Commit Graph
23 Commits
Author SHA1 Message Date
Yichen Jiang 680ae53bb6 Merge remote-tracking branch 'origin/master' into codex/skill-system
# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/module-graph.md
#	docs/rfc/INDEX.md
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/core/agent-core/src/index.ts
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
#	packages/support/acp-snapshot/src/suite.ts
#	packages/ui/acp-agent/src/index.ts
2026-07-10 14:43:33 +08:00
Yichen Jiang 6292d52236 feat(skill): move catalogs into session prefixes 2026-07-10 14:19:06 +08:00
Yichen Jiang b9bf67d0a7 Merge remote-tracking branch 'origin/master' into codex/skill-system 2026-07-09 23:11:10 +08:00
Tianyi Cui 19fc33f172 Merge remote-tracking branch 'origin/master' into code-mode-tools
# Conflicts:
#	docs/config-catalog.md
#	docs/module-graph.md
#	docs/tool-catalog.md
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
#	packages/ui/acp-agent/package.json
#	pnpm-lock.yaml
#	scripts/gen-tool-catalog.ts
2026-07-09 21:10:40 +08:00
Yichen Jiang 56091d5b5d fix review findings: keep ask-user opt-in for acp app 2026-07-09 00:42:36 +08:00
Yichen Jiang f453ba77a2 refactor: split skill providers 2026-07-08 15:50:38 +08:00
Tianyi Cui b59d245c7c feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge
The dsh-tools half of the Code Mode RFC (its fourth, final change): the
registry gains its first config — mode: native | code | both — and OWNS how
its tools reach the model. 'code' contributes exactly one wire tool,
run_code, plus a lazy tools:sdk prompt section declaring every other tool
as a generated TypeScript API (jsonSchemaToTs: total over the defineTool
subset, unknown degradation, lexicographic byte-identical rendering);
'both' ships both representations; 'native' is byte-for-byte the old
behavior. Non-native modes fail every assembly loudly without a
typescript-language ctx.codeRuntime.

run_code's dispatch bridge: JSON-normalizes each binding argument before
dispatch (what dispatches is what the tool/code-dispatch event logs — the
append can never fail on payload shape; BigInt/circulars reject that one
call), serializes all program tool calls through a per-run queue (even
Promise.all — no concurrency-safety metadata yet), routes every sub-call
through tools/pre-execute → tools/post-execute (a deny rejects the
program-side promise), drops sub-call additionalContext (no safe outlet
mid-run; pinned), owns a run-scoped abort that follows the outer signal in
and fires on settlement (in-flight sub-dispatch aborted, queued abandoned,
queue drained before returning), and converts a failed run into
CodeRunFailedError → a structured isError carrying kind + captured logs.
tool/code-dispatch joins SessionEventMap by declaration merging (log-only;
deriveMessages ignores it).

The composed surface: the tools config forwards through agent-core and
both app packages; examples/code-agent + demo:code run the worker runtime
under mode code (keyless boot smoke + a with-key e2e proving the collapsed
[run_code] header, the dispatch events, and the file the program wrote);
two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK
section, collapsed header, dispatch events, and result card — each its own
header-pinning class (the harness gains per-scenario config overlays and
per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the
RFC (moved to implemented/, restructured to decision-era headings) updated
in the same change.
2026-07-08 12:58:23 +08:00
Yichen Jiang d3f86996f7 Merge remote-tracking branch 'origin/master' into codex/ask-user-question
# Conflicts:
#	docs/config-catalog.md
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	pnpm-lock.yaml
2026-07-08 11:09:20 +08:00
imccyu 42e7a2f691 fix: add tools reorder to system prompt 2026-07-07 11:03:11 +08:00
Yichen Jiang 545b2775db Merge remote-tracking branch 'origin/master' into codex/skill-system
# Conflicts:
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/rfc/README.md
#	packages/core/agent-core/package.json
#	packages/core/agent-core/src/index.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/index.ts
#	packages/ui/acp-agent/src/index.ts
#	packages/ui/acp-agent/tests/acp-agent.spec.ts
#	packages/ui/stdio-agent/README.md
#	packages/ui/stdio-agent/src/index.ts
#	packages/ui/stdio-agent/tests/stdio-agent.spec.ts
2026-07-06 10:09:26 +08:00
Yichen Jiang 7d7c4a3c16 Merge remote-tracking branch 'origin/master' into codex/ask-user-question
# Conflicts:
#	docs/rfc/README.md
#	packages/ui/acp-agent/src/index.ts
2026-07-06 10:08:58 +08:00
Tianyi Cui 3f83a4ee96 review: the persona becomes the system-prompt plugin's deployment config
Review round 2 (tianyicui inline comments):

