Yichen Jiang
37ebe87087
Moving the task registry to the host plane put every preset's `tool-tasks` listener on ONE `LocalTaskService`. `settle()` computes a single snapshot and walks every registered listener with no scope filter, and it marks `reported` only when a waiter is present — so a task settling without a waiter reached each mount's listener with `reported` false and every one of them injected the same completion into the same owner. Three shipped presets carry `tool-tasks`, and a preset file edit adds a second generation of the same mount, so an agent read N copies of one notice as model-visible durable context. A mount now claims an owner only when the owner's scope chain reaches the mount's own scope. An unscoped mount is the host-plane instance that serves every agent, which keeps the TUI composition and every existing test intact. Registry-side ownership was the alternative: mark `reported` once the first listener claims it. It is wrong because `onTaskDone` is not a notice-only seam — the `dsh-tasks` invariant companion registers a validating listener — so first-claim-wins would silence observers that are not delivering anything. The regression test mounts two scoped `tool-tasks` over one registry and settles an unowned-wait task, which is the only path that reaches the notice listeners at all: the shipped-composition e2e uses `wait: true`, and a waiter marks `reported` before settlement, so that test structurally cannot cover it. Also corrects the standing-mounts Agent Note, which still listed `tasks-local` among the stateful PRESET plugins. Refs #2141
Packages
English | 中文
Packages use the @deepseek-ai/dsh-* scope. Cordis Service subclasses and function plugins contribute through ctx.effect(), ctx.on(), or ctx.waterfall(). Authoring rules: package and root.
Hierarchy
Groups hold packages/<group>/<pkg>/; names stay @deepseek-ai/dsh-<pkg>. Group READMEs own package/ctx-key maps.
| Group | Role | Release expectation |
|---|---|---|
core/ |
Product API spine: sessions, prompts, tools, agent services, and the concrete loop | Product — stable surface |
api/ |
Remote BFF assembly and TypeRT RPC gateway | Product — stable surface |
typert/ |
Type graph generation, artifact loading, and runtime registry | Product — stable surface |
goal/ |
Same-session goal persistence and lifecycle | Product — stable surface |
feedback/ |
Human feedback | Product — stable surface |
llm/ |
LLM capability family: the abstract service + provider adapters | Product — stable surface |
e2b/ |
E2B providers | POC |
subprocess/ |
Subprocess capability family: Service Definition + local process-tree provider | Product — stable surface |
bash/ |
Bash capability family: executor seam, local impl, model-facing tool | Product — stable surface |
pty/ |
Persistent PTY capability family: owner-scoped sessions, local implementation, and model-facing tools | Product — stable surface |
code-runtime/ |
Code-execution capability family: Service Definition + worker-thread provider + Code Mode Consumer | Product — stable surface |
sandbox/ |
Process-confinement seam; bwrap/Landlock/Seatbelt backends | Product — stable surface |
fs/ |
Filesystem capability family: seam, local impl, model-facing file tools, bash-backed discovery tools | Product — stable surface |
lsp/ |
LSP capability family: seam, generic stdio provider, and the lsp tool |
Product — stable surface |
skill/ |
Skill capability family: the provider registry, local provider, and model-facing catalog/loader | Product — stable surface |
compact/ |
Compaction capability family: Service Definition + basic provider + command Consumer | Product — stable surface |
context/ |
Model-visible request context, including workspace instructions and time context | Product — stable surface |
subagent/ |
Subagent capability family: the provider-registry contract and the model-facing delegation tool | Product — stable surface |
tasks/ |
Generic background-task runtime and model-facing task_* control tools |
Product — stable surface |
workflow/ |
Workflow seam, worker-thread engine, and model-facing workflow/ralph tools |
Product — stable surface |
web/ |
Web capability family: seam, search/fetch provider impls, and the model-facing web tools | Product — stable surface |
spill/ |
Spill capability family: storage seam, local impl, tool-result spill policy | Product — stable surface |
todo/ |
The model-facing todo_write tool |
Product — stable surface |
plan/ |
Plan collaboration state with a direct entry command and reviewed exit | Product — stable surface |
preset/ |
Per-session agent composition from preset cordis.yml files |
Product — stable surface |
guard/ |
Loop-hygiene guards: advisory repeat-call reminders + the tools/execute deadline enforcer |
Product — stable surface |
bundle/ |
Installable dsh --profile patch layers |
Product — stable surface |
self-modification/ |
The agent modifies its own runtime: inspect the live runtime's plugins and services, mount/unmount model-written plugins (design) and restricted repository Plugin loading | Product — stable surface |
hooks/ |
Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface |
session/ |
Durable session data plane: persistence seam + JSONL/SQLite backends, projection seam, log-backed titles, session reporting | Product — stable surface |
session-query/ |
Session retrieval family: logical corpus, bounded reads, lineage, event relationships, semantic filtering, and SQLite full-text search | Product — stable surface |
settings/ |
User-settings seam + file-backed provider | Product — stable surface |
credentials/ |
Credential-reference seam + env-over-.env provider |
Product — stable surface |
storage/ |
Non-session storage hub + backends + domain form | Product — stable surface |
workspace/ |
Workspace entity | Product — stable surface |
scaffold/ |
Create/launch/drive project tooling: helper, launcher, initializer, wire protocol with both ends, launcher telemetry | Product — stable surface |
acp/ |
Automation-only Agent Client Protocol server | Product — stable surface |
interaction/ |
Human-collaboration plane: approval/interaction seams, permission preset, commands, ask-user tool | Product — stable surface |
boot/ |
Shared app-bin boot glue | Product — stable surface |
host/ |
Web-GUI host half: API gateway + HTTP route server | Product — stable surface |
client/ |
Web-GUI browser half: shell, wire, object services, slots, ui-* plugins |
Product — stable surface |
experimental/ |
Prototypes and internal plugins | Unreleased |
examples/ |
Demo bundles (agent-spine + CLI/ACP/JSON-RPC bins) leaves load | Support — example infra |
support/ |
Support infrastructure (testkits, invariants, replay, Loader smokes) | Support — lower compatibility expectations |
util/ |
Low-level zero-dependency utilities shared across groups (Branded<B>, Harness home/path helpers, timeout, retention) |
Support — small, stable, harness-dep-free |
New packages join existing groups; new groups update their README and this table.
Dependencies
The dependency graph is generated: docs/module-graph.md (pnpm run gen-module-graph, freshness-gated in CI).
Extension plugins depend on Service Definitions, never concrete providers. dsh-agent-loop is swappable; UI, hook, and tool plugins use dsh-agent. Composition bundles, including dsh-agent-spine-demo, may depend on spine plugins. Capabilities separate Service Definition / Service provider / Consumer roles when they evolve independently; see capability seams.
Package READMEs cover purpose, APIs, extension points, and Model Experience unless on the model-agnostic omission allowlist. They also carry ## Known Limitations and Deferred Work or use its allowlist.