystem.md](filesystem.md) | the filesystem seam: `FsTarget`, read/write/edit outcomes, observed-file state, `FsErrorCode` |
| [skills.md](skills.md) | the skill service: discovery priority, `SkillSummary`/`SkillDefinition`, session-prefix catalog, model-facing `skill` loading |
| [compaction.md](compaction.md) | the compaction seam: the `compact/*` session events, `CompactionResult`, the `CompactService` interface |
| [subagent.md](subagent.md) | the subagent seam: the named-provider registry, `SubagentStartRequest`/`Result`/`Run`, the start-time-vs-runtime capability split |
| [web.md](web.md) | the web access seam: `WebSearchRequest`/`Result`, `WebFetchRequest`/`Result`, `WebFetchBody`, provider/capability status, `WebError` |
@@ -196,7 +201,7 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition`
### The request envelope: `LlmCallConfig` and the logged header
Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the assembly's canonical order (dsh-system-prompt's `toolOrder` config, lexicographic when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch model or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws.
Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch model or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws.
On the wire, a loop-built request reads in this order: the `system` slot (the rendered prompt assembly) → `messagePrefix` (the frozen session prefix) → the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The prefix never enters the derived history; its durable record is the header events, and the dev invariant recomputes exactly this equation against every loop-built request.
@@ -254,12 +259,29 @@ interface Agent {
readonly session: Session
readonly status: AgentStatus
/** Queue a user message. Starts a turn when idle; otherwise waits for the next turn. */
/**
* The agent's scope context (`@deepseek-ai/dsh-scope`, key = this agent):
* registrations through it — tools, prompt sections/variables, listeners,
* restrictions — are visible to this agent only and unwind when it is
* disposed; `agent.ctx.on('agent/…')` listeners fire only for this agent.
*/
readonly ctx: Context
/**
* Queue a user message. Starts a turn when idle; otherwise waits for the next
* turn. Content and the resolved source are accepted as one detached,
* deeply-frozen lossless-JSON record before notification or enqueue, so
* caller or `agent/queued` listener in-place mutation cannot change later
* log/model input. Throws synchronously when either value is not losslessly
* JSON-serializable; `agent/prompt-submit` may still return an explicit
* replacement.
*/
send(content: ContentBlock[], options?: SendOptions): void
/**
* Steer a running turn: content is injected between steps of the current
* turn. When idle, behaves like {@link send}.
* turn. Uses the same owned-value and synchronous-validation boundary as
* {@link send}; when idle, behaves exactly like that method.
*/
steer(content: ContentBlock[], options?: SendOptions): void
@@ -331,7 +353,7 @@ interface Agent {
}
```
`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging; the persona is NOT an agent option but the `dsh-system-prompt` plugin's `persona` config, shared context-wide. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, the serial `agent/pre-step` surface-mutation seam, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits.
`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits.
## Interception decisions
@@ -362,6 +384,12 @@ type ContinuationDecision =
| { action: 'continue'; reason?: HookContext }
```
`agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering.
```ts type-equiv
type ContinuationStop = Extract<ContinuationDecision, { action: 'stop' }>
```
`agent/session-start` carries a `SessionStartSource` (why the session lifecycle began; a bridge keys its SessionStart matcher on it):
```ts type-equiv
docs/core-data-structures/persistence.md
+13 -8
View File
@@ -25,15 +25,15 @@ interface SessionHeader {
* session is created. A persistence backend rejects any other version on load
* (no migration — see the constant).
*/
version: number
readonly version: number
/** The session's id (mirrors the {@link Session}'s id). */
id: SessionId
readonly id: SessionId
/** Unix epoch milliseconds when the session was created. */
createdAt: number
readonly createdAt: number
/** Absolute working directory the session was created in (if any). */
cwd?: string
readonly cwd?: string
/** The session this one was forked from (seed lineage), if any. */
parentSession?: SessionId
readonly parentSession?: SessionId
/**
* How many leading events were INHERITED via a seed rather than produced by
* this session — the seed boundary. Set when a fork seeds a child with a
@@ -43,7 +43,7 @@ interface SessionHeader {
* harness can skip the inherited prefix when deriving the child's OWN script
* (the seeded events are the parent's, not this child's model calls).
*/
seedLength?: number
readonly seedLength?: number
}
```
@@ -54,7 +54,7 @@ Creating a `Session` through the store takes a `seed` (replay/fork an existing e
```ts type-equiv
interface CreateSessionOptions {
/** Events to seed the new session with (replay/fork). */
seed?: SessionEvent[]
readonly seed?: readonly SessionEvent[]
/**
* Creation metadata. The store fills in `version`/`id` and defaults
* `createdAt` to now; the caller supplies the storage-level fields (validated
@@ -67,7 +67,12 @@ interface CreateSessionOptions {
* length, not the original boundary — the caller must pass the persisted
* boundary back. A fresh fork passes its actual seeded-prefix length.
*/
meta?: { cwd?: string; parentSession?: SessionId; createdAt?: number; seedLength?: number }
readonly meta?: {
readonly cwd?: string
readonly parentSession?: SessionId
readonly createdAt?: number
readonly seedLength?: number
}
}
```
docs/core-data-structures/sandbox.md
+82
View File
@@ -0,0 +1,82 @@
# Process Sandbox
The process-sandbox seam of [dsh-sandbox](../../packages/sandbox/sandbox) wraps a same-world subprocess argv in a file-effect policy without coupling consumers to a platform runner. [dsh-sandbox-local](../../packages/sandbox/sandbox-local) supplies the Linux bwrap/Landlock and macOS Seatbelt backends; [dsh-bash-sandbox](../../packages/bash/bash-sandbox) is the first consumer. Containers, microVMs, and remote execution are sibling implementations of whole capability seams, not providers of `ctx.sandbox`.
Source: [`packages/sandbox/sandbox/src/index.ts`](../../packages/sandbox/sandbox/src/index.ts)
## Modes and enforcement
`SandboxMode` governs filesystem effects only. `read-only` denies writes except the required `/dev/null` sink; `workspace-write` permits writes under the workspace root and the backend's promised temp area; `danger-full-access` bypasses confinement. Network and process visibility are outside this vocabulary.
```ts type-equiv
type SandboxMode = 'read-only' | 'workspace-write' | 'danger-full-access'
```
Only the first two modes can be sent to a provider. A `danger-full-access` consumer spawns its original argv and does not call `ctx.sandbox`.
```ts type-equiv
type ConfinedSandboxMode = Exclude<SandboxMode, 'danger-full-access'>
```
Enforcement is a reported fact. `full` means the backend governs every file effect promised by the mode; `partial` means an active backend or older kernel ABI governs only a subset, so consumers that require the absolute promise must reject or surface that distinction.
```ts type-equiv
type SandboxEnforcement = 'full' | 'partial'
```
## Per-call policy
The policy is fully resolved and carried per call. This permits concurrent consumers and one-shot escalated retries to ask the same provider for different boundaries without mutating provider state.
```ts type-equiv
interface SandboxPolicy {
/** The file-effect mode this execution runs under. */
mode: ConfinedSandboxMode
/** Absolute root directory `workspace-write` may write under. */
workspaceRoot: string
}
```
## Wrapped argv and classification dialects
`ConfinedArgv` is what the consumer spawns. Besides the replacement argv, it carries the backend's enforcement fact and two orthogonal stderr dialects. `denialSignatures` identify the confined command being blocked while the sandbox works correctly. `runnerFailureSignatures` identify the sandbox runner refusing or failing before it executes the command; consumers check these first and surface a sandbox infrastructure failure, never an ordinary task failure.
```ts type-equiv
interface ConfinedArgv {
/** The wrapped argv (runner, profile, separator, then the caller's argv). */
argv: string[]
/** How completely the selected backend enforces the policy's file effects. */
enforcement: SandboxEnforcement
/**
* The selected backend's denial DIALECT: the case-insensitive stderr
* substrings a file effect denied by THIS backend produces (EROFS text
* under bwrap's read-only binds, EACCES under Landlock, EPERM under
* Seatbelt). A consumer that infers denials from a failed run's stderr
* matches against exactly these rather than a cross-backend union — the
* union claims denials a given backend never produces.
*/
denialSignatures: readonly string[]
/**
* How the RUNNER ITSELF failing identifies itself: case-insensitive stderr
* substrings produced when the sandbox binary is missing, refuses its
* profile, or fails closed before exec'ing the command (`bwrap: `,
* `landlock-run: `, `sandbox-exec: ` — each covers both the runner's own
* error prefix and the shell's runner-not-found message). ORTHOGONAL to
* {@link denialSignatures}: a denial is the confined COMMAND being blocked
* (the sandbox working as designed); a runner failure means the command
* NEVER RAN and must surface as a sandbox failure, not a task failure —
* consumers check these signatures FIRST (a runner's own error text may
* contain denial words, e.g. an unopenable grant root reporting
* `Permission denied`).
*/
runnerFailureSignatures: readonly string[]
}
```
An operator-configured local runner must supply at least one `runnerFailureSignatures` entry for its own pre-exec refusal dialect; the provider adds outer-shell missing and unexecutable forms automatically. This makes an executable custom runner rejecting its profile distinguishable from the wrapped command exiting with the same status.
## Provider and fail-closed errors
`ctx.sandbox.confine(argv, policy)` returns a `ConfinedArgv` or throws `SandboxUnavailableError` with code `SANDBOX_UNAVAILABLE` when no usable backend exists. A selected runner can also fail closed at execution time, in which case its failure signature carries the same infrastructure meaning. Silent unconfined passthrough is never legal for a confined policy.
Provider probing arbitrates between multiple candidates and is cached for the provider lifetime. A platform with one candidate may select it directly; execution-time refusal retains the safety property. The local provider reports bwrap and Seatbelt as full and preserves the Landlock launcher's full/partial kernel verdict.
docs/core-data-structures/scope.md
+31
View File
@@ -0,0 +1,31 @@
# Scoped Registration
The [scope package](../../packages/core/scope) supplies the identity and carrier vocabulary that makes one registration context mean both per-agent visibility and shared lifetime ownership. It is a library primitive rather than a Cordis service; the [agent-scope runtime-design RFC](../rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#scope-routing-one-opaque-key-selects-one-layer) owns the implementation rationale, while the package [README](../../packages/core/scope/README.md) owns the callable API and filtering semantics.
Source: [`packages/core/scope/src/index.ts`](../../packages/core/scope/src/index.ts).
## Identity and dispatch carrier
`ScopeKey` is an opaque object identity. The shipped loop uses the live `Agent` object as its own key, but the primitive never inspects the object.
```ts type-equiv
type ScopeKey = object
```
`Scoped<T>` is the compile-time brand on the opaque routing receiver returned by `scopeTarget(base, key)`. Scope-filtered event declarations require this carrier as their `this` type, while the real event subject remains an explicit argument.
```ts type-equiv
type Scoped<T extends object> = object & { readonly [ScopedBrand]: T }
```
## Owned registration context
`Scope` pairs the tagged registration context with two teardown surfaces. `rawDispose` preserves the exact Cordis disposer identity needed by an ordered composite effect; `dispose()` is the public shared quiescence boundary for direct and racing callers.
```ts type-equiv
interface Scope {
ctx: Context
rawDispose: () => Promise<void> | void
dispose(): Promise<void>
}
```
docs/core-data-structures/skills.md
+116
View File
@@ -0,0 +1,116 @@
# Skills
The [skill capability family](../../packages/skill) is split across three packages: the registry ([dsh-skill](../../packages/skill/skill), `ctx.skills`) merges provider catalogs; the local provider ([dsh-skill-local](../../packages/skill/skill-local)) scans project/custom/user directories; the consumer ([dsh-tool-skill](../../packages/skill/tool-skill)) owns the session-prefix catalog and model-facing `skill` tool. Skills are optional instructions, not session events, so their vocabulary lives here rather than in [core.md](core.md).
Source: [`packages/skill/skill/src/index.ts`](../../packages/skill/skill/src/index.ts), [`packages/skill/skill-local/src/index.ts`](../../packages/skill/skill-local/src/index.ts), and [`packages/skill/tool-skill/src/index.ts`](../../packages/skill/tool-skill/src/index.ts).
## Provider registry
`ctx.skills` is a multi-provider registry. Providers can represent local directories, embedded plugin data, HTTP catalogs, or another source. Provider plugins register synchronously during `apply()`; remote initialization, authentication, and discovery are awaited by `list()`. Provider objects, lookup options, and candidates are readonly same-process contracts, so the registry borrows them instead of manufacturing defensive snapshots. The registry still validates semantic fields, resolves duplicate skill names first-wins by rank/provider order/local order, and sorts the final summaries by `name` for deterministic consumers. A provider `list()` rejection is logged and skipped without caching the degraded catalog; malformed candidates still fail fast because they violate the provider contract.
```ts type-equiv
interface SkillProvider {
readonly name: string
readonly list: (options: SkillLookupOptions) => Promise<readonly SkillCandidate[]>
readonly get: (candidate: SkillCandidate, options: SkillLookupOptions) => Promise<SkillDefinition | undefined>
}
```
## Local discovery priority
The shipped local provider scans roots in rank order:
| Rank | Source | Root |
|---|---|---|
| 100 | `project-dsh` | `<projectRoot>/.dsh/skills` |
| 200 | `project-agents` | `<projectRoot>/.agents/skills` |
| 300 | `custom` | `Config.customSkillDirs` |
| 400 | `user-dsh` | `<dshHome>/skills` |
| 500 | `user-agents` | `<agentsHome>/skills` |
The project root is the nearest ancestor containing `.git`; without one, the current cwd is used. When `ctx.fs` is available, the git-root walk probes `.git` through the filesystem service so remote or sandboxed workspaces do not fall back to the host filesystem boundary. The user DSH root skips its `.system` child. The local provider does not ship built-in system skills; deployments supply built-ins through another provider.
## Skill identity
Skill names are kebab-case (`^[a-z0-9]+(?:-[a-z0-9]+)*$`). The local provider accepts directory bundles (`<name>/SKILL.md`) and flat Markdown files (`<name>.md`). Nested recursive `**/SKILL.md` discovery is intentionally outside v1.
```ts type-equiv
type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | 'user-agents' | 'custom' | (string & {})
```
## Summaries, candidates, and complete definitions
`SkillSummary` is the registry's model-invocable summary shape. Consumers choose which fields to render; the session catalog uses only `name` and `description`, never the body or absolute file path. `disableModelInvocation` hides a skill from model listings while allowing trusted code to load it by name.
```ts type-equiv
interface SkillSummary {
readonly name: string
readonly description: string
readonly whenToUse?: string
readonly disableModelInvocation?: boolean
readonly source: SkillSource
readonly provider: string
readonly resourceBase?: SkillResourceBase
}
```
`SkillCandidate` is the provider-to-registry shape. `locator` is opaque provider state; the registry only stores it and gives it back to the winning provider's `get()`.
```ts type-equiv
interface SkillCandidate extends SkillSummary {
readonly rank: number
readonly locator: unknown
readonly path?: string
readonly metadata?: Readonly<Record<string, unknown>>
}
```
`SkillDefinition` is the complete parsed result returned by `ctx.skills.get()` and used by the `skill` tool. `resourceBase` tells the tool how to render relative-resource guidance for local, URL, or provider-managed skills.
```ts type-equiv
type SkillResourceBase =
| { readonly kind: 'directory'; readonly path: string }
| { readonly kind: 'url'; readonly url: string }
| { readonly kind: 'opaque'; readonly description: string }
```
```ts type-equiv
interface SkillDefinition extends SkillSummary {
readonly content: string
readonly path?: string
readonly metadata?: Readonly<Record<string, unknown>>
}
```
Runtime skills use the same complete shape and participate in the same first-wins collection order. The returned disposer removes the contribution and invalidates discovery caches.
```ts type-equiv
type SkillRegistration = Omit<SkillDefinition, 'provider'> & {
readonly provider?: string
}
```
## Lookup and configuration
Skill lookup is cwd-sensitive because providers may expose workspace-local skills, and its optional signal cancels provider work for the caller. Providers receive the same readonly options object used for cache identity and loading. Cancellation is checked before and after catalog selection, including cache hits, and races both discovery and full-definition loading. If no git root is found, the local provider treats the supplied cwd itself as the project root.
```ts type-equiv
interface SkillLookupOptions {
readonly cwd?: string | undefined
readonly signal?: AbortSignal | undefined
}
```
The registry owns only its discovery-cache bound. The local provider owns filesystem roots (`dshHome`, `agentsHome`, and `customSkillDirs`). The consumer owns its catalog description bound.
```ts type-equiv
interface Config {
readonly collectCacheMaxEntries?: number
}
```
## Session catalog and tool contract
`dsh-tool-skill` contributes a user-role `<system-reminder>` through `agent/session-prefix`. The catalog contains sorted skill `name` and normalized, XML-escaped `description` only; it omits bodies, paths, sources, providers, and routing hints. Prefix discovery forwards the caller's abort signal through `SkillLookupOptions`. `catalogDescriptionMaxLength` is the consumer config for the description bound, with default `500` and integer minimum `3`. Its request-only, header-logged lifecycle is defined by the [session-prefix RFC](../rfc/implemented/feature/2026-07-07-session-prefix.md).
The model-facing `skill({ name })` tool validates the kebab-case name, loads the complete definition for the calling agent cwd, reports an unresolved skill as unknown or no longer available, rejects `disableModelInvocation` skills, and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` resolves explicitly referenced scripts, references, and assets only as needed; the loaded result does not enumerate a skill directory. The tool result is the model-visible path for complete instructions.
docs/core-data-structures/subagent.md
+26 -23
View File
@@ -12,37 +12,41 @@ A provider advertises its **start-time** features on a static descriptor the ser
```ts type-equiv
interface SubagentCapabilities {
outputSchema: boolean
depthLimit: boolean
toolFilter: boolean
readonly outputSchema: boolean
readonly depthLimit: boolean
readonly toolFilter: boolean
readonly persona: boolean
}
```
## The start request
What a caller asks for when starting a subagent. The tool layer builds this from the model's `{ description, prompt }` plus its own config; the service validates the start-time capabilities against the named provider, then passes it to `provider.start`. `parent` is REQUIRED — in-process backends read `parent.session.header` for the working directory, the `parentSession` lineage, and the delegation depth. The three optional fields (`outputSchema`, `maxDepth`, `toolFilter`) each gate on the matching `SubagentCapabilities` flag. `outputSchema` is an object-rooted JSON Schema within the subset `assertSupportedOutputSchema` (dsh-tools) enforces — a schema outside it is rejected loud at start; the in-process backends realize it with a forced `structured_output` capture tool (see the [driver README](../../packages/subagent/subagent-inprocess/README.md)).
What a caller asks for when starting a subagent. The tool layer builds this from the model's `{ description, prompt }` plus its own config; the service validates the start-time capabilities against the named provider, then passes it to `provider.start`. `parent` is REQUIRED — in-process backends read `parent.session.header` for the working directory, the `parentSession` lineage, and the delegation depth. The four optional fields (`outputSchema`, `maxDepth`, `toolFilter`, `persona`) each gate on the matching `SubagentCapabilities` flag — in-process backends realize `toolFilter` as a scoped `tools.restrict()` and `persona` as a scoped shadowing `deployment:persona` section, both composed in the child's creation window. `outputSchema` is an object-rooted JSON Schema within the subset `assertSupportedOutputSchema` (dsh-tools) enforces — a schema outside it is rejected loud at start; the in-process backends realize it with a forced `structured_output` capture tool (see the [driver README](../../packages/subagent/subagent-inprocess/README.md)).
```ts type-equiv
interface SubagentStartRequest {
prompt: ContentBlock[]
parent: Agent
signal?: AbortSignal
agentOptions?: AgentOptions
outputSchema?: StructuredOutputSchema
maxDepth?: number
toolFilter?: { allow?: string[]; deny?: string[] }
readonly prompt: ContentBlock[]
readonly parent: Agent
readonly signal: AbortSignal
readonly agentOptions?: AgentOptions
readonly outputSchema?: StructuredOutputSchema
readonly maxDepth?: number
readonly toolFilter?: ToolRestriction
readonly persona?: string
}
```
`signal` is the single cancellation channel before and after readiness. The [subagent composition-controls RFC](../rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the persona, live global-tool filter, absolute-depth, and visibility-not-authority rationale.
## The terminal result: `SubagentResult`
The outcome of a run, resolved by `SubagentRun.result`. `structured` is present iff the request carried an `outputSchema` AND the provider honored it. A non-`completed` `stopReason` means `output` may be partial — the consumer maps it to an `isError` tool result rather than reporting partial output as success.
The outcome of a run, resolved by `SubagentRun.result`. `structured` is present only after a requested `outputSchema` was successfully satisfied; requesting a schema does not guarantee it, and a provider may return `stopReason: 'error'` when the child fails or finishes without a valid capture. A non-`completed` `stopReason` means `output` may be partial — the consumer maps it to an `isError` tool result rather than reporting partial output as success.
```ts type-equiv
interface SubagentResult {
output: ContentBlock[]
structured?: unknown
stopReason: SubagentStopReason
readonly output: ContentBlock[]
readonly structured?: unknown
readonly stopReason: SubagentStopReason
}
```
@@ -60,37 +64,36 @@ interface SubagentStopReasonMap {
## A live run: `SubagentRun`
The handle the consumer holds while a child executes. The consumer awaits `result`, may `cancel` mid-flight, and MUST `dispose` on every path to reach child quiescence (no leaked idle child / session). `result` does NOT reject on a child-level failure — a model/transport failure resolves with `stopReason: 'error'` — so the consumer maps a non-`completed` reason to an `isError` result; it rejects only on an infrastructure fault the seam cannot represent. `sendMessage` and `resume` are OPTIONAL: a provider that supports the runtime capability defines the method; one that doesn't omits it.
The handle the consumer holds after a provider has established a ready child. The consumer awaits `result` and MUST `dispose` on every path to cancel remaining work and reach child quiescence. `result` does NOT reject on a child-level failure — a model/transport failure resolves with `stopReason: 'error'` — so the consumer maps a non-`completed` reason to an `isError` result; it rejects only on an infrastructure fault the seam cannot represent. `sendMessage` and `resume` are OPTIONAL: a provider that supports the runtime capability defines the method; one that doesn't omits it.
```ts type-equiv
interface SubagentRun {
readonly id: AgentId
readonly result: Promise<SubagentResult>
cancel(reason?: string): void
dispose(): Promise<void>
sendMessage?(content: ContentBlock[]): void
resume?(content: ContentBlock[]): SubagentRun
resume?(content: ContentBlock[]): Promise<SubagentRun>
}
```
## The provider seam: `SubagentProvider`
One transport for running a child agent. Implementations register under a unique name via `SubagentService.registerProvider`; multiple coexist in one context. The service validates every requested start-time capability before calling `start`, so an implementation may assume e.g. `request.maxDepth` is honorable when present. `inheritsParentContext` is a DESCRIPTIVE fact beside the capabilities (nothing validates against it): whether a child sees the parent conversation (`fork`: true, `spawn`/`acp`: false) — the model-facing consumer derives truthful tool wording from it.
One transport for running a child agent. Implementations register under a unique name via `SubagentService.registerProvider`; multiple coexist in one context. The service validates every requested start-time capability before calling `start`, so an implementation may assume e.g. `request.maxDepth` is honorable when present. `inheritsParentContext` is a DESCRIPTIVE fact beside the capabilities (nothing validates against it): whether a child sees the parent conversation (`fork`: true, `spawn`/`acp`: false) — the model-facing consumer derives truthful tool wording from it. It describes conversation history only, not tool registrations, injected services, or authority inheritance.
```ts type-equiv
interface SubagentProvider {
readonly name: string
readonly capabilities: SubagentCapabilities
readonly inheritsParentContext: boolean
start(request: SubagentStartRequest): SubagentRun
start(request: SubagentStartRequest): Promise<SubagentRun>
}
```
The service (`ctx.subagents`) emits `subagent/start` when a run begins and `subagent/end` when it settles (see the [events catalog](../cordis-catalog/events.md)). `subagent/end` carries `lastAssistantMessage` (the child's final `output`) on the settle path, so an observer sees WHAT the subagent produced without holding the run (absent when the run rejected at the infrastructure level — no result was produced). These are **observe-only** events: both are plain `emit`s (the `subagent/end` fires from a detached `.then` after the result settles and awaits no listener), so a subscriber observes but cannot change the run. Both emits contain a thrown listener **per listener** (logged, never propagated): one bad subscriber can neither strand a live run, surface as an unhandled rejection on the detached settle hook, nor starve the listeners registered after it.
`SubagentProvider.start()` and `ctx.subagents.start()` are the publication boundary: their promises fulfill only with a ready run. The service attaches result observation, emits `subagent/start`, and returns the same holder-owned run; a rejected start has already cleaned provider-owned partial resources and emits neither lifecycle event. For an in-process provider, a start listener can resolve the live child with `ctx.agents.get(info.id)`; a remote provider need not publish into the local registry. `subagent/end` carries `lastAssistantMessage` (the child's final `output`) on the settle path and reports `error` on infrastructure rejection. Both lifecycle events are observe-only emits with per-listener exception containment.
## In-process backends: depth and seed
The two in-process backends ([dsh-subagent-spawn](../../packages/subagent/subagent-spawn) fresh, [dsh-subagent-fork](../../packages/subagent/subagent-fork) seeded) run the child as a child `Agent` on the same context via `ctx.agents.create`. Two pieces of vocabulary ride on the existing agent/session types rather than new core types:
The two in-process backends ([dsh-subagent-spawn](../../packages/subagent/subagent-spawn) fresh, [dsh-subagent-fork](../../packages/subagent/subagent-fork) seeded) run the child as an ordinary `Agent` in the same application. The provider creates it directly through `parent.ctx`, passes the required signal into the core creation transaction, and delegates quiescent disposal to the returned `AgentHandle`. Provider removal prevents new starts but does not revoke an accepted run. The child receives a flat new scope rather than inheriting the parent's registrations. Two pieces of vocabulary ride on the existing agent/session types rather than new core types:
- **Delegation depth** is a merge-extensible `AgentOptions.subagentDepth` field (`0` for a top-level agent, parent + 1 for a child). The seam owns it — the loop neither sets nor reads it — so a nested spawn reads its parent's depth from `parent.options.subagentDepth` and the `depthLimit` capability caps the tree by refusing a child whose depth would exceed `request.maxDepth`.
- **Delegation depth** is a merge-extensible `AgentOptions.subagentDepth` field (`0` for a top-level agent, parent + 1 for a child). Only `undefined` means top level; every stored present value must be a non-negative safe integer. The seam owns it — the loop neither sets nor reads it — so a nested spawn validates its parent's stored depth, rejects a derived child depth outside the safe-integer domain, and applies a defined absolute `request.maxDepth` cap to that child.
- **Fork seeding** uses `CreateAgentOptions.seed` (a `SessionEvent[]` prefix threaded through `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })`, the same primitive `resume` uses). The fork backend passes a *balanced completed-turn prefix* of the parent's log — the parent's events up to and including its last `turn/end` — so the seed is contiguous-from-0 and the [invariants](../../packages/support/invariants) replay accepts it (the in-flight, unbalanced turn is excluded).
docs/core-data-structures/system-prompt.md
+38
View File
@@ -0,0 +1,38 @@
# System Prompt Assembly
The [system-prompt package](../../packages/core/system-prompt) owns the data exchanged between prompt contributors and one assembly call. The package [README](../../packages/core/system-prompt/README.md) documents registration, ordering, scoping, and rendering behavior; this page pins the literal cross-package shapes that plugins implement or pass.
Source: [`packages/core/system-prompt/src/index.ts`](../../packages/core/system-prompt/src/index.ts).
## Assembly context
`AssembleContext` identifies the scope layer one assembly resolves. It is merge-extensible: `dsh-agent` adds the optional live `agent` field, and `assembleContextFor(agent)` sets that field and `scope` together.
```ts type-equiv
interface AssembleContext {
scope?: ScopeKey
}
```
## Tool-provider result
`ToolProviderResult.schemas` is the model-visible set for the current assembly. `knownNames` is the provider's pre-restriction name universe used to distinguish a configured-name typo from a known tool that is deliberately hidden in this scope.
```ts type-equiv
interface ToolProviderResult {
readonly schemas: readonly ToolSchema[]
readonly knownNames?: readonly string[]
}
```
## Prompt sections
`PromptSection` is a readonly same-process registration contract. Its text may be static or resolved from the current assembly context.
```ts type-equiv
interface PromptSection {
readonly name: string
readonly order: number
readonly text: string | ((context: AssembleContext) => string)
}
```
docs/core-data-structures/tools.md
+50 -10
View File
@@ -1,6 +1,6 @@
# Tools
The tool pipeline of [dsh-tools](../../packages/core/tools). [core.md](core.md) introduces `ToolDefinition` as the one pipeline-authoring type promoted to the spine and `ToolSchema` as the model-facing wire shape. This page owns the full `ToolDefinition`, the typed schema DSL that builds it, the waterfall execution shapes, and the UI-presentation vocabulary.
The tool pipeline of [dsh-tools](../../packages/core/tools). [core.md](core.md) introduces `ToolDefinition` as the one pipeline-authoring type promoted to the spine and `ToolSchema` as the model-facing wire shape. This page owns the full `ToolDefinition`, the typed schema DSL that builds it, the guarded execution shapes, and the UI-presentation vocabulary.
Source: [`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index.ts) · [`packages/core/tools/src/schema.ts`](../../packages/core/tools/src/schema.ts) · [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts)
@@ -81,22 +81,60 @@ type InferArgs<S extends SchemaSpec> = Simplify<
`defineTool({ name, description, parameters, execute, … })` ties it together: `parameters` is a `SchemaSpec`, `execute(args, exec)` gets `args: InferArgs<typeof parameters>`, and the helper converts the spec to JSON Schema (`schemaSpecToJsonSchema`) for the wire and validates model-generated args (`validateArgs`) before the typed body runs. A mismatch throws `ToolArgsError` (`code: 'INVALID_ARGS'`), which the registry turns into an `isError` result so the model can self-correct. Why a custom DSL and not schemastery: tool parameters need JSON Schema (the LLM wire format), not validation/transformation — the lightweight DSL gives the best authoring DX with the smallest surface.
## Execution: the `tools/pre-execute` / `tools/post-execute` pipeline shapes
Registration is a trusted same-process contract. The registry borrows the typed definition as readonly input and validates only semantic requirements such as a positive finite `timeoutMs`; `schemas()` materializes the explicit model-facing projection at the model boundary so execution and presentation share one resolved definition without leaking callbacks onto the wire.
`ctx.tools.execute()` runs each call through a two-waterfall pipeline — `tools/pre-execute` (the allow/deny/ask gate) → core dispatch → `tools/post-execute` (inspect/replace the result, attach context) — the seams where sandbox, permission, hook, and plan-mode plugins gate or transform a call. The pending call is a `ToolExecution`; the outcome is a `ToolExecutionResult`.
## `ToolRestriction` — one scope's live global filter
`ToolRestriction` applies only to the live deployment-global tool layer. The registry compiles readonly names into private sets, intersects multiple restrictions, then overlays scope-local tools. A deny-only filter admits later unlisted globals, while an allow-list excludes them.
```ts type-equiv
interface ToolExecution {
callId: CallId
name: string
interface ToolRestriction {
readonly allow?: readonly string[]
readonly deny?: readonly string[]
}
```
## Execution: extensible waterfalls plus monotonic policy
`ctx.tools.execute()` accepts a caller-owned `ToolExecutionInput`, materializes its parsed JSON arguments once into a pipeline-owned `ToolExecution`, and runs that call through `tools/pre-execute` (the reorderable allow/deny/ask waterfall) → registered monotonic guards → `tools/execute` (around-dispatch wrappers) → `tools/post-execute` (inspect/replace the result) → `tools/result` (the immutable authoritative outcome). The outcome is a `ToolExecutionResult`.
```ts type-equiv
type ToolExecutionToken = symbol & { readonly [toolExecutionTokenBrand]: true }
```
```ts type-equiv
interface ToolExecutionInput {
readonly callId: CallId
readonly name: string
/** Parsed JSON arguments (unknown — tools validate their own input). */
arguments: unknown
readonly arguments: unknown
/** The agent on whose behalf the call runs (set by the agent loop). */
agent?: Agent
readonly agent?: Agent
/**
* Opaque token of the enclosing transport execution, when one exists. Code
* Mode sets this on SDK sub-dispatches so commit-style observers can wait for
* the outer `run_code` outcome without receiving its live mutable execution.
*/
readonly parent?: ToolExecutionToken
signal?: AbortSignal
}
```
```ts type-equiv
interface ToolExecution extends ToolExecutionInput {
/** Registry-assigned identity shared with nested calls only as their opaque `parent` token. */
readonly token: ToolExecutionToken
}
```
`ToolExecutionToken` is a compile-time opaque fresh `Symbol` at runtime; identity comparison is its only operation. Before policy runs, `ctx.tools.execute()` materializes `arguments` as detached lossless JSON, assigns the token, and deep-freezes the accepted arguments. A non-JSON value is normalized to an error before policy. `token`, `callId`, `name`, `arguments`, `agent`, and the optional `parent` token are readonly throughout the waterfalls, while an around-dispatch wrapper may add, replace, or remove only optional `signal`. After the complete pipeline the registry freezes the execution and exposes its stable identity to `tools/result` observers.
A `ToolGuard` is scope-aware final pre-dispatch policy. Its shape deliberately has no allow result: `undefined` preserves the waterfall decision, while a returned reason can only reduce permission, so a later listener cannot undo it.
```ts type-equiv
type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined
```
```ts type-equiv
interface ToolExecutionResult {
callId: CallId
@@ -129,7 +167,9 @@ interface ToolExecutionResult {
}
```
Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`:
The registry materializes and freezes the final accepted result immediately before `tools/result`. Its content, structured error, additional context, and presentation metadata must round-trip losslessly through JSON; an invalid outcome becomes a JSON-safe `isError` result, so the observed live outcome is safe for the later durable `tool/result` append.
Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/execute` wrappers return a `ToolExecutionResult`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`:
```ts type-equiv
type PreToolDecision =
@@ -144,7 +184,7 @@ type PostToolDecision =
| { kind: 'block'; feedback: ContentBlock[]; additionalContext?: HookContext }
```
Call `next()` to delegate to the default (allow / accept-unchanged), or return a decision to short-circuit. A `pre-execute` `deny` (or `ask`, which degrades to deny until the permission system lands) skips dispatch and yields an `isError` result; input rewrite is deliberately NOT offered on `PreToolDecision` (it would desync the pre-execution audit/history/UI from what ran — its own proposed RFC). A `post-execute` `accept` may replace the model-facing `content` (clean, because `tool/result` is logged after `execute()` returns); a `block` turns the call into an `isError` whose content is the corrective `feedback`. Core dispatch sits between the waterfalls as plain code; the tool body keeps its own try/catch so a thrown tool still reaches `post-execute` as an `isError`. An unregistered tool routes through the same catch as a tool-thrown error, so both failure classes get a structured `{ name, code }` (`ToolNotFoundError` → `UNKNOWN_TOOL`) — the loop records a failed tool call instead of failing the whole turn.
Call `next()` to delegate to the default (allow / dispatch / accept-unchanged), or return a decision/result to short-circuit. A `pre-execute` `deny` skips dispatch and yields an `isError` result. An `ask` resolves through the optional approval seam: only `allowed-once` proceeds, while every non-grant, missing channel/service, or agent-less request becomes a normalized denial. A registered `ToolGuard` then runs and can still impose a final denial. Input rewrite is deliberately NOT offered on `PreToolDecision` because it would desync the pre-execution audit/history/UI from what ran. A `post-execute` `accept` may replace the model-facing `content`; a `block` turns the call into an `isError` whose content is the corrective `feedback`. The synchronous `tools/result` notification then receives the frozen execution identity and a deep-frozen result snapshot after every wrapper, post decision, and outer error catch; observers cannot transform the outcome or race each other through payload mutation, and one observer failure neither changes the result nor starves peers. An unregistered tool routes through the same catch as a tool-thrown error, so both failure classes get a structured `{ name, code }` (`ToolNotFoundError` → `UNKNOWN_TOOL`) — the loop records a failed tool call instead of failing the whole turn.
## The structured-output schema subset
docs/development.i18n.yaml
+2 -2
View File
@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write
development.md: bd6f6b561480419abea7a42a44b4078e2c59b1cb
development.zh.md: 54bf19765d2b4dc419e6b71684dbcfcd28230541
development.md: ea5f2e5d08acbaf1dfce4661530218dbf1a051b9
development.zh.md: 50877796f2ff47ad46cc67b35f3cd7b5704c8315
docs/development.md
+1 -1
View File
@@ -67,7 +67,7 @@ These hooks do not exactly mirror CI. Notably, `pre-push` runs unit tests withou
## CI gates
The keyless GitHub workflow has eight jobs: five Node 24 lanes run static gates, lint, coverage, snapshot replay, and artifact gates separately, and three compatibility jobs run `pnpm run check:node-compat` on Node 22.19, 24, and 26. The lane schedulers fan out independent gates from `package.json`: constraints, typecheck, lint, coverage, snapshot replay, `doc-sync` members, module-graph freshness, `knip`, and the echo-agent smoke test.
The keyless GitHub workflow has eight jobs: five Node 24 lanes run static gates, lint, coverage, snapshot replay, and artifact gates separately, and three compatibility jobs run `pnpm run check:node-compat` on Node 22.19, 24, and 26. The compatibility command runs the TypeScript typecheck and a keyless workflow-workerthread source-launch smoke on every runtime, so the matrix proves that the source graph typechecks and that a real unbuilt Worker loader path executes; the other lane schedulers fan out independent gates from `package.json`: constraints, lint, coverage, snapshot replay, `doc-sync` members, module-graph freshness, `knip`, and the echo-agent smoke test.
`pnpm run build` feeds the artifact lane, and `publint`, `verify-node-next-types`, and built-bin smoke tests wait for build output. The separate real-API workflow runs `pnpm run test:e2e` with a secret and `DSH_E2E_MAX_WORKERS=14`.
docs/development.zh.md
+1 -1
View File
@@ -67,7 +67,7 @@ vendor manifest 守卫检查 `vendor/*/src` 下的改动是否连同对应的 `v
## CI 门禁
keyless GitHub 工作流有八个 job：五个 Node 24 lane 分别运行 static gates、lint、coverage、snapshot replay 和 artifact gates，三个兼容性 job 在 Node 22.19、24 和 26 上运行 `pnpm run check:node-compat`。各 lane 调度器并发运行来自 `package.json` 的独立门禁：constraints、typecheck、lint、coverage、snapshot replay、`doc-sync` 成员、module graph 新鲜度、`knip` 和 echo-agent 冒烟测试。
keyless GitHub 工作流有八个 job：五个 Node 24 lane 分别运行 static gates、lint、coverage、snapshot replay 和 artifact gates，三个兼容性 job 在 Node 22.19、24 和 26 上运行 `pnpm run check:node-compat`。兼容性命令会在每个运行时上运行 TypeScript 类型检查和 keyless 的 workflow-workerthread 源码启动冒烟测试，因此该矩阵既证明源码图能通过类型检查，也会实际执行一条未构建的 Worker loader 路径；其他 lane 调度器并发运行来自 `package.json` 的独立门禁：constraints、lint、coverage、snapshot replay、`doc-sync` 成员、module graph 新鲜度、`knip` 和 echo-agent 冒烟测试。
`pnpm run build` 供给 artifact lane，`publint`、`verify-node-next-types` 和 built-bin 冒烟测试等待 build 输出。单独的真实 API 工作流带密钥运行 `pnpm run test:e2e`，并设置 `DSH_E2E_MAX_WORKERS=14`。
docs/event-producer-consumer.md
+40 -28
View File
@@ -7,40 +7,52 @@ This matrix shows which packages dispatch each harness-owned event and which pac
| Event | Mode | Declared in | Dispatchers | Listeners |
| --- | --- | --- | --- | --- |
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:265`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:272`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:476`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:357`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) |
| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:370`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:290`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:394`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:441`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:305`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:281`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:451`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:464`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) |
| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) |
| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) |
| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
| `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) |
| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |
| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) |
| `session/created` | `emit` | [`packages/core/session/src/index.ts:39`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`emit`) | [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence) |
| `session/event` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`emit`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`parallel`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:98`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | - | [`tool-subagent`](../packages/subagent/tool-subagent) |
| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:38`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - |
| `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:44`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:132`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:111`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:127`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:91`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
| `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence) |
| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - |
| `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:101`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
| `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
| `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - |
| `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:128`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:148`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) |
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:101`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:163`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
| `workflow/agent-end` | `emit` | [`packages/workflow/workflow/src/index.ts:96`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/agent-start` | `emit` | [`packages/workflow/workflow/src/index.ts:85`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/end` | `emit` | [`packages/workflow/workflow/src/index.ts:106`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/log` | `emit` | [`packages/workflow/workflow/src/index.ts:77`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/phase` | `emit` | [`packages/workflow/workflow/src/index.ts:70`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/start` | `emit` | [`packages/workflow/workflow/src/index.ts:62`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/log` | `emit` | [`packages/workflow/workflow/src/index.ts:75`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/phase` | `emit` | [`packages/workflow/workflow/src/index.ts:68`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
| `workflow/start` | `emit` | [`packages/workflow/workflow/src/index.ts:60`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
## Non-harness or undeclared event strings seen in package source
| Event string | Dispatchers | Listeners |
| --- | --- | --- |
| `internal/dispatch` | - | [`invariants`](../packages/support/invariants) |
Maintenance mode: hybrid generated: Cordis event declarations and most producer/listener edges are AST-scanned; dynamic dispatch sites are classified in `scripts/gen-doc-graphs.ts`.
docs/glossary.md
+17
View File
@@ -0,0 +1,17 @@
# Glossary
Domain vocabulary for the DeepSeek Harness SDK uses one canonical term per concept. Terms link to their entries with standard Markdown anchors; implementation detail stays in package READMEs and RFCs.
FIXME(glossary-completeness): Expand this glossary before the first release so it covers the SDK's other core and capability subsystems, not only agent scope.
## agent-scope
- **scope** — the unit of per-agent registration: a contribution (tool, prompt section, variable, restriction, listener) is either *global* (visible to every agent) or *scoped* (owned by exactly one [scope key](#scope-key)). Two levels, flat: scoped registrations do not inherit down to subagents; subtree behavior is expressed with [lineage](#lineage) data, never scope structure.
- **scope key** — the opaque identity a scope is keyed by, compared by object identity. The harness convention: a live agent is the key of its own scope. <a id="scope-key"></a>
- **agent context (`agent.ctx`)** — the agent's scoped context; registrations through it are scope-visible AND scope-lifetime (one fact drives both), and listeners on it participate in that agent's scope-filtered dispatches. Registry-subject events may remain deliberately unfiltered under their own event contracts.
- **scope carrier** — the `thisArg` a scope-filtered dispatch carries (built by `scopeTarget`); its filter admits untagged listeners plus the subject's own. A *subject-less* carrier (no key) admits untagged listeners only.
- **scoped dispatch** — the rule: an event about one agent's activity dispatches with that agent's carrier. Events about a registry itself (a tool was added) are *registry-subject* and stay unfiltered.
- **shadowing** — most-specific-wins name resolution: a scoped tool/section/variable replaces its same-named global twin for that scope alone. The per-agent persona and per-agent tool-variant mechanism.
- **restriction / scope-local registration** — a restriction (`tools.restrict`) filters the GLOBAL tool surface for one scope (compose by intersection); scope-local registrations are merged after that filter. A filtered-away global tool is absent from the prompt AND refuses execution, indistinguishably from a nonexistent one.
- **setup window** — the creation slot where a creator composes an agent's scoped world (`CreateAgentOptions.setup`): after the scope and agent object exist but before the agent or session is published, `agent/session-start` fires, or the first prompt is assembled. Setup registers; it never drives the agent.