- dsh-system-prompt itself registers the harness:identity (-100) and
  deployment:persona (0) sections — they must survive a swapped loop
  plugin, so they leave dsh-agent-loop; the persona text is the plugin's
  own validated 'persona' config. The model/cwd variables STAY on the
  loop: runtime facts of the agents it drives.
- AgentOptions.systemPrompt is deleted with all its forwarding plumbing:
  the app configs' systemPrompt keys become 'persona' routed through
  dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge
  and tool-subagent stop carrying persona configuration, and subagent
  children now render the deployment persona like every other agent.
- Example personas drop transport/interface trivia (ACP, CLI) — facts
  irrelevant to the model.
- Root CONTEXT.md removed (not idiomatic); its persona definition was
  wrong under the new ownership anyway.
- Docs, READMEs, the prompt-variables RFC, and generated catalogs
  updated; new loop test pins the assemble-waterfall escape valve
  (an emptied assembly sends NO system field).
2026-07-05 23:23:46 +08:00
Yichen Jiang c7a833a893 fix: simplify skill config wiring 2026-07-05 21:05:43 +08:00
Yichen Jiang dca2cc257d fix: harden skill discovery 2026-07-05 18:33:27 +08:00
Yichen Jiang ff8d38a9a8 Merge remote-tracking branch 'origin/master' into codex/ask-user-question
# Conflicts:
#	docs/architecture.md
#	docs/cordis-catalog/events-and-services.md
#	docs/core-data-structures/core.md
#	docs/module-graph.md
#	docs/tool-catalog/tools.md
#	packages/README.md
#	packages/core/README.md
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
#	packages/support/README.md
#	packages/support/ui-stdio/README.md
#	packages/ui/acp-agent/tests/built-bin.e2e.ts
#	packages/ui/acp/README.md
#	packages/ui/stdio-agent/README.md
#	packages/ui/stdio-agent/package.json
#	packages/ui/stdio-agent/src/index.ts
#	packages/ui/stdio-agent/src/stdio-chat.ts
#	packages/ui/stdio-agent/tests/built-bin.e2e.ts
#	packages/ui/stdio-agent/tests/readline.spec.ts
#	packages/ui/stdio-agent/tests/stdio-chat.spec.ts
#	packages/web/web/package.json
#	packages/web/web/tsconfig.json
#	pnpm-lock.yaml
#	scripts/gen-tool-catalog.ts
2026-07-05 17:05:33 +08:00
Tianyi Cui 4a0941fb4b feat(ui): share the app bins' boot glue in @deepseek-ai/dsh-app-boot
The four near-twin helpers the two published bins carried — loadEnv,
installFailLoud, assertEntriesLoaded, boot — live once in
packages/ui/app-boot, parameterized by the bin's diagnostic prefix and
injectable at their side-effect seams (warn sink, process slice), so
every branch sits under the per-file 100% coverage gate: the unit suite
drives boot() in-process against the real Loader (relative-specifier
configs) through both the settled-tree path and the fiber-less-entry
rejection, and exercises the ENOENT/unloadable .env split, the
Error/non-Error/stackless fail-loud arms, and the disabled-entry
exclusion. resolveConfigPath (snapshot-aware) becomes the single path
resolver for both bins.