- **lineage** — parent/child facts carried as data (`parentSession`, `subagentDepth`); never affects visibility. <a id="lineage"></a>
docs/module-graph.md
+83 -25
View File
@@ -20,6 +20,7 @@ flowchart TD
pkg_agent["agent"]
pkg_agent_core["agent-core"]
pkg_agent_loop["agent-loop"]
pkg_scope["scope"]
pkg_session["session"]
pkg_system_prompt["system-prompt"]
pkg_tools["tools"]
@@ -27,6 +28,7 @@ flowchart TD
subgraph group_bash["packages/bash"]
pkg_bash["bash"]
pkg_bash_local["bash-local"]
pkg_bash_sandbox["bash-sandbox"]
pkg_tool_bash["tool-bash"]
end
subgraph group_fs["packages/fs"]
@@ -35,6 +37,11 @@ flowchart TD
pkg_fs_policy["fs-policy"]
pkg_tool_fs["tool-fs"]
end
subgraph group_skill["packages/skill"]
pkg_skill["skill"]
pkg_skill_local["skill-local"]
pkg_tool_skill["tool-skill"]
end
subgraph group_compact["packages/compact"]
pkg_compact["compact"]
pkg_compact_basic["compact-basic"]
@@ -87,6 +94,7 @@ flowchart TD
pkg_app_boot["app-boot"]
pkg_stdio_agent["stdio-agent"]
pkg_tool_ask_user["tool-ask-user"]
pkg_user_approval["user-approval"]
pkg_user_interaction["user-interaction"]
end
subgraph group_code_runtime["packages/code-runtime"]
@@ -96,30 +104,40 @@ flowchart TD
subgraph group_guard["packages/guard"]
pkg_repeat_tool_guard["repeat-tool-guard"]
end
subgraph group_sandbox["packages/sandbox"]
pkg_sandbox["sandbox"]
pkg_sandbox_local["sandbox-local"]
end
subgraph group_workflow["packages/workflow"]
pkg_tool_workflow["tool-workflow"]
pkg_workflow["workflow"]
pkg_workflow_workerthread["workflow-workerthread"]
end
pkg_llm --> pkg_brand
pkg_bash --> pkg_brand
pkg_code_runtime_worker --> pkg_code_runtime
pkg_llm_deepseek --> pkg_llm
pkg_llm_pi_ai --> pkg_llm
pkg_session --> pkg_brand
pkg_session --> pkg_llm
pkg_session --> pkg_scope
pkg_system_prompt --> pkg_llm
pkg_bash_local --> pkg_bash
pkg_bash_local --> pkg_timeout
pkg_system_prompt --> pkg_scope
pkg_fs --> pkg_brand
pkg_fs --> pkg_llm
pkg_web --> pkg_llm
pkg_sandbox --> pkg_llm
pkg_agent --> pkg_brand
pkg_agent --> pkg_llm
pkg_agent --> pkg_scope
pkg_agent --> pkg_session
pkg_agent --> pkg_system_prompt
pkg_bash --> pkg_brand
pkg_bash --> pkg_sandbox
pkg_bash --> pkg_session
pkg_fs_local --> pkg_fs
pkg_fs_policy --> pkg_fs
pkg_skill_local --> pkg_fs
pkg_skill_local --> pkg_skill
pkg_compact --> pkg_llm
pkg_compact --> pkg_session
pkg_web_fetch_local --> pkg_timeout
@@ -127,34 +145,51 @@ flowchart TD
pkg_web_search_deepseek --> pkg_web
pkg_web_search_exa --> pkg_web
pkg_web_search_perplexity --> pkg_web
pkg_hook_protocol --> pkg_bash
pkg_hook_protocol --> pkg_session
pkg_session_persistence --> pkg_session
pkg_llm_replay --> pkg_llm
pkg_llm_replay --> pkg_session
pkg_tools --> pkg_agent
pkg_tools --> pkg_code_runtime
pkg_tools --> pkg_llm
pkg_tools --> pkg_session
pkg_tools --> pkg_system_prompt
pkg_sandbox_local --> pkg_llm
pkg_sandbox_local --> pkg_sandbox
pkg_bash_local --> pkg_bash
pkg_bash_local --> pkg_timeout
pkg_compact_basic --> pkg_agent
pkg_compact_basic --> pkg_compact
pkg_compact_basic --> pkg_llm
pkg_compact_basic --> pkg_session
pkg_hook_protocol --> pkg_bash
pkg_hook_protocol --> pkg_session
pkg_session_persistence_jsonl --> pkg_session
pkg_session_persistence_jsonl --> pkg_session_persistence
pkg_session_persistence_sqlite --> pkg_session
pkg_session_persistence_sqlite --> pkg_session_persistence
pkg_invariants --> pkg_agent
pkg_invariants --> pkg_llm
pkg_invariants --> pkg_scope
pkg_invariants --> pkg_session
pkg_user_approval --> pkg_agent
pkg_user_approval --> pkg_brand
pkg_user_approval --> pkg_llm
pkg_user_approval --> pkg_scope
pkg_user_approval --> pkg_session
pkg_user_approval --> pkg_system_prompt
pkg_user_interaction --> pkg_agent
pkg_user_interaction --> pkg_llm
pkg_workflow --> pkg_agent
pkg_workflow --> pkg_brand
pkg_workflow --> pkg_llm
pkg_tools --> pkg_agent
pkg_tools --> pkg_code_runtime
pkg_tools --> pkg_llm
pkg_tools --> pkg_scope
pkg_tools --> pkg_session
pkg_tools --> pkg_system_prompt
pkg_tools --> pkg_user_approval
pkg_bash_sandbox --> pkg_bash
pkg_bash_sandbox --> pkg_bash_local
pkg_bash_sandbox --> pkg_sandbox
pkg_agent_loop --> pkg_agent
pkg_agent_loop --> pkg_llm
pkg_agent_loop --> pkg_scope
pkg_agent_loop --> pkg_session
pkg_agent_loop --> pkg_session_persistence
pkg_agent_loop --> pkg_system_prompt
@@ -162,15 +197,22 @@ flowchart TD
pkg_tool_bash --> pkg_agent
pkg_tool_bash --> pkg_bash
pkg_tool_bash --> pkg_llm
pkg_tool_bash --> pkg_sandbox
pkg_tool_bash --> pkg_system_prompt
pkg_tool_bash --> pkg_tools
pkg_tool_bash --> pkg_user_approval
pkg_tool_fs --> pkg_fs
pkg_tool_fs --> pkg_llm
pkg_tool_fs --> pkg_session
pkg_tool_fs --> pkg_system_prompt
pkg_tool_fs --> pkg_tools
pkg_tool_skill --> pkg_agent
pkg_tool_skill --> pkg_llm
pkg_tool_skill --> pkg_skill
pkg_tool_skill --> pkg_tools
pkg_subagent --> pkg_agent
pkg_subagent --> pkg_llm
pkg_subagent --> pkg_scope
pkg_subagent --> pkg_tools
pkg_tool_web --> pkg_llm
pkg_tool_web --> pkg_system_prompt
@@ -182,6 +224,7 @@ flowchart TD
pkg_tool_todo --> pkg_agent
pkg_tool_todo --> pkg_session
pkg_tool_todo --> pkg_tools
pkg_tool_cordis --> pkg_scope
pkg_tool_cordis --> pkg_tools
pkg_hooks_codex --> pkg_agent
pkg_hooks_codex --> pkg_hook_protocol
@@ -189,10 +232,13 @@ flowchart TD
pkg_hooks_codex --> pkg_session
pkg_hooks_codex --> pkg_tools
pkg_acp --> pkg_agent
pkg_acp --> pkg_bash
pkg_acp --> pkg_llm
pkg_acp --> pkg_sandbox
pkg_acp --> pkg_session
pkg_acp --> pkg_session_persistence
pkg_acp --> pkg_tools
pkg_acp --> pkg_user_approval
pkg_acp --> pkg_user_interaction
pkg_tool_ask_user --> pkg_agent
pkg_tool_ask_user --> pkg_tools
@@ -209,8 +255,11 @@ flowchart TD
pkg_agent_core --> pkg_invariants
pkg_agent_core --> pkg_llm
pkg_agent_core --> pkg_session
pkg_agent_core --> pkg_skill
pkg_agent_core --> pkg_skill_local
pkg_agent_core --> pkg_system_prompt
pkg_agent_core --> pkg_tool_bash
pkg_agent_core --> pkg_tool_skill
pkg_agent_core --> pkg_tools
pkg_subagent_acp --> pkg_agent
pkg_subagent_acp --> pkg_llm
@@ -238,6 +287,7 @@ flowchart TD
pkg_workflow_workerthread --> pkg_agent
pkg_workflow_workerthread --> pkg_brand
pkg_workflow_workerthread --> pkg_llm
pkg_workflow_workerthread --> pkg_session
pkg_workflow_workerthread --> pkg_subagent
pkg_workflow_workerthread --> pkg_tools
pkg_workflow_workerthread --> pkg_workflow
@@ -268,58 +318,66 @@ flowchart TD
| --- | --- | --- |
| [`brand`](../packages/util/brand) | `util` | — |
| [`timeout`](../packages/util/timeout) | `util` | — |
| [`scope`](../packages/core/scope) | `core` | — |
| [`skill`](../packages/skill/skill) | `skill` | — |
| [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | `subagent` | — |
| [`acp-snapshot`](../packages/support/acp-snapshot) | `support` | — |
| [`app-boot`](../packages/ui/app-boot) | `ui` | — |
| [`code-runtime`](../packages/code-runtime/code-runtime) | `code-runtime` | — |
| [`llm`](../packages/llm/llm) | `llm` | [`brand`](../packages/util/brand) |
| [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand) |
| [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime) |
| [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`llm`](../packages/llm/llm) |
| [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`llm`](../packages/llm/llm) |
| [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
| [`system-prompt`](../packages/core/system-prompt) | `core` | [`llm`](../packages/llm/llm) |
| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
| [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) |
| [`system-prompt`](../packages/core/system-prompt) | `core` | [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) |
| [`fs`](../packages/fs/fs) | `fs` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
| [`web`](../packages/web/web) | `web` | [`llm`](../packages/llm/llm) |
| [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
| [`sandbox`](../packages/sandbox/sandbox) | `sandbox` | [`llm`](../packages/llm/llm) |
| [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
| [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) |
| [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) |
| [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) |
| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) |
| [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
| [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) |
| [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) |
| [`web-search-exa`](../packages/web/web-search-exa) | `web` | [`web`](../packages/web/web) |
| [`web-search-perplexity`](../packages/web/web-search-perplexity) | `web` | [`web`](../packages/web/web) |
| [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) |
| [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) |
| [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
| [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
| [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) |
| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
| [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) |
| [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
| [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) |
| [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
| [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) |
| [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
| [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) |
| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) |
| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) |
| [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) |
| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) |
| [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) |
| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |
| [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) |
| [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
| [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
| [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`tools`](../packages/core/tools) |
| [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |
| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) |
| [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
| [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) |
| [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
| [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tools`](../packages/core/tools) |
| [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) |
| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) |
| [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
| [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) |
| [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
| [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
| [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
| [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
| [`acp-agent`](../packages/ui/acp-agent) | `ui` | [`acp`](../packages/ui/acp), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) |
docs/persistence-catalog.md
+62 -16
View File
@@ -11,6 +11,40 @@ The on-disk envelope around every payload is `SessionEvent` — `type`, monotoni
## Events
### `approval/*`
#### `approval/asked` — log-only
An approval question was put to the answerer chain — log-only audit (like `hook/*`; NOT a surface event, carries no `surfaceOp`). `id` pairs it with the `approval/decided` that always follows; `toolName` is the tool the question is about, `callId` the exact tool call when the asker had one, `reason` the asker's human-readable explanation (e.g. a hook's permission-decision reason).
```ts persistence-catalog
'approval/asked': { id: ApprovalRequestId; toolName: string; callId?: CallId; reason?: string }
```
Types: [CallId](core-data-structures/core.md)
Source: [`packages/ui/user-approval/src/index.ts:84`](../packages/ui/user-approval/src/index.ts)
#### `approval/decided` — log-only
The outcome of a prior `approval/asked` (same `id`) — log-only audit. Exactly one per ask, appended when the outcome is known: a decision, a cancellation, or the fail-closed `'unavailable'`.
```ts persistence-catalog
'approval/decided': { id: ApprovalRequestId; outcome: ApprovalOutcome }
```
Source: [`packages/ui/user-approval/src/index.ts:95`](../packages/ui/user-approval/src/index.ts)
#### `approval/policy` — log-only
The session's approval policy was switched — log-only, durable, replayable, never in the model transcript (the model learns the policy from the prompt section and the narrator's notices). The LAST such event is the session's override (effectiveApprovalPolicy); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user).
```ts persistence-catalog
'approval/policy': { policy: ApprovalPolicy }
```
Source: [`packages/ui/user-approval/src/index.ts:107`](../packages/ui/user-approval/src/index.ts)
### `assistant/*`
#### `assistant/chunk` — log-only
@@ -23,7 +57,7 @@ Raw stream chunk — token-level replay fidelity.
Types: [StreamChunk](core-data-structures/llm-streaming.md)
Source: [`packages/core/session/src/types.ts:313`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:322`](../packages/core/session/src/types.ts)
#### `assistant/message` — surface
@@ -35,7 +69,19 @@ Assembled assistant message for one step (derived history uses this). Carries th
Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md)
Source: [`packages/core/session/src/types.ts:320`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:329`](../packages/core/session/src/types.ts)
### `bash/*`
#### `bash/sandbox-mode` — log-only
The session's sandbox mode was switched — log-only (like `approval/*`; NOT a surface event, carries no `surfaceOp`): durable and replayable, never in the model transcript. The LAST such event is the session's override (effectiveSandboxMode); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user; see the tool layer's narrator).
```ts persistence-catalog
'bash/sandbox-mode': { mode: SandboxMode }
```
Source: [`packages/bash/bash/src/session-mode.ts:31`](../packages/bash/bash/src/session-mode.ts)
### `compact/*`
@@ -83,7 +129,7 @@ In-session context injection (file-change notices, subdir AGENTS.md, skill conte
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:311`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:320`](../packages/core/session/src/types.ts)
### `hook/*`
@@ -119,7 +165,7 @@ A queued prompt an `agent/prompt-submit` listener VETOED — the durable record
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:305`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:314`](../packages/core/session/src/types.ts)
### `request/*`
@@ -131,7 +177,7 @@ Full snapshot of the EpochHeader the NEXT request is built under, with the Reque
'request/header': { header: EpochHeader; reason: RequestHeaderReason }
```
Source: [`packages/core/session/src/types.ts:365`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:374`](../packages/core/session/src/types.ts)
#### `request/header-delta` — log-only
@@ -141,7 +187,7 @@ Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta
'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] }
```
Source: [`packages/core/session/src/types.ts:382`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:391`](../packages/core/session/src/types.ts)
### `steering/*`
@@ -155,7 +201,7 @@ Steering content injected between steps of a running turn.
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:338`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:347`](../packages/core/session/src/types.ts)
### `step/*`
@@ -167,7 +213,7 @@ Closes step `step` of turn `turn`.
'step/end': { turn: number; step: number }
```
Source: [`packages/core/session/src/types.ts:292`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:301`](../packages/core/session/src/types.ts)
#### `step/start` — log-only
@@ -177,7 +223,7 @@ Opens step `step` of turn `turn` — one model call plus the tool executions it
'step/start': { turn: number; step: number }
```
Source: [`packages/core/session/src/types.ts:290`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:299`](../packages/core/session/src/types.ts)
### `todo/*`
@@ -193,7 +239,7 @@ NOT a SurfaceEventType: it produces no LLM message and never reaches `deriveMess
Types: [TodoItem](core-data-structures/session.md)
Source: [`packages/core/session/src/types.ts:352`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:361`](../packages/core/session/src/types.ts)
### `tool/*`
@@ -207,7 +253,7 @@ The model requested one tool invocation: `name` with the raw `arguments` JSON st
Types: [CallId](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:326`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:335`](../packages/core/session/src/types.ts)
#### `tool/code-dispatch` — log-only
@@ -219,7 +265,7 @@ One bridged sub-dispatch from a `run_code` program: the parent `run_code` call i
Types: [CallId](core-data-structures/core.md)
Source: [`packages/core/tools/src/code-mode.ts:36`](../packages/core/tools/src/code-mode.ts)
Source: [`packages/core/tools/src/code-mode.ts:38`](../packages/core/tools/src/code-mode.ts)
#### `tool/result` — surface
@@ -231,7 +277,7 @@ A completed tool call's model-facing result, plus an optional tool-private `meta
Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:336`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:345`](../packages/core/session/src/types.ts)
### `turn/*`
@@ -245,7 +291,7 @@ Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awai
Types: [TurnEndReason](core-data-structures/session.md)
Source: [`packages/core/session/src/types.ts:288`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:297`](../packages/core/session/src/types.ts)
#### `turn/start` — log-only
@@ -257,7 +303,7 @@ Opens turn `turn`. `trigger` records what started it — a drained message batch
Types: [TurnTrigger](core-data-structures/session.md)
Source: [`packages/core/session/src/types.ts:282`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:291`](../packages/core/session/src/types.ts)
### `user/*`
@@ -271,4 +317,4 @@ A user-visible prompt (queued message drained at turn start).
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:294`](../packages/core/session/src/types.ts)
Source: [`packages/core/session/src/types.ts:303`](../packages/core/session/src/types.ts)
docs/rfc/INDEX.md
+9 -3
View File
@@ -8,8 +8,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| Title | First proposed |
|---|---|
| [Agent Client Protocol (ACP) support — drive the coding agent from external editors](proposed/feature/2026-06-14-acp-agent-client-protocol.md) | 2026-06-14 |
| [Multiplex concurrent ACP sessions over one connection](proposed/feature/2026-06-14-acp-multi-session.md) | 2026-06-14 |
| [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 |
| [Claude Code and Codex subagent backends (out-of-process delegation to external coding agents)](proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md) | 2026-07-07 |
| [Interactive side sessions and merge-back](proposed/feature/2026-07-08-interactive-side-sessions.md) | 2026-07-08 |
@@ -50,6 +48,8 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| Title | First proposed |
|---|---|
| [Agent Client Protocol (ACP) support — drive the coding agent from external editors](implemented/feature/2026-06-14-acp-agent-client-protocol.md) | 2026-06-14 |
| [Multiplex concurrent ACP sessions over one connection](implemented/feature/2026-06-14-acp-multi-session.md) | 2026-06-14 |
| [Code Mode — the model writes TypeScript against the tool registry](implemented/feature/2026-06-15-code-mode.md) | 2026-06-15 |
| [Filesystem tool schemas — model-facing read/write/edit shapes](implemented/feature/2026-06-17-filesystem-tool-schemas.md) | 2026-06-17 |
| [Rich ACP bash rendering — the terminal card via the `_meta` convention](implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) | 2026-06-18 |
@@ -64,10 +64,14 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| [SessionStore fork API](implemented/feature/2026-06-30-session-store-fork-api.md) | 2026-06-30 |
| [Subagent lifecycle enrichment — lastAssistantMessage (observe-only)](implemented/feature/2026-06-30-subagent-observe-enrich.md) | 2026-06-30 |
| [Dynamic workflows — a script-driven multi-agent orchestration seam](implemented/feature/2026-07-05-dynamic-workflows.md) | 2026-07-05 |
| [Skill system — progressive disclosure instructions for agents](implemented/feature/2026-07-05-skill-system.md) | 2026-07-05 |
| [The approval seam — one-shot permission decisions over a waterfall of answerers](implemented/feature/2026-07-06-approval-seam.md) | 2026-07-06 |
| [Explicit model-facing tool order](implemented/feature/2026-07-06-explicit-tool-order.md) | 2026-07-06 |
| [The subprocess sandbox — confinement seam, native runners, escalation, and per-session modes](implemented/feature/2026-07-06-sandbox.md) | 2026-07-06 |
| [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 |
| [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 |
| [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 |
| [Configure subagent persona, tool visibility, and depth](implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) | 2026-07-12 |
### Simplification
@@ -99,7 +103,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
|---|---|
| [Provider-neutral content-block vocabulary owned by dsh-llm](implemented/architecture/2026-06-11-content-block-vocabulary.md) | 2026-06-11 |
| [Custom typed tool-schema DSL instead of schemastery](implemented/architecture/2026-06-11-custom-schema-dsl.md) | 2026-06-11 |
| [Dev-mode invariants over compile-time deep-readonly](implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md) | 2026-06-11 |
| [Source-owned session immutability and dev-mode invariants](implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md) | 2026-06-11 |
| [Event-sourced sessions with derived message history](implemented/architecture/2026-06-11-event-sourced-sessions.md) | 2026-06-11 |
| [Microkernel — extension via Cordis event taxonomy, one concrete loop](implemented/architecture/2026-06-11-microkernel-event-taxonomy.md) | 2026-06-11 |
| [Runtime arg validation at the model boundary](implemented/architecture/2026-06-11-runtime-arg-validation.md) | 2026-06-11 |
@@ -130,6 +134,8 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| [Subagent provider-lifecycle events — `subagent/provider-added` / `subagent/provider-removed`](implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md) | 2026-07-05 |
| [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 |
| [Tool-call timeout policy as a plugin](implemented/architecture/2026-07-07-tool-call-timeout-policy.md) | 2026-07-07 |
| [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 |
| [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 |
### Process
docs/rfc/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md
+41 -12
View File
@@ -1,29 +1,58 @@
# RFC: Dev-mode invariants over compile-time deep-readonly
# RFC: Source-owned session immutability and dev-mode invariants
Status: implemented
## Problem
The session log is append-only by contract, but the types don't enforce it: `session.events` returns `readonly SessionEvent[]` whose *elements* are mutable, and `deriveMessages()` handed the logged `content` arrays/blocks out by reference. The loop then passes those derived messages into the `agent/request` waterfall and on to adapters, where mutating the request is sanctioned — so a request middleware could reach back and rewrite history, silently breaking replay equivalence and the derived-history guarantee. Separately, the event taxonomy (turn/step nesting, seq monotonicity, tool-call/result pairing, legal status transitions) was asserted only where individual tests happened to look.
The session log needs two different protections: immutable ownership of each stored fact, and checks for relationships among facts across time and service seams. Conflating them in an optional development plugin would leave production history vulnerable; trying to express both through TypeScript readonly types would not create a runtime boundary or describe relational rules.
Two ways to defend the log: make immutability part of the type (`DeepReadonly<SessionEvent>` on the way out), or catch corruption at runtime in dev. The runtime-validation proposal took the runtime route; [the deep-readonly proposal](../../rejected/architecture/2026-06-11-immutable-public-surfaces.md) took the type route.
The session log is the durable source of truth for replay, request reconstruction, persistence, and user-visible history. Code outside the session package must be able to inspect that history without retaining a reference that can rewrite it later, and inputs accepted from callers must not remain connected to caller-owned mutable objects.
Immutability of individual values is only half of the contract. A log can contain perfectly immutable records whose sequence, turn/step nesting, tool-call pairing, scoped delivery, or reconstructed model request is wrong. Those rules relate multiple records or services and cannot be established by freezing one object.
TypeScript readonly types are not a sufficient runtime boundary. They disappear when the program runs, a cast can bypass them, and a recursive `DeepReadonly<T>` would spread through every log and message consumer even though some downstream request-processing APIs intentionally work with mutable values.
## Decision
Reject the pervasive `DeepReadonly<T>` type flip. Instead:
Responsibility is split between an always-on storage boundary and optional development assertions.
1. **Always-on:** `deriveMessages()` deep-clones the content it emits (one `structuredClone` per derived message). In-flight mutation of a request can no longer reach the log — this is the real fix, and it costs nothing meaningful next to a model call.
2. **Dev-mode:** a new `dsh-invariants` plugin (pure listeners, off in production, on in tests and demos) asserts the event contract and `Object.freeze`s logged event data so any *other* code that mutates a logged event throws instead of corrupting silently. Seeded sessions are frozen and checked on `session/created` (the constructor copies the seed without emitting `session/event`).
### Session owns immutable history
The invariants encode the *real* contract, not an idealized one: a `tool/call` may have no `tool/result` (a thrown tool-execution pipeline step ends the turn), and both `idle→disposed` and `running→disposed` are legal.
`Session` accepts an event only after one recursive pass has materialized a lossless JSON snapshot. That pass rejects unsupported values and produces the exact detached record that enters the log, so validation and storage cannot observe different values from a stateful getter or retain caller-owned nested references.
The accepted event and all of its descendants are deep-frozen before publication. `append()` returns that owned frozen event, `session/event` observers receive the same record, and `session.events` returns a frozen array snapshot. A previously returned array does not grow after a later append. Seed records pass through the same validation, snapshot, and freeze boundary before construction succeeds.
This guarantee belongs in `Session`, not in an optional listener, because every composition relies on trustworthy history. A production deployment, a focused test, or a custom embedding receives the same storage semantics whether or not development support plugins are registered.
### Derived requests remain detached
`deriveMessages()` projects logged surface events into detached, deep-frozen `Message` objects and returns a fresh array snapshot. Request assembly can therefore combine derived history with other inputs without exposing a path back into the log. The cache reuses safe immutable projections rather than recloning the complete history for each model call.
### The invariants plugin checks relationships
`dsh-invariants` is a pure-listener development plugin. It does not freeze records and has no configuration; disposal removes only its assertions. It checks rules that require trace state or observation of another seam, including monotonic sequence numbers, turn and step nesting, tool-call/result pairing, legal agent-status transitions, subject-correct scoped dispatch, and equality between a loop-built request and the request reconstructed from its session-log prefix.
When the plugin attaches to an existing or seeded session, it replays the immutable log to rebuild trace state. This makes hot reload safe in the middle of a turn without giving the plugin ownership of session storage.
## Alternatives considered
**The pervasive `DeepReadonly<T>` type flip** ([the rejected proposal](../../rejected/architecture/2026-06-11-immutable-public-surfaces.md)) — compile-time only (a plugin casts straight through it), high type-noise across every log/message consumer and adapter, and it would force readonly types through code where mutation is the sanctioned API. The clone draws the mutable/immutable boundary exactly at "logged vs in-flight" without any of that noise.
### Pervasive deep-readonly types
[The rejected immutable-public-surfaces proposal](../../rejected/architecture/2026-06-11-immutable-public-surfaces.md) would apply a recursive readonly type across public log and message surfaces. That provides editor feedback but not a runtime guarantee: TypeScript types are erased and plugin code can cast through them. It also pushes readonly types into consumers where mutation is intentional. Runtime ownership at the `Session` boundary protects every caller without that type propagation.
### Development-only freezing
Freezing history only when an invariants plugin is installed would make the core guarantee composition-dependent. Code could pass development tests and still corrupt history in production or in a focused composition that omits the plugin. Storage immutability is therefore always on, while the more expensive relational checks remain opt-in development support.
### Clone only when deriving messages
Detaching `deriveMessages()` would protect the most common request path but leave other readers of `session.events`, append return values, and session-event observers able to mutate durable history. The log must protect its own boundary; derived projections are an additional isolation boundary, not a substitute.
## Consequences
- History corruption is caught loudly in tests and demos, at zero production cost and zero type noise. The trade-off is that the guarantee is dynamic (a dev-mode tripwire) rather than static.
- The invariants plugin doubles as executable documentation of the event taxonomy — the assertions are the contract.
- `Session.events` keeps its `readonly SessionEvent[]` type; no consumer churn.
- This folds in [the deep-readonly proposal](../../rejected/architecture/2026-06-11-immutable-public-surfaces.md) — there is no separate deep-readonly record; this records the decision to *not* pursue that approach. `InvariantError` is a plain `Error` with a `code` for now; a later taxonomy change can promote it.
- Every accepted live or seeded session event is detached from caller-owned inputs and deeply immutable before any observer can receive it.
- `session.events` exposes stable immutable snapshots instead of the private growing array.
- Request-side mutation cannot reach stored history through derived messages.
- Development builds can enable relational assertions without changing storage behavior, and disposing or omitting the plugin does not weaken log immutability.
- `dsh-invariants` has no `Config` surface because it has no behavior to tune.
- The runtime boundary carries a recursive snapshot-and-freeze cost once per accepted event; later readers and cached projections reuse the owned immutable records.
docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md
+4 -3
View File
@@ -10,9 +10,10 @@ The product principle is "everything is a plugin": hooks, /goal, /loop, dynamic
Pure Cordis event taxonomy. The loop's extension seams are typed events with deliberate dispatch modes:
- **waterfall** (around-middleware) where plugins mutate or veto: `agent/prompt-submit`, `agent/request`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`.
- **emit** (sync fire-and-forget) for notifications: turn/step boundaries, stream chunks, lifecycle, errors.
- **parallel** (awaited) for the one durability checkpoint: `session/flush`.
- **waterfall** (around-middleware) where plugins transform, veto, or wrap: `agent/prompt-submit`, `agent/request`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`.
- **serial** (awaited in listener order; a bail value stops later listeners) for ordered checkpoints: every `agent/pre-step` listener runs when all abstain, while the first stop returned from `agent/turn-stop` makes the terminal decision final.
- **parallel** (awaited fan-out) where every listener must get an independent chance: the `session/flush` durability checkpoint.
- **emit** (synchronous fire-and-forget) for notifications: turn/step boundaries, stream chunks, lifecycle, errors, and the contained immutable `tools/result` observation.
The event vocabulary lives in interface packages (dsh-agent declares the agent/* events); `@deepseek-ai/dsh-agent-loop` is the only concrete loop plugin and is itself swappable — nothing outside it may depend on it.
docs/rfc/implemented/architecture/2026-06-14-session-persistence.md
+3 -3
View File
@@ -6,7 +6,7 @@ Status: implemented
## Problem
Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../../proposed/feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible.
Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible.
The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append-only log the single source of truth and derives LLM history from it. Persistence had to stay faithful to that: persist the existing `SessionEvent` directly, with no parallel "persisted message" type that the log is converted to and from. The backend also had to be swappable — a file store now, a database store later — behind one interface.
@@ -23,7 +23,7 @@ Key choices recorded here because they are durable, contested, and surprising:
- **Append-only; a crashed turn is closed, never truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. The loop only flushes at `turn/end`, so a crash can leave a durable log whose final turn never closed: real, fully-written events sit after the last `turn/end`. **A single turn can be huge in a long-horizon task** (many steps, large tool output spanning a long autonomous run), so discarding the interrupted turn would silently destroy a large amount of real work — truncating a turn is wrong. Instead, on reload `load` PRESERVES those events and CLOSES the orphaned turn by durably appending the minimal synthetic boundary events: an error `tool/result` for every `tool-call` the crash left unanswered, then a `step/end` if a step was still open, then a `turn/end` carrying the merge-extensible `{ kind: 'interrupted' }` reason (a marker that records the turn was cut short by a crash, not completed by the model — no loop ever emits it). The synthetic tool results matter for resume correctness: the loop logs the `assistant/message` (carrying the `tool-call` blocks) BEFORE running the tools, so a crash mid-tool leaves calls without results; `deriveMessages()` would then replay a dangling assistant tool-call, which every provider rejects as an invalid transcript on the next request. Answering each orphaned call with an error result keeps the rehydrated history valid. `load` returns the balanced log, so a resumed session is immediately usable. The ONLY thing discarded is a never-fully-written **torn tail fragment** — a final record whose bytes (JSONL) or row were never completely flushed; that fragment is not a valid event and is dropped before the synthetic closers are written. A parse error or `seq` gap in the COMMITTED region (at or before the last real `turn/end`) is genuine corruption and makes the session unloadable.
- **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows.
- **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).)
- **Resume is an async factory, not a change to synchronous create.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on the resumed id (NOT `${agentId}-session`). The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent.
- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on the resumed id (NOT `${agentId}-session`). The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent.
## Alternatives considered
@@ -33,4 +33,4 @@ Format versioning: the header carries a `version`; `load` rejects any non-curren
## Consequences
Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and the foundation the ACP `session/load` ([ACP support](../../proposed/feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only / contiguous-seq / lazy-materialization / serializability semantics. This completes [event-sourced sessions](2026-06-11-event-sourced-sessions.md)'s deferred "real persistence backend" and resolves its `TODO(review)` on the event vocabulary: persisting the log freezes its shape, and the `assistant/chunk` fidelity question is answered above (persist verbatim).
Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and the foundation the ACP `session/load` ([ACP support](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only / contiguous-seq / lazy-materialization / serializability semantics. This completes [event-sourced sessions](2026-06-11-event-sourced-sessions.md)'s deferred "real persistence backend" and resolves its `TODO(review)` on the event vocabulary: persisting the log freezes its shape, and the `assistant/chunk` fidelity question is answered above (persist verbatim).
docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md
+5 -7
View File
@@ -16,9 +16,9 @@ A new `cancel()` verb on the `Agent` interface — the single public stop primit
### 2. `AgentHandle` async disposer
`ctx.agents.create`/`resume` (and the `AgentFactory` interface) return `AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **capability** — only the holder can tear down exactly this agent: stop its loop, `await` the loop's exit (true quiescence, not just the `disposed` status flip), unregister it, and remove its session from the store. `ctx.agents.get(id)` still returns a bare `Agent`. Config-created agents stay owned by the `AgentLoop` fiber (the handle is discarded). ACP holds each session's disposer in its `SessionRecord` and runs it on disconnect/teardown, so a bare client disconnect leaves no registered agent and no session-store entry — even when `session/load` races teardown (the just-resumed handle is disposed before the closed-guard throw).
`ctx.agents.create`/`resume` (and the `AgentFactory` interface) return `AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **consumer capability** — a registry observer holding only the bare `Agent` cannot tear it down. The caller fiber and registered factory provider are structural co-owners: caller unload enforces structured ownership, while provider unload must stop old instances whose scoped dependency surface resolves through that provider. All three paths reach the same memoized teardown: stop the loop, await its exit and idle flushes (true quiescence, not just the `disposed` status flip), detach the agent, detach its session, and unwind its scope. Each public ID becomes reusable when its exact registry entry detaches; there is no separate reservation-release phase. Config-created agents are already owned by the `AgentLoop` fiber (the handle is discarded). ACP holds each session's disposer in its `SessionRecord` and runs it on disconnect/teardown, so a bare client disconnect leaves no registered agent and no session-store entry — even when `session/load` races teardown (the just-resumed handle is disposed before the closed-guard throw).
**Teardown ORDER is load-bearing for durability**, and the implementation folds the session lifecycle into the agent's SINGLE composite cordis effect (`SessionStore.prepare`/`enter`/`announce`, replacing a sibling-effect split). A fiber unload disposes sibling effects concurrently (`Promise.all`), which would race the session's `onAppend` detach against the loop's closing `session/flush` and drop the closing `turn/end`; inside one effect the disposers run as an ordered LIFO chain (loop stopped + `await agent.done` BEFORE the session detaches), so the loop's final flush is captured on BOTH the handle's `dispose()` and a fiber unload. The register disposer's `agent/disposed` emit is contained (a throwing listener must not reject the chain and skip the later session detach).
**Teardown ORDER is load-bearing for durability**, and the implementation folds the session lifecycle into the agent's SINGLE composite cordis effect (`SessionStore.prepare`/`enter`/`announce`, replacing a sibling-effect split). A fiber unload disposes sibling effects concurrently (`Promise.all`), which would race removing the session store's append publication hooks against the loop's closing `session/flush` and drop the closing `turn/end`; inside one effect the disposers run as an ordered LIFO chain (loop stopped + `await agent.done` BEFORE the session detaches), so the loop's final flush is captured on BOTH the handle's `dispose()` and a fiber unload. The contained `agent/disposed` and `session/disposed` notifications cannot reject the chain or skip later teardown.
### 3. Bash owner token in the seam
@@ -33,16 +33,14 @@ These invariants hold and are pinned by tests:
- A `tool-bash` HMR reload does NOT make an existing background task readable or killable by a different session (ownership survives on the executor).
- Existing non-ACP demos still work without managing handles explicitly; config-created agents remain owned by the `AgentLoop` plugin fiber.
## Seam precondition (recorded)
## Session owner tokens are unique among live agents
The bash owner-token comparison relies on `session.header.id` being unique among live agents. The agent registry does NOT enforce this — it rejects a duplicate *agentId*, not a duplicate session id, and `createAgent` accepts an arbitrary `sessionId`. This is NOT reachable via ACP (UUID sessionId, `agentId === sessionId`, duplicate-load rejected), so it is not a live product hole, but a programmatic caller that registers two agents with the same session id would break bash isolation and mis-route the completion notice. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/impl/consumer split.
The planned resolution is to remove the precondition by construction — see [unify the agent id and the session id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md): once an agent IS its session (one id), the registry's existing unique-`agentId` check is a unique-session-id guarantee and no two live agents can share a session token.
The bash owner-token comparison relies on `session.header.id` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split.
## Alternatives considered
- **A public `BashTask.owner` field** instead of the `BashExecutor.ownerOf(id)` seam — rejected: one read path, no redundant API.
- **Sibling cordis effects for the agent's session lifecycle** — rejected: a fiber unload disposes sibling effects concurrently (`Promise.all`), racing the session's `onAppend` detach against the loop's closing `session/flush`; the single composite effect's ordered LIFO chain is what captures the closing `turn/end` on both disposal paths.
- **Sibling cordis effects for the agent's session lifecycle** — rejected: a fiber unload disposes sibling effects concurrently (`Promise.all`), racing removal of the store-owned append publication hooks against the loop's closing `session/flush`; the single composite effect's ordered LIFO chain is what captures the closing `turn/end` on both disposal paths.
- **A separate step-only `abort()` beside `cancel()`** — shipped originally, then removed as unused; `cancel()` is the single public stop primitive ([the public-stop-surface RFC](../simplification/2026-06-20-public-agent-stop-surface.md)).
## Consequences
docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md
+2 -2
View File
@@ -28,9 +28,9 @@ This is the foundational change in a stack that adds a Hooks subsystem; it estab
## Consequences
- The loop no longer emits any boundary mirror; `closeStep` appends `step/end` only and `closeTurn` appends `turn/end` only. A throwing `step/end`/`turn/end` session-event listener is the surviving boundary-listener failure path (contained inside `closeStep`/`closeTurn` — `Session.append` pushes the event before notifying listeners, so the boundary is durable and the turn closes balanced regardless).
- The loop no longer emits any boundary mirror; `closeStep` appends `step/end` only and `closeTurn` appends `turn/end` only. `Session.append` owns post-commit observer containment, so a throwing boundary observer cannot change the turn outcome or starve later consumers; an acceptance or internal validation failure still escapes before the boundary enters the log.
- Tests that observed boundaries via the removed emits now observe the durable `turn/start`/`turn/end`/`step/start`/`step/end` session events — the behavior they pin (boundary ordering, step counting) is unchanged; only the feed they read moved to the canonical one. The tests that exercised a *throwing turn-boundary emit listener* were deleted, because that code path no longer exists (there is no emit to throw from). Per [AGENTS.md "tests document behavior, not golden truth"](../../../../AGENTS.md), the behavior and its test moved (or died) together.
- The loop marks the step open (`stepOpen = true`) BEFORE appending `step/start`, because `Session.append` pushes the event to the log before notifying `session/event` listeners (validation throws happen earlier, before the push — see [the session append contract](../../../core-data-structures/session.md)). So a throwing `step/start` session-event listener runs with the step already open and the event already in the log: the loop's outer catch then calls `closeStep()`, which appends the balancing `step/end`, and the turn closes balanced with an error (`turn/start → step/start → step/end → turn/end` — verified by the invariants oracle in the regression test). Closing the open step is owed precisely because the marker is set first.
- The loop marks the step open (`stepOpen = true`) only after `append('step/start')` returns. Internal dispatch validation runs before the log push and may reject without opening a step; post-commit `session/event` observer failures are contained inside `Session.append`. The marker therefore represents exactly the committed boundary that owes a later `step/end`.
- The full realization of this is [the simplification RFC "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that RFC's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable `steering/message`.
- The cordis events catalog (`docs/cordis-catalog/events.md`) is regenerated to drop the mirror events.
docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
+6 -6
View File
@@ -16,11 +16,11 @@ The assembled system prompt had four defects, all of one family: facts the harne
## Decision
**One principle: every fact in the prompt has exactly one owner.** The model name and workspace are config/session facts → the harness exposes them as variables and the persona references them. Per-tool semantics and when-to-use → the tool's `description`. Cross-call habits a description cannot carry → the tool package's prompt section. Identity and behavior → the deployment's persona, and nothing else.
**One principle: every fact in the prompt has exactly one owner.** The model name and workspace are config/session facts → the harness exposes them as variables and the persona references them. Per-tool semantics and when-to-use → the tool's `description`. Cross-call habits a description cannot carry → the tool package's prompt section. Harness provenance → the static `harness:identity` section. Deployment role and behavior → the deployment's persona.
### Assemble context
`SystemPrompt.assemble(context)` takes an `AssembleContext` — declared EMPTY and merge-extensible in `dsh-system-prompt` (the package stays agnostic of who assembles); `dsh-agent` declaration-merges `agent?: Agent` onto it (a new type-level edge `agent → system-prompt`, no cycle — `tools` already depends on both). The loop passes `{ agent }` each step; section text providers become `string | ((context) => string)` (zero-arg providers stay valid), and the `system-prompt/assemble` waterfall gains the context parameter so a listener can filter or extend per agent.
`SystemPrompt.assemble(context)` takes a merge-extensible `AssembleContext`. `dsh-system-prompt` declares the optional `scope` selector used for scoped routing, while `dsh-agent` declaration-merges the optional typed `agent` field onto it (a type-level edge `agent → system-prompt`, with no runtime dependency cycle). The loop calls `assembleContextFor(agent)` each step so both fields identify the same agent; section text providers may read that context, and the `system-prompt/assemble` waterfall receives it so a listener can filter or extend per agent.
### Prompt variables
@@ -30,15 +30,15 @@ Plugins contribute named values via `ctx.systemPrompt.variable(name, provider)`;
### Persona as the order-0 section
`dsh-system-prompt` itself registers the two harness-owned sections (they must survive a swapped loop plugin, so they do NOT live on `dsh-agent-loop`): the static `harness:identity` at order `-100` — every prompt opens by stating the agent is powered by the DeepSeek Harness SDK — and `deployment:persona` at order 0, whose text is the plugin's own `persona` config. The persona is per-DEPLOYMENT, not per-agent: every agent in the context (subagents included) renders the same one, `AgentOptions.systemPrompt` is deleted along with the per-agent forwarding plumbing (the app configs' `systemPrompt` keys become a `persona` key routed to this plugin through `dsh-agent-core`), and the ACP bridge and `dsh-tool-subagent` stop carrying persona configuration entirely. The loop's special-case join is deleted: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. Order bands are now convention: harness identity `-100`, persona `0`, tool guidance `100–199`; other negative orders also render before the persona.
`dsh-system-prompt` itself registers the two harness-owned sections (they must survive a swapped loop plugin, so they do NOT live on `dsh-agent-loop`): the static `harness:identity` at order `-100` — every prompt opens by stating the agent is powered by the DeepSeek Harness SDK — and the global default `deployment:persona` at order 0, whose text is the plugin's own `persona` config. `AgentOptions.systemPrompt` and the loop's special-case join are gone: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. An agent-scoped section with the same `deployment:persona` name shadows the default for that agent; programmatic setup may register one directly, and the subagent persona feature installs one before publishing an in-process child when the selected provider supports it. Order bands are convention: harness identity `-100`, persona `0`, tool guidance `100–199`; other negative orders also render before the persona.
### Tool guidance ownership
Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship in every request — the YAML prose was ~fully redundant with them. Sections carry only the cross-call habits a single call's description cannot: `dsh-tool-bash` contributes `tool:bash` (order 105) — check the `[exit code: N]` marker on every result; `dsh-tool-fs`'s read section gains the "not shell commands like cat" contrast. `todo_write` and the subagent tools need NO section — their descriptions already carry the whole contract. The leaf personas shrink to identity + behavior (verify your work; keep answers brief), and the welcome banner stops enumerating tools.
### The subagent context contract
### The subagent conversation-history descriptor
`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag (`providerWording`): the fork instance now tells the model the child inherits the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md).
`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag (`providerWording`): the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md).
## Alternatives considered
@@ -56,7 +56,7 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship
## Shipped invariants
- `renderPrompt(assemble({ agent }))` for the coding-agent example renders the persona FIRST (with the agent's model name interpolated), then the fs/bash/web guidance sections; the loop has no other prompt-composition path.
- `renderPrompt(await assemble(assembleContextFor(agent)))` for the coding-agent example renders the harness identity, then the persona (with the agent's model name interpolated), then the fs/bash/web guidance sections; the loop has no other prompt-composition path.
- The `subagent_fork` schema description says the child inherits the conversation; the `subagent` one says it does not. The tool follows its provider: absent before the backend activates, present after, gone when the backend unloads, re-worded from the fresh provider on reload.
- Unknown/valueless/malformed/unbalanced `{{…}}` references throw with the section name in the message; duplicate section, variable, and tool-name registrations all throw.
- Snapshot goldens are prompt-independent by construction: llm-replay keys replay on (turn, step) chunk streams and never re-verifies the outgoing request.
docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md
+1 -1
View File
@@ -24,7 +24,7 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro
**The loop, transmission-stateless.** Per step: render assembly (every step — value comparison needs no change-signal discipline, and a section that varies per step surfaces as a *logged* header event per step instead of a silent bust) → on the instance's FIRST step only, the `agent/session-prefix` waterfall — request-ONLY messages fronting the entire derived history (a frozen empty seed, contributions returned as an extension of `next()`; the home for session-stable openers that must NOT become history — a skills catalog, an AGENTS.md digest), deep-frozen and cached on the instance so reuse is structural and the prefix cannot drift mid-session — → `agent/pre-step`, carrying the composed prefix (compaction's surface mutations land before derivation, and its pressure gate counts the prefix this instance will actually send — never a previous instance's logged one, which could under-gate a resumed/forked instance whose contributor grew) → **messages snapshot, then `step/start` appended as the next operation in the same synchronous frame** → seed the call config (first request of the instance: from `AgentOptions`, so explicit options always beat the logged baseline — fork model-overrides and resume reconfiguration stay correct; afterwards: from the folded header) → the `agent/request` waterfall, re-typed `(agent, turn, step, config: LlmCallConfig, next) → LlmCallConfig` — a frozen seed and a returned replacement are ALL a listener shapes; durable content flows through the log channels (`inject()`, steering, prompt-submit `additionalContext`, sections via `system-prompt/assemble`) — → the header event the request owes the log, carrying the prefix as `messagePrefix` (no session event carries it, so the header is its only durable record; resume = a new instance = a recompose, anchored by its `'resume'` snapshot) → build `GenerateOptions` from `messagePrefix + snapshot` + header, deep-freeze (`deepFreeze` exempts the `AbortSignal`, the one live control channel — freezing one breaks `AbortController.abort()`), dispatch. The loop's per-instance bookkeeping is one boolean plus the cached prefix: whether this instance has logged its anchoring snapshot, and what it composed.
**The reconstruction boundary is `step/start`, unconditionally.** A step's messages are the derivation over `events[0..stepStartSeq)`. Because the snapshot precedes the `step/start` append in the same synchronous frame, nothing can enter this request past the boundary: an `agent.inject()` from an `agent/request` listener (or any concurrent task, or a `session/event` listener firing on `step/start` itself) lands in the log after the boundary and joins the NEXT request. For waterfall-window appends this matches the prior loop (it also derived before its waterfall); for a synchronous `step/start` listener it is a deliberate change — such a listener could previously reach the current request — and `agent/pre-step` is the sanctioned seam for content that must affect the CURRENT request. A step's header for reconstruction is the fold after its own `request/header*` event (which sits between its `step/start` and first response event) or the fold carried forward.
**The reconstruction boundary is `step/start`, unconditionally.** A step's messages are the derivation over `events[0..stepStartSeq)`. Because the snapshot precedes the `step/start` append in the same synchronous frame, an `agent.inject()` from an `agent/request` listener or any concurrent task lands after the boundary and joins the NEXT request. `session/event` is observe-only during publication: a reentrant append is rejected until the current callback list drains, preventing nested event delivery from overtaking the event being observed. `agent/pre-step` is the sanctioned seam for content that must affect the CURRENT request. A step's header for reconstruction is the fold after its own `request/header*` event (which sits between its `step/start` and first response event) or the fold carried forward.
**Enforcement.** Dev-mode ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)), on `llm/stream`: a frozen request with a live `sessionId` — the loop-built marker; hand-built one-shots are unfrozen and skipped — must carry messages deep-equal to the folded header's `messagePrefix` followed by the boundary derivation — the derivation rebuilt through a FRESH `Session` over `events[0..stepStartSeq)` so the live cache cannot vouch for itself — and header fields equal to `foldRequestHeader` over the log. There is no divergence allowance and nothing to allow: no seam can put unlogged content into a request — the `agent/session-prefix` seam's product enters only because the header event records it first. `prepend: true` only defends against the replay adapter's short-circuit (an append-registered listener); two prepended listeners have no defined mutual order in cordis, so correctness rests on the seq-bounded fold, never on listener timing. Measurement stays lean: the with-key e2e ([request-cache.e2e.ts](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts)) proves `usage.cacheReadTokens > 0` on every request after the first against the live API, and per-step usage in the log is the production observable — a header event or compaction shows up as a cache-read collapse on the next step.
docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md
+170
View File
@@ -0,0 +1,170 @@
# RFC: The agent is a registration scope
Status: implemented
## Problem
One application needs to share infrastructure across many agents while letting each agent have its own tools, prompt contributions, policies, and listeners. Shared adapters, persistence, and user interfaces belong to the deployment; a persona, tool variant, or listener often belongs to one agent.
A separate service graph per agent duplicates shared infrastructure. One global registration graph has the opposite failure: an agent-specific contribution can leak into unrelated agents. Contributors need one ordinary registration mechanism that determines both who can see a contribution and when it is cleaned up.
The mechanism also needs a publication boundary. An agent must not become visible before its local world is complete, and teardown must retain that world until final work has stopped.
## Decision
Every live agent owns one flat registration layer exposed as `agent.ctx`. Code registers through the context that owns a contribution; scope-aware services combine deployment-global registrations with exactly one matching agent layer; operations choose that layer from their real agent; and the layer exists for the agent's complete published lifetime.
Cordis is the plugin framework underneath the SDK. A Cordis **context** is the object plugins use to access services and register effects whose cleanup follows that context. The [Cordis primer](../../../cordis-primer.md) explains the framework in more detail.
For most contributors, the complete contract is four rules:
| Question | Rule |
|---|---|
| Where do I register behavior for one agent? | Call the ordinary registration API through `agent.ctx` |
| What does an operation for an agent see? | Deployment globals plus that agent's layer, using the owning service's merge rules |
| Which scoped listeners run? | Unscoped listeners plus listeners registered for the operation's agent |
| How long does the layer exist? | Setup completes before publication; disposal keeps it until work reaches quiescence |
The scope is flat. Resolution never walks parent or sibling scopes, and lifetime ownership does not imply registration inheritance.
```mermaid
flowchart LR
plain["Plain plugin context<br/>cleanup follows the plugin"] -->|"registers into"| globalLayer["Deployment-global layer"]
agentAContext["agentA.ctx<br/>cleanup follows Agent A"] -->|"registers into"| agentALayer["Agent A layer"]
agentBContext["agentB.ctx<br/>cleanup follows Agent B"] -->|"registers into"| agentBLayer["Agent B layer"]
operationA["Operation for Agent A"] -->|"selects"| agentAView["Agent A view<br/>globals plus A local"]
globalLayer --> agentAView
agentALayer --> agentAView
operationB["Operation for Agent B"] -->|"selects"| agentBView["Agent B view<br/>globals plus B local"]
globalLayer --> agentBView
agentBLayer --> agentBView
```
The missing cross-edges are the isolation rule: Agent A's local registrations do not enter Agent B's view, and a parent's registrations do not enter a child merely because the parent owns the child's lifetime.
The companion [runtime-design RFC](2026-07-12-agent-scope-runtime-design.md) explains the implementation and correctness reasoning. The [subagent composition-controls RFC](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the separate `persona`, `toolFilter`, and `maxDepth` feature.
### Registration origin chooses visibility and cleanup
A registration made through a plain plugin context is deployment-global and is disposed with that plugin. The same method called through `agent.ctx` contributes to one agent and is disposed with that agent's scope.
| Registration origin | Default visibility | Disposed with |
|---|---|---|
| Plain plugin context | Every eligible agent view | Registering plugin |
| `agent.ctx` | Exactly that agent's view | Agent scope |
Tools, prompt sections and variables, tool restrictions, guards, and scoped event listeners adopt this contract. Named local values ordinarily shadow a same-named global value for that agent; each owning service documents exceptions and merge behavior.
The ordinary contributor pattern is to register the complete local world during agent setup:
```js
const handle = await ctx.agents.create({
agentId: AgentId('reviewer'),
sessionId: SessionId('reviewer-session'),
agentOptions: { model: 'model-name' },
setup(agentCtx) {
agentCtx.systemPrompt.section({
name: 'deployment:persona',
order: 0,
text: 'Review code, but do not modify files.',
})
agentCtx.tools.register({
name: 'review_summary',
description: 'Return the review summary.',
parameters: { type: 'object', properties: {} },
async execute() {
return [{ type: 'text', text: 'review complete' }]
},
})
},
})
ctx.tools.get('review_summary') // undefined: not global
ctx.tools.get('review_summary', handle.agent) // the reviewer-local tool
await handle.dispose()
ctx.tools.get('review_summary', handle.agent) // undefined: scope is gone
```
Setup receives a full trusted Cordis context so it can compose ordinary plugins and services. Its contract is composition-only: driving or publishing the in-flight agent through casts or internal registry calls is unsupported.
### The operation chooses the view
Registration origin and operation subject are separate facts. Calling a service through `agent.ctx` selects where a new registration belongs; it does not bind later reads to that agent.
Tool lookup and execution receive the agent they act for. Prompt assembly receives an assembly context for the agent whose request is being built. Event dispatch receives its domain subject. This keeps shared service instances reusable across agents while making each operation's view explicit.
Only services that adopt the scope contract resolve an agent layer. `agent.ctx` does not automatically change arbitrary Cordis service calls.
### Scoped events keep routing separate from event data
An event about Agent A normally reaches unscoped listeners and A-scoped listeners, not B-scoped listeners. An event without an agent subject reaches only unscoped listeners.
At the Cordis level, `Scoped<T>` is an opaque routing receiver. It carries the filter used to choose listeners but is not the domain object. Event signatures therefore keep the real `Agent`, tool execution, approval request, or other subject as an explicit argument that listeners can inspect.
A listener registered with `{ global: true }` deliberately bypasses contextual audience filtering while its cleanup still follows the registering context. Registry-membership notifications remain unfiltered because they describe shared registry state rather than one agent's operation. The generated [event catalog](../../../cordis-catalog/events.md) is the exhaustive event reference.
### Creation publishes last and disposal revokes last
`ctx.agents.create()` and `resume()` build an unpublished session, scope, agent, and driver. They await `setup`, admit the final session and agent entries, announce them in order, start the loop, and only then return a handle.
An optional creation signal cancels work only while create or resume is pending. After the promise resolves, the returned `AgentHandle` owns explicit disposal.
If loading, setup, admission, or publication fails, the private transaction rolls back everything it prepared. Concurrent operations using the same caller-supplied live ID may both reach setup, but final registry entry admits only one; every loser rejects and cleans its private resources. Sequential reuse after awaited disposal remains valid.
`AgentHandle.dispose()` reverses the boundary. It deactivates creation or driving, waits for synchronous publication to unwind, stops and drains the driver and final session flushes, detaches the agent and session, and finally disposes the scope. Repeated or racing disposal requests join one completion promise.
The calling Cordis context and the concrete AgentLoop factory are structural co-owners. Unloading either disposes the transaction or live agent.
```mermaid
flowchart TB
request["Create or resume"] --> privateWorld["Build private session, scope, agent, and driver"]
privateWorld --> setup["Await composition through agent.ctx"]
setup --> admission["Admit final session and agent entries"]
admission --> publish["Announce lifecycle and start the driver"]
publish --> live["Return AgentHandle"]
privateWorld -->|"failure, cancellation, or owner loss"| rollback["Rollback private work"]
setup -->|"failure, cancellation, or owner loss"| rollback
admission -->|"duplicate or owner loss"| rollback
publish -->|"listener failure or owner loss"| rollback
live -->|"handle or owner disposal"| quiesce["Stop and drain work"]
rollback --> quiesce
quiesce --> detach["Detach agent, then session"]
detach --> revoke["Dispose the agent scope"]
```
## Security and authority are non-goals
Agent scopes compose trusted same-process registrations. They do not sandbox plugins, define a parent-to-child authority lattice, freeze grants at creation, or guarantee that a child can do no more than its parent.
A parent may own a child whose visible tools are wider than its own because lifetime ownership does not donate or cap registrations. A plugin holding a Cordis context also runs in the same process and can call available services directly.
Deployments that need non-escalation require a separate authority representation, propagation rule, and execution check. Parent-subset grants, creation-time authorization snapshots, explicit future-grant APIs, and generic capability/output/termination tags are outside this decision.
## Alternatives considered
The rejected designs either separate visibility from cleanup, cover only one registration family, duplicate shared infrastructure, or conflate lifetime ownership with inheritance.
### Pass an agent option to every registration
An API such as `tools.register(definition, { agent })` repeats scope plumbing in every registry and permits visibility ownership to drift from cleanup ownership. Registering through `agent.ctx` makes both facts follow one Cordis effect owner.
### Filter events while keeping registries global
Listener filtering prevents the wrong hook from running but does not scope tool schemas, executable lookup, prompt sections, variables, or other registered data. Agent-local composition would still require temporary global mutation.
### Create one service graph per agent
The required view is shared deployment services plus one local registration layer. Per-agent graphs duplicate adapters and complicate shared persistence, provider registries, and application boot.
### Inherit parent registration scopes
Parentage describes lifetime and conversation lineage, not a universal merge policy. Hierarchical lookup makes unrelated services inherit accidentally and cannot define security without a separate authority model.
## Consequences
Contributors use one familiar pattern: register shared behavior through a plugin context, register local behavior through `agent.ctx`, select the real agent on operations, and dispose the returned handle. Setup is atomic from an observer's perspective, and teardown preserves local behavior until work stops.
The cost is explicit subject selection, asynchronous programmatic creation, and service-specific scope adoption. Flat registration scope is intentionally not authority, and subagent composition controls remain a separate feature rather than hidden scope semantics.
docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md
+390
View File
@@ -0,0 +1,390 @@
# RFC: Agent-scope runtime design and correctness
Status: implemented
## Problem
The [agent-scope contract](2026-07-08-agent-scope-contexts.md) is simple for contributors: register through `agent.ctx`, resolve one global-plus-agent view, publish only after setup, and retain the scope until work stops. The runtime must preserve that contract across a cooperative plugin framework, asynchronous creation, reentrant listeners, durable session commits, and worker or process failure.
The main design risk is adding a second mechanism for every race. Separate reservations, readiness sentinels, cancellation relays, snapshot layers, and protection registries can mirror the same fact until no reader can tell which one is authoritative. That machinery also encourages the runtime to treat trusted typed calls as hostile serialization boundaries.
The implementation needs enough state to preserve real ownership and settlement boundaries, but no more. A correctness reviewer must be able to follow one fact from acceptance through publication and teardown without reconciling parallel representations.
## Decision
The runtime uses one mechanism per independent fact. Scope routing has an opaque carrier; each live registry object has one entry record; each create or resume operation has one transaction; typed same-process calls borrow readonly values; real data boundaries materialize once; the cooperative prompt-assembly result is authoritative; and worker/process code retains separate terminal and quiescence state only where different owners can genuinely race.
The design can be skimmed as seven choices:
| Problem | Authoritative mechanism |
|---|---|
| Select global plus one agent's registrations | Opaque scope key and routing carrier |
| Own one live agent or session | One registry entry captured by its disposer |
| Coordinate create/resume | One `AgentCreationTransaction` |
| Protect durable, queued, model, or wire data | Materialize once at that boundary |
| Pass typed values inside one process | Readonly borrowed contract |
| Compose the model-visible prompt and tool surface | One shared tool view plus the authoritative assembly-waterfall result |
| Coordinate subagent, worker, and process shutdown | One cancellation signal plus the independent terminal/quiescence facts of that boundary |
The rest of this RFC expands those choices in dependency order. It first explains the Cordis mechanics, then scope routing, creation and session commit, tools and prompts, subagents and workflows, and finally the checks that make the reasoning executable.
The [July 8 RFC](2026-07-08-agent-scope-contexts.md) remains the contributor contract. The separate [subagent composition-controls RFC](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns `persona`, `toolFilter`, and `maxDepth`; this document discusses only how their setup fits the lifecycle.
## Cordis model: context, fiber, effect, receiver, and waterfall
Five Cordis ideas are required to understand the implementation. A context selects services and registration ownership; a fiber is one live plugin or child lifecycle; an effect attaches cleanup to a fiber; an event receiver selects listeners; and a waterfall lets listeners transform or veto an operation in sequence.
### A context is an ownership path through one service graph
All agents share one Cordis service graph. A derived context does not clone `ToolRegistry`, `SystemPrompt`, persistence, or model adapters; it changes how registrations made through that context are tagged and which effects own their cleanup.
`agent.ctx` is such a derived context. Service calls still reach the shared instances, while a registration can inspect its calling context and store a contribution under the nearest scope key. Ordinary plugin contexts carry no scope key and therefore register globally.
### Fibers and effects make cleanup structural
A Cordis fiber is the live instance created when a plugin or child context is activated. Its state records whether that lifecycle is active, unloading, failed, or disposed. `ctx.effect()` and `ctx.on()` return disposers and also attach those disposers to the registering fiber, so unloading a plugin or agent scope removes everything registered through that context without a separate inventory.
The vendored Cordis fiber implementation establishes ownership before arbitrary setup or `internal/plugin` observers run. A reentrant unload can see the child fiber or effect that has started, reject effects added after unload begins, and join cleanup already started through a public single-shot disposer. Teardown observers are contained individually so one callback cannot prevent structural cleanup.
These are framework lifecycle guarantees rather than agent-specific policy. Agent creation depends on them because setup can activate arbitrary plugins and synchronously reenter owner disposal.
### Receivers route listeners; waterfalls compose decisions
Cordis filters listeners using the dispatch receiver (`this`), while harness listeners need an explicit agent, execution, request, or other subject. `Scoped<T>` marks the receiver expected by a scoped event declaration, but the runtime carrier deliberately exposes no subject API.
Product helpers therefore construct the carrier and pass the domain subject separately. This prevents listener routing from becoming an alternate object model and keeps event signatures understandable without knowledge of carrier internals.
A Cordis waterfall is middleware-style dispatch. Each listener receives `next()`: calling it delegates to the remaining listeners and base operation, while returning without it vetoes or replaces the downstream result. Waterfalls power prompt assembly and tool policy; ordinary emit events notify synchronously, and parallel events await all listeners without a veto result.
## Scope routing: one opaque key selects one layer
The scope package implements the smallest object needed for Cordis routing. Its carrier holds only a composed service filter and scope predicate, while the package records the opaque key privately and exposes the scope fiber's quiescent disposer separately.
### Scope identity uses object identity
A `ScopeKey` is an opaque object compared by identity. The harness uses the live `Agent` as its own key, but the primitive is domain-neutral and supports other scoped owners.
`createScope(parent, key)` returns a scope whose `ctx` shares the parent's services and whose effects are tagged with that key. `scopeOf(ctx)` reads the nearest registration key. `scopeTarget(base, key)` creates the event receiver whose filter preserves the base receiver's Cordis service filter, then admits unscoped listeners and listeners with that exact key.
The receiver is a small carrier rather than a transparent proxy for the domain object. Code that needs the agent receives the explicit event argument; code that needs registration ownership receives `agent.ctx`.
### Registry reads overlay one exact map
Scope-aware registries store global contributions separately from identity-keyed local contributions. A read resolves the global layer and at most one local layer; it never traverses parentage.
Each service retains its domain rule. Named prompt values and tools use local shadowing, tool restrictions filter globals before local tools are added, and events select listener audiences rather than registered data. Scope supplies identity and ownership, not a universal merge algorithm.
### Fused dispatch helpers prevent subject drift
`agentEvents(context, agent)` constructs the agent's carrier and injects the same agent as the event subject. Session, tool, approval, prompt, and subagent services likewise derive routing from the object they already own instead of accepting an unrelated key.
The type marker rejects ordinary bare-receiver mistakes, and development invariants cover direct JavaScript or casted dispatch. The subject remains explicit because routing correctness and useful event data are different concerns.
## Agent creation: one transaction owns the complete operation
Create and resume are one asynchronous lifecycle with several phases, not several lifecycles. `AgentCreationTransaction` owns caller and factory liveness, optional cancellation, private resources, publication, rollback, and the memoized teardown observed by every owner.
### Registry entries are the only live identity records
AgentRegistry and SessionStore each keep one entry per live object. The entry holds the stable ID, object, scoped carrier, and the small amount of publication or append state that belongs to that object.
A detach closure captures its exact entry. It deletes only when the map still points to that entry, so an old disposer cannot delete a later object that reuses the same ID. No registry rereads a mutable caller object to decide identity.
There is no reservation API. Caller-supplied IDs are admitted at final entry. Concurrent same-ID operations may both complete private setup; exactly one final `enter()` succeeds, and every loser rolls its private resources back. Sequential reuse is valid after the earlier disposer reaches quiescence.
### The transaction owns preparation before awaiting it
The transaction is installed under both the calling Cordis context and the concrete AgentLoop factory before persistence load or setup can suspend. It also observes an optional create/resume signal until the public operation settles.
Create prepares a new Session. Resume loads and validates the persisted Session before preparing the same live session identity. Both paths then build the scope, agent, and driver and invoke the same setup/publication algorithm.
The factory stores concrete trace targets but invokes them through a caller-bound Cordis trace. This preserves dependency origin and caller ownership without stacking trace proxies.
### Setup is trusted composition inside a private world
Setup receives the full child context and may await plugin activation. It can register tools, prompt sections, restrictions, listeners, and other effects, but the public contract does not support driving or publishing the in-flight agent through casts or internal registry calls.
The transaction races asynchronous load and setup against deactivation rather than waiting forever for a promise owned by external code. If cancellation or owner unload wins, public creation rejects after transaction-owned cleanup even when the external promise never settles.
### Publication has one ordered commit path
Publication admits and announces resources in the order required by observers:
1. Enter the session.
2. Enter the agent.
3. Announce `session/created`.
4. Announce `agent/created`.
5. Enable public driving.
6. Emit `agent/session-start`.
7. Start the driver.
The agent never drives before both registries and creation notifications agree. A synchronous listener may veto or dispose an owner; the transaction records publication in progress and waits for that callback stack to unwind before teardown continues. Every creation announcement that begins has a matching disposal announcement during rollback.
The sequence diagram isolates the non-obvious race: a synchronous creation listener can request disposal while the publication call stack still owns both registry entries. Teardown must deactivate immediately but wait for that stack to unwind before stopping and detaching anything.
```mermaid
sequenceDiagram
participant Tx as AgentCreationTransaction
participant Registries
participant Listener as Synchronous listener
participant Driver
Tx->>Tx: mark publication in progress
Tx->>Registries: announce agent/created
Registries->>Listener: invoke inside the same call stack
Listener->>Tx: dispose reentrantly
Tx->>Tx: deactivate, teardown waits for publication
Tx-->>Listener: disposal request accepted
Listener-->>Registries: return
Registries-->>Tx: announcement unwound
Tx->>Tx: resolve publication settlement
Tx->>Driver: stop and drain
Tx->>Registries: detach agent, then session
Tx->>Tx: dispose scope and resolve teardown
```
### Teardown preserves work before revoking registrations
Every teardown request joins one memoized path. The order is:
1. Deactivate creation or driving and let synchronous publication finish.
2. Stop and drain the driver, including idle injection flushes.
3. Detach the agent.
4. Detach the session.
5. Dispose the agent scope.
6. Retire transaction ownership tracking.
This order lets final agent and session events use the matching scoped listeners and keeps persistence observers attached through the final flush. Scope disposal comes last because registration revocation is the externally visible lifetime boundary.
## Session append: materialize, validate, commit, notify
Session events cross a durable boundary, so append owns their data. The rest of the algorithm uses one attached entry and one commit point.
### Durable data is materialized once
Session headers, seeds, and appended events are lossless JSON data. The Session constructor or append path materializes and validates them before storage and exposes frozen snapshots, so later caller mutation cannot change persistence, replay, or model reconstruction.
This is a real ownership boundary: the values leave the caller, may be persisted, and must reconstruct the same request later. It is intentionally stricter than a typed same-process callback or registry definition.
### Pre-commit listeners can veto; post-commit observers cannot
Append follows one sequence:
1. Materialize the durable event and surface intent.
2. Claim the SessionEntry and reject reentrant append on that entry.
3. Resolve scoped callbacks and run internal invariant validation.
4. Push exactly once; this is the commit point.
5. Notify each observer independently, containing synchronous and asynchronous failures.
6. Release append state and honor a detach requested during publication.
No observer error makes a committed event look uncommitted, and one bad listener cannot starve later listeners. Session invariants stage their transition before commit and apply it only when the same event reaches the contained post-commit observer.
`flush()` starts every persistence listener and awaits every result before reporting failure. This deliberate all-settled behavior prevents a synchronous failure from starving another backend or final flush.
## Trust boundaries: copy only when ownership actually changes
The runtime distinguishes typed in-process contracts from serialization and durability boundaries. This is the main simplification rule for values and callbacks.
| Boundary | Ownership rule |
|---|---|
| Typed service/plugin call in the same process | Borrow readonly values and callbacks |
| Parsed plugin configuration or external file | Validate semantic and structural input |
| Queued inbox message | Materialize before asynchronous consumption |
| Model/tool JSON input or output | Materialize at the model/tool boundary |
| Durable session or persistence data | Materialize and validate before commit |
| Worker, process, or wire message | Serialize, validate, and own the decoded value |
Tests that fabricate hostile getters, replace typed callbacks after handoff, or cast fake service objects do not define a production contract by themselves. The runtime keeps checks where data crosses a parser, queue, model, durable, file, worker, process, or wire boundary and relies on readonly types plus plugin discipline inside the trusted process.
Callback containment is separate from data ownership. Listeners are arbitrary extension code and can throw even when their arguments are trusted; publication and post-commit paths still contain failures according to their event contract.
## Tools and prompts: one view, authoritative assembly, committed outcomes
Tool presentation and execution share one private resolver. Prompt assembly remains trusted cooperative composition: registries supply the ordered input, and the assembly waterfall's returned value is exactly what the loop logs and sends. Execution uses separate one-way boundaries only where policy or outcome settlement must be monotonic.
### One resolver defines the tool view
The private resolver applies the current presentation mode, live global restrictions, exact local overlay, and local shadowing. Schemas, lookup, execution, Code Mode SDK generation, and restriction validation all use that resolver or its pre-restriction global-name view.
The [subagent composition-controls RFC](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md#tool-filtering-is-one-live-global-view-rule) owns the user-visible allow/deny semantics. The implementation requirement is agreement: a filtered-away global cannot remain executable through a different lookup path, and a locally shadowed definition is the same definition presented and executed.
`ToolRestriction` accepts readonly allow/deny names and compiles them into internal sets. Multiple restrictions intersect. Public `visible()` and `knownNames()` methods are unnecessary because only the registry needs the intermediate views.
### Tool execution owns identity and boundary materialization
The registry assigns every execution a fresh branded `Symbol` token. Nested Code Mode calls carry the outer token as `parent`, so structured output can correlate an inner capture with its enclosing `run_code` result by identity.
A fresh registry-assigned Symbol provides collision-free execution identity without a WeakSet membership registry. Callers cannot supply the execution's own token through `ToolExecutionInput`; they only receive the pipeline-owned `ToolExecution` after the registry creates it. This is a trusted typed contract, not a runtime defense against arbitrary casts or JavaScript callers.
Arguments are materialized once where model/tool JSON enters the pipeline. Pre-, around-, and post-execute listeners operate on the typed execution and decisions. Call ID correlation, approval, monotonic guards, and Code Mode nesting remain explicit relational checks.
After the last post-execute listener, the registry materializes and freezes the accepted final result once. Every synchronous `tools/result` observer receives that exact committed object, and observer failures are contained individually. An outer pipeline failure is normalized into a committed error result, so observers can discard staged work against the same authoritative boundary.
### The assembly waterfall owns the final model-visible composition
SystemPrompt first resolves the global-plus-agent sections, variables, and tool providers into a deterministic registry contribution. The scope-filtered `system-prompt/assemble` waterfall may then reorder, replace, add, or remove any section, variable, or schema. Its returned assembly is authoritative; there is no later restoration pass and no finality metadata on ordinary prompt sections, tool definitions, or provider results.
This is a trusted same-process extension seam, not an authority boundary. A listener that changes Code Mode's `run_code` schema or `tools:sdk` instructions, or a structured child's capture schema or instruction, owns preserving a coherent protocol in the assembly it returns. ToolRegistry still reserves `run_code` against ordinary tool registration and restriction because those are registry invariants, but assembly middleware remains free to transform the final model-visible surface.
Scope solves the real isolation problem directly. Structured-output contributions register in the child's exact scope, while Code Mode derives its transport and SDK from the same resolved tool view. A second named-protection system would need another ownership and collision rule across arbitrary schema providers—including providers that intentionally contribute duplicate names—without creating a new trust boundary.
### Structured output commits only authoritative outcomes
Structured output combines child-scoped composition with a two-phase execution commit. The child registers its `structured_output` tool and instruction before publication; a trusted assembly listener may transform those ordinary contributions and is responsible for preserving the protocol if the child is expected to complete. The tool body validates a candidate and stages it by the current `ToolExecution`, but successful capture is decided only by immutable `tools/result` observations.
For a native call, the observer deletes the stage and commits its value only when that exact execution's final result succeeds. A post-execute block or outer pipeline failure therefore cannot leave a captured value behind.
For a Code Mode SDK call, the inner successful result records `{ parentToken, value }` rather than committing. The observer waits for the `run_code` execution whose token matches `parentToken` and commits only if that outer final result also succeeds. Program failure, runtime abort, or outer post-policy denial discards the pending value.
Once a value is pending or committed, a scoped monotonic guard denies later tool calls. After commit, the ordinary serial `agent/turn-stop` listener returns a stop decision after continuation and steering have already folded. A schema-validation failure remains an ordinary `INVALID_ARGS` tool error and leaves the child able to retry within the same turn.
Pure Code Mode's registry contribution omits `structured_output` from native wire schemas and exposes it through the generated SDK. The assembly waterfall may deliberately change that presentation; execution still validates against the child-scoped definition, and the listener owns the consistency of any alternate model-visible route it creates.
### Three execution boundaries are deliberately one-way
Prompt assembly is intentionally cooperative, but three execution facts need one-way settlement after their extensible stages:
| Boundary | Final power | Why ordinary listener order is insufficient |
|---|---|---|
| Tool pre-policy | Deny monotonically | A later listener must not re-allow an already denied call |
| Tool result | Observe the immutable committed outcome | Structured output must commit only the result that actually escaped the pipeline |
| Turn continuation | Stop after ordinary continuation folding | A committed terminal output must end the turn |
`ToolGuard` is the monotonic policy registry. Committed tool observation is the contained `tools/result` point described above. Terminal structured output listens on the ordinary serial `agent/turn-stop` fold after normal continuation and steering decisions; no public `strictSerial()` dispatcher is needed for the typed listener contract.
### Skill and approval services trust typed callers
Skill registry definitions and approval policies are readonly same-process contracts. Their services do not clone callback objects or defend against post-handoff callback replacement.
Skill still validates external skill files and parsed provider output, routes catalogs through the calling agent's tool view, and disposes registrations exactly. Approval still resolves policy, observes cancellation, routes `approval/request` by `request.agent`, records the durable audit pair, and contains answerer and post-commit observer failures.
## Subagents: readiness is the start promise
Subagent startup has one ownership transfer. The provider owns partial resources until its start promise fulfills with a ready published run; the caller owns the returned run and must dispose it.
### The service contract has one cancellation channel
`SubagentProvider.start()` and `SubagentService.start()` return `Promise<SubagentRun>`. The promise fulfills only after the backend has established the child it promises, so callers and `subagent/start` observers never need a second `run.started` readiness promise.
`SubagentStartRequest.signal` is required. Aborting it requests cancellation during startup and after readiness. `SubagentRun.dispose()` also requests cancellation and awaits quiescence. There is no separate public `run.cancel()` channel.
Optional `sendMessage()` supports a live backend that can accept steering. Optional `resume()` returns `Promise<SubagentRun>` because the resumed child has the same asynchronous readiness boundary.
The service validates provider capabilities and request semantics before calling the provider. A provider rejection cleans any partial resources before the rejection escapes and emits no `subagent/start`/`subagent/end` pair. After fulfillment, the service attaches result observation, emits scoped start, and returns the run. Provider removal prevents later starts but does not revoke a run already accepted by the provider.
### In-process providers reuse the core transaction
Spawn and fork share one in-process driver. It creates the child through `parent.ctx`, passes the required signal into the core creation transaction, and installs persona, tool restriction, and structured-output contributions during unpublished setup.
The provider awaits creation and returns only the published run. At the handoff, core creation detaches its creation-only abort listener; the provider immediately rechecks the signal before installing the live-run listener, so an abort in that narrow interval disposes the new handle instead of escaping cancellation. Parent teardown follows the child because the operation belongs to `parent.ctx`; provider unload blocks new starts but does not become a second revocation owner for accepted runs. The run disposer cancels the child and awaits the AgentHandle's ordered teardown.
Spawn uses an empty session seed. Fork uses a validated completed-turn prefix. Conversation seeding changes history only and does not import scope, tools, services, or authority.
### ACP providers own the process until readiness or cleanup
An ACP provider crosses a real process and wire boundary, so it retains validation, environment scrubbing, message serialization, abort/process races, and kill-to-exit quiescence.
Start resolves only after `initialize` and `newSession` succeed. Abort, spawn failure, RPC failure, or invalid startup response reaps the process before rejection. After readiness, result maps the ACP prompt outcome and streamed output; dispose requests cancellation, closes the connection, and awaits process exit through one memoized path.
## Workflows and ACP UI: retain only independent async facts
Worker and editor bridges need more state than same-process registries because messages, process death, and rendering can settle independently. Their state is organized around those real facts rather than duplicate cancellation protocols.
### Workflow children are pending starts or published records
The workflow host keeps pending provider-start promises and published child records. A child moves from pending to published only when async `SubagentService.start()` fulfills; rejected starts clean their partial provider work and produce no child lifecycle pair.
One host-owned AbortController supplies the required signal to pending and live children. Closing workflow admission aborts that signal, so there is no duplicate `ChildCancel` worker RPC or explicit host-side `run.cancel()` fanout. Quiescence waits for both pending starts and published child disposal.
The worker boundary still serializes requests and outcomes. The host retains first-terminal-outcome arbitration, exact child accounting, worker-death handling, grace termination, late/duplicate message rejection, and bounded cleanup because result receipt, worker exit, and child quiescence are genuinely independent facts.
### Terminal result and physical cleanup remain separate
The workflow result records the first accepted terminal outcome according to the public precedence rules. Cleanup can continue after that result is chosen: live children still need disposal, a worker still needs termination, and a slow external backend may outlive the configured grace bound.
Public disposal claims its memoized promise before invoking callbacks. Worker death closes admission before processing any queued late child request, synthesizes missing lifecycle ends, and starts child/process cleanup without rewriting an outcome already claimed.
### ACP prompt settlement does not depend on rendering success
The ACP UI correlates a prompt with its observed turn directly. It does not scan from a `logWatermark` or use session status as a second reconciliation oracle.
Prompt handling settles correlation in a `finally` around transcript rendering. A rendering failure can fail presentation, but it cannot skip prompt settlement or leave the session permanently in flight. Concurrent loads of the same persisted caller-supplied session ID remain excluded because that is a real persistence identity race, not a UUID collision concern.
## Correctness enforcement
The design is enforced at types, runtime escape points, generated contracts, and behavioral tests. No one layer is asked to prove what it cannot observe.
### Types make the ordinary path hard to misuse
Readonly contracts describe borrowed same-process values. `Scoped<T>` marks event receivers, `agentEvents()` fuses carrier and subject, tool inputs omit registry-owned tokens, and subagent async return types expose readiness directly.
TypeScript cannot govern JavaScript casts, direct Cordis dispatch, process messages, or durable files, so runtime enforcement remains at those escape points.
### Runtime invariants cover cross-service facts
The invariants plugin verifies that every declared scoped event uses a marked carrier and that event families exposing a subject use the matching key. Session trace validation stages before append commit and advances after the same event commits.
The plugin does not police trusted setup by scanning registries or reject prompt assembly objects fabricated through casts. Those checks would turn composition contracts into speculative runtime machinery without protecting a real external boundary.
### Generated artifacts keep public contracts aligned
The event catalog, service catalog, producer/consumer matrix, configuration catalog, module graph, tool catalog, and type-equivalence blocks are generated or freshness-gated from source. `verify-scoped-dispatch` keeps the declared scoped-event set aligned with runtime invariant coverage.
Behavioral tests pin scoped routing and disposal, final-entry collision cleanup, publication rollback, ordered quiescence, durable pre/post-commit behavior, live tool filtering across presentation and execution, cooperative prompt assembly, structured-output commit in native and Code Mode, async subagent startup and signal cancellation, worker terminal arbitration, ACP settlement, and process teardown.
## Alternatives considered
The [July 8 RFC](2026-07-08-agent-scope-contexts.md#alternatives-considered) owns alternatives to the public flat-scope contract. The alternatives here concern implementation shape.
### Use a transparent proxy as the scope carrier
A proxy that impersonates the subject must preserve property, callable, constructable, private-field, descriptor, and proxy-invariant behavior that listener routing never needs. A small opaque carrier keeps the filter and key while the explicit event argument carries the subject.
### Reserve agent and session IDs before setup
Reservations prevent duplicate private setup work but require cross-service capabilities, release ordering, abandoned-reservation cleanup, and prepared-object binding. IDs are caller-supplied and concurrent reuse is caller error; final entry can choose the winner while the losing transaction rolls back cleanly.
### Snapshot every typed same-process argument
Universal copying defends against stateful getters and callers that violate readonly contracts, but it adds allocation, duplicated validators, and paths that can forget to copy. Materialization belongs at parser, queue, model, durable, worker, process, and wire boundaries where ownership actually changes.
### Give readiness, cancellation, and disposal separate controllers
Parallel sentinels can all mirror whether one operation is live. One transaction or start promise owns the operation; separate promises remain only where publication unwind, external work, terminal result, and physical quiescence can settle independently.
### Keep synchronous subagent start plus `run.started`
This splits provider acceptance from readiness and forces every consumer to register a partial run, attach result observation, await readiness, and clean up readiness failure. An async start promise makes provider-to-caller ownership transfer the readiness boundary itself.
### Restore selected prompt or tool contributions after assembly
A post-waterfall restoration pass would create a second composition rule after the documented cooperative seam. Correctly assigning canonical presence or absence would also require provider ownership and collision rules for arbitrary tool-schema providers, whose ordinary output may contain duplicate names. Scoped registration already supplies the required per-agent isolation, and trusted assembly listeners own the protocol consistency of what they return, so named restoration adds machinery without establishing an independent boundary.
### Remove worker/process lifecycle guards with same-process hardening
Worker messages, process death, and durable input do cross ownership and serialization boundaries. First-outcome arbitration, validation, environment scrubbing, and quiescent process cleanup remain necessary even though hostile same-process callback machinery does not.
## Consequences
The implementation is smaller and its proof follows the same shape as its ownership graph. One key selects a layer, one entry owns a live registry object, one transaction owns creation, one resolver owns a tool view, and one async promise transfers subagent ownership.
### What the design guarantees
- A scoped contribution is visible only in its exact agent view and is disposed with that scope.
- Create and resume expose no partially configured handle; final-entry losers and publication failures clean every prepared resource.
- Disposal retains scoped listeners and persistence through driver drain and final session work, then revokes the scope.
- Durable, queued, model, worker, process, and wire values are owned at their real boundary; typed same-process values follow readonly contracts.
- ToolRegistry's presentation, lookup, and execution resolve the same live view before expert assembly transforms, and committed results have one immutable observation point.
- Registry contributions are deterministic inputs, while the trusted assembly waterfall owns the final model-visible composition.
- Subagent start returns only a ready run, required signals cancel pending or live work, and disposal reaches the backend's quiescence contract.
- Worker/process result precedence and cleanup remain correct under death, late messages, and bounded teardown.
### Costs and limits
Scope-aware services still maintain global and identity-keyed maps, and operations must carry their real agent explicitly. Async create/resume and subagent start require callers to await ownership transfer and dispose returned handles.
A trusted `system-prompt/assemble` listener can remove or replace Code Mode and structured-output protocol pieces. This is deliberate: the listener owns final composition and must preserve any protocol the deployment expects to remain usable.
The design trusts typed plugins in the same process. It does not defend against arbitrary casts, stateful getters, mutation that violates readonly contracts, or a plugin deliberately using ambient service access outside the supported composition API.
The [security and authority non-goal](2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals) remains fundamental. These mechanisms prove registration composition, publication, and lifetime ownership; they do not prove confinement or parent-to-child non-escalation.
docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md
+57
View File
@@ -0,0 +1,57 @@
# RFC: Agent Client Protocol (ACP) support — drive the coding agent from external editors
Status: implemented
## Problem
The harness originally exposed agents only through a readline loop. That surface could carry text, but it gave an editor no structured way to create or resume sessions, correlate prompt completion, stream reasoning and tool activity, render tool-specific UI, ask for permission, or cancel one conversation without disturbing another. ACP defines those interactions as JSON-RPC over stdio, and Zed is the target client used to make concrete compatibility decisions.
The bridge must preserve the harness's existing ownership boundaries. It cannot depend on the concrete agent loop, bypass the tool registry, execute shell commands in the editor, or invent a second source of session truth. stdout is also the protocol transport, so any accidental log output corrupts the connection.
## Decision
`@deepseek-ai/dsh-acp` is a UI/client-driver plugin under `packages/ui/acp`. It uses `@agentclientprotocol/sdk`'s `AgentSideConnection` over stdin/stdout and programs only interface services: the agent create/resume factory, session persistence, tool registry, user interaction, and optional approval/bash capabilities. It does not change the agent loop and is not a capability-seam implementation.
The bridge implements the following stable session path:
- `initialize` negotiates the protocol version, advertises text plus `resource_link` prompts, and advertises `loadSession`.
- `session/new` validates an absolute `cwd`, stores it in `SessionHeader`, creates an agent through `ctx.agents`, and returns any composition-backed config options.
- `session/load` validates the requested cwd against persisted metadata before constructing an agent, reserves the id across the asynchronous resume, replays user/assistant/tool events as ACP updates, and reports the resumed config-option fold.
- `session/prompt` accepts text and resource links, rejects unsupported or empty content, allows one in-flight prompt per session, and settles against that prompt's owning `turn/end`. An error turn rejects the RPC; other closed turn reasons map through a total ACP stop-reason codec.
- `session/cancel` calls the queue-aware agent cancel path and settles only the addressed session's prompt.
Tool-call presentation remains tool-owned. A tool's `presentCall` and `presentResult` return the `generic`, `terminal`, or `diff` render-intent variants; the bridge switches on that union and maps it to ACP. Presenter-less tools receive a generic fallback. Bash terminal cards use Zed's capability-gated `_meta.terminal_info`, `_meta.terminal_output`, and `_meta.terminal_exit` convention; the harness still executes the command through `ctx.bash`, preserving sandbox, environment scrub, ownership, and cwd. Clients without that extension receive ordinary text content. Filesystem tools provide diff cards and file locations without hard-coded tool-name branches in the bridge.
Permission handling is an answerer on the [user-approval seam](2026-07-06-approval-seam.md), not an ask-every-tool policy in ACP. An `approval/request` for a bridge-owned agent with a call id becomes `session/request_permission` on that agent's editor session, with one-shot allow/reject choices. Foreign or call-less requests delegate; a missing or failed answerer remains fail-closed. The plugin that asks—such as a pre-execute policy or bash escalation—owns the decision to ask.
The bridge advertises ACP config options instead of session modes. `sandbox-mode` exists only when the mounted bash executor reports sandbox capability, and `approval-policy` exists only when `ctx.approval` is composed. Each option is an independent select whose current value is the session event fold over the composition default. `session/set_config_option` validates against the owning domain vocabulary and writes through `setSandboxMode` or `setApprovalPolicy`. An open-turn switch appends immediately; an idle switch is overlaid in the response and anchored at the next turn start. Until that anchor it is memory-only and a crash reverts to the durable fold. ACP session modes are deliberately not modeled because one mode list cannot represent these orthogonal knobs and config options are the forward protocol surface. Runtime model selection remains outside this decision; `AcpConfig.model` is connection-wide.
The bridge also provides the ACP-backed `UserInteractionProvider`: `ask_user_question` requests become form elicitations on the owning session. Select, multi-select, option descriptions, and custom-answer override semantics are preserved.
Lifecycle ownership is explicit. The bridge holds an `AgentHandle` per live session. Disconnect and Cordis disposal cancel pending prompts, dispose every handle in parallel, await loop quiescence and persistence flush, and then remove the records. Stream notification failures are contained so a vanished client cannot corrupt an agent turn. The ACP app composition loads no stdout logger; a test guards stdout as framed JSON-RPC only.
The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-feature-support.md`](../../../../packages/ui/acp/acp-feature-support.md); the package README is the operational contract.
## Alternatives considered
**A prepended `tools/execute` listener that asks on every ACP-owned call** — rejected. It would hard-code permission policy into the UI bridge, ask even when no policy requires it, and could not serve approval requests that arise after execution begins. The shared user-approval seam keeps mechanism, asking policy, and UI answerer separate.
**Inject the concrete `agentLoop`** — rejected. Agent creation, resume, idle observation, and disposal are interface-level ownership operations on `dsh-agent`; a UI plugin does not need a dependency-rule exception.
**Execute bash through ACP `terminal/*`** — rejected. That would move execution outside the harness and bypass its sandbox, credential scrub, task ownership, cwd resolution, and session log. Terminal metadata is presentation only.
**Represent sandbox and approval as ACP session modes** — rejected. They are independent composable settings, while a single current mode is mutually exclusive. ACP config options represent both without a cross-product and match the protocol's forward direction.
**Hijack stdout defensively** — rejected. Process-wide monkey-patching is outside Cordis effect ownership and races the protocol transport. The app composition owns stdout purity.
## Consequences
Editors can create, load, prompt, cancel, render, ask, and reconfigure multiple harness sessions over one ACP connection without a loop-specific dependency. The session event log remains the durable source for replay, prompt settlement, cwd, and per-session configuration. Tool presentation and human-answer channels remain extensible plugin contracts instead of ACP-specific behavior.
The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, runtime model selection, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. The feature checklist records these as unsupported rather than silently accepting them.
An idle config selection is truthful in the live response but not durable until the next turn anchors it. Crashing before that boundary loses the pending selection; this is the cost of keeping session events turn-enclosed and replay-safe.
## Verification
The ACP suites cover the in-memory protocol codec, create/load replay, exact prompt settlement, cancellation races, unsupported content, tool presentation, terminal capability fallback, permission outcome mapping, config-option validation and persistence, multi-session isolation, disconnect/disposal quiescence, and HMR cleanup. Snapshot and built-bin tests exercise the app composition, while the real-API e2e self-skips without a key.
docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md
+37
View File
@@ -0,0 +1,37 @@
# RFC: Multiplex concurrent ACP sessions over one connection
Status: implemented
## Problem
An ACP editor can keep several conversations alive over one agent subprocess. A single-active-session bridge would force extra processes and would not match Zed's client model, which tracks multiple session ids and concurrent loads. Multiplexing introduces isolation risks: events, prompt completion, cancellation, permission prompts, config selections, and predictable background-task ids must never cross session boundaries.
## Decision
The ACP bridge stores live sessions in `Map<SessionId, SessionRecord>` and keeps a `WeakMap<Agent, SessionId>` reverse index for agent-scoped callbacks. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently.
Every `session/event` and `agent/status` callback resolves the owning record before sending or settling anything. Each session permits one in-flight prompt independently. The prompt records a log watermark, captures its own `turn/start`, and settles only on the matching `turn/end`; a late end from a cancelled prior turn cannot resolve a newer prompt. `session/cancel` addresses one record and calls only that agent's queue-aware cancel path.
Permission ownership uses the same reverse index. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them.
Background bash tasks carry an opaque owner token equal to the owning session id. `bash_output` and `bash_kill` compare the caller's token with the executor's task ownership before reading or killing; a predictable task id alone grants no access. Ownership is stored with the executor task, so a tool plugin reload does not erase it.
Connection teardown clears the live map, settles each pending prompt as cancelled, and disposes all `AgentHandle`s in parallel. Each handle stops and awaits its loop, flushes the session while attached, unregisters the agent, and removes the session. Teardown is memoized and shared by client disconnect and plugin disposal.
## Alternatives considered
**One live session per connection** — rejected. It adds process overhead and contradicts the target client's multi-session shape without removing multiplexing needs from the editor.
**A per-session `ctx.extend()`** — rejected. A child context does not by itself create a child plugin fiber, so listeners would still belong to the bridge fiber. The implemented bridge instead uses global listeners with explicit O(1) demultiplexing and per-session owned records; agent lifecycle is owned by `AgentHandle`.
**Agent object identity as bash-task ownership** — rejected. A resumed or replaced agent object may legitimately represent the same durable session. The opaque session token is the cross-boundary identity that should survive plugin reloads.
## Consequences
N sessions can stream, prompt, request permission, switch config, and run background tasks concurrently without interleaving or cross-settling. A cancel or dispose in one session does not affect its neighbors. The bridge pays for explicit maps and isolation tests, but it does not add one listener set per session and therefore avoids listener fan-out during long-lived connections.
The bridge still exposes no protocol method to close one live session independently. Today records leave together on connection teardown; session close/resume lifecycle capabilities remain deferred in the ACP feature checklist.
## Verification
The multi-session suite drives concurrent sessions through interleaved updates, independent in-flight prompts, targeted cancellation, same-id and distinct-id load races, permission routing, config isolation, and teardown. Tool-bash tests prove one session cannot read or kill another session's background task.
docs/rfc/implemented/feature/2026-06-15-code-mode.md
+28 -26
View File
@@ -4,47 +4,49 @@ Status: implemented
## Problem
Today the agent loop advertises every registered tool to the model as a native JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request.
In the registry's native presentation, the agent loop advertises every visible capability as a JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request.
For multi-step tool work this is token-heavy and serial. The model cannot compose tools — loop over a result set, branch on an intermediate value, fan out, post-process — without a full model round-trip per call, and each round-trip drags the entire intermediate result back into context whether the model needs it or not.
Cloudflare's [Code Mode](https://blog.cloudflare.com/code-mode/) proposes an alternative grounded in a simple observation: LLMs are better at writing code than at emitting tool calls, because they have seen millions of lines of real code and comparatively few contrived tool-calling traces. Instead of one tool call per step, the model writes a TypeScript program against a generated API over the tools, the program executes in a sandboxed runtime, and the model curates what comes back — only what it prints or returns — instead of every intermediate result.