Each bin.ts is now a thin self-executing composition plus its
app-specific lifecycle (acp: replay env-skip + stdin-EOF dispose;
stdio: nothing extra), exports nothing, and stays coverage-excluded;
the built-bin smokes still prove both artifacts under plain node in the
node_modules-shaped temp dir (now symlinking ui/app-boot), including
the missing-config non-zero exit.

Implements docs/rfc/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md
(moved from proposed/ and amended); the extract-example-app-packages
RFC's bin-ownership facts are amended in the same change.
2026-07-04 16:43:06 +08:00
Yichen Jiang 03e3c430be Merge remote-tracking branch 'origin/master' into codex/ask-user-question
# Conflicts:
#	docs/cordis-catalog/events-and-services.md
#	docs/module-graph.md
#	docs/rfc/README.md
#	packages/README.md
#	packages/ui/README.md
#	packages/ui/acp/tests/harness.ts
2026-07-01 18:49:25 +08:00
Tianyi Cui 0478f5965a docs: address review sync gaps 2026-07-01 12:56:13 +08:00
Yichen Jiang 51700d4685 Fix ask_user_question review findings 2026-06-29 10:49:07 +08:00
Tianyi Cui 4d7726ecd3 fix review findings: don't treat disabled entries as load failures; scope the verify-package-paths lib skip to a real package root
assertEntriesLoaded() flagged ANY fiber-less entry as a failed import, but a
`disabled: true` entry settles without a fiber by design (Entry.refresh() skips
init() when disabled) — a valid "plugin off" config, not a broken import. Both
app bins now filter `fiber === undefined && !entry.disabled`. The stdio built-bin
smoke gains a disabled-(unresolvable)-entry config that must still boot.

The verify-package-paths lib-skip was unconditional and ran before the
moved-package check, so a stale group-less `packages/acp-agent/lib/bin.js` (the
exact drift this gate catches) was silently ignored just for containing `lib`.
Scope the skip: only exempt `lib` when it is the segment after an EXISTING
`packages/<group>/<pkg>` root, so a real-but-unbuilt `lib/bin.js` is still exempt
while a stale package path flags.
2026-06-21 19:47:22 +08:00
Tianyi Cui 3567808171 fix review findings: harden the app bins + built-bin smokes, arch-exception doc, snapshot fixture-guard
BLOCKER — the published lib/bin.js (stdio + acp) was exercised only via tsx
(demo:* / the src/bin.ts smokes); the built artifact under plain `node` was
unguarded. Root-cause on the BUILT bin:
  1. Settle race: boot() returned once loader.create() registered the include
     ENTRY, but the include loads its child plugins asynchronously — so boot()
     (and main()) resolved while the app plugins (stdin reader, agent loop, ACP
     bridge) were still mounting. A CLI with no attached handles yet exits 0
     silently, and a load error surfaces as an unhandled rejection AFTER boot.
     Fix: `await ctx.loader.await()` after create() — settle the whole tree.
  2. Config-path robustness: hand the include the config's ABSOLUTE file:// URL
     so resolution never depends on ctx.baseUrl / can never fall back to cwd.
Both bins fixed identically. NOTE: the cordis Loader resolves a config's bare
plugin specifiers via its internal module loader, active only under
`node --expose-internals`; the bin cannot add a node flag itself, so this is
documented in the bin JSDoc + both package READMEs (the demos already comply).
The repo `examples/*/cordis.yml` are tsx-only artifacts (workspace plugins
resolve through the tsconfig paths map, not node_modules), so they are not a
valid plain-node bin target — the smokes use a real-install-shaped temp dir.