An earlier draft of this RFC designed Code Mode as an add-on consumer plugin with zero core changes, deferring the execution substrate to a follow-up. Both constraints are dropped here, deliberately. First, the harness is pre-release and optimizes for the correct foundation over blast radius: tool presentation is the registry's own concern, and bolting a second presentation onto it from outside means transforming the registry's contribution after the fact — a waterfall listener whose correctness depends on listener ordering, which fights the [reconstructable-requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md) design instead of riding it (that refactor removed request mutation from `agent/request`, the seam the old draft relied on). Second, the substrate question is answerable now: a Node `worker_threads` runtime gives real containment — separate isolate, empty environment, heap caps, and a `terminate()` that reliably stops a hot synchronous loop — where the old draft's `node:vm` stub had none of those, and it fits the harness's existing trust model (§Trust posture) without a hardening follow-up.
Tool presentation belongs to the registry that owns tool visibility: implementing a second presentation as an after-the-fact waterfall transform would make correctness depend on listener order and fight [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md). The execution substrate is also part of the foundation rather than a placeholder: Node `worker_threads` provides a separate isolate, an empty environment, heap caps, and termination of a hot synchronous loop, while fitting the harness's existing trust model (§Trust posture).
## Decision
Three decisions, each elaborated in its own section below:
1. **Code Mode is a first-class presentation mode of `ToolRegistry`** (`dsh-tools`), selected by a validated `mode` config: `'native'` (today's behavior, the default), `'code'` (the wire carries exactly one tool, `run_code`, plus a generated SDK `.d.ts` in the system prompt), or `'both'` (native schemas *and* `run_code` + SDK). The registry's existing tool-schema provider contributes whatever the mode dictates, so the wire tool list is shaped at its source — no interception, no listener-ordering caveats — and the logged request header records it for free.
2. **Code execution is a capability seam** — a new group `packages/code-runtime/` with the interface package `@deepseek-ai/dsh-code-runtime` owning `ctx.codeRuntime` ([capability seams](../../implemented/architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is a new implementation package, not a redesign.
1. **Code Mode is a first-class presentation mode of `ToolRegistry`** (`dsh-tools`), selected by a validated `mode` config: `'native'` (the default, contributing the visible capability schemas), `'code'` (the registry contributes only its reserved `run_code` transport plus a generated SDK `.d.ts` in the system prompt), or `'both'` (native schemas and the transport + SDK). The registry shapes its canonical contribution at the source; the cooperative prompt-assembly result remains authoritative, and the logged request header records exactly that returned presentation.
2. **Code execution is a capability seam** — `packages/code-runtime/` contains the interface package `@deepseek-ai/dsh-code-runtime`, which owns `ctx.codeRuntime` ([capability seams](../../implemented/architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is another implementation package, not a redesign.
3. **The shipped implementation is `@deepseek-ai/dsh-code-runtime-worker`**: one fresh Node worker thread per run, executing the model's TypeScript after type-strip, with bindings bridged over the message port, an empty environment, configurable heap/output/time caps, and hard termination. Its trust posture is bash-equivalent by design — no unsafe-acknowledgement flags — because the harness already ships `dsh-bash-local`, which executes arbitrary model-written shell commands with strictly *more* ambient authority.
### The registry owns the mode
`ToolRegistry` gains a schemastery-validated config (`static Config`), its first: `mode: 'native' | 'code' | 'both'`, default `'native'`. A deployment flips it from `cordis.yml` (`tools: { mode: code }`) — no code edit, per the no-hardcoded-tunables convention.
**Wire tool list = the registry's contribution.** The registry already feeds the assembly through `ctx.systemPrompt.tools(() => this.schemas())`; the provider becomes mode-aware: `'native'` contributes all schemas (unchanged), `'code'` contributes only `run_code`'s schema, `'both'` contributes all schemas plus `run_code`. Because [`PromptAssembly.tools` is the single source the loop's request header snapshots](../../../../packages/core/system-prompt/src/index.ts), the collapse is automatically logged and reconstructable — model-visible ⟺ logged holds with zero new mechanism. Scope of the guarantee, stated honestly: the mode governs the **registry's** contribution, and the registry is the only shipped schema source — but `systemPrompt.tools()` is a public multi-provider API and the `system-prompt/assemble` waterfall may transform the assembly, so a deployment that wires a second direct provider (or a mutating listener) owns what it adds, exactly as in native mode. Those are deliberate acts; what the design eliminates is the *accidental* leak the old draft worried about — a listener-ordering race around an after-the-fact collapse — and the shipped-configuration invariant (`'code'` ⇒ assembled tools exactly `[run_code]`) is pinned by tests and, like every request, by the logged header.
**Wire tool list = the registry's contribution before cooperative assembly.** The registry feeds assembly through a mode-aware provider: `'native'` contributes every capability visible to that assembly scope, `'code'` contributes only `run_code`, and `'both'` contributes both. Because [`PromptAssembly.tools` is the single source the loop's request header snapshots](../../../../packages/core/system-prompt/src/index.ts), the final presentation is logged and reconstructable. The reserved transport is not a capability: it lives outside global/scoped registration and restriction layers, cannot be registered or shadowed there, and cannot be named by `ctx.tools.restrict()`. The mode governs this provider's input to assembly; other direct `systemPrompt.tools()` providers own their schemas, and the trusted assembly waterfall owns the returned wire list.
**Interaction with `toolOrder`, stated up front:** a configured `systemPrompt.toolOrder` naming native tools rejects every assembly under `mode: 'code'` (those names are no longer contributed), by the existing fail-loud rule for unlisted names. This is correct behavior, not a bug: a deployment switching modes updates its order config or drops it.
**Interaction with `toolOrder`, stated up front:** a configured `systemPrompt.toolOrder` naming native capabilities rejects every assembly under `mode: 'code'`, because those names are outside that mode's wire-validation universe. This is correct behavior, not a bug: a deployment using Code Mode updates its order config or drops it.
**The SDK prompt section.** Under `'code'` and `'both'` the registry registers one lazy prompt section (`tools:sdk`, in the 100–199 tool-guidance order band) whose thunk regenerates, at each assembly, a TypeScript declaration of every registered tool except `run_code` itself, plus fixed usage instructions. The thunk reads the live store and emits tools in lexicographic name order, so its output is deterministic and stable across steps — an unchanged tool set produces byte-identical text (prefix-cache-friendly; a mid-session registration surfaces as one logged header delta, exactly like a native-mode tool change).
**The SDK prompt section.** Under `'code'` and `'both'` the registry registers one lazy prompt section (`tools:sdk`, in the 100–199 tool-guidance order band) whose thunk regenerates, for each assembly scope, a TypeScript declaration of every visible end-capability tool plus fixed usage instructions. It uses the same visibility resolver as lookup and execution, so scoped grants and shadows appear while restricted globals disappear; the reserved `run_code` transport itself is excluded. The thunk emits tools in lexicographic name order, so an unchanged visible set produces byte-identical text.
**Assembly ownership.** `run_code` and `tools:sdk` enter the trusted `system-prompt/assemble` waterfall as normal assembly inputs. A scoped `tools:sdk` section may shadow the global default before dispatch, and a listener may remove or replace either contribution. The waterfall's returned assembly is final, so whoever changes these inputs owns preserving a viable Code Mode protocol when the deployment expects Code Mode to remain usable; no restoration pass overrides deliberate composition.
**Codegen.** A pure `jsonSchemaToTs(schema)` module inside `dsh-tools` (sibling of `json-schema.ts` — `schemas()` and the SDK are two projections of the same store) maps the JSON-Schema subset the `defineTool` DSL emits (object/string/number/boolean/array, `properties`, `required`, string `enum` → literal union, nested objects, array `items`, `description` → JSDoc) to a TS type literal. It is **total**: any construct outside that subset (`$ref`, `oneOf`/`anyOf`, `integer`, future MCP shapes, …) degrades to `unknown` without throwing. Because `ToolSchema.name` is an arbitrary string, the SDK is declared as one object constant — `declare const tools: { "some-mcp-tool"(args: …): Promise<string>; bash(args: …): Promise<string>; … }` — quoted keys make every name reachable with no sanitization or alias-collision logic. Typing is advisory (the runtime executes type-stripped JS); the instructions say so.
### The run_code tool and the dispatch bridge
Under `'code'` and `'both'` the registry registers `run_code` in itself as an ordinary tool — one required parameter `{ code: string }` — so the unchanged loop dispatches it through the normal pipeline and `tools/pre-execute` / `tools/post-execute` gate it like any other call (a permission plugin can inspect the program text before it runs). Its `execute(args, exec)`:
Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with one required parameter, `{ code: string }`. It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
1. **Builds the bindings**: the bridge owns a **run-scoped `AbortController`** whose signal follows `exec.signal` (an outer cancel propagates in) and which the bridge itself fires the moment the run settles for any reason — completion, program exception, `computeMs`/`maxWallMs` expiry, worker exit. For every registered tool except `run_code`, the binding is an async function that (a) checks the run signal before and after (throwing stops the program — necessary because `ctx.tools.execute()` converts errors to `isError` data), (b) **JSON-normalizes the argument** — a `JSON.parse(JSON.stringify(args))` round-trip, rejecting that one call with a descriptive `Error` when the value does not survive (`BigInt`, circular structures) — because the seam's structured-clone boundary is wider than JSON while the session log accepts only JSON: normalizing BEFORE dispatch makes the dispatched form and the logged form the same JSON value by construction, so an executed sub-call can never fail at logging time, (c) awaits its turn on the **per-run serialization queue** (below), (d) calls `this.execute({ callId, name, arguments, agent: exec.agent, signal: runSignal })` with a deterministic sub-id `` CallId(`${exec.callId}:code:${n}`) `` — the run signal, not the bare outer one, so a budget expiry aborts an in-flight sub-tool (`bash-local` kills on its spec signal) instead of orphaning it, (e) appends a `tool/code-dispatch` session event, and (f) maps the result: success → the text-block contents joined as a `string` (non-text blocks become placeholders, an MVP limitation), `isError` → **the binding rejects** with an `Error` carrying the result text. Rejection is the deliberate model-facing contract — real code signals failure by throwing, `try/catch` and `Promise.all` short-circuiting behave as every model has seen them behave — where the old draft's `{ output, isError }` envelope made error handling a bespoke convention.
2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: exec.signal })`.
3. **Surfaces the outcome — after reaching quiescence.** When `ctx.codeRuntime.run()` resolves, the bridge fires the run-scoped abort (cancelling any in-flight sub-dispatch and abandoning queued-unstarted ones), then **awaits the dispatch queue's drain before returning**, per the dispose-to-quiescence rule in [defensive patterns](../../../defensive-patterns.md): an aborted in-flight sub-call still settles and logs its `isError` `tool/code-dispatch` event *inside* the open turn, and nothing can append after `run_code` returns. A successful run then returns one text block — the captured console/stdout output followed by the rendered return value (if any) — plus a `meta` payload (capped logs, dispatch count) for presentation. A run with `result.error` throws a `CodeRunFailedError extends HarnessError` (`code: 'CODE_RUN_FAILED'`, message = the error kind and text plus captured logs so the model can self-correct); the registry's existing catch turns it into a structured `isError` result.
1. **Builds the bindings**: the bridge owns a **run-scoped `AbortController`** whose signal follows `exec.signal` (an outer cancel propagates in) and which the bridge itself fires the moment the run settles for any reason — completion, program exception, `computeMs`/`maxWallMs` expiry, worker exit. For every visible capability tool, the binding is an async function that (a) checks the run signal before and after, (b) **JSON-normalizes the argument** — a `JSON.parse(JSON.stringify(args))` round-trip, rejecting that one call with a descriptive `Error` when the value does not survive (`BigInt`, circular structures) — because the seam's structured-clone boundary is wider than JSON while the session log accepts only JSON, (c) awaits its turn on the **per-run serialization queue** (below), (d) calls `this.execute({ callId, name, arguments, agent: exec.agent, parent: exec.token, signal: runSignal })` with a deterministic sub-id `` CallId(`${exec.callId}:code:${n}`) ``, (e) appends a `tool/code-dispatch` session event, and (f) maps the result: success → the text-block contents joined as a `string` (non-text blocks become placeholders), `isError` → **the binding rejects** with an `Error` carrying the result text. The child's readonly `parent` is only the outer execution's frozen, property-free token, so commit-style observers can correlate outcomes without receiving a mutation path into the live `run_code` wrapper. Every sub-call still traverses the full pipeline under its own immutable identity and registry-assigned token. The run signal, rather than the bare outer one, lets budget expiry abort an in-flight sub-tool instead of orphaning it. Rejection gives programs ordinary `try/catch` and `Promise.all` failure semantics rather than a bespoke result envelope.
2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
3. **Surfaces the outcome — after reaching quiescence.** When `ctx.codeRuntime.run()` settles, whether by fulfillment or rejection, the bridge fires the run-scoped abort (cancelling any in-flight sub-dispatch and abandoning queued-unstarted ones), then **awaits the dispatch queue's drain before returning or propagating**, per the dispose-to-quiescence rule in [defensive patterns](../../../defensive-patterns.md): an aborted in-flight sub-call still settles and logs its `isError` `tool/code-dispatch` event *inside* the open turn, and nothing can append after `run_code` settles. A successful result then returns one text block — the captured console/stdout output followed by the rendered return value (if any) — plus a `meta` payload (capped logs, dispatch count) for presentation. A fulfilled run with `result.error` throws a `CodeRunFailedError extends HarnessError` (`code: 'CODE_RUN_FAILED'`, message = the error kind and text plus captured logs so the model can self-correct); a backend rejection propagates through the same registry error boundary. Both become structured `isError` tool results.
**Sub-call `additionalContext` is suppressed, deliberately.** A `tools/post-execute` hook may attach `additionalContext` to a call; for loop-dispatched calls the loop buffers those and appends each as a `context/message` only after the step's `tool/result`s, preserving call/result adjacency. A sub-dispatch result's `additionalContext` has no such safe outlet from inside a running `run_code`: injecting immediately would land a `context/message` between the parent's `tool/call` and its `tool/result` (breaking the adjacency the buffering exists to protect), and `PostToolDecision.additionalContext` is singular where a program may produce many. The MVP therefore drops sub-call `additionalContext`, pinned by a test and stated in the hooks bridge's docs; the follow-up (a plural context channel or loop-level sub-dispatch buffering) is deferred until a real hook needs it through Code Mode.
**Concurrency: serialized, enforced by the binding.** The bindings are async, so a model writing `Promise.all([tools.a(…), tools.b(…)])` starts both immediately — concurrent dispatch would be the *default*, while the tool contract still carries no concurrency-safety metadata (the open parallel-execution TODO). Each `run_code` invocation therefore owns a dispatch queue and every binding call chains onto it, so even `Promise.all` executes the underlying `ctx.tools.execute()` calls one at a time in submission order; when the run settles, queued-but-unstarted dispatches are abandoned. Lifting this per-tool once tools can declare themselves concurrency-safe is deferred work, same as before.
**Concurrency: serialized, enforced by the binding.** The bindings are async, so a model writing `Promise.all([tools.a(…), tools.b(…)])` starts both immediately — concurrent dispatch would be the default, while the tool contract carries no concurrency-safety metadata (the open parallel-execution TODO). Each `run_code` invocation therefore owns a dispatch queue and every binding call chains onto it, so even `Promise.all` executes the underlying `ctx.tools.execute()` calls one at a time in submission order; when the run settles, queued-but-unstarted dispatches are abandoned. Lifting this per tool remains tied to tools declaring themselves concurrency-safe.
**Presentation.** `run_code`'s render intent is decided here per the [render-intent RFC](../../implemented/architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title `Run code`, `rawInput` = the program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). Not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not.
**Presentation.** `run_code`'s render intent is decided here per the [render-intent RFC](../../implemented/architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title = the program text, `rawInput` = the same program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). The program is the title because ACP execute cards reliably render that field while some clients omit body and raw-input content. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not.
### Observability: `tool/code-dispatch`
@@ -56,12 +58,12 @@ Each sub-dispatch appends one session event, declared by `dsh-tools` via `Sessio
- `CodeRunRequest = { program: string; bindings: CodeBindingNamespace[]; signal?: AbortSignal }`
- `CodeBindingNamespace = { global: string; functions: Record<string, (args: unknown) => Promise<unknown>> }` — the runtime exposes each namespace as a global object of async functions inside the program; binding arguments and resolutions must be structured-cloneable (a runtime may cross a serialization boundary; ours does).
- `CodeRunResult = { value?: unknown; logs: CodeLogEntry[]; error?: CodeRunFailure }` — an error is a field on a resolved result, never a rejection of `run()`.
- `CodeRunResult = { value?: unknown; logs: CodeLogEntry[]; error?: CodeRunFailure }` — program execution outcomes, including exception, timeout, abort, and worker exit, resolve as the `error` field. `run()` may reject only for caller/seam misuse (for example a duplicate binding namespace); consumers still contain a non-conforming backend rejection at their own error boundary.
- `CodeLogEntry = { source: 'console' | 'stdout' | 'stderr'; level?: 'log' | 'info' | 'warn' | 'error' | 'debug'; text: string }`
- `CodeRunFailure = { kind: 'exception' | 'timeout' | 'abort' | 'worker-exit'; message: string }` — orthogonal outcomes reported independently per [defensive patterns](../../../defensive-patterns.md); a timed-out run is not an exception, an abort is not a timeout.
- Two readonly backend descriptors, informational not gating: `language` (what the program must be written in — `'typescript'` for the shipped backend; a Python backend would say so, and pair with its own SDK generator on the presentation side) and `isolation` (`'worker-thread'` for the shipped backend; `'process'`, `'container'`, … for future ones). `dsh-tools` requires `language === 'typescript'` in the MVP — its codegen emits TS — and fails the assembly loudly otherwise, the same misconfiguration idiom as `toolOrder` violations (as when `mode` is non-native with no `ctx.codeRuntime` loaded at all).
Per explicit-over-implicit at seams, the request spells out everything the runtime acts on; defaulting (timeouts, caps) is the implementation's validated config, never a hidden `??` inside `run()`. Consumption uses the loop's established optional-backend idiom: cordis has no optional injection — every `inject` entry gates activation — so a static `inject` on the registry would hold `ctx.tools` (and every tool plugin behind it) hostage to a code runtime existing even under `mode: 'native'`; instead the registry reads `ctx.get('codeRuntime')` at use time, exactly as `agent-loop` consumes `sessionPersistence`, with absence failing loud in the provider thunk as above. The seam split is justified by real planned divergence on both axes — substrate (worker now; container/microVM later) and language (the Python/AssemblyScript direction sketched in the earlier draft survives as future work) — not by speculation: `dsh-tools` consumes the interface today and tests against a trivial in-repo fake, exactly the interface/implementation/consumer shape of the bash template.
Per explicit-over-implicit at seams, the request spells out everything the runtime acts on; defaulting (timeouts, caps) is the implementation's validated config, never a hidden `??` inside `run()`. Consumption uses the loop's optional-backend idiom: Cordis has no optional injection — every `inject` entry gates activation — so a static `inject` on the registry would hold `ctx.tools` (and every tool plugin behind it) hostage to a code runtime existing even under `mode: 'native'`; instead the registry reads `ctx.get('codeRuntime')` at use time, exactly as `agent-loop` consumes `sessionPersistence`, with absence failing loud in the provider thunk. The seam has concrete divergence on both axes: the worker-thread substrate can be replaced by a container or microVM implementation, and the TypeScript language contract can be paired with a language-specific SDK and runtime. `dsh-tools` consumes only the interface and tests against a trivial in-repo fake, exactly the interface/implementation/consumer shape of the bash template.
### The worker-thread runtime
@@ -76,7 +78,7 @@ Per explicit-over-implicit at seams, the request spells out everything the runti
### Trust posture
The worker runtime is **containment, not a security boundary**, and the RFC says so without ceremony. Model code in the worker can reach Node globals — `fetch`, `process` (with an empty env), dynamic `import()` of built-ins — so a deliberately adversarial program has ambient authority comparable to what the harness's own `bash` tool already grants every model turn: `dsh-bash-local` runs arbitrary model-written commands with the host filesystem, network, and a scrubbed-but-populated environment. One asymmetry runs the other way and is stated plainly: `worker.terminate()` ends the thread, not OS processes a program may have spawned via `node:child_process` — weaker than `bash-local`'s process-group kill for direct children (equivalent for double-forked daemons, which survive both); the wall-clock ceiling bounds the worker itself, and orphan cleanup is the same deployment-level concern it already is for bash. Code Mode is gated where bash is gated — `tools/pre-execute`, where permission/sandbox plugins veto or approve the program before it runs — and adds containment bash does not have: empty env, heap caps, hard termination of the program itself, a separate isolate. The earlier draft's two-flag unsafe ceremony (`{ unsafe: true }` constructor + `allowUnsafeRuntime`) existed for a `node:vm` stub with *no* containment and is dropped with it; demanding scarier flags for the better-contained executor than for bash would be posture theater. A deployment that needs a hard boundary (untrusted multi-tenant input) needs it for bash too; that is a future `isolation: 'container'` backend, and the `isolation` descriptor exists so such a deployment can tell backends apart.
The worker runtime is **containment, not a security boundary**. Model code in the worker can reach Node globals — `fetch`, `process` (with an empty env), dynamic `import()` of built-ins — so a deliberately adversarial program has ambient authority comparable to what the harness's own `bash` tool grants every model turn: `dsh-bash-local` runs arbitrary model-written commands with the host filesystem, network, and a scrubbed-but-populated environment. One asymmetry runs the other way: `worker.terminate()` ends the thread, not OS processes a program may have spawned via `node:child_process` — weaker than `bash-local`'s process-group kill for direct children (equivalent for double-forked daemons, which survive both); the wall-clock ceiling bounds the worker itself, and orphan cleanup is the same deployment-level concern it is for bash. Code Mode is gated where bash is gated — `tools/pre-execute`, where permission/sandbox plugins veto or approve the program — and adds containment bash does not have: empty env, heap caps, hard termination of the program itself, and a separate isolate. A `node:vm` executor with no containment would need explicit unsafe acknowledgement; imposing that ceremony on the better-contained worker while bash needs none would be posture theater. A deployment that needs a hard boundary (untrusted multi-tenant input) needs it for bash too; that is a future `isolation: 'container'` backend, and the `isolation` descriptor lets deployments distinguish backends.
### What the model sees
@@ -84,37 +86,37 @@ The `tools:sdk` section carries the `.d.ts` plus fixed instructions: the program
## Consequences
The design shipped as four stacked changes — this RFC, the `dsh-code-runtime` interface package, the `dsh-code-runtime-worker` backend, and the `dsh-tools` integration — each gates-green with docs in the same change; review fixes landed on the change that introduced them and merged down.
The design consists of the `dsh-code-runtime` interface package, the `dsh-code-runtime-worker` backend, and the `dsh-tools` presentation and dispatch integration.
What exists now:
Shipped surface:
- **The seam**: `packages/code-runtime/` — `@deepseek-ai/dsh-code-runtime` (abstract `CodeRuntime`, the vocabulary above, `ctx.codeRuntime`) and `@deepseek-ai/dsh-code-runtime-worker` (the worker-thread backend, every cap a validated config field). Rows in the service map, capability-seams graph, config catalog, and cordis catalog.
- **The registry surface**: `ToolRegistry`'s first config (`mode`), the mode-aware wire contribution, the `tools:sdk` section, `jsonSchemaToTs`/`renderToolsSdk` (exported), `run_code` + the dispatch bridge + `CodeRunFailedError`, and the `tool/code-dispatch` log event (declaration-merged into `SessionEventMap`, regenerated into the persistence catalog; `run_code` in the tool catalog).
- **The composed surface**: the `tools` config forwards through `agent-core` and both app packages (`stdio-agent`, `acp-agent`); `demo:code-mode` boots each UI example's `code-mode.cordis.yml` overlay (the worker runtime + `mode: 'code'` over the base tree); the adding-a-tool cookbook states that a registered tool is reachable from programs for free, and the tool-pipeline doc shows sub-dispatches re-entering both waterfalls.
- **Interactions inherited by deployments**: a `toolOrder` naming native tools rejects every assembly under `'code'` (update or drop the order config when switching modes); sub-call `additionalContext` is dropped by the bridge (a plural context channel is deferred until a real hook needs it through Code Mode); sub-dispatch stays serialized until tools can declare concurrency safety — the same metadata the native parallel-dispatch TODO waits on.
- **The registry surface**: `ToolRegistry`'s `mode` config, mode-aware wire contribution, lazy `tools:sdk` section and reserved `run_code` transport, `jsonSchemaToTs`/`renderToolsSdk` (exported), the dispatch bridge and `CodeRunFailedError`, and the `tool/code-dispatch` log event (declaration-merged into `SessionEventMap`, regenerated into the persistence catalog; `run_code` in the tool catalog).
- **The composed surface**: the `tools` config forwards through `agent-core` and both app packages (`stdio-agent`, `acp-agent`); `demo:code-mode` boots each UI example's `code-mode.cordis.yml` overlay (the worker runtime + `mode: 'code'` over the base tree); every program sub-dispatch resolves the same scoped capability view and re-enters the complete tool pipeline with an immutable link to its enclosing transport execution.
- **Interactions inherited by deployments**: a `toolOrder` naming native tools rejects every assembly under `'code'` (update or drop the order config when switching modes); restrictions can hide end capabilities but cannot remove the registry-owned presentation transport, while assembly listeners may rewrite the final model-visible surface and own its protocol integrity; sub-call `additionalContext` is dropped by the bridge (a plural context channel is deferred until a real hook needs it through Code Mode); sub-dispatch stays serialized until tools can declare concurrency safety — the same metadata the native parallel-dispatch TODO waits on.
## Testing
What the suites pin, per tier:
- **Unit — worker runtime** (real workers, no mocks): output/value capture and log-source attribution; error kinds (exception incl. non-erasable syntax, abort, worker-exit under OOM); the two budgets from both sides (a hot loop behind an un-awaited pending dispatch dies at `computeMs` busy time; a program idling on a slow binding outlives `computeMs` and dies only at `maxWallMs`); binding-bridge hostility (junk/forged port traffic incl. non-object messages and forged `log`/`done` cap bypass attempts, unknown names, duplicate ids, post-settlement replies, `__proto__`/`constructor`/`toString` binding names); structured-clone fallback and cap truncation; `env` emptiness verified from inside a program; dispose-awaits-exit. A real-load-path e2e runs the BUILT package under plain `node` so the worker entry resolves both unbuilt (tsx) and built — the published-artifact guard from [docs/testing.md](../../../testing.md).
- **Unit — registry integration**: the codegen table (DSL subset, quoted names, `unknown` degradation, byte-identical determinism); provider contribution per mode (`'native'` unchanged, `'code'` exactly `[run_code]`, `'both'` all + `run_code`); `toolOrder × mode` rejection; missing-runtime / wrong-language loud failures; serialization non-overlap (a probe tool records enter/exit under `Promise.all`); abort aborting the in-flight sub-dispatch and abandoning queued ones; binding rejection on `isError` and on JSON-unrepresentable arguments; `CodeRunFailedError` → structured `isError` carrying kind + logs; `tool/code-dispatch` payloads (JSON-normalized arguments identical to what dispatched); `deriveMessages()` ignoring the event; sub-call `additionalContext` suppression; HMR safety (disposing the registry removes the tool and the section).
- **Unit — registry integration**: the codegen table (DSL subset, quoted names, `unknown` degradation, byte-identical determinism); provider contribution per mode (`'native'` capabilities, `'code'` exactly `[run_code]`, `'both'` capabilities + `run_code`); reserved-name, restriction, scoped shadowing, authoritative assembly transformation, and `toolOrder × mode` invariants; missing-runtime / wrong-language loud failures; full-pipeline and opaque parent-token behavior for sub-dispatches; serialization non-overlap (a probe tool records enter/exit under `Promise.all`); abort aborting the in-flight sub-dispatch and abandoning queued ones; binding rejection on `isError` and on JSON-unrepresentable arguments; `CodeRunFailedError` → structured `isError` carrying kind + logs; `tool/code-dispatch` payloads (JSON-normalized arguments identical to what dispatched); `deriveMessages()` ignoring the event; sub-call `additionalContext` suppression; HMR safety.
- **e2e (with-key, self-skips)**: a real model under `mode: 'code'` composes two bash calls in one program (`examples/coding-agent/tests/code-mode.e2e.ts`) — every logged `request/header` carries exactly `[run_code]`, the dispatch events land under the parent call, the file the program wrote exists, and the final answer is the curated output.
- **Snapshot (keyless replay)**: goldens for a `run_code` turn under `'code'` and `'both'` (`code-mode-turn`, `both-mode-turn`), each its own header-pinning class — the SDK section text, the collapsed header tool list, the dispatch events, and the result card are committed and replayed.
## Alternatives considered
**An add-on consumer plugin, zero core changes (the previous draft of this RFC).** Rejected on both halves. The wire-collapse half aged out from under it: it targeted the `agent/request` waterfall, which [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md) has since re-typed to call-config-only, and the surviving alternative — transforming the assembly a waterfall listener receives — is strictly worse than contributing the right list in the first place (transformation must undo `toolOrder` canonicalization it cannot see the config for, and its correctness depends on where it sits in a listener chain). The deeper reason is ownership: which tools the model is offered, in which representation, is the registry's single concern — `schemas()` for function calling and the SDK for Code Mode are two projections of one store, and splitting the second projection into a satellite package would preserve a boundary the domain does not have.
**An add-on consumer plugin with zero core changes.** Rejected because `agent/request` is call-config-only under [reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md), while transforming an assembled tool list would have to undo `toolOrder` canonicalization without owning its config and would depend on listener order. Which tools the model is offered, and in which representation, is the registry's single concern: native schemas and the SDK are two projections of one visible store.
**`node:vm` as the reference runtime, hardening deferred (also the previous draft).** Rejected: `node:vm` is not isolation (prototype-chain escapes reach the host realm), cannot interrupt a hot loop, and forced the draft into a two-flag unsafe ceremony plus a mandatory follow-up RFC. The worker thread delivers the missing properties now — separate isolate, empty env, `resourceLimits`, reliable `terminate()` (all verified by probe before this revision) — at bash-equivalent trust, so the reference implementation and the production one are the same package and the ceremony dissolves.
**`node:vm` as the reference runtime, with hardening deferred.** Rejected: `node:vm` is not isolation (prototype-chain escapes reach the host realm) and cannot interrupt a hot loop. A worker thread provides a separate isolate, empty environment, `resourceLimits`, and reliable `terminate()` at bash-equivalent trust, so the reference and production implementation are one package without an unsafe-acknowledgement ceremony.
**Result elision / summarization over native tool-calling.** Addresses only the context-bloat half of the problem: trimming old `tool-result`s (now cheap to add as a logged surface replace, per the reconstructable-requests consequences) still pays one model round-trip per call and cannot express loops, branches, or joins. Complementary, not competing; it can layer under Code Mode for residual native calls.
**Result elision / summarization over native tool-calling.** Addresses only the context-bloat half of the problem: trimming old `tool-result`s is cheap to add as a logged surface replacement under reconstructable requests, but still pays one model round-trip per call and cannot express loops, branches, or joins. Complementary, not competing; it can layer under Code Mode for residual native calls.
**Parallel native dispatch in the loop.** The other answer to round-trip cost; still valid future work (the open TODO), still blocked on concurrency-safety metadata, and still no composition — it parallelizes calls the model already decided on in one step. Code Mode's serialized-queue decision keeps the two compatible: when the metadata lands, both native parallel dispatch and per-tool binding parallelism unlock together.
**Always-exclusive (Cloudflare-faithful, no mode).** Rejected for this SDK's primary consumer: a coding agent's bread-and-butter single calls (`bash`, `read`, `edit`) are already ideal as native calls, and forcing every edit through a program taxes the common case. The mode config keeps the faithful form (`'code'`) one line away without imposing it.
**Per-tool visibility tiers (this tool native, that tool code-only).** Deferred again, knowingly: it needs per-tool metadata and a presentation split that `'native' | 'code' | 'both'` does not, and every learning it depends on (how models actually split usage under `'both'`) arrives only after this ships.
**Per-tool visibility tiers (this tool native, that tool code-only).** Deferred: it needs per-tool metadata and a presentation split that `'native' | 'code' | 'both'` does not, and its design depends on evidence about how models split usage under `'both'`.
**Sanitized identifier aliases in the SDK** (`my-tool` → `my_tool`, Cloudflare's approach). Rejected: quoted keys on a `declare const` make every name reachable with zero alias-collision logic; models handle `tools["my-tool"](…)` fine.
docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md
+1 -1
View File
@@ -4,7 +4,7 @@ Status: implemented
## Problem
The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](../../proposed/feature/2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block.
The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block.
That is a correct, capability-free baseline, but not how the reference editors render a *terminal* tool at its best. An editor like Zed has a dedicated terminal tool-call card — a header showing the working directory, the command as the label, the command output rendered as a terminal, and an exit-status pill — but it only builds that card when the `tool_call` carries terminal metadata (below). With a plain text block the output appears as static markdown and there is no cwd header. (Zed also HIDES `rawInput` for `kind: 'execute'`, which is why the command IS the title — both reference adapters do the same. The human-readable description rides as a separate content block above the card; note this is a DELIBERATE divergence — claude-agent-acp DROPS the description in terminal mode and renders only the card — we keep the summary visible alongside.)
docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md
+6 -6
View File
@@ -35,18 +35,18 @@ A new package group `packages/subagent/`:
| `@deepseek-ai/dsh-subagent-mock` | support: a scripted provider for testing the seam through the real load path |
| `@deepseek-ai/dsh-tool-subagent` | consumer: the model-facing `subagent` tool over `ctx.subagents` |
### The primitive: `start → SubagentRun`
### The primitive: async `start → SubagentRun`
A provider exposes `start(request) → SubagentRun`. The run carries a `result` promise (the terminal `SubagentResult`), `cancel()`, and `dispose()`. The transport-neutral verb is **`start`**; "spawn" is reserved for the in-process `dsh-subagent-spawn` backend's identity, not the service verb. The service's `start(name, request)` resolves the named provider, validates capabilities, delegates, and emits `subagent/start` / `subagent/end` around the run.
A provider exposes `start(request) → Promise<SubagentRun>`. Promise fulfillment is the publication/readiness and provider-to-caller ownership boundary: for an in-process backend the child is already published in `ctx.agents`, and for ACP the remote session already exists. `SubagentStartRequest.signal` is the single cancellation channel before and after readiness; `SubagentRun` carries the terminal `result` and a `dispose()` method that cancels remaining work and awaits quiescence. The transport-neutral verb is **`start`**; "spawn" is reserved for the in-process `dsh-subagent-spawn` backend's identity, not the service verb. A rejected start cleans provider-owned partial resources and emits neither subagent lifecycle event.
### Two kinds of optional capability, discovered two ways
- **Start-time features** (`outputSchema`, `depthLimit`, `toolFilter`) ride on a static `provider.capabilities` descriptor. The service checks every requested one BEFORE delegating and **rejects loud** (`SubagentError('UNSUPPORTED_CAPABILITY')`) if the provider lacks it — never accepted-then-ignored. They must be checked before a run exists, which is why they cannot be runtime methods.
- **Start-time features** (`outputSchema`, `depthLimit`, `toolFilter`, `persona`) ride on a static `provider.capabilities` descriptor. The service checks every requested one BEFORE delegating and **rejects loud** (`SubagentError('UNSUPPORTED_CAPABILITY')`) if the provider lacks it — never accepted-then-ignored. They must be checked before a run exists, which is why they cannot be runtime methods.
- **Runtime features** (steering via `sendMessage`, follow-up via `resume`) are **optional methods** on `SubagentRun`. The method's presence IS the capability, and TypeScript narrowing is the discovery mechanism: a consumer cannot call an absent method without narrowing first, so there is no silent-degradation path and no separate flags object to keep in sync.
### Fork vs. fresh are separate backends, not a flag
Rather than a `context: 'fresh' | 'fork'` request field, the distinction is the provider's identity: `dsh-subagent-spawn` (fresh, isolated, own system prompt) and `dsh-subagent-fork` (seeded from the parent's log) are two registered providers. You pick behavior by picking a provider — consistent with the registry being the selection mechanism. The fork backend seeds only a **balanced, completed-turn prefix** of the parent log: at tool-execute time the parent's turn is open (it holds the `assistant/message` and the dangling spawn `tool/call` with no `tool/result`), and seeding that raw prefix would give the child an unbalanced turn the [invariants](../../../../packages/support/invariants/src/index.ts) freeze-check rejects.
Rather than a `context: 'fresh' | 'fork'` request field, the distinction is the provider's identity: `dsh-subagent-spawn` (fresh, isolated, own system prompt) and `dsh-subagent-fork` (seeded from the parent's log) are two registered providers. You pick behavior by picking a provider — consistent with the registry being the selection mechanism. The fork backend seeds only a **balanced, completed-turn prefix** of the parent log: at tool-execute time the parent's turn is open (it holds the `assistant/message` and the dangling spawn `tool/call` with no `tool/result`), and seeding that raw prefix would give the child an unbalanced turn that the [invariants](../../../../packages/support/invariants/src/index.ts) trace replay rejects.
### Child isolation and the parent log
@@ -54,7 +54,7 @@ Each subagent runs in its **own `Session`** (own id, `parentSession` lineage), p
### Synchronous collect (first cut)
The `dsh-tool-subagent` consumer awaits `run.result` and returns the child's final output as the tool result, blocking the parent's turn until the child finishes. It does so inside a `try/finally` that always `dispose()`s the run (no leaked idle child/session on any path), bridges `exec.signal` to `run.cancel()`, and maps a non-`completed` stop reason to an `isError` result rather than returning partial output as success. Steering (`sendMessage`) is part of the contract but **intentionally unused** this cut.
The `dsh-tool-subagent` consumer passes its execution signal into the start request, awaits the ready run's `result`, and returns the child's final output as the tool result, blocking the parent's turn until the child finishes. A `try/finally` always `dispose()`s the run, so no success, failure, or cancellation path leaks an idle child/session. A non-`completed` stop reason maps to an `isError` result rather than returning partial output as success. Steering (`sendMessage`) is part of the contract but intentionally unused in this consumer.
### Provider selection is config, not model-facing
@@ -66,7 +66,7 @@ The seam is tested through the real cordis Loader / export path, not a hand-buil
## Consequences
- **Recursion.** Without a guard, an in-process child inherits the spawn tool and can spawn unboundedly. Depth-limit is an optional capability (the in-process backends enforce it; ACP advertises it off and rejects a `maxDepth` request); tool-filtering is likewise optional. Tool-filtering, when implemented, needs a `tools/pre-execute` deny in the child context — schema filtering alone is insufficient because a model can hallucinate a denied tool name.
- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls RFC](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits.
- **Blocking the parent turn.** Synchronous collect holds the parent's `runStep` open for the child's full duration. This is acceptable for the first cut; **background / poll / spill semantics are deferred to a future redesign that unifies long-running-tool handling across subagents AND bash** (a sub-agent and a long `bash` background task pose the same "the model started something slow, how does it collect later" problem, and should share one mechanism rather than each inventing its own).
- **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
- **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.
docs/rfc/implemented/feature/2026-06-22-acp-subagent-backend.md
+1 -1
View File
@@ -34,7 +34,7 @@ The child is a separate process, so it inherits an environment. Credential-shape
Designed at every tier the backend touches, per the root AGENTS.md rule that a new capability shape names its coverage at every tier at plan time:
- **Keyless unit/integration** (`subagent-acp.spec.ts`): spawns a scripted mock ACP server subprocess (`tests/mock-acp-server.ts`) and drives it through the real backend over real ACP stdio. Covers: the prompt round-trip + output accumulation; every StopReason mapping; cancellation via `run.cancel()` and via the request signal; the already-aborted-before-start case; the cancel-races-ahead-of-newSession case; a torn-pipe-after-cancel (child crashes on cancel) settling `aborted`; permission auto-answer under both policies (including the allow-policy-no-allow-option fallback); a non-message update consumed but not accumulated; a nonexistent-command spawn failure settling `error`; HMR provider cleanup; and the namespace export shape. 100% per-file coverage.
- **Keyless unit/integration** (`subagent-acp.spec.ts`): spawns a scripted mock ACP server subprocess (`tests/mock-acp-server.ts`) and drives it through the real backend over real ACP stdio. Coverage includes the prompt round-trip and output accumulation; every StopReason mapping; cancellation through the required request signal and through disposal; already-aborted and cancel-races-ahead-of-newSession starts; a torn pipe after cancellation settling `aborted`; permission auto-answer under both policies; non-message updates; nonexistent-command startup failure with process reaping; provider HMR; and the namespace export shape.
- **With-key e2e** (`subagent-acp.e2e.ts`): the harness drives ITSELF — the backend spawns the real `acp-agent` example process and a real model in that child answers a prompt (PONG) and does real file work (writes `proof.txt`, verified on disk). Self-skips without `DEEPSEEK_API_KEY`. This is the "talk to our own process" smoke and the out-of-process analogue of the in-process spawn e2e.
- **Snapshot**: deferred as `TODO(acp-subagent-replay)`. An ACP child is a distinct replay shape — each child is its own PROCESS with its own single-agent replay (booted under `DSH_SNAPSHOT=replay` with its own sessions-root + fixture), unlike the in-process per-session keying that [the per-session replay RFC](../testing/2026-06-22-subagent-snapshot-replay.md) added. The keyless mock-server tests give deterministic coverage of the backend in the meantime; the snapshot follow-up would record the parent driving a real-but-replayed ACP child.
docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
+5 -4
View File
@@ -26,9 +26,11 @@ Each bridge maps the neutral `MergedHookOutcome` from the shared lib onto the se
| `tools/pre-execute` | `deny`→`deny`; `ask`→`ask` | `block`→`deny` (no allow/ask) |
| `tools/post-execute` | `deny`→`block`+feedback; context-only→delegate+fold | same |
| `agent/turn-continuation` | blocking Stop → `continue` (reason = next-step steering) | same |
| `subagent/start` (emit) | additionalContext → inject into the live child | — (not a Codex event) |
| `subagent/start` (emit) | additionalContext → inject into a live in-process child; a remote child has no local injection target | — (not a Codex event) |
| `subagent/end` (emit) | observe-only | — |
The CC bridge's `ask` result is a real permission path, not a terminal bridge decision: `dsh-tools` resolves it through the optional [approval seam](2026-07-06-approval-seam.md). A composed ACP answerer prompts the owning editor session and `allowed-once` proceeds; without an ApprovalService or answerer, the call fails closed to `deny`.
### Context source is always the plugin (the mislabel guard)
`agent.inject()` defaults a missing `MessageSource` to `{ kind: 'user' }` — which would record plugin-injected context as if the user had typed it. So every bridge `inject()` and every `HookContext` passes an explicit `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }` source. A test asserts the resulting `context/message.source` is the plugin, never `user`.
@@ -52,11 +54,10 @@ Two different cwds, kept distinct on purpose. The hooks **themselves** run in th
## Deferred (faithful-but-degraded)
- **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + ACP/tool-bash presentation, so an honest rewrite is a design unit, not a field.
- **Stop loop-guard** (`TODO(stop-loop-guard)`). CC/Codex break an infinite force-continue with `stop_hook_active` (true once a Stop hook fired this run) plus a max-consecutive cap; both are deferred. Today `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
- **Permission `ask`** degrades to `deny` at the `tools/pre-execute` seam (`FIXME(permissions)` in the interception-seams RFC) — there is no interactive permission prompt yet.
- **Stop loop-guard** (`TODO(stop-loop-guard)`). CC/Codex break an infinite force-continue with `stop_hook_active` (true once a Stop hook fired this run) plus a max-consecutive cap; both are deferred. `stop_hook_active` is always `false`, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.
- **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception seams have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; the halt request is recorded in the `hook/result` log, and the hook keeps its per-point effect (decision/context) meanwhile.
- **Config discovery.** The path is explicit in `cordis.yml` and process-level (see above); the full multi-layer CC/Codex precedence walk, per-session project-local discovery, and the trust/hash model are not reimplemented (`TODO(per-session-hook-config)`).
- **Session-start / subagent-start context is best-effort, not gated (`TODO(session-start-gating)`).** `agent/session-start` is a synchronous emit and the bridge runs its hook on a detached `.then`, so the injected `additionalContext` is not guaranteed to land before the first turn reaches the model — a slow hook can miss the first request (the context then arrives as a later injection). `subagent/start` is sharper: an in-process provider may have already queued the child's prompt before the listener runs, and a short-lived child can finish before the detached inject fires. Making startup context a gated/awaited primitive is a loop-level change deferred to the interception seams; today the contract is "injected as soon as the hook resolves", not "before the first request". The bridge tests do NOT wait on the injection where they assert the guaranteed-timing behavior, so they document the real (best-effort) timing rather than masking it.
- **Session-start / subagent-start context is best-effort, not gated (`TODO(session-start-gating)`).** `agent/session-start` is a synchronous emit and the bridge runs its hook on a detached `.then`, so the injected `additionalContext` is not guaranteed to land before the first turn reaches the model — a slow hook can miss the first request (the context then arrives as a later injection). `subagent/start` is emitted only after child publication, so the bridge can capture the live in-process child synchronously, but the result driver may queue the prompt as that same readiness boundary resolves and a short-lived child can finish before the detached hook injects. Making startup context a gated/awaited primitive is a loop-level change deferred to the interception seams; the contract is "injected as soon as the hook resolves", not "before the first request". The bridge tests do NOT wait on the injection where they assert the guaranteed-timing behavior, so they document the real (best-effort) timing rather than masking it.
## Alternatives considered
docs/rfc/implemented/feature/2026-06-30-interception-seams.md
+21 -11
View File
@@ -6,21 +6,31 @@ Status: implemented
The harness needs a hooks subsystem: users extend or gate the agent at lifecycle points the way Claude Code (CC) and Codex do. The key reframe driving this design is that **"native hooks" are not a package** — a native hook is just an ordinary Cordis plugin subscribing to the canonical lifecycle events. So the real product is a *powerful, well-typed canonical event surface*; the CC/Codex bridges (the `dsh-hooks-claude` / `dsh-hooks-codex` packages) are merely translators that map an external shell-hook protocol onto that same surface. Anything a bridge can do, a plain plugin can do directly — more powerfully (no serialization boundary, full `ctx`, typed returns).
Before this change the interception surface was incomplete and inconsistent for that goal: there was no per-prompt seam (CC's `UserPromptSubmit`), no session-start signal (CC's `SessionStart`), the single `tools/execute` waterfall conflated the pre-gate and post-inspect phases (CC splits `PreToolUse`/`PostToolUse`), and `agent/turn-continuation` returned a bare `boolean` with no room for a force-continue *reason*. The [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md) pinned down the three-domain rule and the typed-Decision idiom as the interception convention; this RFC builds the actual seams on top of it.
The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubmit`), session-start observation (CC's `SessionStart`), pre-tool policy, around-dispatch control, post-tool transformation, final-result observation, and continuation with a model-facing reason. Conflating those phases gives plugins mutation channels they do not need and makes finality depend on listener ordering. The [event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md) supplies the three-domain rule and the typed-Decision idiom; this RFC applies them to the lifecycle seams.
## Decision
Add/​reshape the interception seams so every one returns a small, seam-specific **typed Decision union**, and the set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation).
The canonical surface separates transformable policy, around-dispatch control, and observe-only notification. Policy waterfalls return small seam-specific **typed Decision unions**; wrappers return normalized results; notifications receive immutable snapshots and cannot affect the outcome. The set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation) while leaving non-hook execution policy independently composable.
**New `agent/*` events** (`dsh-agent`):
**Agent events** (`dsh-agent`):
- `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching `additionalContext`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below).
**Reshaped** `agent/turn-continuation` from `(…, defaultDecision: boolean) → boolean` to `(…, defaultDecision: ContinuationDecision) → ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the existing `/goal` step-end-steer pattern.
**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern.
**Split** the single `tools/execute` waterfall into `tools/pre-execute` (→ `PreToolDecision` allow/deny/ask gate) and `tools/post-execute` (→ `PostToolDecision` accept/block, optionally replacing content or attaching `additionalContext`). Core dispatch sits between them as plain code inside `ToolRegistry.execute`'s outer try/catch, and the tool body keeps its own inner try/catch so a thrown tool still becomes an `isError` result that `post-execute` listeners can inspect.
### The tool pipeline gives each phase one kind of authority
**New `TurnEndReason` variant** `rejected` (`dsh-session`): a turn whose entire prompt batch was blocked by `prompt-submit`.
Every call follows one ordered pipeline: `tools/pre-execute` → monotonic guards → `tools/execute` → core dispatch → `tools/post-execute` → `tools/result`. The registry reads each caller-owned input field once, materializes `arguments` as detached lossless JSON in one recursive pass, and snapshots `ToolExecutionInput` into a pipeline execution with its own opaque token. Identity fields and deeply frozen arguments are immutable for the whole pipeline, and a nested call's `parent` contains only the enclosing execution's token rather than its live object. Optional `signal` is the only operational field an around-dispatch wrapper may add, replace, or remove, and the complete object freezes before final observers run. This identity contract prevents a policy listener from silently changing what the log, UI, and tool body believe ran.
- **`tools/pre-execute`** is the extensible waterfall gate. Its `PreToolDecision` allows, denies, or asks. Deny skips `tools/execute` and core dispatch. Ask resolves through the optional approval seam: only `allowed-once` continues through guards and dispatch; rejection, cancellation, an unavailable channel, a missing approval service, or an agent-less call becomes a normalized denial. Every outcome still reaches post-policy and final observers.
- **`ctx.tools.guard()`** installs synchronous scope-aware policy after the whole pre-execute waterfall. A guard may deny or abstain, never force-allow, so listener ordering cannot resurrect an operation that a final invariant forbids.
- **`tools/execute`** is the around-dispatch waterfall for timeout, retry, and metrics plugins. A wrapper delegates to core dispatch with `next()`, may add, replace, or remove only `exec.signal` before doing so, and receives the already-normalized result of a thrown or unknown tool; returning its own valid result short-circuits dispatch.
- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, optionally replaces content, or attaches `additionalContext`; in-place mutation of the result is not a transform channel, because the registry rebuilds the outcome from a protected snapshot plus the returned decision.
- **`tools/result`** is the synchronous contained notification after every transform, lossless-JSON materialization, and the outer error boundary. It receives the same frozen execution identity and an immutable snapshot of the authoritative result; observer failures are contained per listener and cannot change or reject `ToolRegistry.execute()`'s returned outcome.
Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, malformed-result, non-JSON result, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool, and a final observer sees exactly what the caller receives and the session log can persist.
**`TurnEndReason.rejected`** (`dsh-session`): a turn whose entire prompt batch was blocked by `prompt-submit`.
### Three load-bearing loop decisions
@@ -30,13 +40,13 @@ Add/​reshape the interception seams so every one returns a small, seam-specifi
3. **A forced `continue` `reason` is enqueued through the steering channel**, so the next step's top-of-loop drain records it as steering for the continued turn — next-*step* steering within the SAME turn, not a next-*turn* prompt (matching the existing `hasSteering` force-continue override).
### Pre-tool INPUT rewrite is DEFERRED (the over-reach signal)
### Pre-tool input rewrite is a separate consistency decision
`PreToolDecision` is allow/deny/ask only — **no `arguments` rewrite**. Output replacement (`PostToolDecision.accept.content`) is safe because `tool/result` is logged AFTER execution (one source of truth). Input rewrite is NOT safe today: `assistant/message` (the model-history source) and `tool/call` (the audit record) are both logged BEFORE execution, and live consumers READ `tool/call.arguments` for presentation (the ACP bridge remembers them for `presentResult`; `dsh-tool-bash` derives the title/cwd/terminal-vs-background from them). A rewrite that changed only execution would make the UI show one command while another RAN. Designing that consistently (rewriting the audit + history + presentation as one unit) is a real consistency-design problem CC itself warns is racy — so it gets its own [proposed RFC](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md), and `TODO(pre-tool-input-rewrite)` anchors it at the loop's pre-execute call site. This does not regress any production consumer (no production `tools/execute` listener mutated `exec.arguments`). The low-level capability to mutate `exec` in a `pre-execute` listener still exists (unadvertised — a test shim uses it to thread a generated id), but it is not a first-class advertised contract.
`PreToolDecision` is allow/deny/ask only — **no `arguments` rewrite**. Output replacement is safe because `tool/result` is logged after execution from the final result. Input rewrite is different: `assistant/message` (model history) and `tool/call` (the audit record) are logged before `ToolRegistry.execute()`, while ACP and tool presentation read those arguments. The registry therefore seals the materialized arguments before `tools/pre-execute`; no listener or test shim can mutate them in place. An honest rewrite must update history, audit, presentation, and execution as one unit before that identity is created, which belongs to the separate [pre-tool input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md) and its loop-side `TODO(pre-tool-input-rewrite)`.
### What this PR does NOT do
### Boundaries
It does **not** declare `hook/*` SessionEvents (the durable hook-invocation log) — those belong to the `dsh-hook-protocol` library, because a native plugin can already use the typed Decisions without a durable hook log. A worked native-plugin example/test in this PR (`packages/core/agent-loop/tests/interception.spec.ts`) proves all the seams compose end-to-end through the REAL loop with NO `hook/*` involved — the concrete proof that "native hooks are just a plugin". Compaction (`PreCompact`/`PostCompact`), the Notification hook, Codex `PermissionRequest`, the permission/`ask` system, and the Stop loop-guard remain deferred (`FIXME(permissions)` marks the `ask`→deny degrade).
The seam package does **not** declare `hook/*` session events (the durable hook-invocation log); those belong to `dsh-hook-protocol`, because a native plugin uses typed decisions without an external hook log. The native-plugin integration test (`packages/core/agent-loop/tests/interception.spec.ts`) composes the seams through the real loop with no `hook/*` protocol. Compaction (`PreCompact`/`PostCompact`), Notification, and Codex `PermissionRequest` remain outside this decision. The [approval seam](2026-07-06-approval-seam.md) resolves `ask` decisions through `ctx.approval`, while terminal monotonic stopping is owned separately by `agent/turn-stop`.
## Alternatives considered
@@ -45,4 +55,4 @@ It does **not** declare `hook/*` SessionEvents (the durable hook-invocation log)
## Consequences
The canonical interception surface is now complete and uniformly typed: a native plugin returns typed decisions directly, and a CC/Codex bridge maps its protocol fields onto the same unions. The loop gained four firing points (session-start emit, prompt-submit waterfall, the post-tool context buffer, the continuation reshape) and the `dsh-tools` registry runs a two-waterfall pipeline; both are documented in [architecture.md](../../../architecture.md) and the package READMEs, and the decision types in [core-data-structures](../../../core-data-structures/core.md#interception-decisions) + [tools.md](../../../core-data-structures/tools.md). All existing `tools/execute` and `turn-continuation` listeners (tests, docs) migrated to the new seams. The ACP bridge maps the new `rejected` reason to `cancelled` (its codec). A pure internal change with no editor-visible transcript shift for the existing scenarios — the new behavior only fires when a hook is registered — so the snapshot goldens are unchanged; a hook-driven snapshot scenario lands with the `dsh-hooks-claude` bridge, which is what makes a hook observable end-to-end through ACP.
The canonical interception surface is uniformly typed without giving every extension the same power: hooks return decisions, execution wrappers wrap, terminal guards only deny, and final observers only observe. The loop owns session-start, prompt-submit, post-tool context buffering, and continuation; `dsh-tools` owns identity sealing and the five-phase execution pipeline. Their contracts are documented in [architecture.md](../../../architecture.md), package READMEs, [core interception decisions](../../../core-data-structures/core.md#interception-decisions), and [tool structures](../../../core-data-structures/tools.md). The ACP bridge maps `rejected` turns to its `cancelled` codec value, while hook-driven snapshots verify the observable bridge behavior end to end.
docs/rfc/implemented/feature/2026-06-30-subagent-observe-enrich.md
+3 -3
View File
@@ -6,13 +6,13 @@ Status: implemented
The hooks subsystem ([interception seams RFC](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run.
This RFC enriches the end payload. It is deliberately **observe-only**: no control-flow change, no waterfall, no `start()` restructure. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope.
This RFC enriches the end payload. It is deliberately **observe-only**: no control-flow change and no waterfall. A run-affecting subagent-stop decision (continuation, injection that changes the run) is a separate, larger redesign and stays out of scope.
## Decision
**Add `lastAssistantMessage` — the child's final output — to `SubagentRunEndInfo`.** On the settle path it is a DEEP CLONE of `SubagentResult.output` (so an observer sees WHAT the subagent produced without holding the run). On the REJECT path (an infrastructure fault where no `SubagentResult` was produced — the seam only knows `stopReason: 'error'`) it is absent. The clone is load-bearing for observe-only: the `subagent/end` emit fires from a detached `.then` registered *before* `start()` returns, i.e. before the caller's own `await run.result` continuation — handing listeners the same array reference would let a mutating listener corrupt the caller's `SubagentResult.output`. `structuredClone` makes the event a read-only view (a regression test mutates the event's array and asserts the caller's result is untouched); a clone failure is contained (logged, the event still fires without `lastAssistantMessage`) rather than becoming an unhandled rejection on the detached `.then`.
**Add `lastAssistantMessage` — the child's final output — to `SubagentRunEndInfo`.** On the settle path it is the readonly typed `SubagentResult.output`, so an observer sees what the child produced without holding the run. On an infrastructure rejection where no `SubagentResult` exists, it is absent and the event reports `stopReason: 'error'`. Providers and listeners are trusted same-process collaborators and honor the borrowed immutable payload contract.
Both events stay plain **`emit`s**. `subagent/end` fires from a detached `.then` on `run.result` and awaits no listener, so it is genuinely observe-only by construction — a `subagent/start` listener can still reach the live child via `ctx.agents.get(info.id)` and `inject()` into it; a `subagent/end` listener can only observe (the run has settled). Per-listener containment (already in place) keeps one bad subscriber from stranding a live run or surfacing as an unhandled rejection on the detached settle hook.
Both events stay plain **`emit`s**. Async `SubagentService.start()` attaches result observation to the ready provider run, emits `subagent/start`, and then returns the run; an in-process listener can therefore reach the published child via `ctx.agents.get(info.id)`, while a remote provider need not have a local registry entry. A rejected provider start emits neither event. The callbacks remain observe-only and per-listener containment keeps one bad subscriber from stranding a live run or starving later listeners.
## Alternatives considered
docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md
+12 -6
View File
@@ -24,7 +24,9 @@ One deliberate strictness DIVERGENCE from CC: hook misuse — unknown or deferre
**Trust premise (governs every engine decision below)**: workflow scripts are MODEL-WRITTEN — the same trust level as the model's existing bash access — so the engine defends against BUGGY scripts, never hostile ones. In scope: `result` never rejects, no unhandled rejections from dropped hook promises, loud rejection of values JSON cannot carry, fatal-vs-null hook discipline, cancellation that always frees the caller. Out of scope, deliberately: adversarial values (throwing/spinning accessors, proxies with hostile traps, prototype forgery, `prepareStackTrace` hijack) AND Node-API escape from the script's context — the vm context shares object machinery with its surrounding realm, so a script can reach the `Function` constructor (`globalThis.constructor.constructor`) and from it `process` and every Node builtin; the absent globals are API surface, not containment, and a worker thread is NOT a security boundary (an escapee holds process-wide privileges — Node's permission model is per-process). Worker-side code MAY run script code while reading script values, and that is accepted: a synchronous spin costs the script its OWN thread (terminated at the post-cancel grace), never the host loop, so containing error VALUES would be cost without a threat model. Genuine sandboxing (isolated-vm, a separate process) remains an engine swap behind the seam, not incremental defenses here.
**Why node:worker_threads**: one run = one worker thread, no pooling — a run is heavyweight (many children), so thread spin-up (~tens of ms) is noise. The script runs in a vm context INSIDE the worker, keeping the script-visible surface exactly the hook contract above (a bare worker realm would leak `setTimeout`/`fetch`/`process` as accidental API), and every `agent()` bridges to `ctx.subagents` by message-port RPC — children are I/O-bound LLM loops and stay on the host loop; the thread isolates the SCRIPT, the only part that can spin. What the thread buys: `start()` never blocks the host (an in-process engine runs the initial synchronous slice inline and cannot kill a spin past the first await — it could only ABANDON such a script, leaving the spin on the host loop), the post-cancel grace ends in a REAL `worker.terminate()`, and the value boundary is serialization by construction. isolated-vm was rejected for actual sandboxing: maintenance mode, `--no-node-snapshot` on EVERY consumer process (including published bins) on Node ≥ 20, node-gyp source-build fallback. Key mechanics (details in the package README): meta shape-validation and a body pre-parse stay HOST-side (preserving the seam's synchronous throws), a ready→go handshake keeps a run cancelled before start from ever executing the body, `cancel()` drives both child-cancel channels host-side (the shared request signal AND each child's explicit `cancel()` — a wedged worker cannot relay its own cancel RPCs), a host-side child registry backs worker-death reaping and `dispose()` quiescence, the wire protocol is enum-keyed payload maps private to the package, and on a termination path `agentsStarted` degrades to the host-observed count. Coverage puts the worker-side session on an in-process `MessageChannel` (real-Worker code is invisible to main-process v8) and proves the built `lib/worker.js` — a second tsdown entry, sanctioned in the workspace-constraints gate by the `"./worker"` subpath export — under plain node in the built-bin smoke gate.
**Why node:worker_threads**: one run uses one unpooled worker because a workflow run is already heavyweight relative to thread startup. The script runs in a vm context inside the worker, keeping the script-visible surface to the hook contract instead of exposing a bare worker realm, while `agent()` bridges by message-port RPC to I/O-bound child loops on the host. This keeps `start()` from blocking the host on the script's synchronous slice, makes the post-cancel deadline end in a real `worker.terminate()`, and gives cross-thread values a serialization boundary by construction. isolated-vm was rejected for its maintenance state, required `--no-node-snapshot` consumer flag on Node ≥ 20, and node-gyp fallback.
Host-side meta validation and body pre-parsing preserve the seam's synchronous errors, and private enum-keyed payload maps define the wire protocol. Pending async starts, published child records, one host cancellation signal, worker-death reaping, result precedence, and disposal quiescence preserve the subagent run contract across that wire; the [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) owns those race algorithms. Coverage uses an in-process `MessageChannel` for worker-side logic that main-process V8 coverage cannot see and separately proves the built `lib/worker.js`—a second tsdown entry sanctioned by the `"./worker"` subpath export—under plain Node in the built-bin smoke gate.
**Meta as data, never evaluated**: the meta block reaches the seam as a plain JSON request field (the tool's schema-validated `meta` parameter) and the engine only shape-validates it, every violation named. This is a host-isolation invariant, not a convenience: evaluating a meta literal host-side — even one contractually "pure", in an empty timed vm context — hands script-controlled getters a host stack with no timeout the moment the result is READ, defeating the exact spin isolation the worker thread buys.
@@ -36,7 +38,11 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai
### The foundation: structured output on the subagent seam
`agent({schema})` needs `SubagentStartRequest.outputSchema` to actually work; it was vocabulary without an implementation (`outputSchema: false` everywhere). Implemented in `dsh-subagent-inprocess` for both in-process backends: a globally registered `structured_output` capture tool whose per-child schema is enforced by a `prepend: true` `system-prompt/assemble` listener doing FINAL-ASSEMBLY enforcement (post-processing `await next()` — cooperative mutation would not survive a downstream listener returning a replacement assembly; the calling instruction rides as a trailing prompt section, since `AgentOptions` carries no per-agent prompt field, and the loop logs the result as the step's `request/header`, keeping the injection reconstructable), a `prepend: true` `agent/turn-continuation` veto after capture (no wasted extra model step) plus a `tools/pre-execute` deny for calls arriving after the capture (terminal within the step, not only at its end), and validation-retry in-turn via `ToolArgsError`. The schema is `structuredClone`d at `start()` (caller mutation cannot drift enforcement). Deliberately NO re-prompt: a child that finishes cleanly without calling the tool settles `error` to the parent. Lifetime is refcounted by backends (plugin lifetime) AND live runs (start → settle). The seam's `outputSchema` type became the raw JSON-Schema SUBSET (`StructuredOutputSchema` in dsh-tools: single-string `type`, `properties`/`required`/`additionalProperties`, `items`, scalar `enum`/`const`; anything unenforced is rejected loud) — the schema travels verbatim to the model as the forced tool's parameters, so the wire format, not the author DSL, is the right vocabulary.
`SubagentStartRequest.outputSchema` is implemented by `dsh-subagent-inprocess` for both in-process backends. Each structured child receives its own scoped capture tool, instruction, and enforcement registrations on `child.ctx`; concurrent children can use different schemas without sharing mutable policy, and disposing the child removes the entire attachment.
An output schema makes a schema-valid committed capture mandatory for successful child completion. The scoped runtime presents the capture tool and instruction, commits only a successful final outcome—including the enclosing `run_code` outcome for an SDK call—denies later side effects after capture becomes pending, and stops the child without another model step after commit. A validation failure remains a retryable tool error; clean completion without a committed capture settles as an error.
`StructuredOutputSchema` is the raw enforceable JSON-Schema subset in `dsh-tools` (single-string `type`, `properties`/`required`/`additionalProperties`, `items`, scalar `enum`/`const`), and unsupported keywords fail loudly because that wire data becomes the capture tool's parameters verbatim. The [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#structured-output-commits-only-authoritative-outcomes) owns the assembly, commit, guard, and terminal-stop correctness algorithms.
## Deferred (documented non-goals of this cut)
@@ -51,11 +57,11 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai
## Alternatives considered
- **Hostile-value containment in the host** (trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition): an earlier revision built all of it, and review showed the cost was real while the threat model was not — every one of those defenses guards against an author the premise already trusts. Removed in favor of the plain boundary above; the thread boundary makes such machinery redundant anyway (serialization by construction).
- **In-process `node:vm` execution** (the first cut of this RFC shipped it): mechanically simplest — no RPC, no thread — but `start()` blocks the caller for the script's initial synchronous slice, a synchronous spin past the first await cannot be killed in-process (the vm `timeout` covers only that first slice), and `dispose()` could only ABANDON an unsettling script, leaving the spin on the host loop. Superseded by the worker-thread engine, which keeps the same vm-context script surface while unblocking the host and making termination real.
- **Hostile-value containment in the host** (trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition): rejected because every defense targets an author the trust premise accepts, while the thread's serialization boundary already makes cross-realm values total by construction.
- **In-process `node:vm` execution**: mechanically simplest — no RPC, no thread — but `start()` blocks the caller for the script's initial synchronous slice, a synchronous spin past the first await cannot be killed in-process (the vm `timeout` covers only that first slice), and `dispose()` could only abandon an unsettling script on the host loop. The worker-thread engine keeps the same vm-context script surface while unblocking the host and making termination real.
- **Background execution as the default** (CC's shape): deferred; foreground-synchronous matches `dsh-tool-subagent`'s cut, and background semantics should be designed ONCE across bash/subagent/workflow rather than per-tool.
- **Workflow-layer JSON parsing for `agent({schema})`**: duplicating a seam concern at one consumer while the seam's capability flag stayed dishonestly `false`.
- **Meta embedded in the script as `export const meta = {...}`** (CC's exact format; the first cut shipped it): keeps scripts self-contained and CC scripts drop-in, but obtaining meta means evaluating model-written text on the HOST — the shipped extractor ran the literal in an empty timed vm context, yet reading the RESULT still executed script-controlled getters on the host stack outside any timeout, re-opening the host-spin hole the worker thread exists to close. A JSON parameter deletes the scanner, the evaluation, and the hole outright; the cost is that a CC script's meta header must move into the parameter (the body stays drop-in).
- **Meta embedded in the script as `export const meta = {...}`** (CC's exact format): keeps scripts self-contained and CC scripts drop-in, but obtaining meta requires evaluating model-written text on the host. Even an empty timed vm context cannot bound script-controlled getters when the host reads the resulting object. A JSON parameter removes the scanner, evaluation, and host-spin hole; the cost is that a CC script's meta header must move into the parameter (the body stays drop-in).
- **`SchemaSpec` as the outputSchema type**: the author-facing DSL cannot express what arrives as data and cannot be validated against without conversion loss.
- **A schema-object library (zod, or the repo's schemastery) for the structured-output subset**: the schema is wire data — plain JSON that crosses the vm realm boundary in `agent({schema})` and lands verbatim in the forced tool's parameters — exactly where live schema objects cannot sit; consuming raw JSON Schema at runtime would need a third-party converter on top (zod core only emits JSON Schema, not the reverse), and it would put a second schema language beside schemastery's config role.
- **ajv for value validation**: it validates FULL JSON Schema, so the subset gate — the module's actual point, since every accepted keyword must be one the harness enforces — would remain hand-written regardless; it compiles validators through `new Function`; and it would be dsh-tools' first runtime dependency, all to replace the ~70-line value walker while the path-qualified, every-violation error reporting stays custom either way.
@@ -63,4 +69,4 @@ A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, awai
## Consequences
The harness gains CC-compatible script orchestration: fan-out plans live in a rerunnable artifact instead of the parent context, and the structured-output half of the subagent seam is now real (the vocabulary stopped lying about `outputSchema`). What it cost, all bounded by the trust premise: a worker thread per run (~tens-of-ms spin-up), every hook crossing a message port as RPC, and a termination-path `agentsStarted` that degrades to the host-observed count; in exchange `start()` never blocks the host, a post-cancel grace ends in a real `worker.terminate()`, and the value boundary is serialization by construction. A worker thread is still NOT a security boundary — scripts share the model's trust level, and actual sandboxing names its exit (the isolated-vm/separate-process engine swap behind the seam). The fatal-vs-null strictness divergence from CC means a CC-authored script that RELIES on option typos dissolving to `null` behaves differently here — judged worth it to keep the repo's no-accepted-then-ignored rule. Consumers must hold the run handle for control (`cancel`/`dispose`); observers get data snapshots only, so no listener can extend a run's lifetime or corrupt another's view.
The harness gains CC-compatible script orchestration: fan-out plans live in a rerunnable artifact instead of the parent context, and `outputSchema` yields an authoritative structured child result across native and Code Mode presentation. The cost, bounded by the trust premise, is a worker thread per run (~tens-of-ms spin-up), every hook crossing a message port as RPC, and a termination-path `agentsStarted` that degrades to the host-observed count; in exchange `start()` never blocks the host, a post-cancel grace ends in a real `worker.terminate()`, and the value boundary is serialization by construction. A worker thread is still not a security boundary — scripts share the model's trust level, and actual sandboxing requires an isolated-vm/separate-process engine behind the seam. The fatal-vs-null strictness divergence from CC means a CC-authored script that relies on option typos dissolving to `null` behaves differently, preserving the repo's no-accepted-then-ignored rule. Consumers must hold the run handle for control (`cancel`/`dispose`); observers get data snapshots only, so no listener can extend a run's lifetime or corrupt another's view.
docs/rfc/implemented/feature/2026-07-05-skill-system.md
+53
View File
@@ -0,0 +1,53 @@
# RFC: Skill system — progressive disclosure instructions for agents
Status: implemented
## Problem
Agent products have converged on a skill pattern: keep the request prompt small by listing only available instruction bundles, then load the full body when the model decides a task matches. Codex, Claude Code, OpenCode, and Kimi Code differ in details, but all separate discovery metadata from complete instructions so a workspace can carry reusable behavior without paying the full prompt cost on every turn.
DeepSeek Harness uses the same primitive so project-specific review, plugin-authoring, and tool-usage guidance lives next to the workspace or the user's agent configuration instead of being hard-coded into the loop.
## Decision
`@deepseek-ai/dsh-skill` is the pure provider registry (`ctx.skills`), `@deepseek-ai/dsh-skill-local` is the shipped local filesystem provider, and `@deepseek-ai/dsh-tool-skill` owns the session-prefix catalog and model-facing loader tool. `dsh-agent-core` loads the registry, local provider, and consumer by default so stdio and ACP apps get the same behavior while embedded or remote providers contribute skills without changing the registry or consumer. Its `skills` config forwards `registry`, `local`, and `tool` branches to those owners.
Provider plugins register synchronously during `apply()`. Provider catalogs return ranked candidates from awaited `list()` calls, where remote providers perform initialization, authentication, and discovery while honoring the lookup abort signal. The registry validates each candidate, resolves same-name skills first-wins by rank, provider registration order, and provider-local order, then sorts summaries by skill name for deterministic consumers. It caches only completed catalog snapshots and retries when a provider/runtime revision changes during discovery, so an unload cannot freeze a stale, unresolvable skill into a session prefix. Runtime `ctx.skills.register(...)` remains a convenience for embedded in-process skills and uses project-over-user priority; `runtime` is reserved as the registry-owned provider name.
The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. DeepSeek Harness does not ship built-in system skills; embedded or remote providers supply additional skills when configured.
Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `disableModelInvocation`, and `metadata` are optional. Names are kebab-case. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
Local skill filesystem I/O goes through `ctx.fs` when a filesystem service is loaded: project-root lookup probes `.git` with `resolve` and `stat`, root discovery uses `listDir`, and skill reads use `readText`. The Node filesystem remains a fallback for minimal contexts that mount `dsh-skill-local` without the fs seam. Missing roots, unreadable or malformed skill files, and transient provider `list()` failures degrade to warn-and-skip so one bad source does not make every agent request fail; malformed candidates still fail fast because they are provider contract violations.
`dsh-tool-skill` contributes one user-role `<system-reminder>` catalog through [`agent/session-prefix`](2026-07-07-session-prefix.md). The catalog contains sorted skill name and description only; it excludes bodies, paths, sources, providers, and routing hints. Descriptions are whitespace-normalized, XML-escaped, and capped by `catalogDescriptionMaxLength`, whose default is `500` and minimum is `3`. The session-prefix seam freezes the request-only catalog per loop instance and records it in the request header, preserving reconstructability without adding it to durable history. Full skill bodies are never included in the catalog.
The `skill({ name })` tool loads one full skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills marked `disableModelInvocation` retain distinct tool errors. The tool result is the model-visible disclosure path.
The data structures and catalog/tool contract are documented in [skills.md](../../../core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../cordis-catalog/services.md).
## Alternatives considered
**Inject full skill bodies into every system prompt.** Rejected because it destroys progressive disclosure and makes every request pay for instructions that may not apply.
**Expose skills only as slash commands.** Rejected because model-initiated loading is the core capability; slash/ACP command advertisement does not change discovery.
**Put local filesystem scanning directly inside `ctx.skills`.** Rejected because coding agents, web agents, and future plugin ecosystems need different skill sources. A provider registry mirrors the subagent seam: the registry owns conflict resolution and consumers, while implementations own loading.
**Use a system-prompt section.** Rejected because the rendered system prompt is a single string, while the catalog is a user-role `<system-reminder>` message with request-only lifecycle requirements. [`agent/session-prefix`](2026-07-07-session-prefix.md) is the selected mechanism: it places the catalog ahead of derived history and records the composed message in the request header.
**Materialize built-in DSH authoring skills under `~/.dsh/skills/.system`.** Rejected because bundled skills do not write user home on startup, and embedded or remote providers supply configured skills.
**Recursively discover nested `**/SKILL.md`.** Rejected. Flat files and one-level directory bundles cover the configured roots while keeping duplicate handling and catalog order easy to reason about.
**Hand-parse frontmatter.** Rejected because the accepted schema includes an open `metadata` object. A narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
## Consequences
The agent-core spine includes one session-prefix contributor, one local provider, and one model-facing tool. Skill discovery is cwd-sensitive, so callers that create agents with different session cwd values can observe different project skill overrides by design.
The catalog is deterministic for a fixed root set and runtime registration revision, but disk changes are not watched; discovery is memoized until runtime registration invalidates the cache or the process restarts.
## Deferred
Forked skill contexts (`context: fork`), direct user/slash invocation (`user-invocable`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields.
docs/rfc/implemented/feature/2026-07-06-approval-seam.md
+141
View File
@@ -0,0 +1,141 @@
# RFC: The approval seam — one-shot permission decisions over a waterfall of answerers
Status: implemented
## Problem
Two callers need to put one question — "may this specific action proceed?" — to a human: `tools/pre-execute`'s `ask` decision (including the Claude-Code hook bridge's `permissionDecision: ask`) and the [sandbox RFC](2026-07-06-sandbox.md)'s post-denial one-shot escalation retry. A shared seam keeps them from inventing separate outcome vocabularies, UI routing, cancellation, and audit trails, while guaranteeing that a deployment with no UI can never grant an unanswerable request.
The routing problem is ownership: an approval prompt must reach the editor session that owns the asking agent (the ACP bridge multiplexes N sessions over one connection), fail closed for agents nobody owns (in-process subagents, tests), and stay out of deployments that compose no UI (headless, CI).
## Decision
One package, `dsh-user-approval` (`packages/ui/user-approval`), owning the vocabulary and the `ctx.approval` service — the MECHANISM. The POLICY — who answers, and whether a session is asked at all — lives outside it: answerers are `approval/request` waterfall listeners registered by the plugins that own the channel (the ACP bridge; future terminal UIs; test scripts), and a per-session policy tier can decide before any human is involved. Consumers (`dsh-tools`' ask routing, the sandbox escalation gate) resolve a question to a closed outcome and derive their own tool results from it. Deliberately ONE package, not the capability-seam three (see Alternatives).
### How a deployment uses it
One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-out: consumers deny unanswerable requests with zero approval code registered.
```yaml
- id: approval
name: '@deepseek-ai/dsh-user-approval'
# config:
# policy: never # deployment default for sessions without an override; 'ask' when omitted
```
The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-agent`, as in [the sandbox example](../../../../examples/sandbox-acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws.
What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked.
One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once:
```
tool/call bash {"command": "printf 'escalated\n' > escalated.txt && cat escalated.txt",
"sandbox_permissions": "workspace-write",
"justification": "the user asked to write escalated.txt in the workspace"}
approval/asked {"toolName": "bash", "callId": "call_00_…",
"reason": "escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}
→ session/request_permission {"toolCall": {"toolCallId": "call_00_…"},
"options": [{"optionId": "allow-once", "name": "Allow once", "kind": "allow_once"},
{"optionId": "reject-once", "name": "Reject", "kind": "reject_once"}]}
← the user picks "Allow once" on the prompt the editor attaches to the streamed bash call
approval/decided {"outcome": "allowed-once"}
tool/result "escalated" — this one call ran under the wider mode; the grant died with it
```
The `escalation-rejected` twin ends in `{"outcome": "rejected"}` instead: nothing executes, and the model's result carries the asker's verbatim fail-closed text (`the user rejected escalating this command to "workspace-write"`). A hook's `permissionDecision: ask` rides the identical wire; only the asker and its deny texts differ (§ Ask routing in dsh-tools). Headless, the same request skips the prompt entirely and settles `unavailable`.
### Design detail
#### The seam: mechanism and policy split
After request validation and a successful `approval/asked` append, the answerer phase always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable`. `ApprovalRequest` is a readonly same-process contract, so the service borrows its routing identity and cancellation signal instead of copying the record or capturing a parallel callback bundle. It dispatches the `approval/request` waterfall, races the request signal (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the request agent's session log. Request acceptance and either pre-commit audit append may still reject; returning a decision that could not be logged would violate the pair. Session owns post-commit observer containment, so a callback failure cannot turn an authoritative audit append into a rejected request or suppress the matching event. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. `request()` also throws before appending anything when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every ask path runs mid-turn already, and idle asks are a deferred design.
Answerers are the policy, and they are `approval/request` waterfall listeners. The waterfall buys exactly what the seam needs: with zero listeners the dispatch falls through to the caller-supplied default — `unavailable`, so fail-closed needs no configuration and no code in any deployment; a listener that recognizes the request's agent answers by returning an outcome without calling `next()` (the decision slot is single-occupancy, first answer wins — the same documented semantics as the `fs/write-intent` gate); a listener that does not recognize the agent MUST delegate via `next()` so another answerer or the default gets the question; and listeners dispose with their owning fiber, so an unloaded UI plugin degrades the next ask to `unavailable` instead of leaving a dangling channel. Registration order across sibling plugins is not load-order deterministic (the loader starts siblings concurrently), so a deployment composes ONE terminal answerer and reserves `prepend` listeners for decide-or-delegate gates.
`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The caller retains ownership and honors the readonly contract for the duration of `request()`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call.
#### Ask routing in dsh-tools
`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to guards and dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: with no ApprovalService, or after one unmounts, the next ask fails closed without gating the registry's fiber. An agent-less execution also fails closed — without an agent there is no session to audit to and no UI to route to.
#### The per-session policy tier
The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged and falls through to fail-closed `'unavailable'` when nobody answers. Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections.
#### The ACP answerer
The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap<Agent, sessionId>` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment.
The answerer routes through the bridge's reverse-map ownership seam described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md).
#### Audit, and what the model sees
`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended.
#### Entities and dependencies
One package, no cycles: `dsh-user-approval` peers on `cordis`, `dsh-session` (event-map merge + append), `dsh-agent` (the `Agent` type), `dsh-llm` (`CallId`, via `dsh-brand`). `dsh-tools` and `dsh-acp` each peer on it; the escalation phase's asker lives in `dsh-tool-bash` (see [the sandbox RFC](2026-07-06-sandbox.md) § Escalation), so the sandbox family keeps its ZERO-edge relation (the executor contributes the per-call override mechanism, and transport seams never ask humans questions). The seam is one package, not the capability-seam three: the service body (dispatch + audit) has no replaceable implementation — the replaceable part is the answerer listeners, and those live with their owners (the bridge; future terminal UIs; test scripts). `@cordisjs/plugin-capability` stays orthogonal (a static grant registry answers "is this already authorized", not "ask the user now"), and `subagent-acp`'s child-side `permission` auto-answer is untouched — routing a child's approvals to the parent session is deferred (§ Deferred).
### Testing
Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation), scoped routing, post-append observer throws on both audit events, and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`.
Snapshot tier: the harness accepts scripted permission answers (`permissionAnswers` in a scenario's `input.json`, consumed FIFO; an unscripted prompt answers `cancelled`, fail closed). The seam's wire is recorded end to end in the sandbox example's suite: both escalation branches drive `session/request_permission` through this seam over scripted answers (grant and rejection), and the recorded `mode-switching` scenario pins the `'never'` prompt sentence and the policy-switch notice ([the sandbox RFC](2026-07-06-sandbox.md) § Testing).
## Deferred
- **`allow_always` grant storage** — honoring a persistent grant means designing storage, scope identity (call? path? prefix? session? time window?), and revocation; until designed, only the one-shot options are advertised ([the sandbox RFC](2026-07-06-sandbox.md) § Escalation records the open scope question).
- **A recorded hook-driven `ask` through a composed answerer** — the human-prompt wire is recorded through the sandbox example's escalation branches. The hook matrix's `hook-cc-pretool-ask` pins the no-ApprovalService fallback denial, while the hook-producer-plus-answerer composition remains on the unit tier.
- **Routing a child agent's approvals to the parent session** — `subagent-acp`'s child auto-answers its own `permission` requests; surfacing them to the parent's editor is its own design.
## Alternatives considered
- **A single registered provider instead of waterfall listeners** — rejected: a `registerProvider()` surface forces every composition question — allowlist pre-filters, external hook deciders, scripted test answers, a policy gate in front of a human — inside one provider implementation. The waterfall gets composition, fail-closed absence, and HMR disposal from machinery the runtime already has; the seam's JSDoc pins the single-decision-slot convention instead of inventing a provider registry.
- **An inline `tools/pre-execute` permission gate in the ACP bridge** — rejected: prompting for every bridge-owned call hardwires the asking POLICY into the UI plugin, cannot serve a second asker (sandbox escalation happens after execution starts, with no pre-execute moment), and leaves hook-produced `ask` decisions without a shared mechanism.
- **The generic user-interaction seam (`ctx.userInteraction`)** — rejected as the approval mechanism: the two share a skeleton (route by agent, block for a human, handle absence), but approval's contract is narrower in every dimension that matters: a closed outcome vocabulary instead of free text, a protocol-native prompt attached to a tool call instead of a generic form, mandatory fail-closed absence, and audit events. Approval therefore does not ride the shipped `packages/ui/user-interaction` / `ask_user_question` elicitation path — an elicitation form is not a permission prompt, and a free-text answer is not a closed outcome; sharing provider plumbing stays open if the two ever converge.
- **Static optional injection in `dsh-tools`** — rejected: the vendored cordis `Inject` type has no optional flag — the object form maps service names to intercept config, and a declared inject gates the fiber. `ctx.get('approval')` is the documented opportunistic-consumption pattern (the `tool-bash` owner-token lookup, the loop's persistence probe), reads presence per call, and degrades correctly across HMR without extra machinery.
- **The capability-seam three-package split** — rejected: interface/implementation/consumer fits a seam whose implementation is swappable (bash-local vs bash-sandbox). Here the service body is fixed mechanism and the variable part is listeners that live with their owners — splitting would manufacture an implementation package with nothing in it ("don't split preemptively").
- **Offering `allow_always` now** — rejected: the protocol can express it, but honoring it means designing grant storage, scope identity, and revocation (§ Deferred). Advertising an option the harness cannot honor manufactures doomed grants.
## Consequences
The implemented contract is pinned by the suites in Testing:
- With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason.
- A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)).
- Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection.
- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair.
- Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor.
- A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request.
Costs and accepted limits:
- **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have.
- **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it.
- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead.
## FAQ
Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that.
- **What happens in a deployment with no answerer at all (headless, CI)?** Every ask falls through the empty waterfall to `unavailable` and the tool call denies with the "no approval channel is available" reason. Fail-closed is the zero-listener default, not a configuration.
- **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred).
- **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel.
- **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt.
- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two.
- **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant.
- **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred).
- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection.
- **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state.
- **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own.
## Prior art
In-repo precedents this design copies or contrasts with:
- The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses.
- `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer.
- [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services.
- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the `WeakMap<Agent, sessionId>` ownership seam the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements.
- The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it.
docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md
+3 -3
View File
@@ -17,7 +17,7 @@ The system-prompt assembly owns the canonical model-facing tool order, exactly w
- The list must contain the rest entry exactly once and no duplicate names.
- When `toolOrder` is unset, the canonical order is plain lexicographic name order (code-unit comparison, locale-independent), so determinism requires no configuration.
The policy is applied where the list is born: `assemble()`, before the `system-prompt/assemble` waterfall. The assembly canonicalizes the tools it collects from providers the same way it sorts sections by their `order` field — on the initial assembly, killing the registration-order entropy at its source. Everything downstream inherits the order untouched: the waterfall, the loop's `EpochHeader`, the `request/header` event, the deep-frozen request, and the dev invariant's cross-check all see one deterministic list, with no new loop change.
The policy is applied where the list is born: `assemble()`, before the `system-prompt/assemble` waterfall. The assembly canonicalizes the tools it collects from providers the same way it sorts sections by their `order` field — on the initial assembly, killing the registration-order entropy at its source. The waterfall therefore starts from one deterministic list; when a listener leaves that order intact, the loop's `EpochHeader`, the `request/header` event, the deep-frozen request, and the dev invariant's cross-check inherit it with no new loop change.
Scope is deliberately narrow: this fixes the REGISTRATION-ORDER race, not plugin behavior. A `system-prompt/assemble` listener may still add, remove, or rearrange tools — same as it may edit sections after their sort — and owns the determinism of what it emits; the waterfall contract already demands deterministic listeners (the reconstructability invariant would catch a listener that diverges between build and replay).
@@ -36,8 +36,8 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it:
## Consequences
- Every assembly — and therefore every `request/header` event and model request — has a deterministic tool order on every host; the CI-vs-local golden flip is structurally gone. The default order is lexicographic, no longer registration order.
- `PromptAssembly.tools` itself is canonical, so every assembly consumer (the loop, waterfall listeners, any future prompt inspector) sees the model-facing order; provider registration order is observable nowhere downstream of the registry.
- Every registry-built assembly starts with a deterministic tool order on every host; absent an expert listener that deliberately changes it, every `request/header` event and model request inherits that order. The CI-vs-local registration-order flip is structurally gone, and the default is lexicographic.
- The initial `PromptAssembly.tools` is canonical, so waterfall listeners start from the model-facing order; provider registration order is observable nowhere before that cooperative seam.
- The snapshot suite's single pinned request-header fixture (`text-turn`) carries the new canonical tool order; every other ACP snapshot keeps the header bulk scrubbed as `{{system}}`/`{{tools}}`, per the pinned-header design.
- A pure tool reordering between steps is representable only as a `request/header` `'fallback'` snapshot (the name-keyed `ToolsDelta` cannot express it); with a stable canonical order such reorders no longer occur in practice, so the fallback path stays a safety valve.
- The `toolOrder` key rides the app → `agent-core` → `SystemPrompt` forwarding chain, so deployments set it next to `persona` in the app config; `dsh-llm` and the agent loop are untouched.
docs/rfc/implemented/feature/2026-07-06-sandbox.md
+225
View File
@@ -0,0 +1,225 @@
# RFC: The subprocess sandbox — confinement seam, native runners, escalation, and per-session modes
Status: implemented
## Problem
A coding agent needs this product path: bash subprocesses — and the hook commands that ride them — execute under a restricted file sandbox by default; if and only if the sandbox actually denies an operation, the model may request one user approval for that same operation and, once granted, retry it once with wider permissions. An every-tool boundary is deliberately NOT the claim: fs/web/todo execute in-process where an `execve` wrapper is meaningless (§ In-process tools), and the cross-family boundary is staged follow-up work (§ Deferred phases). Without a shared vocabulary, every tool reinvents approval fields, denial parsing, retry matching, and permission-state hints.
The harness is an SDK, so confinement must be a capability developers COMPOSE: whether to sandbox, and which backend per platform, belongs in the leaf `cordis.yml` as a first-class entry — not inside one executor's private machinery. And the first-choice runner, `bwrap`, is unusable on exactly the hosts a sandbox matters most (minimal containers, disabled unprivileged userns, LSMs that deny `mount`), so a fallback runner has to ship with the SDK rather than be assumed on the host.
Confinement alone leaves two gaps. A denial with no escalation path is terminal — the model can only give up, which pressure-cooks operators into configuring `workspace-write` or `danger-full-access` globally and defeats the sandbox. And the model-visible knobs (the sandbox mode, the approval policy) change over an agent's lifetime — an ACP user flips a per-session setting, an operator edits `cordis.yml` while the process is down — while the model must never act on a stale belief about them: what IS the state on every request, what changed while the agent lives, and what changed while nobody was watching all need answers.
## Decision
One seam, one per-platform chain of local backends, one consumer, and two levers on top: a per-call escalation path and per-session runtime modes. Everything below composes from the leaf `cordis.yml`; nothing touches `agent-loop`. The scope is deliberately bounded: the phases this RFC names but does not design — per-session workspace root, cross-family fs enforcement, the `subagent-acp` consumer, more environments, a Windows chain — are listed under § Deferred phases, each a follow-up design, not a config knob.
### How a deployment uses it
Three `cordis.yml` entries turn an unconfined coding agent into the sandboxed product path; [`examples/sandbox-acp-agent`](../../../../examples/sandbox-acp-agent/README.md) is this composition, live:
```yaml
- id: sandbox
name: '@deepseek-ai/dsh-sandbox-local' # the per-platform runner provider (ctx.sandbox)
- id: bash
name: '@deepseek-ai/dsh-bash-sandbox' # the confined executor, replacing dsh-bash-local behind ctx.bash
config:
mode: read-only # the deployment default every session starts from
workspaceRoot: !!js process.cwd() # the boundary workspace-write may write under
- id: approval
name: '@deepseek-ai/dsh-user-approval' # the escalation gate's channel (the approval RFC)
```
The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook commands, and background tasks run exactly as before, spawned through the wrapped argv the provider returns. Deleting the `sandbox` and `bash` entries and loading `@deepseek-ai/dsh-bash-local` instead is the opt-out — execution is unconfined again and the escalation fields vanish from the tool schema, because they are capability-gated on the mounted executor, not on configuration. Omitting only `approval` keeps confinement but fails every escalation closed with its own error text.
Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` — at `confine()` before the command ever spawns — rather than degrading to unconfined execution. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner seam for keyless tests.
What the model then experiences: denied file effects come back as result facts with a `[sandbox: file access denied under <mode> mode]` marker plus standing instructions not to retry around them; under a confining executor the schema offers `sandbox_permissions` + `justification` for the one-approval escalated retry (validated strictly wider than the session's effective mode at execution); the system prompt deliberately does NOT state the sandbox mode — the model learns the boundary from the marker (which names the mode) when it hits it, instead of preemptively refusing work a standing declaration discourages. What an ACP editor experiences: a `sandbox-mode` and an `approval-policy` config-option select per session (each advertised only when its knob is composable), switchable at runtime; a sandbox switch simply changes what subsequent commands may do, while an approval-policy switch to `'never'` is stated in the prompt and narrated.