Fail loud on a load failure: boot() previously exited 0 SILENTLY when a config
path's directory does not exist — the include plugin fails to IMPORT, the cordis
Loader catches+LOGS it and leaves the entry with no fiber (no rejection), and
`loader.await()` does not rethrow (EntryTree.await uses Promise.allSettled). Fix:
boot() now calls assertEntriesLoaded(ctx) after the tree settles and throws on
any entry with no fiber, so a typo'd config dir exits non-zero with a clear
message. main() also installs an unhandledRejection guard (installFailLoud) that
replaces Node's stack dump with a single labelled stderr line for the
companion case (a missing config FILE in a real dir, whose include-init throw
surfaces as a rejection Node already exits non-zero on). Regression tests added
to both built-bin smokes (missing dir + missing file → non-zero exit + stderr);
verified the missing-dir test fails on the pre-fix bin.

Built-bin smokes (the reviewer's ask): packages/ui/{stdio,acp}-agent/tests/
built-bin.e2e.ts run the REAL lib/bin.js under `node` (NOT tsx) in a temp
consumer dir, asserting the stdio echo round-trip / the acp initialize response
+ stdout purity, plus the fail-loud cases above. They build-gate (skip if lib/
absent) and run in a new ci.yml step after the build.

Issue 2 — packages/README.md + docs/architecture.md said "plugins depend on
interfaces, never on the concrete loop", but dsh-agent-core imports the concrete
dsh-agent-loop. Scope the rule to EXTENSION plugins and carve out the sanctioned
COMPOSITION/bundle exception (dsh-agent-core composes the concrete spine); note
it in the implemented RFC too.

Issue 3 — examples/acp-agent/tests/acp.snapshot.ts fixture-guard claimed
no-model scenarios need no session.jsonl, but runScenario() always boots
llm-replay with the session.jsonl path and loadReplayScript() throws when it is
absent. Require session.jsonl for ALL scenarios (no-model ones ship a
header-only fixture) and rewrite the comment to match reality.
2026-06-21 15:39:24 +08:00
Tianyi Cui bfc5a9097d fix review findings: soften the last stdout-purity overclaim in the acp-agent module doc
The acp-agent README/RFC overclaim was already softened; this module doc comment
still said the footgun is "structurally unreachable from the leaf". A leaf
cordis.yml CAN still add a sibling @cordisjs/plugin-logger-console — the app does
not prevent it. Reword to the accurate claim: the app gives the default front
door no logger entry to misconfigure, and the "never add a stdout logger to an
ACP leaf" rule still stands.
2026-06-21 13:08:11 +08:00
Tianyi Cui e2bde2902c refactor(examples): extract the app spine into dsh-agent-core + app packages
Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each
example was thick — a hand-rolled start.ts, an infra preamble, nested
base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door
cluster enforced only by prose. This moves the composition into packages so
each example is a thin leaf cordis.yml: pick the swappable backends, load one
app package.

New packages:
  - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin
    that loads the providerless/executor-less/UI-less spine (timer + llm +
    sessions + system-prompt + tools + agents + invariants + tool-bash +
    agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's
    `agents` list as its own Config (export const Config = AgentLoop.Config,
    default []).
  - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP —
    agent-core + console logger + readline UI + a pre-created `main` agent, with
    a bin. The demo:echo/coding front door.
  - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP —
    agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a
    bin. The stdout-purity footgun is structurally unreachable from the leaf.

Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into
dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without
--expose-internals; the in-process test tier can't even import its decorator
form), so a package statically importing it could never carry the per-file
coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity
footgun, so leaving it at the leaf costs no safety. With hmr out, all three new
packages carry in-process unit specs at 100%.

Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose
lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/
acp-tail.yml are deleted. Each app package gets a keyless real-load-path test
that boots through its bin + the cordis Loader (guarding the unwrapExports
export-shape bug class, postmortem 0001). ACP snapshot replay stays green
against the existing committed goldens (pure boot restructuring). RFC moved
proposed->implemented with the amendment recorded; package/example/architecture
docs and the module graph updated.
2026-06-21 12:06:38 +08:00