The product path, concretely (the escalation arc is verbatim from the recorded `escalation-approved` scenario; the denial leg is pinned on the real-kernel e2e tier):
```
tool/result … [sandbox: file access denied under read-only mode] ← the write RAN; the kernel refused it
tool/call bash {"command": "printf 'escalated\n' > escalated.txt && cat escalated.txt",
"sandbox_permissions": "workspace-write",
"justification": "the user asked to write escalated.txt in the workspace"}
→ the editor is prompted on this very call (session/request_permission through the approval seam); Allow once
tool/result "escalated" — THIS call ran under workspace-write and its result facts say so; the session stays read-only
```
Reject instead and nothing executes: the result is the verbatim `the user rejected escalating this command to "workspace-write"`, and the teaching makes that final — no re-ask.
### Design detail
#### Grounding — verified against the code
- Runtime OS subprocesses exist at exactly two sites: the `ctx.bash` seam's single spawn (`packages/bash/bash-local/src/run.ts`; hook commands flow through `ctx.bash`, so bash confinement covers them transitively) and `subagent-acp`'s child agents (`packages/subagent/subagent-acp/src/run.ts`) — the second consumer that makes a shared seam due rather than preemptive under the [capability seams RFC](../architecture/2026-06-13-capability-seams.md)'s "don't split preemptively" rule.
- Everything else executes inside the harness process (fs is in-process `node:fs`, web is in-process `fetch`, every `ToolDefinition.execute()` closes over `ctx`): an OS sandbox wraps `execve` and cannot wrap an in-process function call, so "sandbox any tool" is policy at each tool's seam, never a mechanical transport change.
- `tools/pre-execute` (`allow`/`deny`/`ask`) exists, with `ask` serviced by [the approval seam](2026-07-06-approval-seam.md); the fs intent gates are version guards with no mode input yet.
- `dsh-bash`'s request/spec split (`BashExecRequest` → `resolve()` → `BashExecSpec`) carries per-call fields the way escalation needs — `owner` is the template: request-optional, spec required-but-nullable, carried verbatim — and the result types already speak `SandboxMode`, so a per-call policy field adds no dependency edge.
- The pinned-header snapshot design means a schema/description change churns at most one pinning fixture per suite, and the escalation fields are advertised only under a sandboxing executor — so they live in exactly one pinned header, the sandbox example suite's `mode-switching` fixture.
#### The seam: `ctx.sandbox`
`dsh-sandbox` owns the vocabulary and the `SandboxProvider` contract: `confine(argv, policy)` returns the argv to spawn INSTEAD of the caller's own — wrapped so the process and everything it spawns run confined — plus the `enforcement` completeness the selected backend achieves, its denial dialect (`denialSignatures`, the stderr substrings that backend's kernel prints on a denied file effect), and its runner-failure dialect (`runnerFailureSignatures`, how the runner ITSELF failing — and therefore the command never running — identifies itself); with no usable backend it throws the fail-closed `SANDBOX_UNAVAILABLE` error, never a silent unconfined passthrough. The vocabulary: `SandboxMode` (`read-only` / `workspace-write` / `danger-full-access`, FILE effects only — network and process visibility are not claimed), `SandboxEnforcement` (`full` / `partial`), `SandboxPolicy` (mode + workspace root).
Policy rides each CALL, not the provider: two consumers may confine under different policies at the same instant (bash under `read-only` while a confined child agent keeps its state directory writable), and an approved escalated retry is a new call with a wider policy — inexpressible under a config-fixed provider mode.
The seam confines SAME-WORLD subprocesses only: a backend shares the host's filesystem and kernel. Containers, microVMs, and remote executors are NOT backends of this seam — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups, because an agent whose bash runs in a container while its fs tools write the host lives in two split worlds.
Left open, for the phase that needs them: whether network restriction arrives as a separate `network_mode` or merges into `sandbox_mode` once a runner enforces both, and whether `SandboxPolicy` grows extra writable-root grants now (the launcher already speaks `--rw <path>`) or only when escalation needs them.
#### Local backends and the shipped launcher
`dsh-sandbox-local` selects BY PLATFORM, once per lifetime, and caches the verdict: each platform names its runner chain, a chain of one is selected directly — probing arbitrates between candidates, and a sole candidate leaves nothing to arbitrate — and a chain of several is probed FUNCTIONALLY in preference order (build and enforce a real profile, never `--version` — a present-but-unusable `bwrap` must fail its probe). Linux: `bwrap` first (its mount profile is closest to the mode vocabulary: whole tree read-only, fresh `/dev`+`/proc`, `workspace-write` adds an ephemeral `/tmp` and rebinds the workspace root; deliberately no `--unshare-pid` and no network claim), else the npm-distributed `landlock-run` Landlock launcher. darwin: `sandbox-exec` speaking a Seatbelt (SBPL) profile — allow-default with `(deny file-write*)` plus write allow-lists, every granted root canonicalized because Seatbelt matches resolved paths (`/tmp` IS `/private/tmp`) — unprobed, the sole candidate. A platform with no chain fails closed at `confine()`; an unprobed runner that turns out unusable fails closed at EXECUTION instead — it refuses to run the command, and every wrap carries `runnerFailureSignatures` (the runner's own error prefix, which also matches the shell's runner-not-found message) so the consumer classifies that as a SANDBOX failure, never a task failure: on either path the command neither runs unconfined nor slips through as a plain failure. A non-empty `runnerCommand` config is the operator's assertion of a runner that fully enforces the bwrap-shaped profile — chain and probes skipped; it doubles as the deterministic fake-runner seam for keyless tests. It is not exempt from fail-closed execution: its wrap carries argv0-scoped outer-shell failure shapes (`exec: <argv0>: not found`, `<argv0>: No such file or directory`, `<argv0>: Permission denied`) as its runner-failure dialect, so a missing or unexecutable configured runner classifies as a sandbox failure like every other rung — never as a failing command, and never as a denial.
The launcher is a ~300-line C program (plain C11 over the raw Landlock UAPI — no libraries beyond a statically linked musl, so the audit surface is that one file plus the kernel's stable syscall contract): `--ro <path>` / `--rw <path>` grants, `--`, the wrapped argv; it installs the ruleset on itself and `exec`s (rulesets are inherited across `execve`, and it sets `no_new_privs` before restricting); `--probe` enforces a maximal ruleset in a short-lived child and exits 0 only when the kernel actually enforces; launcher failures exit 125 without exec'ing.
The launcher lives in its own repository and reaches the harness as the npm package family [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) (the per-platform-package pattern of `node-addon-require-builtin` and esbuild): an entry package — `dsh-sandbox-local`'s one runtime dependency — plus per-platform binary packages selected at install time by npm's `os`/`cpu` fields. The entry package owns the launcher's CLI contract end to end (`launcherPath()` resolution with a never-existing fallback, the functional `probe()`, `grantArgs()` flag spelling), versioned together with the binary so probe-report parsing can never drift against it; the harness keeps only the policy side, `landlockProfileArgs()` mapping the mode vocabulary to grants. Native-only per-architecture builds, pack gates (binary presence, executability, ELF architecture), and the byte-pinned publish rehearsal are that repository's release pipeline; this repo's Landlock CI legs install the published family from the registry — the true consumer path — and prove real-kernel confinement through it.
FIXME: Revisit the separate-repository boundary and try to maintain the launcher source and its platform package family inside this monorepo, so the native release surface and harness contract evolve together.
Profile parity is honest rather than identical: under Landlock, `read-only` grants `--ro /` plus `--rw /dev/null` (the node, not `/dev` — the host's `/dev/shm` is a persistent shared tmpfs), and `workspace-write` grants the HOST `/tmp` where bwrap's is ephemeral; under Seatbelt, `read-only` likewise grants only the `/dev/null` literal, and `workspace-write` grants the host `/tmp` plus the per-user darwin temp dir (`os.tmpdir()` — the platform's real temp area for mkstemp-family tools; omitting it would deny what the mode promises). Every wrap carries the rung's denial dialect (`denialSignatures`: EROFS text under bwrap, EACCES under Landlock, EPERM under Seatbelt) so consumers match the active backend rather than a cross-runner union. Enforcement is honest per ABI level: an older kernel enforces the subset its ABI governs (path truncate is ungoverned before ABI v3), the probe's report line distinguishes the cases, and every confined result carries the structured `enforcement: 'full' | 'partial'` fact — refusing partial enforcement would deny the fallback to precisely the older-kernel hosts that need it. The bwrap and Seatbelt profiles govern every promised file effect by construction, so their passing probes always report `full`.
#### The bash consumer
`dsh-bash-sandbox` extends `LocalBashExecutor` (spawn mechanics, process-group kills, spill files, background tasks, credential scrub inherited verbatim) and hands `ctx.sandbox` the exact `['bash', '-c', command]` argv it is about to spawn. A sandbox denial is a RESULT FACT, not an error: the command RAN and the kernel refused a file operation, so `result.sandbox.denied` is orthogonal to `exitCode`/`signal`. Classification is conservative text inference over the collected stderr tail against the WRAP's own dialect, so a backend is never credited with a denial text its kernel does not speak (bare EPERM under a Linux runner names non-file boundaries the mode vocabulary does not govern); the known residual false positive is non-sandbox text in the active dialect (an ssh auth failure under Landlock, a refused `kill` under Seatbelt), and a structured runner signal wins once one exists. A RUNNER failure is the opposite of a denial and outranks it in classification (a runner's error text can itself contain denial words): the wrap's `runnerFailureSignatures` matching a failed run means the sandbox broke and the command NEVER RAN — the foreground path re-throws it as the structured `SANDBOX_UNAVAILABLE` error (the late twin of the confine-time throw, carrying the runner's first stderr line), a settled background task stamps `sandbox.runnerFailed` and `bash_output` renders its own marker — so a broken sandbox can never read as a failing command.
The model's view is result facts only: the static tool description explains the denial marker (`[sandbox: file access denied under <mode> mode]`), encourages attempting commands that may be denied, and forbids retrying around a denial; when the escalation fields are advertised, a denied result additionally carries the escalation hint itself, so the sanctioned same-turn retry is prompted at the decision point rather than depending on the model recalling the description (§ Escalation). No prompt section states the sandbox mode (§ Per-session modes).
#### Escalation: one approved wider retry after a denial
The seam level is mechanism only. `BashExecRequest` carries `sandboxMode?: SandboxMode`, an explicit per-call policy input; `BashExecSpec` carries it required-but-nullable (the `owner` pattern: a forgotten field is a visible `undefined`, and `resolve()` is the one explicit defaulting step); `BashExecutor` exposes the capability fact `get sandboxMode(): SandboxMode | undefined` — `undefined` in the base class, the configured mode in `SandboxBashExecutor` — so the tool layer can advertise only what the mounted executor honors: composition truth, not configuration. The seam honors ANY explicit mode, including a narrower one; the wider-only ladder is escalation policy and lives in the tool. A non-sandboxing executor (`dsh-bash-local`) carries the field verbatim and confines nothing — the field reaching it means the caller bypassed the tool's gate, and its honest behavior stays unconfined execution, not a guess at enforcement it does not have.
`SandboxBashExecutor.resolve()` stamps the effective mode — escalation grant > session override > configured default — so `run()`/`start()` read the spec, never the config. The `danger-full-access` branch, the confine call, and the result facts all key off the spec's mode, and the per-task facts map carries each task's mode alongside its wrap facts (`notifyTaskDone()` stamps from the map entry): one escalated call — foreground or background — reports the mode it ACTUALLY ran under while every neighbor keeps its own.
The tool gate advertises two extra parameters exactly when `ctx.bash.sandboxMode` reports a confining mode at registration: `sandbox_permissions`, an enum of the closed escalation-target vocabulary — `workspace-write`/`danger-full-access`, every mode a session could ever escalate TO — and `justification`, required together with it. The enum is deliberately NOT cut down to the modes wider than the executor's DEFAULT: schemas are registry-global while the effective mode is per-session and switchable, so a default-relative ladder strands a session overridden NARROWER than the default (with a `danger-full-access` default and a `read-only` override it would advertise nothing at all — confined, but with no lever). Strict widening is instead enforced at EXECUTION against the call's effective mode (session override ?? executor default): a request that is not strictly wider fails closed with its own text and prompts no one. An escalating call resolves approval BEFORE anything executes — no `ctx.approval` composed, or no agent on the execution, fails closed with its own text; otherwise `ctx.approval.request({ agent, toolName: 'bash', callId, reason, signal })` with the audit-self-contained reason `escalate sandbox to ${mode}: ${justification}`, while the UI attaches the prompt to the already-streamed call (the command is visible there; the approval RFC's no-arguments rule holds). The four outcomes map to distinct results: `allowed-once` stamps `sandboxMode` onto the bash request and proceeds; `rejected`, `cancelled`, and `unavailable` each produce their own error text, so the model can tell a human "no" from a dismissed prompt from a missing channel. The grant is consumed by the very call that asked; nothing is stored.
The tool description teaches — and a denied result itself prompts — the SAME-TURN flow when the fields exist: on a denial a wider mode would cure, escalate immediately in that turn by retrying the exact command once with `sandbox_permissions` (the narrowest mode that suffices) + `justification`, without detouring through chat to ask first — the approval prompt raised by the retry IS how the user consents. Never speculatively: an escalation is grounded in a real denial — normally the one the command just hit, up front only when the session already denied the same access — and a prompt stating approvals are disabled turns the exception off entirely; a rejected escalation is final for that command. Denial-grounding is deliberately model discipline plus human judgment, not harness bookkeeping — the human sees the exact command and justification on the prompt (see Alternatives for why hard-matching is rejected). No new session events anywhere: the attempt is an ordinary `tool/call` whose logged arguments carry the two fields, the decision is the approval seam's `approval/asked`/`approval/decided` pair, the outcome is an ordinary `tool/result` whose sandbox facts name the mode it ran under. The asker lives in `dsh-tool-bash`, NOT the executor: a transport seam has no `agent`, no `callId`, and no business asking humans questions.
Left open, recorded for the phase that picks them up: what a grant's scope identity is beyond the sandbox mode — the exact call, a path, a command prefix, the session, a time window — the question `allow_always` grant storage must answer before that option can be advertised; how cancellation behaves while an approval prompt is pending; and how escalation is defined for `run_in_background` denials that arrive via `bash_output`.
#### Per-session modes: the session log as the store
```
effective(session) = findLast(the session's own knob events)?.value ?? the composition-config default
```
The default is composition config (`cordis.yml`) — operator-owned, process-wide. A runtime switch is a SESSION-SCOPED override recorded as one log-only event in that session's own log. Restart immunity (resuming a session replays its log, so overrides come back with zero catch-up machinery) and multi-session isolation (one editor tab's `workspace-write` cannot disturb another's `read-only`) both fall out by construction, and no external config store exists anywhere.
**One event per knob, owned by its domain** — the merge-extensible `SessionEventMap` idiom every existing event family already follows (`approval/*` in `dsh-user-approval`, `hook/*` in the hooks packages):
```ts
interface SessionEventMap {
'bash/sandbox-mode': { mode: 'read-only' | 'workspace-write' | 'danger-full-access' }
'approval/policy': { policy: 'ask' | 'never' }
}
```
Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval RFC](2026-07-06-approval-seam.md)'s side of the same pattern.
**Visibility is deliberately asymmetric between the knobs.** The SANDBOX mode is stated nowhere and its switches are not narrated: a standing "you are read-only" declaration teaches the model to refuse preemptively (observed live: sessions where the model would not even attempt a write it could have escalated), while the denial marker already names the mode the command ran under at exactly the moment the boundary matters — behavior, not belief, carries the state, and a switch simply changes what the next command does. The APPROVAL policy keeps both layers, because its failure mode is the opposite: an auto-rejected ask under `'never'` returns "the user rejected …" wording no behavior can disambiguate, so the prompt states `'never'` (and ONLY `'never'` — an `'ask'` promise is unknowable without asking, and absence under a logged header is how the narrator reads `'ask'` back), and an `agent/pre-step` narrator injects at most one coalesced notice per policy switch: idle flip-flops collapse to one notice at the next turn's first step, a net-zero round trip to none, and a mid-turn change is narrated no later than the next step. Its "last told" is in-memory with a log-derived fallback (the folded header's system text parsed against the closed candidate sentence; LAST occurrence wins, so a persona quoting it cannot shadow the real section), so restarts lose nothing; attribution is positional (a knob event after the log's last `request/header*` reads `changed by the user`, a drift with no such event reads `changed by the operator/config`).
**The editor surface** is protocol-native [Session Config Options](https://agentclientprotocol.com/protocol/session-config-options) — the spec's replacement for session modes (slated for removal in ACP v2), already SDK-typed. The bridge advertises one independent `select` per composable knob — `sandbox-mode` (category `mode`) iff the mounted executor confines, `approval-policy` iff the approval seam is composed — with `currentValue` folded from each session's own log, in `session/new` and `session/load` responses. `session/set_config_option` validates against the same closed lists, routes to the domain setter, and returns the complete refreshed state (the spec contract).
**Anchoring: turn-enclosure is the commit boundary.** The turn-enclosure contract makes a bare between-turns append invalid (the JSONL backend treats a post-`turn/end` tail as crash garbage; dev invariants throw). A switch while a turn is open appends immediately — openness read from the LOG (last boundary event is `turn/start`), not `agent.status`, which stays `running` between queued turns. An idle switch is held on the bridge's session record and anchored at the next turn's `agent/prompt-submit` — inside the turn, before anything in it assembles or executes, last write per knob, and OUTSIDE any `session/event` emit (appending from inside that feed reorders events for later-registered listeners — a bug the dev invariants caught live). Until anchored, the switch exists only in bridge memory: responses overlay it truthfully, and a crash before the next turn reverts it — `session/load` then reports the fold's truth, so the editor UI self-corrects rather than lies.
#### In-process tools
fs/web/todo execute in-process, so their sandbox semantics are policy at their seams: the fs intent gates deciding by the shared mode vocabulary (§ Deferred phases, cross-family) make `read-only` a real boundary instead of a bash-only approximation — until then the contract says so honestly. No generic per-tool sandbox runtime: a host-mediated tool leaves the process only by returning declarative effects the host validates, which is a rewrite, not a wrapper.
FIXME: Revisit this tool-local boundary. The follow-up design needs to determine whether sandboxing becomes a global harness capability that applies uniformly to every tool, instead of expressing in-process enforcement independently at each tool seam.
### Testing
- Unit tier (no real runner anywhere): profile dialects, per-platform chain selection (sole candidate unprobed, no chain fails closed, multi-candidate probe order), verdict caching, the fail-closed end, probe-report parsing, and the launcher/`sandbox-exec` CLI contracts via fake runner scripts in `dsh-sandbox-local`; wrapping, policy hand-off, fact stamping, and runner-failure-outranks-denial classification (foreground throw, background `runnerFailed` fact) against a fake provider in `dsh-bash-sandbox`; the error's structured identity in `dsh-sandbox`. The escalation matrix spans the three bash packages: verbatim carry-through in `dsh-bash-local`, stamp/branch/per-task-facts in `dsh-bash-sandbox`, and the capability gate, `justification` pairing, fail-closed texts (pinned verbatim), and grant stamping in `dsh-tool-bash`. The switching surface pins the folds, the stamping precedence, the `'never'` gate, per-session section rendering, the full narrator matrix (cold start, coalescing, net-zero, resume drift with operator wording, positional attribution, persona-shadow hardening), and the bridge's advertisement gating, validation rejections, idle-vs-mid-turn anchoring (dev invariants mounted), and `session/load` reporting over a real two-process JSONL round trip.
- Keyless real-runner e2e, split along the seam and per rung: CI's `sandbox-e2e` matrix runs bwrap and Landlock on Linux (the Landlock leg once per architecture, each confining through the registry-installed launcher) and Seatbelt on macOS against real kernels, failing on a silent all-skip. World-proofs live in `dsh-sandbox-local` (denied writes absent on disk, workspace writes landing, temp-area grants pinned, kernel denial text matching the advertised dialect) and `dsh-bash-sandbox` (the through-`ctx.bash` consumer proofs, including denied-then-overridden-write-lands). This package's own publish path is rehearsed without publishing (`packed-install.e2e.ts`): `pnpm pack`, tarballs installed into a throwaway consumer with the launcher family resolving from the registry, plain `node` confining through the INSTALLED launcher — asserted executable apart, so a mode-stripped binary can never masquerade as a non-enforcing kernel. The switching surface has its own keyless e2e (`examples/sandbox-acp-agent`): the real `cordis.yml` tree advertises both options, honors switches end to end, and rejects out-of-vocabulary values.
- With-key e2e (`examples/sandbox-acp-agent/tests/escalation.e2e.ts`): real model + real runner + the REAL bridge answerer, world-verified — denied under `read-only`, escalates with justification, the scripted editor grants and the retried write lands on disk, while a rejected escalation leaves no write. Self-skips without `DEEPSEEK_API_KEY` or a usable runner (e2e.yml installs bubblewrap so it actually executes in CI).
- Snapshot tier (`examples/sandbox-acp-agent/tests/acp.snapshot.ts`): the keyless config-option wire; the recorded mode-switching arc as the suite's pinned header — necessarily, since mid-session switches emit the `request/header-delta`s the uniformity guard licenses only in the pin — committing both switches, the prompt-section delta and one "changed by the user" notice per knob, and a confined write landing under the switched mode; and both recorded escalation branches over scripted `permissionAnswers` (grant runs confined under `workspace-write`; rejection executes nothing and pins the fail-closed text). Replay re-executes every fixture's bash calls under the host's real runner (ci.yml's snapshot lane installs bubblewrap). Deliberately absent: a fixture carrying a real DENIAL — denial stderr is the backend's dialect and would pin a fixture to its recording platform; the escalation prompts assert the prior denial instead, and the denial→marker path stays on the tiers above.
## Deferred phases
Each phase gets its full design when picked up, validated against the code at that time, and lands with unit, real-API e2e, and snapshot coverage at the tiers it touches.
- **Per-session workspace root** — the executor's write boundary stays config-fixed for its lifetime while each ACP session has its own cwd; a per-session root rides the same per-call policy carrier once designed.
- **Cross-family boundary** — the fs intent gates decide by the shared mode, making `read-only`/`workspace-write` real boundaries beyond bash.
- **Second consumer** — `subagent-acp` optionally confines child agents (per-call policy; unconfined default — a child agent must write its own persistence).
- **More environments** — an environment-coherent capability group example (e.g. bash+fs against one container).
- **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from its own repository on the `node-addon-landlock-run` template, plus its profile dialect and denial/runner-failure signatures.
## Alternatives considered
- **Command-string heuristic preflight** — rejected: cannot understand expansion/subprocesses/symlinks; the strict attempt (run it, let the kernel decide) is the only trustworthy denial signal.
- **Functionally probe even a platform's sole backend** — rejected: probing arbitrates between candidates; with one there is nothing to decide, and probe cost taxes the first confined command of every session (prohibitive for heavy future backends). The runner's own exec-time fail-closed refusal plus `runnerFailureSignatures` classification carries the safety property instead.
- **Commit the built launcher binaries** — rejected: a binary in a diff is unreviewable and churns history; reviewed source + native CI builds + the launcher repo's byte-pinned publish rehearsal keep bytes out of every tree.
- **Compile the launcher on install** — rejected: pushes a C toolchain onto every consumer; a fallback that exists only where a compiler happens to be is not a fallback.
- **Cross-compile both architectures from one builder** — rejected: requires carrying a pinned cross toolchain (rustup targets, zig, or a container image) solely to rebuild two ~70 KB binaries; per-architecture native runners already exist and each builds its own platform package (the `node-addon-require-builtin` model, the launcher repo's own pipeline).
- **No fallback (bwrap or fail closed)** — rejected: concentrates failure on the hosts a sandbox matters most, degrading to `danger-full-access` by resignation.
- **Keep the mechanism inside `dsh-bash-sandbox`** — rejected: blocks the existing second consumer, makes future phases read mode out of a bash plugin's config, and cannot express escalation.
- **Config-fixed mode on the provider** — rejected: one mode per process; cannot serve concurrent consumers with different policies nor the one-shot widened retry.
- **One interface spanning containers/VMs too** — rejected: `confine(argv)` presupposes a shared filesystem; environment isolation is capability-sibling backends deployed as coherent groups.
- **Generic ToolRuntime wrapping any tool** — rejected: mechanically false for in-process tools (closures over `ctx`); the declarative-effects rewrite is unjustified for fs/web/todo.
- **Ask inside the executor (`dsh-bash-sandbox`)** — rejected: no `agent` to route through, no `callId` to attach the prompt to; adding them teaches a transport seam about sessions and UIs — the tool layer holds both and owns the model-facing vocabulary.
- **Auto-retry inside the same tool call** — rejected: a hidden re-entry the log cannot reconstruct: one `tool/call` would have produced two executions with different policies — the retry is a NEW logged call with its own arguments and result facts.
- **Advertise the escalation fields unconditionally** — rejected: under `dsh-bash-local` they are a dead lever — advertising an option the harness cannot honor manufactures doomed grants; capability-gating costs one registration-time read.
- **A default-relative escalation ladder (advertise only the modes wider than the executor's registration-time default)** — rejected: per-session overrides make the default the wrong baseline — a session switched narrower than the default loses exactly the lever it needs, and under a `danger-full-access` default the fields vanish entirely while a `read-only`-overridden session stays confined with no escalation path. The enum pins the closed target vocabulary; strict widening is a per-call execution check against the session's effective mode.
- **Per-session dynamic tool schemas** — rejected: schemas are registry-global by design (one assembly vocabulary, the pinned-header snapshot contract), and re-registering per session would buy only what the execution-time strict-wider check already guarantees, at the cost of a per-session schema surface and header churn on every switch.
- **Hard-match the retry to a prior denial** — rejected: command-string identity is fragile (quoting, `workdir`, env prefixes, a pipeline retried as its failing stage) — false-rejects honest retries or is trivially satisfied; the real boundary is the human seeing command + justification. Revisit only if `allow_always` grant storage ever needs machine-checkable scopes.
- **A generic `env/state` facts map with an owner service** — rejected: approval and sandbox compose independently, so neither's state may drag in a third package; single-key folds are one `findLast` each, dissolving the owner service; no invariant spans the knobs, so atomic multi-key patches bought nothing.
- **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener.
- **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no".
- **Track "last told" with its own bookkeeping events** — rejected: the `request/header*` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store.
- **ACP session modes instead of config options** — rejected: one mode list cannot carry two orthogonal knobs; config options are the spec's designed surface and modes are slated for removal in ACP v2.
## Consequences
What shipped pins — the tiers in Testing hold each:
- A denied command retried with `sandbox_permissions` + `justification` prompts the user through the composed answerer chain; a grant runs THAT call under the wider mode (result facts say so) while every other call keeps its own effective mode; every non-grant outcome produces its distinct error text and executes nothing.
- The escalation fields exist exactly when the mounted executor confines; a request that is not strictly wider than the call's effective mode fails closed with its own text and prompts no one; a deployment with no ApprovalService fails escalating calls closed and leaves plain calls untouched.
- The system prompt never states the sandbox mode (an approval `'never'` policy is the one stated knob), and the whole exchange — headers, knob events, notices, approvals, results — reconstructs from the session log alone, with no event types beyond the two knob events.
- N idle-time flips produce at most one anchored event per knob (a net-zero sequence anchors none — a no-op push from a client echoing current selections records nothing); an approval-policy switch is narrated in at most one coalesced notice; a mid-turn sandbox switch is honored by the next call's stamp.
- A resumed session's overrides apply and are reported to the editor with no special-casing; a default changed while the process was down is narrated before the session's first new request, attributed to the operator.
- Two concurrent sessions never see each other's state, notices, or config options.
- `agent-loop` is untouched — everything rides `systemPrompt.section`, `SessionEventMap` merging, `agent.inject()`, `agent/pre-step`, `agent/prompt-submit`, and the ACP handler surface.
Costs and accepted limits:
- **The one-wrapper illusion is given up knowingly.** A `tools/pre-execute` wrapper plus prompt conventions does not solve sandbox approval — the correct design costs structured denials, native runner probes, per-call policy carriage, and consistent cross-family enforcement, and this design pays it.
- **`read-only` is not yet a cross-family boundary.** Until the fs intent gates decide by the shared mode, the claim holds for bash only; the contract says so honestly (§ In-process tools).
- **Windows has no backend.** Its chain slot is reserved empty — fail-closed, never a fallthrough; filling it is a deferred phase.
- **The Seatbelt rung leans on Apple's deprecated-but-shipped `sandbox-exec` CLI.** As darwin's sole candidate it is selected without probing, so a future removal surfaces at execution as the runner-failure classification — re-thrown `SANDBOX_UNAVAILABLE`, the command never runs; fail closed, never open.
- **Landlock confinement is only as complete as the running kernel's ABI.** Reported as `enforcement: 'partial'` rather than refused — the deliberate trade that keeps the fallback available on older-kernel hosts.
- **The launcher arrives as a registry dependency.** Trusted through its own repository's release pipeline (reviewed C source, native CI builders, byte-pinned publish rehearsal) plus this repo's version pin — the real-kernel e2e legs are what vouch for behavior through the installed bytes.
- **The model may over-ask.** Escalating without denial grounding, or picking `danger-full-access` where `workspace-write` suffices: the description steers and the enum forces the ladder, but the human prompt is the actual gate; the `approval/asked` reasons make over-asking auditable, and a `prepend` policy answerer can auto-reject patterns a deployment never wants.
- **The advertised target set is static while the effective mode is per-session** (schemas are registry-global) — a session already at the widest mode is still offered the fields. Harmless by construction: the strict-wider check at execution, not the enum, is the safety boundary — a non-widening request fails with its own text and never prompts anyone.
- **A granted escalation is not a working sandbox.** An unavailable backend still fails closed even for a granted escalation to a confining mode — at `confine()` when the platform has no chain or every probe fails, at execution when an unprobed sole runner refuses (classified as a sandbox failure, not a command failure) — while a granted `danger-full-access` run never touches the provider at all: there the grant, not the probe, is the authority.
- **An idle switch lives in bridge memory until the next turn anchors it.** A crash in that window reverts it (reported honestly on `session/load`), and a session that never runs another turn never persists it — accepted, with the loop-owned idle commit turn named as future work if durability becomes a requirement.
- **The approval narrator's restart baseline parses prompt prose.** The closed candidate sentence is owned by the writing module itself, so a wording change is a coordinated writer+parser edit in one file; a session whose headers predate the section silently adopts the current policy without a notice.
- **The approval section is still a dynamic prompt surface** (a `'never'` switch breaks provider prompt-prefix caching for that session). Accepted: policy switches are rare, and a model acting on a stale `'never'` is worse. The sandbox knob no longer touches the prompt at all.
- **The model may hold a stale belief about the sandbox mode** (nothing announces a switch). Accepted deliberately: the next attempt's marker or success corrects it, and the observed failure mode of announcing — preemptive refusal — is worse than one wasted retry.
## FAQ
Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that.
- **A command came back with `[sandbox: file access denied under read-only mode]` — did it fail?** It RAN, and the kernel refused a file effect: the denial is a result fact orthogonal to exit code. The teaching forbids retrying around it; the one sanctioned move is the same command retried once with an escalation request.
- **How is a BROKEN sandbox told apart from a failing command?** Runner failure outranks denial in classification: a failed run matching the wrap's `runnerFailureSignatures` means the command NEVER ran — foreground re-throws the structured `SANDBOX_UNAVAILABLE` with the runner's stderr line, a background task stamps `sandbox.runnerFailed` and renders its own marker. A broken sandbox can never read as a failing command, and the command never runs unconfined.
- **What happens on a platform with no backend — Windows today?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE` and the command never spawns; `win32` is a reserved EMPTY chain, pinned by test to fail closed identically until a Windows runner fills it (§ Deferred phases).
- **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the registry-installed Landlock launcher, and the verdict is cached for the provider's lifetime.
- **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam.
- **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively. fs/web/todo execute in-process, where an `execve` wrapper is mechanically meaningless; their `read-only` semantics arrive with the cross-family deferred phase, and until then the contract says bash-only honestly.
- **Does a granted escalation persist, or cover background tasks?** Neither: the grant is consumed by the very call that asked (foreground or background), that one call reports the mode it actually ran under, and every neighbor keeps its own. How escalation should be DEFINED for a background denial that only surfaces later via `bash_output` is left open in § Escalation.
- **When does an editor's mode switch take effect?** Mid-turn: appended immediately, honored by the very next call's stamp. Idle: held on the bridge's session record, anchored at the next turn's `agent/prompt-submit`, with N flips coalescing to at most one event (none if net-zero); a crash before anchoring reverts it and `session/load` reports the truth. The model is not told — its next command simply behaves under the new mode.
- **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline changes behavior the same way a switch does (the approval policy, being stated, is additionally narrated with operator/config attribution).
- **What does `enforcement: 'partial'` on a result mean?** The selected backend enforces the subset its kernel ABI governs — e.g. Landlock before ABI v3 does not govern path truncate — and says so structurally instead of refusing the host; the probe's report line distinguishes the cases. The bwrap and Seatbelt profiles govern every promised file effect by construction, so they always report `full`.
## Prior art
In-repo precedents this design copies or contrasts with:
- [The capability-seams RFC](../architecture/2026-06-13-capability-seams.md) — the interface/implementation/consumer split and the "don't split preemptively" timing rule the second consumer satisfied.
- The `dsh-bash` request/spec split and its `owner` field ([the bash vocabulary catalog](../../../core-data-structures/bash.md)) — the per-call carrier template `sandboxMode` rides, and the explicit-`resolve()` defaulting convention.
- [The approval seam RFC](2026-07-06-approval-seam.md) — the channel escalation asks through; its answerer waterfall, audit pair, and one-package rationale are recorded there.
- [Event-sourced sessions](../architecture/2026-06-11-event-sourced-sessions.md) and [the turn-enclosure invariant](../architecture/2026-06-15-turn-enclosure-invariant.md) — the log-as-store foundation the per-session modes fold over, and the commit boundary the anchoring design obeys.
- [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` vocabulary the escalation gate deliberately does not reuse (an escalating call has no pre-execute moment of its own).
docs/rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md
+92
View File
@@ -0,0 +1,92 @@
# RFC: Configure subagent persona, tool visibility, and depth
Status: implemented
## Problem
A reusable subagent provider answers how to run a child, but different delegation tools need different child behavior. One deployment may want a reviewer persona, a research-only tool set, or a hard recursion bound without creating a new provider for every combination.
These controls affect the child's first model request and therefore cannot be installed after the child is visible. They also need honest provider support: an ACP backend cannot silently accept an in-process-only tool filter, and a filter must not be described as a security boundary when every plugin runs in the same trusted process.
## Decision
Subagent starts have three independent composition controls: `persona`, `toolFilter`, and `maxDepth`. A provider advertises support for each control, the service rejects unsupported requests before starting a run, and an in-process provider installs the requested composition while the child is still unpublished.
The controls answer different questions:
| Control | Question | Result |
|---|---|---|
| `persona` | What role instructions replace the deployment persona for this child? | A child-local prompt section shadows `deployment:persona` |
| `toolFilter` | Which deployment-global tools enter this child's visible tool view? | A scoped restriction filters globals before child-local tools are added |
| `maxDepth` | How deep may this delegation tree grow? | A start whose child depth exceeds the absolute cap is rejected |
`dsh-tool-subagent` exposes the controls as plugin configuration and copies them into each request it creates. Direct `SubagentService` callers may choose them per request. The provider capability descriptor remains the source of truth for whether a backend can honor each field.
### Persona is a scoped shadow
The persona control changes one child without changing deployment-wide prompt assembly. During unpublished setup, an in-process provider registers a child-scoped section named `deployment:persona`; ordinary most-specific-wins resolution replaces the global section only in that child's assemblies.
The value has the same strict template semantics as the deployment persona. Omitting it inherits the deployment section through the global layer; an explicit empty string shadows the global persona with an empty section. Parent and sibling personas never enter the child's flat scope.
This uses the normal system-prompt registration mechanism rather than a second persona channel. The first prompt therefore sees the same named contribution that later prompts and prompt-inspection tools see.
### Tool filtering is one live global-view rule
The tool filter controls visibility and executable lookup together. An in-process provider installs `ToolRegistry.restrict()` in the child's scope before publication, and the registry's single resolver applies the same result to prompt schemas, lookup, execution, and Code Mode SDK generation.
Resolution follows these rules:
1. Each restriction applies `allow` before `deny` to the live deployment-global tool registry.
2. Multiple restrictions intersect, so every installed restriction must admit a global tool.
3. Child-scoped tools are added after global filtering and may shadow an admitted global tool.
4. Reserved `run_code` presentation and other scope-local protocol contributions are outside the global filter.
Configuration fails loudly when a filter supplies neither `allow` nor `deny`, or names something outside the current global restrictable set, including a scope-local-only or reserved name. `allow: []` is valid and deliberately hides every global tool. These checks catch misspellings and prevent configuration from appearing effective when it cannot affect the named entry.
The global registry remains live. A deny-only filter admits a later global name unless it explicitly denies that name; an allow-list excludes a later global name unless it explicitly allows that name. Removing a global tool removes it from every resolved view. These semantics preserve hot registration while making the difference between allow and deny explicit.
### Depth is an absolute tree cap
The depth limit bounds recursive delegation independently of tool visibility. A top-level agent has depth zero; an in-process child has its parent's validated depth plus one. `maxDepth` is an absolute non-negative safe integer, and a start rejects before child ownership begins when the derived child depth is greater than the cap.
Every public entry validates the domain rather than relying on one model-facing configuration path. Negative values, fractions, negative zero, non-finite values, unsafe integers, malformed stored parent depth, and derived overflow all reject. Omitting the cap leaves depth unbounded by this mechanism.
A deployment can combine depth and filtering. For example, it may keep the delegation tool visible at depth one but set `maxDepth: 1`, or deny the delegation tool entirely in children. Neither choice changes the provider's conversation-history behavior.
### Capability gating keeps providers honest
Capabilities separate a requested feature from a provider implementation. `SubagentCapabilities` advertises `persona`, `toolFilter`, and `depthLimit`; `SubagentService.start()` checks every present request field against those flags before calling the provider.
This lets spawn and fork providers share the in-process implementation while external providers advertise only what they can enforce. A request never degrades silently: selecting an unsupported control produces `UNSUPPORTED_CAPABILITY`, and no run or lifecycle event exists.
### Unpublished setup makes the first request correct
All child-local composition is complete before the child becomes observable. The in-process provider supplies one setup callback to agent creation; that callback installs persona, tool restriction, and structured-output contributions in the child's scope. Only after setup succeeds does creation publish the session and agent and allow the driver to start.
A setup failure rolls back the private child. No observer can acquire a child whose first prompt used the deployment persona or unfiltered tool set and whose later prompts use the requested configuration.
## Visibility is not authority
These controls compose trusted same-process behavior; they do not authorize it. `toolFilter` changes the child view resolved by the tool registry, but it does not create a parent-to-child grant lattice, require a child to be a subset of its parent, sandbox plugins, or prevent code with another Cordis context from calling services directly.
In particular, a child-local tool is added after the global filter and may be absent from the parent's view. A deny-only child also sees later global tools not named by the deny-list. Those are deliberate live-composition semantics, not non-escalation guarantees.
A security design would need a separate authority representation, propagation rule, and execution-time enforcement point. Creation-time grant snapshots, parent-subset grants, explicit future-grant APIs, and generic capability/output/termination tags are outside this feature.
## Alternatives considered
**Create one provider per persona or tool set.** This multiplies providers that share the same transport and lifecycle implementation, makes dynamic deployment configuration awkward, and still needs a recursion mechanism. Providers remain about execution transport; requests carry per-child composition.
**Copy the parent's complete tool view.** Registration scope is flat by design, and lifetime ownership does not imply visibility inheritance. Copying a resolved view would also freeze dynamic global registrations and conflate composition with authority without defining either contract fully.
**Snapshot allowed global tools at child creation.** A frozen allow-set makes future registration uniformly unavailable, but it changes hot-registration semantics and starts an authorization design. The implemented filter stays a live registry predicate and documents allow-versus-deny behavior directly.
**Hide only tool schemas.** Presentation-only filtering lets the model execute a tool that the prompt says does not exist through Code Mode or a forged call. One resolver governs both presentation and execution instead.
**Use only tool filtering to stop recursion.** Removing the delegation tool is useful but provider-specific and does not protect direct service callers or alternate delegation tools. Absolute depth is an independent structural bound.
## Consequences
Contributors can configure child role, visible global tools, and recursion without defining new providers. Capability checks fail before ownership starts, unpublished setup makes the first request consistent, and one tool resolver prevents presentation/execution drift.
The cost is that deployments must understand live allow/deny behavior and the distinction between visibility and authority. Provider authors must advertise each supported control accurately, and in-process providers must install every requested contribution before publication. The controls deliberately do not solve security confinement or parent-to-child non-escalation.
docs/rfc/implemented/process/2026-07-06-node-engine-floor.md
+2 -2
View File
@@ -8,7 +8,7 @@ The Node 22 branch of the root `engines.node` range is a contract for the instal
## Decision
Set `engines.node` to `^22.19.0 || >=24.0.0` and test the keyless CI compatibility matrix on `['22.19', 24, 26]`. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor.
Set `engines.node` to `^22.19.0 || >=24.0.0` and test the keyless CI compatibility matrix on `['22.19', 24, 26]`. Every matrix leg runs the TypeScript typecheck plus a keyless source-mode worker smoke, so the floor is exercised through both a complete source typecheck and a real unbuilt runtime path. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor.
Two Node features gate the source runtime:
@@ -22,7 +22,7 @@ Those source features clear on the 22.x line at **22.18**, but the installed Pi
## Consequences
- The advertised LTS branch no longer undercuts the Pi adapter dependency floor.
- CI proves the Node 22 LTS floor directly with Node 22.19, keeps the Node 24 branch on `node: 24`, and keeps Node 26 for the next even line.
- CI proves the Node 22 LTS floor directly with Node 22.19, keeps the Node 24 branch on `node: 24`, and keeps Node 26 for the next even line; each leg typechecks the source graph and launches the unbuilt workflow worker for real.
- The built-bin smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the test stays the plain `node lib/bin.js` path it documents.
- A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this RFC in the same change.
docs/rfc/implemented/process/2026-07-06-parallel-github-ci-gates.md
+3 -3
View File
@@ -10,9 +10,9 @@ The hard part is the artifact boundary. `publint`, `verify-node-next-types`, and
## Decision
[CI](../../../../.github/workflows/ci.yml) keeps the keyless workflow to a few broad jobs instead of one job per gate. The Node 24 matrix has five lanes: static gates (`pnpm run check:ci:static`), lint (`pnpm run check:ci:lint`), coverage (`pnpm run check:ci:coverage`), snapshot replay (`pnpm run check:ci:snapshot`), and artifact gates (`pnpm run check:ci:artifacts`). The Node 26 compatibility job installs once and runs `pnpm run check:node-compat`.
[CI](../../../../.github/workflows/ci.yml) keeps the keyless workflow to a few broad jobs instead of one job per gate. The Node 24 matrix has five lanes: static gates (`pnpm run check:ci:static`), lint (`pnpm run check:ci:lint`), coverage (`pnpm run check:ci:coverage`), snapshot replay (`pnpm run check:ci:snapshot`), and artifact gates (`pnpm run check:ci:artifacts`). The compatibility matrix has Node 22.19, 24, and 26 jobs; each installs once and runs `pnpm run check:node-compat`.
Each lane delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), an in-process scheduler with bounded concurrency (`DSH_GATE_CONCURRENCY`). The static lane fans out constraints, the echo-agent demo smoke, `doc-sync` leaf gates, module-graph freshness, and `knip`; the lint lane runs ESLint with its own Node heap cap and a content-strategy ESLint cache; the coverage lane runs Vitest coverage with bounded file workers (`DSH_COVERAGE_MAX_WORKERS`); the snapshot lane isolates replay; the artifact lane builds once and then fans out the artifact consumers; the Node 26 compatibility job owns the TypeScript typecheck. The scheduler buffers each gate's output and prints a named result block with duration, so independent failures stay attributable inside each broad job log.
Each lane delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), an in-process scheduler with bounded concurrency (`DSH_GATE_CONCURRENCY`). The static lane fans out constraints, the echo-agent demo smoke, `doc-sync` leaf gates, module-graph freshness, and `knip`; the lint lane runs ESLint with its own Node heap cap and a content-strategy ESLint cache; the coverage lane runs Vitest coverage with bounded file workers (`DSH_COVERAGE_MAX_WORKERS`); the snapshot lane isolates replay; the artifact lane builds once and then fans out the artifact consumers. Every compatibility job runs the TypeScript typecheck and a keyless workflow-workerthread source-launch smoke, which starts a real unbuilt worker and therefore catches Node-version-specific loader/runtime failures that typechecking cannot. The scheduler buffers each gate's output and prints a named result block with duration, so independent failures stay attributable inside each broad job log.
Generated `.sessions/` logs and `.doc-typecheck-*` temp directories are ignored by lint. The aggregate local CI mode still runs demo smoke after lint, while the split GitHub static lane can run demo smoke directly because lint is isolated in its own lane.
@@ -36,4 +36,4 @@ The broad-lane split repeats checkout, setup, and install more often than a sing
The split introduces a maintenance obligation: when `package.json` adds or removes a gate that belongs in CI, [scripts/run-gates.ts](../../../../scripts/run-gates.ts) needs the matching leaf. That obligation is intentional because the runner is the parallel execution plan for the same gate vocabulary, not a separate quality policy.
The Node 26 signal is narrower than the primary Node 24 signal. It proves the source graph on the newer runtime without doubling documentation, coverage, publication, snapshot, and smoke checks whose failures are not expected to vary by Node minor version.
The compatibility signal is narrower than the primary Node 24 signal. It proves that the source graph typechecks and that the real unbuilt workflow-worker launch path executes on every advertised runtime line without doubling documentation, coverage, publication, snapshot replay, and unrelated smoke checks whose failures are not expected to vary by Node version.
docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md
+1 -1
View File
@@ -13,7 +13,7 @@ Status: implemented
## Problem
The loop records the canonical transcript in `SessionEvent` and also emitted a parallel set of live `agent/*` boundary mirror events: `agent/turn-start`, `agent/turn-end`, `agent/step-start`, and `agent/step-end`. The mirrors made consumers choose between two sources of truth for the SAME durable fact. ACP already chose the session log for the editor-facing transcript because a throwing peer listener can prevent later `agent/*` listeners from observing a boundary, while the session event was already appended. The stdio UI was the only production consumer that still rendered turn boundaries from the mirror events; it already rendered tool calls and results from `session/event`.
The loop records the canonical transcript in `SessionEvent` and also emitted a parallel set of live `agent/*` boundary mirror events: `agent/turn-start`, `agent/turn-end`, `agent/step-start`, and `agent/step-end`. The mirrors made consumers choose between two sources of truth for the SAME durable fact. ACP already chose the session log for the editor-facing transcript because it is the one durable, replayable record; consuming a live mirror would require reconciling its timing with the boundary already stored in that log. The stdio UI was the only production consumer that still rendered turn boundaries from the mirror events; it already rendered tool calls and results from `session/event`.
This duplication is not free. Every lifecycle change had to update the session event, the mirror event, docs, invariants, tests, and snapshot expectations. The duplicate boundary events also made failure ordering subtle: a turn can be durably closed before a live `agent/turn-end` listener runs, so a post-boundary listener failure has no valid in-log position left and must be reported out of band.
docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md
+1 -1
View File
@@ -51,7 +51,7 @@ The ACP server app loads `@deepseek-ai/dsh-llm-deepseek`, whose `apply` throws w
A snapshot run asserts **two** normalized surfaces, because the harness's external surfaces are distinct:
1. The **stdout transcript** — the framed `session/update` JSON-RPC the editor sees. Catches regressions in the ACP bridge's event→update translation (`streamSessionEventUpdate`). Compared against a committed `stdout.golden.jsonl`.
2. The **re-persisted session JSONL** — the log the replay run itself persists, compared against the scenario's `session.jsonl`. Catches regressions in the loop, tool dispatch, and turn/step structure that never surface on stdout. There is no separate session golden: `session.jsonl` is BOTH the replay source (recorded scenarios) and the expected produced log. Both sides pass through `normalizeSessionLog` before comparing — the fixture is raw-harvested (its own real session id / cwd / timestamps) and the replay output has fresh ones, so each is scrubbed against ITS OWN volatile values (the fixture's read from its header line) and the comparison is on normalized form. Request-header CONTENT (the composed system prompt + tool schemas) is additionally scrubbed to `{{system}}`/`{{tools}}` tokens on both sides — in the stored fixtures too — for every scenario except the one that pins it ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)). For an authored override scenario the same `session.jsonl` holds the expected produced log; `replay.override.json` drives the model, and `llm-replay` ignores the fixture for model chunks when an override exists, so committing the expected log there does not affect replay.
2. The **re-persisted session JSONL** — the log the replay run itself persists, compared against the scenario's `session.jsonl`. Catches regressions in the loop, tool dispatch, and turn/step structure that never surface on stdout. There is no separate session golden: `session.jsonl` is both the replay source (recorded scenarios) and the expected produced log. Both sides pass through `normalizeSessionLog` before comparing — the fixture is raw-harvested (its own real session id / cwd / timestamps) and the replay output has fresh ones, so each is scrubbed against its own volatile values (the fixture's read from its header line) and the comparison is on normalized form. Every stored JSONL additionally scrubs composed prompt text to `{{system}}`; each header class's pinning scenario stores that prompt readably in `system-prompt.golden.md` and keeps the complete tool schemas in its JSONL, while other scenarios scrub schemas to `{{tools}}` ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)). For an authored override scenario the same `session.jsonl` holds the expected produced log; `replay.override.json` drives the model, and `llm-replay` ignores the fixture for model chunks when an override exists, so committing the expected log there does not affect replay.
The two are genuinely additive: stdout is the bridge's *lossy projection* of the log (it drops `assistant/message.usage`, `step/*`, exact `seq`/`time`, and renders tool I/O differently), so a loop/tool/turn-structure regression can change the JSONL while leaving the stdout projection identical, and a bridge-translation regression can change stdout while the JSONL is untouched. Asserting the JSONL equality also echoes the proposed [universal replay fixture](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md) idea.
docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md
+9 -8
View File
@@ -4,29 +4,30 @@ Status: implemented
## Problem
Every model-driving ACP snapshot fixture (`session.jsonl`) embedded the full composed system prompt and the complete tool-schema list in its `request/header` event — roughly 8 KB on one line, per fixture. That content is identical across the suite (byte-identical tool list everywhere, including subagent children; identical prompt modulo each recording's temp cwd), so any change touching a tool description or a system-prompt line had to update every fixture: re-record everything against the live API (churning model responses and stdout goldens along the way) or hand-edit ~35 giant header lines. Introducing the dynamic-workflows feature — one new tool plus one prompt paragraph — rewrote every snapshot fixture in the repo, burying the behavioral diff a reviewer should be reading.
An ACP snapshot suite needs to prove the exact composed system prompt and tool-schema list sent in each `request/header`, but duplicating that content inside every `session.jsonl` makes a prompt or schema edit rewrite dozens of giant one-line JSON records. Keeping one raw header avoids the duplication but still makes prompt review poor: prose is JSON-escaped onto one line and mixed with thousands of characters of tool schemas.
## Decision
Exactly one scenario — `text-turn`, flagged `pinsHeader` in the `acp.snapshot.ts` scenario table — commits and compares the full request-header content; the pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per consuming suite. Every other fixture stores and compares that content as stable tokens via the pure normalizer `scrubRequestHeaders` in that package's `normalize.ts`: a `request/header` event's `header.system` becomes `"{{system}}"` and `header.tools` becomes `"{{tools}}"`; a `request/header-delta` keeps its structural facts — the system delta's `keepStart`/`keepEnd` line positions with one `{{system}}` token per inserted line, the tools delta's added/removed/changed tool names — and tokenizes only the bulk (prompt text, schema bodies), so two different deltas still compare different. The scrub is composed in front of `normalizeSessionLog` on BOTH sides of a non-pinning scenario's log compare and applied to the harvested logs record mode writes, so a re-record cannot smuggle the content back. Absent fields stay absent — WHETHER a header carried a prompt or tools is behavior and stays visible — and `config`/`reason` stay verbatim: a model swap churns every fixture by design (it invalidates the recorded responses), while a prompt or schema edit churns none of them (replay derives model behavior exclusively from `assistant/chunk` events and never reads header content — see `dsh-llm-replay`).
Exactly one scenario per header-composition class is flagged `pinsHeader`. Its directory splits the pin by review format: `system-prompt.golden.md` contains the normalized composed prompt as ordinary Markdown, while `session.jsonl` keeps the full tool-schema list, config, and reason but stores `header.system` as `"{{system}}"`. Every other JSONL stores both the system prompt and tool list as `"{{system}}"` / `"{{tools}}"`. The pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per class.
A system-prompt or tool-schema change therefore lands as exactly one committed-fixture diff — the pinned `text-turn` header line — updated by hand or by re-recording that one scenario (`pnpm run test:snapshot:record` with `-t text-turn`).
The pure `scrubSystemPrompts` normalizer applies to every stored session fixture and tokenizes both an initial header's prompt and a header delta's inserted prompt lines. `scrubRequestHeaders` additionally tokenizes tool schemas and session-prefix content for non-pinning scenarios while retaining structural facts: system-delta positions and arity, added/removed/changed tool names, prefix message count, field presence, config, and reason. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate the Markdown prompt from the normalized live header, so neither path can reintroduce prompt text into JSONL or leave the readable snapshot stale.
Guards make the split self-enforcing. On disk (fixture meta-tests): every non-pinning `session*.jsonl` must be a fixed point of `scrubRequestHeaders` (unscrubbed content crept in — apply the scrub), the pinning scenario's fixture must NOT be one (the pin lost its content), and exactly one scenario must pin. Live (every non-pinning scenario run): each `request/header` the run produces — parent, spawn child, fork child, initial or resume — must equal the pinned fixture's header after both sides normalize their own volatile values, and no `request/header-delta` may appear at all (a mid-run header change diverges from the pin by construction, and its content would be invisible under the scrub), so the single-pin premise is asserted rather than assumed.
Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of `scrubSystemPrompts`, only non-pinning fixtures are fixed points of the full header scrub, `system-prompt.golden.md` exists exactly beside pinning fixtures, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, or resume must match both halves of its class's pin after volatile-value normalization. A header without a string prompt or any `request/header-delta` fails loud because the two static pin artifacts cannot represent it.
One pin covers the whole suite because every session — parent, spawn child, fork child — composes the identical tool list and the identical prompt modulo cwd, and the uniformity guard fails the suite the moment that stops holding. If header composition ever becomes session-dependent by design (a restricted subagent toolset, say), the divergent shape gets its own pinning scenario.
## Alternatives considered
- **Re-record or hand-edit every fixture per change** — the status quo; the churn this RFC removes.
- **Scrub at compare time only, keeping fixtures raw** — the compares go green without fixture edits, but every committed fixture then carries a permanently stale copy of the prompt and schemas: dead weight that misleads readers and still rewrites wholesale on the next re-record. Storing the tokens keeps the fixture honest about what it does and does not pin.
- **Re-record or hand-edit every fixture per change** — preserves exact headers but buries behavioral diffs under duplicated prompt and schema content.
- **Scrub at compare time only, keeping fixtures raw** — lets compares pass while committed fixtures retain stale duplicate content and rewrite wholesale on the next recording. Stored tokens state honestly what each JSONL does not pin.
- **Scrub everywhere, pin nowhere** — loses the only end-to-end record of the composed header as actually sent (prompt assembly, registered-tool order, full schemas). The generated tool catalog documents each tool in isolation; only a real fixture pins the composed set.
- **Keep the one full pin entirely in JSONL** — removes suite-wide duplication but leaves system-prompt changes as an escaped one-line diff entangled with the tool list. Markdown gives prompt prose its natural review format without weakening the header assertion.
- **Slim the session log itself (log a content digest, store the header elsewhere)** — violates the reconstructability contract: the product log must reproduce each request bit-for-bit ([reconstructable-requests RFC](../architecture/2026-07-05-reconstructable-requests.md)). Header bulk is a test-artifact concern, solved in test normalization; the live log is untouched.
## Verification
All 37 snapshot scenarios replay green with the scrubbed fixtures (the committed fixtures were rewritten once through `scrubRequestHeaders` itself; `text-turn` untouched). The fixed-point, pin-retains-content, exactly-one-pin, live header-uniformity, and no-unpinned-delta guards run inside the suite, and `scrubRequestHeaders` has unit coverage for both header event types, delta structure preservation (line positions, insert arity, tool names), absent-field preservation, config/reason retention, byte-for-byte pass-through of other lines, and idempotence.
The suite replays every scenario against the split pins. Unit coverage exercises both scrub levels, Markdown formatting, record/refresh regeneration, normalized prompt extraction, fixed-point enforcement, required-file symmetry, header uniformity, and delta rejection.
## Consequences
A tool-description or system-prompt change churns one committed fixture line instead of every fixture in the suite, so snapshot diffs read as behavior again, and ~270 KB of duplicated header bytes leave the repo. The cost: non-pinning fixtures no longer display header content, so reading one shows tokens where the prompt and schemas were — the pinned `text-turn` fixture is the place to look, and the live uniformity guard guarantees it speaks for every session in the suite. A header change surfaces as a suite-wide test failure whose fix is the one pinned line, rather than as ~35 fixture rewrites.
A system-prompt change produces a normal line-oriented Markdown diff in one file per affected composition class; a tool-description change produces one pinned JSONL line per class; ordinary behavioral fixtures remain untouched. Session fixtures display tokens for omitted content, and the live uniformity guard makes each split pin authoritative for every session in its class. The pinning scenario carries one extra generated artifact whose terminal newline is canonicalized for repository hygiene.
docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md
+1 -1
View File
@@ -16,7 +16,7 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su
**`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions.
**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record-mode fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin, non-pinning fixtures are `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each suite flags exactly one `pinsHeader` scenario (the factory throws on zero, a meta-test rejects more than one; WHICH scenario pins is the table's reviewable choice), and the uniformity guard compares only that suite's sessions. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `headerDeltaCount`) are exported for direct unit coverage.
**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerDeltaCount`) are exported from the module for direct unit coverage.
## Alternatives considered
docs/rfc/proposed/feature/2026-06-14-acp-agent-client-protocol.md
-84
View File
@@ -1,84 +0,0 @@
# RFC: Agent Client Protocol (ACP) support — drive the coding agent from external editors
Status: proposed
> **Implementation status (MVP landed):** steps 1, 2, 3, 4, 6, 7, 8 are implemented in `packages/ui/acp` + `examples/acp-agent`. **Step 5 (the `session/request_permission` permission gate) is deferred** — the bridge ships a pass-through (tools run with the executor's full authority) marked `TODO(rfc010-permission-gate)`, and lays down only the `WeakMap<Agent, sessionId>` ownership seam the gate will build on. Status stays `proposed` until the gate lands. `session/cancel` is the queue-aware `agent.cancel()`: it aborts a running step, clears queued + steering work, and drops a turn that is about to start, so a queued-but-not-yet-started prompt never runs and a later prompt cannot be batched into the cancelled turn. **Per-session `cwd` is now honored** (lifting the original "launch the server in the workspace root" restriction — see § Deferred): `session/new` accepts any absolute `cwd`, and `session/load` requires the request `cwd` to match the persisted session `cwd` so the editor and bash executor agree on the workspace.
## Problem
The coding agent is reachable only through the readline `stdio-chat` plugin: it reads lines from stdin, calls `agent.send()`, and prints the assistant token stream (`session/event` `assistant/chunk`) to stdout. There is no structured protocol, so the agent cannot be embedded in an editor — no streaming render, no tool-call display, no permission UI, no resumable sessions.
Editors are converging on the Agent Client Protocol (ACP), which Zed and others speak: JSON-RPC 2.0 over newline-delimited stdio, modeled on the Language Server Protocol. An editor boots the agent as a subprocess and exchanges `initialize` / `session/new` / `session/prompt`, rendering streamed `session/update` notifications and `session/request_permission` prompts. The goal is for the agent to be a drop-in ACP server — implement the protocol once and run in any ACP client, with no per-editor glue.
This RFC has a hard prerequisite on [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md): it assumes durable session persistence (the `SessionPersistence` service and the async `AgentLoop.resume` seam) is implemented, so resuming a session via `session/load` is in scope. None of those APIs exist yet — `AgentLoop` currently exposes only the synchronous `create` — so ACP must land after, or in the same change as, [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md), and pins to its `resume(agentId, resumeSessionId)` contract. Session persistence persists every `SessionEvent` verbatim (including `assistant/chunk`), so a loaded session has the stream chunks needed to replay turns to the client.
## Proposal
A new plugin package `@deepseek-ai/dsh-acp` — a client-driver / UI plugin, the structured analogue of `stdio-chat`. It is NOT a change to the loop and NOT an [capability seams](../../implemented/architecture/2026-06-13-capability-seams.md) interface/implementation/consumer capability split; it consumes the existing `agent/*` event taxonomy and the `tools/pre-execute`/`tools/post-execute` waterfalls.
It depends on the official `@agentclientprotocol/sdk` (the `AgentSideConnection` class) — Apache-2.0, actively versioned. The SDK declares a `zod` peer dependency and imports `zod/v4` at runtime, so `packages/ui/acp` must declare `zod` itself (per the workspace dependency constraints). This is the renamed successor to `@zed-industries/agent-client-protocol`, which is now deprecated on npm.
The mapping between ACP and existing harness seams — each row names the seam and any required extension:
| ACP (client ⇄ agent) | Harness seam | Notes |
|---|---|---|
| `initialize` | static handler | negotiate `protocolVersion` (echo the supported version, else error); advertise text-only `promptCapabilities` and `loadSession: true`; report agent name/version |
| `session/new {cwd, mcpServers, additionalDirectories}` → `{sessionId}` | the `dsh-agent` create factory (see Dependency note + Plan) | the seam must accept `{ sessionId, meta }` so the ACP-generated `sessionId` becomes the live/persisted session id and the validated `cwd` is attached as the `SessionHeader` (today `AgentLoop.create(id)` hardcodes `${id}-session` and takes no metadata); reject a 2nd session (single-session MVP, see [ACP multi-session](2026-06-14-acp-multi-session.md)); `cwd` validated (require absolute) — any absolute cwd is honored: it becomes the session's `SessionHeader.cwd` and the default bash workdir (per-session cwd, see § Deferred → RESOLVED), so the server need not launch in the workspace; non-empty `mcpServers` and `additionalDirectories` are rejected for the MVP because silently ignoring requested servers/roots would desync the client's tool and filesystem-scope UI |
| `session/load {sessionId, cwd, mcpServers, additionalDirectories}` | the `dsh-agent` resume factory ([session persistence](../../implemented/architecture/2026-06-14-session-persistence.md) + Dependency note) | load `{ meta, events }`, seed the session, re-derive history via `deriveMessages()`, replay prior turns to the client as `session/update` per the ACP load contract; `mcpServers` and `additionalDirectories` rejected as in `session/new` |
| `session/prompt {prompt}` | `agent.send()` (idle) | text blocks → `TextBlock`; reject image/audio per advertised capabilities; one in-flight prompt per session |
| resolve `session/prompt` → `{stopReason}` | the `turn/end` `session/event` (its `reason`) | map the harness kebab `TurnEndReason` to the ACP snake_case `StopReason` wire enum: `completed`→`end_turn`, `max-tokens`→`max_tokens`, `aborted`(cancel)→`cancelled`, plus `refusal`/`max_turn_requests` when applicable; honor the batch-into-one-turn and send-not-synchronously-running settle semantics |
| `session/update: agent_message_chunk` | `session/event` `assistant/chunk` `text-delta` only | do NOT also emit on `block-end(TextBlock)` — it carries the fully-assembled block and would duplicate the streamed text |
| `session/update: agent_thought_chunk` | `session/event` `assistant/chunk` `reasoning-delta` | |
| `session/update: tool_call` (pending→in_progress) | `session/event` `tool/call` | demux via a Session→sessionId map; `kind` inferred from the tool name |
| `session/update: tool_call_update` (completed/failed) | `session/event` `tool/result` | a throwing `tools/execute` yields NO `tool/result` → fail the pending tool UI from `agent/error`/turn-end |
| `session/request_permission {sessionId, toolCall, options}` | prepended `tools/execute` listener | no-op unless `exec.agent` is ACP-owned; await the outcome; `selected/allow_*` → `next()`; `reject_*`/`cancelled` → veto `ToolExecutionResult{isError}` |
| `session/cancel` (notification) | `agent.cancel(reason)` | the queue-aware cancel (abort running step, clear queued + steering, drop an about-to-start turn); settle the in-flight prompt as `cancelled`; resolve any pending permission as `cancelled` exactly once |
The permission gate is the first real consumer of the `tools/execute` veto seam (the documented "single veto/sandbox/permission seam" plus the deferred "Permission system" TODO in [docs/architecture.md](../../../architecture.md)). It is a single global listener registered with `prepend: true` so it runs before any other tool wrapper. `ToolExecution.agent` is optional and the `Agent` interface carries no origin marker, so the bridge tracks ownership itself: it records each agent it creates in a `WeakMap<Agent, sessionId>` and the gate no-ops (calls `next()` immediately) for any `exec.agent` it does not own — non-ACP agents and the no-agent case pass straight through. For an owned agent it resolves the session, issues `session/request_permission`, and stores the pending resolver on that session's record so the outcome — or a `session/cancel`/connection-close — settles it exactly once.
Lifecycle and disposal: the connection, listeners, and in-flight permission promises register via `ctx.effect`/`ctx.on`; teardown is async and must *reach* quiescence, not just request it — close the connection, settle/reject pending permissions, and dispose each owned agent through its `AgentHandle.dispose()` (which stops the loop, `await`s its exit, and unregisters). Owner teardown goes through that handle seam, not the loop's concrete `agent.done` (which exists only on `ReactLoopAgent`); a non-owner that merely wants to *observe* the current work settling without tearing the agent down awaits the interface-level `agent.whenIdle()`. Every listener contains its `send()` exceptions (log, never reject the turn) because stream chunks are emitted inside the model step, so a throwing listener would corrupt the turn.
**Dependency note (architecture rule).** [docs/architecture.md](../../../architecture.md) states "plugins depend on interface packages, never on `dsh-agent-loop`." Creating and resuming agents is currently only on the concrete `AgentLoop` (`ctx.agentLoop`), so this RFC proposes adding an **abstract create/resume factory** to the `dsh-agent` interface (registry-level `create({ sessionId, meta })` / `resume(...)`), implemented by the loop, so `dsh-acp` injects only `agents` (the interface) and the dependency rule holds. The alternative — injecting the concrete `agentLoop` and recording a documented exception in the architecture doc — is explicitly the non-preferred fallback.
## Plan
1. Package scaffold `packages/ui/acp/` per [the cookbook](../../../cookbook/adding-a-package.md); add `@agentclientprotocol/sdk` and `zod`. Add the abstract create/resume factory to `dsh-agent` (the interface) so the bridge can `inject: ['agents', 'sessions', 'tools', 'sessionPersistence']` without depending on the concrete loop; `sessionPersistence` is required because `session/load` advertises `loadSession: true`. (Fallback only if the factory is judged not worth it: inject `agentLoop` directly and record the architecture-rule exception in `docs/architecture.md`.)
2. Connection plus `initialize`/`session/new`: wire `AgentSideConnection` to stdin/stdout; protocolVersion negotiation; the single-session guard; create the live session through the new `{ sessionId, meta }` factory seam (so the ACP `sessionId` and validated `cwd` become the session's id and header); the `sessionId↔agent` and `Session↔sessionId` maps.
3. Internal edit — turn-end reason fidelity (sanctioned: edit internals to fit ACP). Extend `TurnEndReasonMap` in the proper places: (a) declaration-merge a `max-tokens` variant in the owning package (`packages/core/session/src/types.ts`, alongside `completed|aborted|error|disposed`) — add `max-tokens` because `FinishReasonMap` produces it (DeepSeek maps `length` → `max-tokens`); do not add `refusal`, since no current adapter produces it (unknown DeepSeek finish reasons collapse to `error`), but leave a comment in `TurnEndReasonMap` noting `refusal` should be added when an adapter first emits it (`FinishReasonMap` is merge-extensible); (b) make `agent-loop`'s `loop.ts` populate the reason from the model `finish` chunk — `assembler.finish` lives inside `runStep`, so `runStep` must return it up to `runTurn`, and the rule is "the last step's finish reason wins, but any `max-tokens` in the turn surfaces as `max-tokens`"; (c) no consumer exhaustively switches over `TurnEndReason` today (the invariants plugin switches on `SessionEventType`, and `deriveMessages` ignores `turn/end`), so adding `max-tokens` is a non-breaking extension — but recheck before landing; (d) update [docs/architecture.md](../../../architecture.md) (the CI-verified loop-lifecycle/event-taxonomy doc) and the affected package READMEs/JSDoc (`dsh-session`, `dsh-agent`, `dsh-agent-loop`) per the repo doc-sync policy. This replaces a fragile "observe the finish chunk in the bridge" hack with a real, documented contract.
4. Prompt-turn streaming plus load: translate `session/event` (the `assistant/chunk` token stream plus boundaries and tool activity) into `session/update`; resolve `session/prompt` on settle, mapping the harness `TurnEndReason` to the ACP `StopReason` wire enum (`completed`→`end_turn`, `max-tokens`→`max_tokens`, `aborted`→`cancelled`) — a small total function with a test asserting the exact wire strings, since the SDK rejects an unknown `stopReason`. Concrete correlation, since the loop batches queued messages into one turn and `send()` does not synchronously flip to running: install the `session/event` listener before `send()`; capture the prompt's owning turn from its `turn/start` record, then resolve on that turn's `turn/end` (with `agent/status` idle/disposed as a fallback); reject an empty/whitespace prompt up front rather than calling `send()` (no turn would ever start, so the RPC would hang). Implement `session/load` on the session-persistence resume seam.
5. Permission gate: a single `tools/execute` listener registered with `prepend: true`, owning a `WeakMap<Agent, sessionId>` of bridge-created agents; no-op (`next()`) for unowned/no-agent calls; for owned calls → `session/request_permission` → allow (`next()`) / veto; settle the stored resolver exactly once on outcome, cancel, or connection close.
6. Example wiring (extract a shared base). `@cordisjs/plugin-include` is itself a plugin entry that resets `ctx.baseUrl` and loads a path, so a child `cordis.yml` can nest-include a shared base; the extraction is safe because every dependent plugin declares `inject` (loader groups initialize via `Promise.all`, so YAML order is NOT the dependency mechanism — never rely on it). Extract the provider/tool core (`llm, sessions, system-prompt, tools, agents, invariants, llm-deepseek, bash-local, tool-bash`) into `examples/base.yml`; have both `coding-agent` and a new `examples/acp-agent/` include it and add their own UI plugin plus logger. Keep `agent-loop` per-example (NOT in the base): `AgentLoop` creates its configured agents in its constructor, and the two examples disagree — `coding-agent` needs a pre-created `main` (its `stdio-chat` calls `ctx.agents.get('main')`), while `acp-agent` must pre-create none (ACP `session/new` creates agents). So `coding-agent` declares `agent-loop` with `agents: [{ id: main, … }]` and `acp-agent` with `agents: []`. `acp-agent` loads `dsh-session-persistence-jsonl` (from [session persistence](../../implemented/architecture/2026-06-14-session-persistence.md) — required for `session/load`), omits the stdout logger (see Risks), and adds `pnpm run demo:acp` plus the Zed `agent_servers` snippet.
7. Tests (the repo cares a lot here): a property-based test for the protocol shape (precedent: [property-based testing](../../implemented/testing/2026-06-11-property-based-testing.md)) — fuzz arbitrary harness event sequences and assert ACP-stream invariants (never a `tool_call_update` before its `tool_call`; exactly one `session/prompt` resolution per prompt; monotonic, well-formed ordering; `stopReason` in the legal set); codec unit tests over an in-memory `Duplex` pair (drive `AgentSideConnection` without a subprocess; assert exact frames for `initialize`, `session/new`, a full prompt turn); the mandatory HMR-safety test (dispose the fiber; assert the connection closed, all `ctx.on` listeners gone, any in-flight `request_permission` settled); failure-path tests (connection closes mid-stream; closes with a permission pending; a notification `send()` rejects but the turn survives; `finish{kind:'error'|'aborted'}`; a `tools/execute` throw with no `tool/result`; a second `session/new` rejected; a `session/prompt` while one is in flight; an empty prompt rejected without hanging; a `session/load` re-derives identical history and replays it); and an e2e (`*.e2e.ts`, self-skips without `DEEPSEEK_API_KEY`) that boots `examples/acp-agent`, connects a `ClientSideConnection`, sends a real prompt, owns and disposes the harness in `afterEach`, and verifies the world (files on disk), not the agent's self-report.
8. Docs: module/JSDoc plus a package README; extend [the extension cookbook](../../../cookbook/extension-cookbook.md) with the client-driver pattern. Flip Status to `implemented` on landing; record a decision in this RFC only if it proves durable, contested, and surprising (candidates: the `tools/execute` permission-ownership rule, the npm-dependency choice) — not auto-required.
Deferred (each names its owning future work):
- Multiplexing concurrent sessions → [ACP multi-session](2026-06-14-acp-multi-session.md).
- ~~`cwd` honoring.~~ **RESOLVED.** Originally there was no path from `session/new.cwd` to the bash workdir (`tool-bash` forwarded only an explicit `args.workdir`; `LocalBashExecutor.resolve` defaulted to its own config or `process.cwd()`), so the MVP validated `cwd` (require absolute) AND required the server to launch in the workspace root, erroring on a mismatch. This is now lifted: the validated `cwd` is stored as `SessionHeader.cwd`, and `dsh-tool-bash` defaults the bash workdir to the calling agent's `session.header.cwd` (an explicit model `workdir` still wins; a relative one resolves against it). Any absolute `cwd` is honored — the server need not launch in the workspace, and N sessions can each target a different directory. Widening scope beyond the single cwd (`additionalDirectories`) remains deferred.
- Client `terminal/*` proxying (a live editor terminal) and `fs/*` (editor-rendered diffs) — a future `BashExecutor` over the [capability seams](../../implemented/architecture/2026-06-13-capability-seams.md) bash seam, gated on `clientCapabilities.terminal`.
- Image/audio prompts (blocked on the DeepSeek adapter, which skips `image` blocks today), modes, auth, `available_commands`/slash-commands, `plan`, and `usage_update`.
## Alternatives considered
- **A process-wide stdout hijack inside `dsh-acp`** (defensively monkey-patching `console.log` / `process.stdout.write`) — rejected: it lives outside Cordis' effect-scoped, HMR-friendly plugin model, races the connection's own stdout handoff, and fights the logger. The stdout guarantee is config-only.
- **Injecting `agentLoop` directly instead of the abstract create/resume factory** — the recorded fallback, taken only if the factory seam is judged not worth it, with the architecture-rule exception recorded in `docs/architecture.md`.
## Acceptance criteria
- The `acp-agent` example speaks ACP over stdio end-to-end: `initialize`, `session/new` with a validated absolute `cwd` honored as the session workspace, streamed `session/update` frames per prompt turn, `session/load` re-deriving identical history, and `session/prompt` resolving with the correct wire `stopReason`.
- stdout carries only framed JSON-RPC (asserted by test); the permission gate settles every `session/request_permission` exactly once — on outcome, cancel, or connection close.
- The plan's test set runs green: the property-based protocol invariants, the codec unit tests over an in-memory duplex pair, the HMR-safety test, the failure-path matrix, and the self-skipping real-API e2e that verifies the world.
## Risks
stdout is the protocol — guaranteed by config, not by monkey-patching. The console logger writes through `console.log` to stdout, so any stdout UI/logger plugin corrupts JSON-RPC. The guarantee is config-only: the `acp-agent` example loads no stdout plugin (no console logger, no `stdio-chat`) and, if logging is wanted, uses a stderr exporter. A defensive process-wide `process.stdout.write`/`console.log` hijack inside `dsh-acp` is explicitly rejected — it lives outside Cordis' effect-scoped, HMR-friendly plugin model, races the connection's own stdout handoff, and fights the logger. A test asserts the example emits only framed JSON-RPC on stdout.
New third-party runtime dependency plus protocol drift: `@agentclientprotocol/sdk` is young (0.25.x, recently renamed) and evolving. Pin the version and isolate churn to the one bridge package. This is not a vendoring-policy violation — [vendoring Cordis as source](../../implemented/process/2026-06-11-vendor-cordis-as-source.md) vendors the framework; genuine third-party deps already live on npm (`@earendil-works/pi-ai`).
Turn-settle and prompt-correlation hazards: honor "queued messages batch into one turn" and "`send()` does not synchronously flip to running" (see `stdio-chat.ts` and the defensive-patterns section of [docs/architecture.md](../../../architecture.md)); gate resolution on an observed running→idle transition and handle the empty-prompt / no-work branch so an RPC can't hang.
Permission-await and disposal hangs: a pending `request_permission` whose connection closes or whose turn aborts must settle exactly once; disposal must reach quiescence — tear each owned agent down through `AgentHandle.dispose()` (which stops the loop and awaits its exit), rather than orphaning awaits on a closed pipe.
The 100% per-file coverage gate (repo policy) makes a branch-heavy protocol bridge real work. Accepted deliberately, surfaced so it isn't a surprise at PR time.
ACP protocol-shape details (exact method names, `session/update` variants, permission option kinds, stop reasons) are taken from the ACP spec and the `@agentclientprotocol/sdk` types; they are not independently verifiable until the dependency is added, so the implementation pins the SDK version and conforms to its types rather than to this RFC's prose where they differ.
docs/rfc/proposed/feature/2026-06-14-acp-multi-session.md
-48
View File
@@ -1,48 +0,0 @@
# RFC: Multiplex concurrent ACP sessions over one connection
Status: proposed
> **Implementation status:** the multi-session bridge (steps 1, 3, 4) and the bash task-ownership isolation are implemented in `packages/ui/acp` + `packages/bash/tool-bash`. **Per-session *permission* ownership is deferred** — it depends on [the ACP support permission gate](2026-06-14-acp-agent-client-protocol.md) (`TODO(rfc010-permission-gate)`), which is itself deferred; the `agent→sessionId` reverse map the gate will route through is in place. Step 2's per-session disposer scope is now implemented (see [agent lifecycle & ownership seams](../../implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md)): the factory returns a per-agent `AgentHandle` whose `dispose()` stops the loop, awaits quiescence, unregisters the agent, and removes its session, so a bare client disconnect leaves no registered agent or session-store entry. Status stays `proposed` until per-session permission ownership lands.
> **Target-client note:** Zed is the current target ACP client, and its ACP client maintains a `HashMap<SessionId, AcpSession>` plus `pending_sessions` for concurrent `session/load` calls. The competing simplification to return to one live session per connection was rejected after checking that target-client shape; this RFC remains the path for finishing multiplexing and per-session permission ownership. See [the rejected simplification](../../rejected/simplification/2026-06-20-single-session-acp-bridge.md).
## Problem
[ACP support](2026-06-14-acp-agent-client-protocol.md) ships with a single active session per connection: a second `session/new` is rejected. Editors expect to run several conversations over one agent subprocess — a user opens multiple threads, or a client pre-warms sessions. The single-session guard is a deliberate MVP scope cut, not an architectural limit; this RFC lifts it.
This paragraph is historical: the multi-session bridge has landed. The remaining proposed work is per-session permission ownership plus the lifecycle seams now tracked in [agent lifecycle and ownership seams](../../implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
## Proposal
The harness core already supports many agents (`AgentRegistry.list()` and `AgentLoop.create` impose no count limit), so multiplexing is a bridge-layer change in `@deepseek-ai/dsh-acp`, not a loop or core change.
- Lift the single-session guard in `session/new`; allow N live sessions, each mapped to its own `ReactLoopAgent`.
- The bridge's `sessionId→agent` and `Session→sessionId` maps (introduced single-entry by [the ACP support RFC](2026-06-14-acp-agent-client-protocol.md)) become true multi-entry, plus a third `agent→sessionId` reverse map: the `tools/execute` permission gate receives only `exec.agent` (no sessionId), so it needs an O(1) reverse lookup to find the owning session. Every `agent/*` event and every `session/event` is demuxed strictly by id, so two sessions streaming at once never interleave their `session/update` notifications.
- Per-session prompt queues: [the ACP support RFC](2026-06-14-acp-agent-client-protocol.md)'s single-entry in-flight-prompt state becomes multi-entry — one in-flight prompt *per session*, tracked per `sessionId`.
- Per-session cancel routing: `session/cancel` cancels only its own session's agent (via the queue-aware `agent.cancel()`) and settles only that session's in-flight prompt. The cancel is scoped to that one agent — a per-agent `AbortController` for the running step plus the agent's own queued/steering FIFOs — so it never touches another session's stream or pending prompt.
- Per-session permission ownership: a `session/request_permission` and its outcome are bound to the originating session via the reverse map, so a permission prompt or a cancel in one session can never resolve another session's pending permission.
## Plan
1. Generalize the two id maps to multi-entry and add the `agent→sessionId` reverse map; add a per-session record holding the agent, the in-flight-prompt state, the pending-permission registry, and the session's disposer scope (see step 2).
2. Give each session a real per-session disposer scope, NOT `ctx.extend()` — in Cordis `ctx.extend()` only creates a child context/prototype, but `ctx.on()` registered on it is still owned by the current plugin fiber, so disposing it would not remove that session's listeners. Use a genuine child fiber (load a per-session sub-plugin, e.g. `ctx.plugin(...)` returning a fork, or collect each session's `ctx.on` disposers in its session record and call them on teardown). Demux every `agent/*` and `session/event` by id into the right session record. Note the single global `tools/execute` listener stays on the bridge root (it must see all agents) and routes via the reverse map.
3. Lift the `session/new` guard; keep `session/load` ([from ACP support](2026-06-14-acp-agent-client-protocol.md)) working per session.
4. Tests for cross-session isolation: two sessions streaming and permission-prompting concurrently never interleave; a cancel/abort in one session leaves the other's stream and pending permission untouched; per-session in-flight-prompt enforcement holds independently; disposing one session leaves the others running.
## Alternatives considered
**A per-session `ctx.extend()` scope** — rejected: in Cordis, `ctx.extend()` only creates a child context/prototype, and `ctx.on()` registered on it is still owned by the current plugin fiber, so disposing it would not remove that session's listeners. A genuine child fiber (or a per-session collection of disposers) is required.
## Acceptance criteria
- N concurrent sessions stream and permission-prompt without interleaving their `session/update` notifications; a cancel in one session leaves every other session's stream, queued prompts, and pending permissions untouched.
- Disposing one session removes exactly its own listeners; connection teardown reaches quiescence across all sessions.
- One session's agent cannot read or kill another session's background bash task.
## Risks
Listener fan-out cost: each session adds listeners; ensure disposal of one session removes exactly its own and the connection teardown ([from ACP support](2026-06-14-acp-agent-client-protocol.md)) still reaches quiescence across all sessions.
The subtle correctness trap is cross-session leakage — a cancel or abort on one session settling another session's pending permission. The per-session permission ownership rule (routed via the `agent→sessionId` reverse map) and its isolation test are the guard.
Shared background-task state: the bash executor's task ids are global and predictable (`bash-1`, `bash-2`, …), and `bash_output`/`bash_kill` look up by id without checking the caller. Under one session this is benign; under N sessions one session's agent could read or kill another's background task. This is a pre-existing `tool-bash` gap that multi-session turns into a real isolation hole — fixing it (validate the caller against the task owner) belongs with this RFC or a companion `tool-bash` change.
docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md
+10 -9
View File
@@ -4,7 +4,7 @@ Status: proposed
## Problem
The [interception-seams RFC](../../implemented/feature/2026-06-30-interception-seams.md) added `tools/pre-execute` returning a `PreToolDecision` (allow/deny/ask) — but deliberately NOT input rewrite (a hook changing a tool call's `arguments` before it runs). Claude Code's `PreToolUse` hook offers an `updatedInput`, so a faithful CC bridge wants the same. This RFC designs that, separately, because doing it consistently is a real problem — not a field to bolt onto the allow decision.
The [interception-seams RFC](../../implemented/feature/2026-06-30-interception-seams.md) defines `tools/pre-execute` as an allow/deny/ask gate over an execution whose identity is already protected and whose arguments are deeply frozen. Claude Code's `PreToolUse` hook also offers `updatedInput`, so a faithful bridge needs an explicit rewrite mechanism. A rewrite cannot be a mutation escape hatch on the existing execution object: it must keep the durable history, audit record, presentation, and executed value consistent.
## The problem: three readers of pre-execution arguments
@@ -14,37 +14,38 @@ In the loop, a tool call's arguments are committed to the log and read by live c
2. **`tool/call`** is the durable AUDIT record, appended before `ctx.tools.execute()`.
3. **Live presentation reads `tool/call.arguments`**: the ACP bridge remembers them and passes them to `presentResult`; `dsh-tool-bash` derives the card title, the rawInput, the cwd, and the terminal-vs-background treatment from them.
So an "input rewrite" that changes ONLY what executes would make the UI show one command while another RAN, and render result state against the wrong arguments — a real inconsistency, not a documentable gap. (The existing low-level capability to mutate `exec.arguments` in a listener has exactly this latent inconsistency; it is unadvertised precisely because of this — yet not unused: a tool-bash integration test rewrites a scripted call's arguments through it (`packages/bash/tool-bash/tests/integration.spec.ts`), so this design must either sanction that path with the consistency unit below or seal it — `readonly` arguments at the seam, with the test shim moved onto a behavior-level helper.)
An execution-only rewrite would make the UI show one command while another ran and render the result against the wrong arguments. The registry prevents that failure mode today: it structured-clones and deep-freezes `arguments`, makes the execution identity properties non-writable, and exposes no test shim or listener path that can replace them. The rewrite design must preserve that protected-identity boundary rather than weaken it.
## Proposal
A sketch, to validate against the code when built. Treat input rewrite as a consistency unit: when a `pre-execute` hook supplies `updatedInput`, the rewrite must be reflected in ALL three readers, atomically, before execution:
A rewrite is a pre-identity consistency transaction. When a hook supplies `updatedInput`, the effective value must be chosen before the registry constructs its immutable `ToolExecution`, and it must be reflected in all three readers atomically:
- The `tool/call` audit event records the REWRITTEN arguments (with the original retained in a sidecar field for the audit trail — a hook changed the call, and both the original and the effective arguments are facts worth keeping).
- The `assistant/message` in derived history must agree with what executed — options to evaluate: rewrite the assistant message's tool-call block in place (changes what the model "sees it said"), or record a separate correction the next request carries. The CC model is that the model sees the rewrite took effect.
- Presentation (`presentCall`/`presentResult`) reads the rewritten arguments, so the UI shows what actually ran.
The shape would extend `PreToolDecision` with an allow-variant `arguments` (or a dedicated `{kind:'rewrite', arguments}`), and the loop would thread the rewrite through the three readers above rather than only into `ctx.tools.execute()`.
Extending `PreToolDecision` at its current firing point is insufficient: both durable records already exist by then, and the execution identity is protected. The implementation must either move the relevant decision before the log commit or add a dedicated earlier rewrite decision over the pending model call. After the loop commits the effective arguments to history and audit, it constructs the ordinary immutable execution and runs the existing allow/deny/ask and tool pipeline unchanged.
## Alternatives considered
### Why not now
### Why not mutate the execution object?
The interception-seams RFC notes input rewrite "fought the code across two review rounds" — the signal AGENTS.md names for an over-reaching change. Shipping allow/deny/ask first keeps the seam honest (no advertised contract that silently desyncs the UI), and a CC/Codex bridge that receives an `updatedInput` logs it and surfaces a faithful-but-degraded warning (like `ask`→deny) until this lands. This RFC is the home for the consistent design; `TODO(pre-tool-input-rewrite)` in the loop's pre-execute call site anchors it.
Allowing a pre-execute listener to assign `exec.arguments` would provide only an execution rewrite, leaving model history, audit, and presentation unchanged. Keeping the identity protected makes such partial behavior unrepresentable. Until the consistency transaction exists, a CC/Codex bridge logs and warns about `updatedInput` rather than claiming it was honored; `TODO(pre-tool-input-rewrite)` at the loop dispatch site anchors the missing earlier phase.
## Acceptance criteria
- A `pre-execute` rewrite is reflected in all three readers atomically before execution: the `tool/call` audit records the rewritten arguments (the original retained in a sidecar field), derived history agrees with what executed, and presentation renders the rewritten arguments.
- The unadvertised `exec.arguments` mutation path is either sanctioned by this consistency unit or sealed (`readonly` arguments at the seam, the test shim moved onto a behavior-level helper).
- A requested rewrite is resolved before `ToolExecution` identity is created and reflected in all three readers atomically: the `tool/call` audit records the rewritten arguments (the original retained in a sidecar field), derived history agrees with what executed, and presentation renders the rewritten arguments.
- The effective `ToolExecution.arguments` remains deeply frozen and non-writable throughout pre-policy, guards, dispatch, post-policy, and final observation; no mutation shim is introduced.
- The CC/Codex bridges honor `updatedInput` instead of logging the faithful-but-degraded warning.
## Risks
- Rewriting the `assistant/message` tool-call block changes what the model "sees it said"; whether any provider rejects that on replay is the open question that must be settled empirically before the decision shape freezes.
- Until this lands, the unadvertised mutation path keeps its latent UI-desync inconsistency.
- An earlier rewrite phase changes the ordering relationship among `assistant/message`, `tool/call`, hook audit events, and execution; the design must pin that ordering without weakening turn enclosure or call/result adjacency.
## Open questions
- Does rewriting the `assistant/message` tool-call block corrupt any provider's expectation on replay, or is a separate correction safer?
- Should the original arguments be preserved on the `tool/call` event (audit) and, if so, under what field?
- Does the rewrite decision move before the log commit or become a dedicated earlier seam, and how do existing pre-tool allow/deny hooks avoid running twice?
- How does this interact with a future permission `ask` flow (a user approving a rewritten call)?
docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md
+4 -4
View File
@@ -8,13 +8,13 @@ Three pieces of public spine surface share one defect class: their only possible
1. **`SurfaceManager.invalidate()`** (`packages/core/session/src/surface.ts`). Its documented trigger — "the log has been replaced wholesale (e.g. after Session seed)" — is structurally unreachable: seeding happens inside the `Session` constructor, `_surface` is created lazily on first access, and the log reference is never reassigned afterward, so no constructed `SurfaceManager` ever observes a wholesale replacement. Sole caller: its own unit test. A rollback primitive protecting a scenario the implementation cannot produce.
2. **The `runLoop`, `Inbox`, and `InboxMessage` exports** (`packages/core/agent-loop/src/index.ts`). `runLoop` has no importer outside the package — the only callers are the package's own internals (the agent constructs its loop with it), so the public re-export has zero consumers; `Inbox`/`InboxMessage` likewise reach outside code only through the package's own inbox spec (switchable to the source module). The exports contradict the package's own docs — the inbox module doc says the public surface is `Agent.send()`/`Agent.steer()` — and the [architecture dependency rule](../../../architecture.md): nothing programs against `dsh-agent-loop`; a replacement loop is a different bundle built on `dsh-agent`, not a consumer of this package's internals. `ReactLoopAgent` stays exported (cross-package tests construct it by package name).
3. **`ToolExecutionResult.callId`** (`packages/core/tools/src/index.ts`; the *input* `ToolExecution.callId` stays). Zero readers — and no listener can even construct a result: `tools/pre-execute`/`tools/post-execute` listeners return Decisions, the registry builds every result itself and always sets `callId` to the input `exec.callId`, and the post-execute dispatch snapshots the outcome before the waterfall precisely so a listener mutating the shared result reference cannot corrupt the id. The loop independently ignores `result.callId` in favor of its own `call.id`, and two regression tests exist solely to prove the field cannot matter (the loop's ignores-result-callId test and the registry's mutation guard). A field that is by construction a copy of its input, defended by snapshot machinery, and pinned by tests proving it is ignored is pure liability surface; the ACP bridge correlates via the session event's `data.callId`, never via the execution result.
3. **`ToolExecutionResult.callId`** (`packages/core/tools/src/index.ts`; the input `ToolExecution.callId` stays). Zero consumers read it. A `tools/execute` wrapper may construct or replace a result, but the registry rejects any `callId` that differs from the immutable execution identity and rebuilds later outcomes from protected snapshots; `tools/post-execute` receives that same execution beside the result, and the observe-only `tools/result` notification receives both as immutable values. The loop independently correlates with its model call's `call.id`, while ACP correlates through the session event's `data.callId`. The result field is therefore a compulsory copy of information already present at every extension point, plus validation and regression tests whose only job is to prove the copy cannot disagree.
## Proposal
Delete the method and its test; delete the three export lines and their `packages/core/agent-loop/README.md` rows, pointing the inbox spec at the source module; drop the result field from the type, the registry's construction sites (the deny result, the dispatch result, `toolErrorResult`, and the post-execute snapshot's `callId` leg), the loop's ignore-comment, the proves-ignored regression test, and the mutation guard's `callId` assertions — the hazard they all pin disappears with the field, while the result's `additionalContext` ferry (a consumed post-execute channel) stays untouched. Update the `ToolExecutionResult` paste in [tools.md](../../../core-data-structures/tools.md) (and its `scripts/type-equiv.manifest.json` row) and the result-shape row in `packages/core/tools/README.md`; for the `invalidate()` removal, amend the [session-surface RFC](../../implemented/architecture/2026-06-18-session-surface.md)'s full-rebuild-after-wholesale-replacement sentence per [implemented/AGENTS.md](../../implemented/AGENTS.md).
Delete the method and its test; delete the three export lines and their `packages/core/agent-loop/README.md` rows, pointing the inbox spec at the source module; drop the result field from the type, the registry's construction sites (deny, dispatch, `toolErrorResult`, post-execute snapshots), its around-wrapper mismatch validation, the loop's ignore-comment, and the tests that prove the duplicate id cannot matter. The result's consumed `additionalContext` ferry and the execution object's authoritative `callId` stay untouched. Update the `ToolExecutionResult` paste in [tools.md](../../../core-data-structures/tools.md) (and its `scripts/type-equiv.manifest.json` row) and the result-shape row in `packages/core/tools/README.md`; for the `invalidate()` removal, amend the [session-surface RFC](../../implemented/architecture/2026-06-18-session-surface.md)'s full-rebuild-after-wholesale-replacement sentence per [implemented/AGENTS.md](../../implemented/AGENTS.md).
Sequencing: the in-flight surface-cache work (tool-pairing balance caching) neither uses nor touches `invalidate`, so that removal lands after or alongside it mechanically. The execute pipeline is `tools/pre-execute` → dispatch → `tools/post-execute`, and post-execute listeners receive the execution object alongside the result — nothing needs the result's own id.
Sequencing: the surface-cache work (tool-pairing balance caching) neither uses nor touches `invalidate`, so that removal can land after or alongside it mechanically. The full execution pipeline carries the immutable execution object through pre-policy, guards, around-dispatch wrappers, post-policy, and final result observation; nothing needs the result to repeat its id.
## Alternatives considered
@@ -25,7 +25,7 @@ A future consumer that swaps a session's log in place would want a reset primiti
## Acceptance criteria
- `invalidate()` and the result `callId` appear only in this RFC; `runLoop`/`Inbox`/`InboxMessage` remain package-internal only — no re-export from the package index and no outside-package importer; the agent-loop README lists only the consumed public surface; the inbox spec imports the source module.
- The pre-/post-execute pipeline contract tests pass with the shrunk result type; the mutation-guard and proves-ignored tests shed their `callId` legs with the hazard they pin.
- The complete tool-pipeline contract tests pass with the shrunk result type; the around-wrapper mismatch test, mutation-guard id assertions, and proves-ignored loop test disappear with the duplicate field.
## Risks
docs/rfc/rejected/architecture/2026-06-11-immutable-public-surfaces.md
+4 -5
View File
@@ -1,25 +1,24 @@
# RFC: Deep-readonly public surfaces
Status: rejected — the pervasive `DeepReadonly<T>` type flip was rejected in favor of an always-on `deriveMessages` clone plus dev-mode `Object.freeze` + invariants. The immutability *goal* shipped via that alternative; see [dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md).
Status: rejected — the pervasive `DeepReadonly<T>` type flip is replaced by source-owned runtime immutability in `Session` plus relational development assertions. See [source-owned session immutability and dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md).
## Problem
The session log is append-only by contract, but `session.events` returns `readonly SessionEvent[]` whose *elements* are mutable: a plugin can reach in and rewrite history (`events[0].data.content.push(...)`), silently breaking replay equivalence and the derived-history guarantee. The same applies to derived messages and prompt assemblies passed through waterfalls — mutation is sometimes the intended idiom (waterfall middleware mutates the request) and sometimes corruption (mutating a *logged* event), and the types don't distinguish.
The rejected proposal targeted an ownership hole that a `readonly SessionEvent[]` type alone cannot close: its elements remain mutable at runtime, so a cast or plain JavaScript can rewrite nested history. The implemented design closes that hole in `Session` by materializing and deep-freezing every accepted event and returning frozen array snapshots. In-flight prompt waterfalls remain intentionally transformable, so immutability is an ownership boundary rather than a blanket type rule.
## Proposal
> **Implemented differently — see the Status line and [dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md).** The `DeepReadonly<T>` design below was rejected as written (compile-only, high type-noise, castable). What shipped: an always-on deep clone in `deriveMessages` (closing the request/adapter aliasing path) plus a dev-mode `Object.freeze` + invariants plugin. The proposal text is kept for the record.
> **Implemented differently — see the Status line and [source-owned session immutability and dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md).** The `DeepReadonly<T>` design below is rejected as written: it is compile-only, noisy across consumers, and castable. `Session` instead snapshots and deep-freezes accepted events and public log snapshots in every composition; `deriveMessages()` returns detached frozen projections; the development plugin checks cross-record and cross-seam relationships.
Make immutability part of the type where mutation is corruption:
- `SessionEvent` data becomes `DeepReadonly` on the way OUT of a session (`events`, `session/event` listeners); `append()` keeps taking plain mutable input. A `DeepReadonly<T>` utility type lands in dsh-llm next to the brand/never helpers.
- `deriveMessages()` returns deep-readonly messages; the loop clones before handing a mutable request to the `agent/request` waterfall (mutation there is sanctioned — the clone makes the boundary explicit and cheap, once per step).
- `PromptAssembly` stays mutable through its waterfall (sanctioned) but the registry's internal section list is cloned per assembly (already true).
- Optionally, dev-mode `Object.freeze` of event data behind [the dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md) flag, so sanctioned-mutation violations throw in tests rather than corrupting silently.
## Plan
Introduce `DeepReadonly`, flip the session read paths, fix resulting compile errors in consumers (expected: a handful in tests), add the freeze-in-dev option alongside [the dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md) plugin.
Introduce `DeepReadonly`, flip the session read paths, and fix the resulting compile errors in consumers.
## Risks
docs/rfc/rejected/simplification/2026-06-20-single-session-acp-bridge.md
+2 -2
View File
@@ -4,7 +4,7 @@ Status: rejected — Zed is the current target ACP client and its ACP implementa
## Problem
The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../proposed/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this RFC is the competing simplification path.
The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this RFC is the competing simplification path.
The product target has proven it needs concurrent editor conversations over one harness process: Zed's ACP connection owns multiple sessions and load states. The snapshot replay tier still avoids concurrent model streams because its replay entries are positional; that is a test-fixture limitation, not a reason to remove bridge multiplexing.
@@ -20,7 +20,7 @@ Remove the multi-session maps and demux where a single `SessionRecord | undefine
- `session/new` and `session/load` reject while that record exists.
- Event handlers no longer demux across a `Map<sessionId, record>`.
- Multi-session tests are removed or moved under the proposal that continues to defend multiplexing.
- The existing [multi-session ACP proposal](../../proposed/feature/2026-06-14-acp-multi-session.md) is updated to link this RFC and remains the live direction.
- The existing [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) is updated to link this RFC and remains the live direction.
## What we give up
docs/testing.md
+4 -4
View File
@@ -1,17 +1,17 @@
# Testing policy
How this repo tests, tier by tier, and the rules that keep a green suite meaning something. Commands live in the root [AGENTS.md](../AGENTS.md) § Commands; the RFCs linked per tier carry the design rationale.
How this repo tests, tier by tier, and the rules that keep a green suite meaningful. Commands live in root [AGENTS.md](../AGENTS.md); linked RFCs carry the rationale.
## Tiers
- **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Excessive tests are welcome — err toward covering edge cases, error paths, event ordering, and concurrency races; review findings get regression tests (see `packages/core/agent-loop/tests/review-fixes.spec.ts`).
- **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, and concurrency races; review findings get regression tests (see `packages/core/agent-loop/tests/review-fixes.spec.ts`).
- **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped.
- **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)).
- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Re-record with `pnpm run test:snapshot:record`; reviewing the golden diff is part of the review. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Use `pnpm run test:snapshot:record` when the model transcript should change; use `pnpm run test:snapshot:refresh` when the committed transcript is still the right mock LLM input and replay goldens need keyless rewrite. Review the golden diff. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
## The with-key policy: inference is cheap here
We are DeepSeek — do not ration real-API tests. A no-key test proves the plumbing; only a with-key run proves the agent works against a real model. Write many: real prompts that write files, multi-turn conversations, tool use, cancellation mid-stream. Cheapest and highest-value are **smoke tests** that boot the real example, send one real prompt, and check the world — they catch the "green unit tests, broken product" class that mocks structurally cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). The self-skip exists only so secretless CI and keyless contributors aren't blocked; it is not a cost signal. Every example ships a keyless smoke and — unless keyless-by-nature — a with-key smoke ([examples/AGENTS.md](../examples/AGENTS.md)).
We are DeepSeek — do not ration real-API tests. A no-key test proves plumbing; only a with-key run proves the agent works against a real model. Write many: file-writing prompts, multi-turn conversations, tool use, cancellation mid-stream. Highest-value are **smoke tests** that boot the real example, send one real prompt, and check the world — they catch the "green unit tests, broken product" class that mocks structurally cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). The self-skip exists only so secretless CI and keyless contributors aren't blocked; it is not a cost signal. Every example ships a keyless smoke and — unless keyless-by-nature — a with-key smoke ([examples/AGENTS.md](../examples/AGENTS.md)).
## Prefer the real implementation over a mock
docs/tool-catalog.md
+27 -3
View File
@@ -16,10 +16,11 @@ This table connects model-visible tool names to the plugin package and service s
| Tool package | Model-visible names | Requires | Writes / affects | Shipped aliases | Deployment note |
| --- | --- | --- | --- | --- | --- |
| `@deepseek-ai/dsh-tool-ask-user` | `ask_user_question` | `ctx.tools`, `ctx.userInteraction` | `tool/call`, `tool/result after a UI/provider answers the question` | - | ask_user_question pauses the tool call until the active UI provider returns a human answer. |
| `@deepseek-ai/dsh-tools` | `run_code` | `ctx.tools`, `ctx.codeRuntime (execution time)`, `ctx.systemPrompt` | `tool/call`, `one tool/code-dispatch per bridged sub-call`, `tool/result` | - | Registered by the tool registry itself under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the ONLY wire tool; the other registered tools are declared to the model as a generated TypeScript SDK prompt section instead, and a program calls them through port-bridged bindings that dispatch through the ordinary tools/pre-execute → tools/post-execute pipeline, one at a time. |
| `@deepseek-ai/dsh-tools` | `run_code` | `ctx.tools`, `ctx.codeRuntime (execution time)`, `ctx.systemPrompt` | `tool/call`, `one tool/code-dispatch per bridged sub-call`, `tool/result` | - | Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. |
| `@deepseek-ai/dsh-tool-bash` | `bash`, `bash_kill`, `bash_output` | `ctx.tools`, `ctx.bash` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The bash/bash_output/bash_kill tools are model-facing consumers of the bash executor seam. |
| `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; the request-header ToolsDelta logs those tool-set changes. |
| `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. |
| `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - |
| `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. |
| `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist or ACP plan. |
| `@deepseek-ai/dsh-tool-workflow` | `workflow` | `ctx.tools`, `ctx.workflows`, `ctx.systemPrompt`, `a calling Agent (exec.agent parents the script children)` | `tool/call`, `tool/result` | - | - |
@@ -118,13 +119,13 @@ Execute a TypeScript program against the available tools. Write the BODY of an a
Source: [`packages/core/tools/src/code-mode.ts`](../packages/core/tools/src/code-mode.ts)
Registered by the tool registry itself under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the ONLY wire tool; the other registered tools are declared to the model as a generated TypeScript SDK prompt section instead, and a program calls them through port-bridged bindings that dispatch through the ordinary tools/pre-execute → tools/post-execute pipeline, one at a time.
Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result.
## `@deepseek-ai/dsh-tool-bash`
### `bash`
Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.
Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.
```json
{
@@ -370,6 +371,29 @@ Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts
The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin.
## `@deepseek-ai/dsh-tool-skill`
### `skill`
Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.
```json
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The exact skill name from the available skills list."
}
},
"required": [
"name"
]
}
```
Source: [`packages/skill/tool-skill/src/index.ts`](../packages/skill/tool-skill/src/index.ts)
## `@deepseek-ai/dsh-tool-subagent`
### `subagent`
docs/tool-execution-pipeline.md
+18 -7
View File
@@ -3,7 +3,7 @@
# Tool Execution Pipeline
This graph shows where policy, hooks, sandboxing, filesystem guards, result rewriting, and UI rendering fit without changing the loop. The key extension points are the `tools/pre-execute`, `tools/execute`, and `tools/post-execute` waterfalls.
This graph shows where policy, hooks, sandboxing, filesystem guards, result rewriting, final-outcome observation, and UI rendering fit without changing the loop. The transformable extension points are the `tools/pre-execute`, `tools/execute`, and `tools/post-execute` waterfalls; monotonic guards and `tools/result` are the owner-enforced boundaries around them.
```mermaid
flowchart TD
@@ -11,32 +11,43 @@ flowchart TD
toolCall["Session event: <code>tool/call</code><br/>logged before execution"]
presentCall["UI pending card<br/>presentCall(args)"]
pre["<code>tools/pre-execute</code> waterfall<br/>hooks, permission, sandbox"]
denied["deny or ask<br/>tool body skipped"]
guards["Registered monotonic guards<br/>deny or abstain; identity protected"]
denied["denied or approval refused<br/>tool body skipped"]
approval["<code>ctx.approval</code> one-shot prompt<br/>absent or unanswerable: deny"]
around["<code>tools/execute</code> waterfall<br/>timeout, retry, metrics (around dispatch)"]
toolBody["Registered tool execute() body"]
fsGate["<code>fs/write-intent</code> or <code>fs/edit-intent</code><br/>tool-fs mutations only"]
owned["Tool-owned session events<br/><code>todo/write</code>, <code>fs/observed</code>, <code>hook/invoked</code>, <code>hook/result</code>, <code>tool/code-dispatch</code>"]
post["<code>tools/post-execute</code> waterfall<br/>accept, block, replace, add context"]
final["<code>tools/result</code> synchronous notification<br/>frozen authoritative outcome"]
context["Buffered additionalContext<br/>context/message after all tool results"]
toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"]
allResults["All calls in the step settled<br/>and tool/result events recorded"]
presentResult["UI completed card<br/>presentResult(args, result)"]
model --> toolCall
toolCall --> presentCall
toolCall --> pre
pre -->|allow| around
pre -->|allow| guards
guards -->|allow| around
guards -->|deny| denied
around --> toolBody
pre -->|deny or ask| denied
pre -->|deny| denied
pre -->|ask| approval
approval -->|allowed-once| guards
approval -->|rejected, cancelled, unavailable| denied
denied --> post
toolBody --> fsGate
fsGate --> toolBody
toolBody --> owned
toolBody --> around
around --> post
post --> context
post --> toolResult
post --> final
final --> toolResult
toolResult --> presentResult
toolResult --> allResults
allResults --> context
```
Filesystem read-before-edit checks live below `tool-fs` on the `fs/*` event gate; hook bridges and future permission prompts live on the generic pre/post tool waterfalls; and around-dispatch concerns like the tool-call timeout policy (`@deepseek-ai/dsh-timeout-policy`) wrap core dispatch on `tools/execute`. That split lets the same hooks observe bash, fs, web, todo, and subagent calls without coupling those tools to one policy service. Code Mode rides the same pipeline twice over: `run_code` is itself a registered tool body, and each tool call its program makes re-enters `ctx.tools.execute()` through BOTH waterfalls — serialized one at a time, logged as a `tool/code-dispatch` session event, with a deny surfacing to the program as a binding rejection (a sub-call's `additionalContext` is deliberately dropped — no safe outlet mid-run preserves call/result adjacency).
Filesystem read-before-edit checks live below `tool-fs` on the `fs/*` event gate; hook bridges and approval-triggering permission policy enter through the generic pre/post tool waterfalls, while `ctx.approval` resolves an `ask` before the monotonic guards; owner policy that must not be reordered uses registered guards; and around-dispatch concerns like the tool-call timeout policy (`@deepseek-ai/dsh-timeout-policy`) wrap core dispatch on `tools/execute`. The synchronous `tools/result` notification observes the immutable final outcome after every transform, lossless-JSON validation, and outer error normalization. That split lets the same hooks observe bash, fs, web, todo, skill, and subagent calls without coupling those tools to one policy service. Code Mode rides the whole pipeline twice over: `run_code` is the reserved registry-owned transport whose body enters the pipeline, and each tool call its program makes re-enters `ctx.tools.execute()` — serialized one at a time, carrying the outer execution's opaque token for correlation, and logged as a `tool/code-dispatch` session event, with a deny surfacing to the program as a binding rejection (a sub-call's `additionalContext` is deliberately dropped — no safe outlet mid-run preserves call/result adjacency).
Maintenance mode: curated Mermaid flow; exact tool schemas and event signatures live in generated catalogs.
eslint.config.mjs
+12 -2
View File
@@ -22,6 +22,7 @@ export default tseslint.config(
'**/lib/**',
'**/node_modules/**',
'**/.sessions/**',
'.claude/**', // harness-local state (worktrees, skills) — other checkouts, not this one's sources
'**/.doc-typecheck-*/**',
'vendor/**', // vendored source keeps upstream style and idioms
'**/*.js',
@@ -38,7 +39,14 @@ export default tseslint.config(
],
languageOptions: {
parserOptions: {
project: ['./packages/*/*/tsconfig.json', './tsconfig.json'],
// One shared tsserver-style project service instead of 60+ standalone
// per-package programs: the old `project` glob built every package's
// full dependency closure (sibling sources via the dev `paths` map +
// the vendored Cordis stack) as its own program and kept them all
// resident — ~5 GB peak, an OOM past node's default heap. The service
// resolves each file to its nearest owning tsconfig and shares the
// graph.
projectService: true,
tsconfigRootDir: import.meta.dirname,
},
},
@@ -89,7 +97,9 @@ export default tseslint.config(
],
languageOptions: {
parserOptions: {
project: ['./tsconfig.json'],
// Same shared project service as the src block: test files resolve
// through the root tsconfig (its include covers every tests/ tree).
projectService: true,
tsconfigRootDir: import.meta.dirname,
},
},
examples/AGENTS.md
+3 -2
View File
@@ -2,7 +2,7 @@
Runnable demos showing how the harness is wired. **Examples are NOT workspaces** — each `examples/*/package.json` is a private, dependency-free stub, never built. They are booted as unbuilt `tsx` subprocesses via the cordis Loader reading a `cordis.yml`; the `@deepseek-ai/dsh-*` plugin names in those YAML files resolve through the root `tsconfig.json` `paths` map, not through `node_modules`.
Because examples are not under the `packages/*/src` coverage gate, an example that grows real, reusable *logic* should extract it into a `packages/` package (where it gets the per-file 100% gate and a README). Keep only example-specific glue here: the `cordis.yml` wiring, demo-only mocks/teaching artifacts, and the e2e/snapshot scenarios. There is no `start.ts` — the boot glue (Loader tail, `.env` load, snapshot-mode selection, stdin-dispose lifecycle) lives in each app package's `bin` (`@deepseek-ai/dsh-stdio-agent`, `@deepseek-ai/dsh-acp-agent`), which the `demo:*` scripts invoke against the leaf `cordis.yml`.
Because examples are not under the `packages/*/src` coverage gate, an example that grows real, reusable *logic* should extract it into a `packages/` package (where it gets the per-file 100% gate and a README). Keep only example-specific glue here: the `cordis.yml` wiring, demo-only mocks/teaching artifacts, and the e2e/snapshot scenarios. There is no `start.ts` — the boot glue lives in each app package's `bin` (`@deepseek-ai/dsh-stdio-agent`, `@deepseek-ai/dsh-acp-agent`), which the `demo:*` scripts invoke against the leaf `cordis.yml`.
## Every example ships e2e smokes (keyless + with-key)
@@ -13,7 +13,7 @@ Each example must have **both** kinds of end-to-end smoke, because they catch di
**Exception — keyless-by-nature examples.** An example whose model is itself a mock/deterministic stand-in (no real provider) has no meaningful with-key smoke; the keyless smoke is the complete requirement. State the exception inline in the test.
A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_PATH` to the repo-root tsconfig — the unbuilt `paths` map is found by searching UP from cwd, so a temp cwd outside the repo would otherwise fall back to stale built `lib/`. Pass `--expose-internals` when the example's `cordis.yml` loads the HMR plugin (mirror the `demo:*` script).
A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_PATH` to the repo-root tsconfig (the unbuilt `paths` map is found by searching UP from cwd), and pass `--expose-internals` when the `cordis.yml` loads the HMR plugin (mirror the `demo:*` script).
## Current state
@@ -22,6 +22,7 @@ A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_P
| `echo-agent` | `tests/echo.e2e.ts` — boots the real `cordis.yml`, drives the echo tool round-trip and the direct canned reply | **N/A — keyless by nature** (the `mock-echo` model has no real provider) |
| `coding-agent` | `tests/keyless-smoke.e2e.ts` — boots the full real tree (dummy key, no prompt → no model call), asserts banner + clean exit; `tests/code-mode-keyless-smoke.e2e.ts` — the same boot guard for the Code Mode overlay | `tests/{full-loop,coding-task,resume,compaction,todo-write}.e2e.ts` — real model + real bash + real todo_write, world-verified; `tests/code-mode.e2e.ts` — a real model composes two bash calls in one `run_code` program; collapsed header, dispatch events, written file all verified |
| `cordis-agent` | `tests/keyless-smoke.e2e.ts` — boots the real tree incl. `@deepseek-ai/dsh-tool-cordis` by package name; the tool logic is unit-tested in `packages/cordis/tool-cordis` | `tests/cordis-tools.e2e.ts` — real model mounts a listener (tagged line fires), builds+calls its own tool, composes two mounts via provide/inject |
| `sandbox-acp-agent` | `escalation.e2e.ts` — boots the real tree (sandbox + approval + bridge) keyless: initialize + `session/new` | same file — denied → escalates → a scripted client grants (the write must land) or rejects (it must not); skips without key/runner |
| `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless (incl. the hook matrix: a scenario per hook point × outcome for BOTH the Claude and Codex bridges — block, deny, ask, context-fold, force-continue); `tests/acp.e2e.ts` also asserts stdout purity without a key | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote; `tests/hooks.e2e.ts` — a real `PreToolUse` hook blocks bash, verifies the file is NOT written |
See [the root AGENTS.md](../AGENTS.md) for repo-wide conventions and [docs/architecture.md](../docs/architecture.md) for the design.
examples/README.md
+7 -1
View File
@@ -19,7 +19,7 @@ A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + th
Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details.
Its `code-mode.cordis.yml` overlay flips the same tree to **Code Mode**: the worker-thread code runtime is loaded and the tool registry runs `mode: code`, so the model gets exactly one wire tool — `run_code` — plus a generated TypeScript SDK section, and composes the other tools by writing a program whose output it curates. Run with: `pnpm run demo:code-mode` (the REPL is the default UI; `acp` as the argument serves the acp-agent example's same-shaped overlay instead) — see the [Code Mode section](coding-agent/README.md#code-mode) for what to try.
Its `code-mode.cordis.yml` overlay flips the same tree to **Code Mode**: the worker-thread code runtime is loaded and the tool registry runs `mode: code`, so its registry contribution is the reserved `run_code` transport plus a generated TypeScript SDK section, and the model composes the other tools by writing a program whose output it curates. Run with: `pnpm run demo:code-mode` (the REPL is the default UI; `acp` as the argument serves the acp-agent example's same-shaped overlay instead) — see the [Code Mode section](coding-agent/README.md#code-mode) for what to try.
## cordis-agent
@@ -32,3 +32,9 @@ Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/R
An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-agent`](../packages/ui/acp-agent) app — drive it from Zed or any other ACP client. Also the home of the keyless snapshot tests.
Run with: `pnpm run demo:acp` (needs `DEEPSEEK_API_KEY`); `pnpm run demo:code-mode acp` boots the same server in Code Mode via the `code-mode.cordis.yml` overlay. See [acp-agent/README.md](acp-agent/README.md) for the Zed setup and the snapshot-test design.
## sandbox-acp-agent
The coding agent with its bash executor swapped for the sandbox stack ([`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local) + [`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) — the one-entry executor swap the `ctx.bash` capability seam exists for), served over ACP with [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval) mounted — the first composition where the approval loop is LIVE: a sandbox denial escalated by the model becomes a `session/request_permission` prompt in the editor, and "Allow once" runs exactly that command under the wider mode.
Run with: `pnpm run demo:sandbox-acp` (needs `DEEPSEEK_API_KEY`; bwrap, a Landlock-enforcing kernel, or macOS for confined runs). See [sandbox-acp-agent/README.md](sandbox-acp-agent/README.md).
examples/acp-agent/README.md
+2 -2
View File
@@ -33,8 +33,8 @@ The editor sets each session's `cwd` to the project it opens; both the agent's b
## Snapshot tests (record-once / replay-deterministic)
This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`<scenario>/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`". The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `<scenario>/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `<scenario>/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design.
This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`<scenario>/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`"; use `pnpm run test:snapshot:record` when the model transcript itself should change, and `pnpm run test:snapshot:refresh` when the committed model transcript is still the right mock input and only the current replay output/goldens need to be rewritten. The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `<scenario>/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `<scenario>/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design.
## MVP limitations
The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, `additionalDirectories` and `mcpServers` are rejected, and the tool-permission gate is deferred (`TODO(rfc010-permission-gate)` — tools run with the executor's full authority). See `packages/ui/acp/README.md` for the full contract.
The bridge supports N concurrent sessions per connection, each in its own workspace `cwd` (RFC 011). Remaining limits: prompts support ACP's baseline `text` and `resource_link` blocks only, and `additionalDirectories` and `mcpServers` are rejected. Permission prompts (`session/request_permission`) are wired through the approval seam, but this example composes no ask-producing policy, so tools run with the executor's full authority. See `packages/ui/acp/README.md` for the full contract.
examples/acp-agent/both-mode.cordis.snapshot.yml
+2 -4
View File
@@ -20,11 +20,9 @@
tools:
mode: both
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'
examples/acp-agent/both-mode.cordis.yml
+2 -4
View File
@@ -19,11 +19,9 @@
tools:
mode: both
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'
examples/acp-agent/code-mode.cordis.snapshot.yml
+2 -4
View File
@@ -20,11 +20,9 @@
tools:
mode: code
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'
examples/acp-agent/code-mode.cordis.yml
+2 -4
View File
@@ -20,11 +20,9 @@
tools:
mode: code
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'
examples/acp-agent/cordis.yml
+2 -4
View File
@@ -44,11 +44,9 @@
# loop resolves per session (every ACP session carries the client's cwd,
# so the persona can state the workspace).
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
# The subagent seam + both in-process backends + two model-facing tools, as leaf
# entries after the app (which provides ctx.agents/ctx.tools). spawn (a fresh
examples/acp-agent/tests/acp.e2e.ts
+20 -4
View File
@@ -63,7 +63,16 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
const child = spawn(
process.execPath,
['--import', tsxLoader, binScript, configPath],
{ cwd, env: { ...env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] },
{
cwd,
env: {
...env,
TSX_TSCONFIG_PATH: repoTsconfig,
DSH_HOME: join(cwd, '.dsh'),
DSH_AGENTS_HOME: join(cwd, '.agents'),
},
stdio: ['pipe', 'pipe', 'pipe'],
},
)
const stderr: string[] = []
child.stderr.setEncoding('utf8')
@@ -80,8 +89,9 @@ function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawn
return Promise.resolve()
},
requestPermission(_params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
// Permission gate is deferred (TODO(rfc010-permission-gate)); the bridge
// never requests permission yet, so just allow if it ever does.
// This example composes no ask-producing policy (no hooks), so the
// bridge never prompts here; answer cancelled (fail closed) if it ever
// does — an unexpected prompt must not grant anything.
return Promise.resolve({ outcome: { outcome: 'cancelled' } })
},
})
@@ -150,7 +160,13 @@ describe('acp-agent over real stdio (no key required)', () => {
// which this purity test never triggers). So this runs WITHOUT real creds.
const child = spawn(process.execPath, ['--import', tsxLoader, binScript, configPath], {
cwd: workdir,
env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig },
env: {
...process.env,
DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot',
TSX_TSCONFIG_PATH: repoTsconfig,
DSH_HOME: join(workdir, '.dsh'),
DSH_AGENTS_HOME: join(workdir, '.agents'),
},
stdio: ['pipe', 'pipe', 'pipe'],
})
const out: string[] = []
examples/acp-agent/tests/acp.snapshot.ts
+25 -9
View File
@@ -1,15 +1,16 @@
import { fileURLToPath } from 'node:url'
import { dirname, join } from 'node:path'
import { defineAcpSnapshotSuite, type Scenario } from '@deepseek-ai/dsh-acp-snapshot'
import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from '@deepseek-ai/dsh-acp-snapshot'
/**
* The acp-agent example's snapshot suite: the scenario table for
* `dsh-acp-snapshot`'s suite factory, which owns every compare/guard mechanic
* (golden + re-persisted-log diffs, record write-back, the pinned-header
* (golden + re-persisted-log diffs, record/refresh write-back, the pinned-header
* uniformity guard, the fixture guards). Fixtures live under `snapshots/<name>/`;
* `pnpm run test:snapshot:record` re-records the `recorded` scenarios against
* the real API. See the package README (packages/support/acp-snapshot) and the
* snapshot RFC, docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
* `pnpm run test:snapshot:record` re-records model transcripts against the real
* API; `pnpm run test:snapshot:refresh` rewrites current replay goldens keyless.
* See the package README (packages/support/acp-snapshot) and the snapshot RFC,
* docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
*/
// The dsh-acp-agent bin (the demo:acp entry), this example's cordis.yml, and
@@ -26,16 +27,31 @@ const AGENT = {
const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
switch (value) {
case undefined:
case '':
case 'replay':
return 'replay'
case 'record':
return 'record'
case 'refresh':
return 'refresh'
default:
throw new Error(`unknown DSH_SNAPSHOT mode: ${value}`)
}
}
const SCENARIOS: Scenario[] = [
{ name: 'handshake', hasModelTurn: false, recorded: false },
{ name: 'reject-extra-dirs', hasModelTurn: false, recorded: false },
// text-turn is the pinned-header scenario: the minimal single text turn,
// whose fixture is the ONE place the full system prompt + tool schemas are
// committed and compared verbatim.
// text-turn is the pinned-header scenario: the minimal single text turn.
// Its system-prompt.golden.md and JSONL tool list pin the composed header.
{ name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
{ name: 'tool-call-turn', hasModelTurn: true, recorded: true },
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
{ name: 'todo-plan', hasModelTurn: true, recorded: true },
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
{ name: 'workspace-edit', hasModelTurn: true, recorded: true },
{ name: 'fs-read', hasModelTurn: true, recorded: true },
{ name: 'fs-write', hasModelTurn: true, recorded: true },
@@ -111,5 +127,5 @@ defineAcpSnapshotSuite({
agent: AGENT,
snapshotsDir: join(dirname(fileURLToPath(import.meta.url)), 'snapshots'),
scenarios: SCENARIOS,
mode: process.env.DSH_SNAPSHOT === 'record' ? 'record' : 'replay',
mode: snapshotModeFromEnv(process.env.DSH_SNAPSHOT),
})
examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md
+136
View File
@@ -0,0 +1,136 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
## Writing code for run_code
Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.
- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.
- Calls execute sequentially, even under `Promise.all`.
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
The available tools:
```ts
declare const tools: {
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
bash(args: {
/** The bash command to execute. */
command: string;
/** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */
description: string;
/** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */
timeoutMs?: number;
/** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */
workdir?: string;
/** Run in the background and return a task id immediately. No timeout applies. */
run_in_background?: boolean;
}): Promise<string>;
/** Ask the executor to kill a running background bash task by task id. */
bash_kill(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */
bash_output(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Edit an existing UTF-8 text file by replacing literal text. */
edit(args: {
/** Path to edit, resolved by the filesystem backend. */
file_path: string;
/** Literal text to replace. Must match exactly. */
old_string: string;
/** Literal replacement text. Use an empty string to delete the match. */
new_string: string;
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
replace_all?: boolean;
}): Promise<string>;
/** Read a UTF-8 text file and return line-numbered content. */
read(args: {
/** Path to read, resolved by the filesystem backend. */
file_path: string;
/** 1-based first line to return. Defaults to 1. */
offset?: number;
/** Maximum number of lines to return. Defaults to 2000. */
limit?: number;
}): Promise<string>;
/** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
skill(args: {
/** The exact skill name from the available skills list. */
name: string;
}): Promise<string>;
/** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */
subagent(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
prompt: string;
}): Promise<string>;
/** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */
subagent_fork(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */
prompt: string;
}): Promise<string>;
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
todo_write(args: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({
/** What the task is — a short imperative line. */
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {
/** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */
script: string;
/** The workflow identity block (plain JSON — never code). */
meta: {
/** Short kebab-case workflow name. */
name: string;
/** One-line description of what the workflow does. */
description: string;
/** Optional guidance on when this workflow applies. */
whenToUse?: string;
/** Optional phase declarations matched by phase() calls. */
phases?: {
/** The phase title phase() calls match by exact string. */
title: string;
/** Optional one-line description of the phase. */
detail?: string;
/** Optional model override this phase is expected to use. */
model?: string;
}[];
};
/** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */
args?: Record<string, unknown>;
}): Promise<string>;
/** Create or fully replace a UTF-8 text file. */
write(args: {
/** Path to write, resolved by the filesystem backend. */
file_path: string;
/** Full UTF-8 text content to write. */
content: string;
}): Promise<string>;
}
```
examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md
+136
View File
@@ -0,0 +1,136 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
## Writing code for run_code
Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.
- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.
- Calls execute sequentially, even under `Promise.all`.
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
The available tools:
```ts
declare const tools: {
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
bash(args: {
/** The bash command to execute. */
command: string;
/** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */
description: string;
/** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */
timeoutMs?: number;
/** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */
workdir?: string;
/** Run in the background and return a task id immediately. No timeout applies. */
run_in_background?: boolean;
}): Promise<string>;
/** Ask the executor to kill a running background bash task by task id. */
bash_kill(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */
bash_output(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Edit an existing UTF-8 text file by replacing literal text. */
edit(args: {
/** Path to edit, resolved by the filesystem backend. */
file_path: string;
/** Literal text to replace. Must match exactly. */
old_string: string;
/** Literal replacement text. Use an empty string to delete the match. */
new_string: string;
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
replace_all?: boolean;
}): Promise<string>;
/** Read a UTF-8 text file and return line-numbered content. */
read(args: {
/** Path to read, resolved by the filesystem backend. */
file_path: string;
/** 1-based first line to return. Defaults to 1. */
offset?: number;
/** Maximum number of lines to return. Defaults to 2000. */
limit?: number;
}): Promise<string>;
/** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
skill(args: {
/** The exact skill name from the available skills list. */
name: string;
}): Promise<string>;
/** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */
subagent(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
prompt: string;
}): Promise<string>;
/** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */
subagent_fork(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */
prompt: string;
}): Promise<string>;
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
todo_write(args: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({
/** What the task is — a short imperative line. */
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {
/** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */
script: string;
/** The workflow identity block (plain JSON — never code). */
meta: {
/** Short kebab-case workflow name. */
name: string;
/** One-line description of what the workflow does. */
description: string;
/** Optional guidance on when this workflow applies. */
whenToUse?: string;
/** Optional phase declarations matched by phase() calls. */
phases?: {
/** The phase title phase() calls match by exact string. */
title: string;
/** Optional one-line description of the phase. */
detail?: string;
/** Optional model override this phase is expected to use. */
model?: string;
}[];
};
/** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */
args?: Record<string, unknown>;
}): Promise<string>;
/** Create or fully replace a UTF-8 text file. */
write(args: {
/** Path to write, resolved by the filesystem backend. */
file_path: string;
/** Full UTF-8 text content to write. */
content: string;
}): Promise<string>;
}
```
examples/acp-agent/tests/snapshots/skill-load/input.json
+7
View File
@@ -0,0 +1,7 @@
{
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Load the snapshot-skill skill with the skill tool, then reply DONE." }
]
}
examples/acp-agent/tests/snapshots/skill-load/session.jsonl
+29
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl
+8
View File
@@ -0,0 +1,8 @@
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The skill is loaded."}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md
+16
View File
@@ -0,0 +1,16 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
examples/acp-agent/tests/snapshots/skill-load/workspace/.dsh/skills/snapshot-skill/SKILL.md
+7
View File
@@ -0,0 +1,7 @@
---
name: snapshot-skill
description: Exercise project skill discovery and loading in snapshot tests.
---
Follow these snapshot-only instructions.
Resolve referenced resources relative to this skill directory.
examples/acp-agent/tests/snapshots/text-turn/session.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md
+16
View File
@@ -0,0 +1,16 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
examples/coding-agent/README.md
+1 -1
View File
@@ -33,7 +33,7 @@ The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_
## Code Mode
[`code-mode.cordis.yml`](code-mode.cordis.yml) is this same tree flipped to [Code Mode](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md): an include overlay over `./cordis.yml` whose two patches insert the worker-thread code runtime (`@deepseek-ai/dsh-code-runtime-worker`, registering `ctx.codeRuntime`) and set `tools: { mode: code }` on the app. The model is then offered exactly ONE wire tool — `run_code` — plus a generated TypeScript SDK section declaring every other registered tool; it composes them by writing a program, each program tool call bridges back through the ordinary `tools/pre-execute`/`post-execute` pipeline one at a time and is logged as a `tool/code-dispatch` session event, and ONLY what the program prints or returns re-enters its context. (Flip the mode to `both` to offer native calls AND `run_code` side by side.)
[`code-mode.cordis.yml`](code-mode.cordis.yml) is this same tree flipped to [Code Mode](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md): an include overlay over `./cordis.yml` whose two patches insert the worker-thread code runtime (`@deepseek-ai/dsh-code-runtime-worker`, registering `ctx.codeRuntime`) and set `tools: { mode: code }` on the app. The registry contributes exactly one reserved wire transport — `run_code` — plus a generated TypeScript SDK section declaring the visible end-capability tools. The model composes those capabilities by writing a program; each program call carries an immutable link to its enclosing transport, bridges back through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation one at a time, and is logged as a `tool/code-dispatch` session event. Only what the program prints or returns re-enters model context. (Flip the mode to `both` to offer native calls and `run_code` side by side.)
```sh
pnpm run demo:code-mode # this overlay under the REPL (default UI)
examples/coding-agent/tests/code-mode-keyless-smoke.e2e.ts
+11 -3
View File
@@ -26,6 +26,14 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
// the repo, so point it at the repo tsconfig.
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
// startup can therefore outlive a tight smoke-test deadline before the child
// emits any output; 30s still detects a wedged process without confusing
// bounded CI contention with a lifecycle failure.
const PROCESS_TIMEOUT_MS = 30_000
// Leave enough room for the process-owned timeout to report captured output
// before Vitest aborts the test itself.
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
let child: ChildProcessWithoutNullStreams | undefined
let workdir: string | undefined
@@ -67,8 +75,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`code-mode overlay did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`code-mode overlay did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, PROCESS_TIMEOUT_MS)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -87,5 +95,5 @@ describe('code-mode overlay keyless smoke (real code-mode.cordis.yml via the Loa
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
expect(stdout).toContain('code-mode agent ready.')
}, 15_000)
}, TEST_TIMEOUT_MS)
})
examples/coding-agent/tests/keyless-smoke.e2e.ts
+13 -3
View File
@@ -35,6 +35,14 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
// the repo, so point it at the repo tsconfig (root is four levels up).
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
// startup can therefore outlive a tight smoke-test deadline before the child
// emits any output; 30s still detects a wedged process without confusing
// bounded CI contention with a lifecycle failure.
const PROCESS_TIMEOUT_MS = 30_000
// Leave enough room for the process-owned timeout to report captured output
// before Vitest aborts the test itself.
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
let child: ChildProcessWithoutNullStreams | undefined
let workdir: string | undefined
@@ -62,6 +70,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
// A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
// No prompt is sent, so the adapter never streams — no network call.
DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
DSH_HOME: join(cwd, '.dsh'),
DSH_AGENTS_HOME: join(cwd, '.agents'),
},
stdio: ['pipe', 'pipe', 'pipe'],
},
@@ -76,8 +86,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`coding-agent did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`coding-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, PROCESS_TIMEOUT_MS)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -96,5 +106,5 @@ describe('coding-agent keyless smoke (real cordis.yml via the Loader)', () => {
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
expect(stdout).toContain('agent REPL ready.')
}, 15_000)
}, TEST_TIMEOUT_MS)
})
examples/coding-agent/tests/resume.e2e.ts
+2 -2
View File
@@ -39,11 +39,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// dispose the whole context (simulating process exit) so only the JSONL
// log on disk survives.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const first = ctx.agents.create({
const first = (await ctx.agents.create({
agentId: AgentId('resume-1'),
sessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash' },
}).agent as ReactLoopAgent
})).agent as ReactLoopAgent
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
await waitForIdle(ctx, first)
await ctx.fiber.dispose()
examples/cordis-agent/tests/keyless-smoke.e2e.ts
+11 -3
View File
@@ -29,6 +29,14 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
// the repo, so point it at the repo tsconfig (root is three levels up).
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
// startup can therefore outlive a tight smoke-test deadline before the child
// emits any output; 30s still detects a wedged process without confusing
// bounded CI contention with a lifecycle failure.
const PROCESS_TIMEOUT_MS = 30_000
// Leave enough room for the process-owned timeout to report captured output
// before Vitest aborts the test itself.
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
let child: ChildProcessWithoutNullStreams | undefined
let workdir: string | undefined
@@ -70,8 +78,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`cordis-agent did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`cordis-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, PROCESS_TIMEOUT_MS)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -90,5 +98,5 @@ describe('cordis-agent keyless smoke (real cordis.yml via the Loader)', () => {
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
expect(stdout).toContain('cordis-agent ready.')
}, 15_000)
}, TEST_TIMEOUT_MS)
})
examples/echo-agent/README.md
+1 -1
View File
@@ -31,4 +31,4 @@ node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples
Type a message and press Enter. "echo <text>" triggers a tool call round-trip (the mock model requests the `echo` tool, which echoes the text uppercased, and the next model step acknowledges it).
The session is persisted under `.sessions/` relative to the directory you launch the demo from. `pnpm run demo:echo` runs from the repo root, so the logs land in `<repo-root>/.sessions/` (a session with no cwd goes in the `_no-cwd/` bucket, one `.jsonl` log per session). Clean up with: `rm -rf .sessions`
The session is persisted under `.sessions/` relative to the directory you launch the demo from. `pnpm run demo:echo` runs from the repo root, so the logs land in `<repo-root>/.sessions/cwd-<hash>/` (one `.jsonl` log per session). Clean up with: `rm -rf .sessions`
examples/echo-agent/tests/echo.e2e.ts
+24 -7
View File
@@ -37,6 +37,14 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// a temp cwd OUTSIDE the repo, so point tsx at the repo tsconfig explicitly
// (repo root is four levels up from examples/echo-agent/tests).
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
// startup can therefore outlive a tight smoke-test deadline before the child
// emits any output; 30s still detects a wedged process without confusing
// bounded CI contention with a lifecycle failure.
const PROCESS_TIMEOUT_MS = 30_000
// Leave enough room for the process-owned timeout to report captured output
// before Vitest aborts the test itself.
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
let child: ChildProcessWithoutNullStreams | undefined
let workdir: string | undefined
@@ -51,7 +59,7 @@ afterEach(async () => {
/**
* Boot echo-agent, write `lines` to its stdin, close stdin, and resolve with
* the full stdout once the process exits (the stdio UI exits on EOF after the
* agent settles). Rejects on a non-zero exit or a 10s timeout.
* agent settles). Rejects on a non-zero exit or the process deadline.
*/
async function runEcho(lines: string[]): Promise<{ stdout: string; code: number }> {
workdir = await mkdtemp(join(tmpdir(), 'echo-smoke-'))
@@ -63,7 +71,16 @@ async function runEcho(lines: string[]): Promise<{ stdout: string; code: number
// requires it (mirrors the `demo:echo` script). The whole point is to boot
// the example EXACTLY as it really runs, through the bin + Loader.
['--expose-internals', '--import', tsxLoader, binScript, configPath],
{ cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] },
{
cwd,
env: {
...process.env,
TSX_TSCONFIG_PATH: repoTsconfig,
DSH_HOME: join(cwd, '.dsh'),
DSH_AGENTS_HOME: join(cwd, '.agents'),
},
stdio: ['pipe', 'pipe', 'pipe'],
},
)
child = proc
let stdout = ''
@@ -75,8 +92,8 @@ async function runEcho(lines: string[]): Promise<{ stdout: string; code: number
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`echo-agent did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`echo-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, PROCESS_TIMEOUT_MS)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -96,19 +113,19 @@ describe('echo-agent keyless smoke (real cordis.yml via the Loader)', () => {
const { stdout, code } = await runEcho([])
expect(code).toBe(0)
expect(stdout).toContain('echo-agent ready.')
}, 15_000)
}, TEST_TIMEOUT_MS)
it('runs the echo tool round-trip for an "echo …" line', async () => {
const { stdout } = await runEcho(['echo hello world'])
// mock-llm.ts emits a tool-call for the echo tool; echo-tool.ts uppercases.
expect(stdout).toContain('[tool call] echo')
expect(stdout).toContain('[tool result] ECHO: HELLO WORLD')
}, 15_000)
}, TEST_TIMEOUT_MS)
it('streams a direct canned reply for a non-echo line', async () => {
const { stdout } = await runEcho(['just chatting'])
// The direct-response branch of mock-llm.ts quotes the input back.
expect(stdout).toContain('just chatting')
expect(stdout).not.toContain('[tool call]')
}, 15_000)
}, TEST_TIMEOUT_MS)
})

Some files were not shown because too many files have changed in this diff Show More