Commit Graph

343 Commits

Author SHA1 Message Date
pku-xht
b38e02462b Merge commit '5427cbcc19cfd1ce9f3af1ae22207852cc5740fa' into codex/workflow-runs-chat-node-f6 2026-08-11 18:09:43 +08:00
Hypatia May
6c4ed5e036 test(snapshot): refresh pins after master merge 2026-08-11 14:45:14 +08:00
Hypatia May
7b8635d47d test(snapshot): refresh pins after master merge 2026-08-11 14:41:11 +08:00
Hypatia May
87f446ca62 test(snapshot): refresh pins after master merge 2026-08-11 14:37:44 +08:00
Hypatia May
bb11d72962 test(snapshot): refresh pins after master merge 2026-08-11 14:02:16 +08:00
Hypatia May
8d5223bd1a test(snapshot): refresh pins after master merge 2026-08-11 13:58:36 +08:00
Hypatia May
e673a125bd test(snapshot): refresh pins after master merge 2026-08-11 13:54:51 +08:00
Hypatia May
c2261bad05 test(snapshot): refresh fork schema pins after master merge 2026-08-11 13:23:43 +08:00
Hypatia May
8d9b71d50a test(snapshot): refresh fork schema pins after master merge 2026-08-11 13:17:40 +08:00
Hypatia May
41790845e9 test(snapshot): refresh fork schema pins after master merge 2026-08-11 13:10:25 +08:00
Hypatia May
48dd924eda Merge branch 'feat/subagent-settlement-delivery' into feat/subagent-list-agents-vocabulary 2026-08-11 13:02:40 +08:00
Hypatia May
9340604ea5 Merge branch 'feat/subagent-report-semantics' into feat/subagent-settlement-delivery 2026-08-11 13:02:22 +08:00
Hypatia May
dbcbdfa9ce Merge commit '7baf2c33efb98eeea690c5ac58579c95dc52edd1' into feat/subagent-report-semantics 2026-08-11 13:01:29 +08:00
Hypatia May
567fcadba0 fix(subagent): report resumable children as ready
list_agents called a storage-only continuable child 'complete', inviting
parents to poll it for a result that will never appear there. Rename the
status to 'ready' — resumable, not terminal — and rewrite the tool
description to say a parent is told when a child finishes, so listing is
for recall, not polling.
2026-08-11 12:38:57 +08:00
Hypatia May
85dd22fd4f feat(subagent): deliver continuable child settlement to parents
A continuable child that stopped without reporting — an error, a token
ceiling, cancellation, teardown — left its parent nothing to act on.
The continuation manager now delivers an unconditional settlement
notice to the durable direct parent before releasing ownership, folding
consumed work (foldConsumedWork supersedes findLastMessageTurnEnd) so a
claimed-but-unrun prompt reads as aborted rather than completed, waking
an idle parent, steering a busy one, and never waking a closing tree.
2026-08-11 12:31:49 +08:00
Turtle
a9852a2b5b Merge pull request #2152 from deepseek-harness/codex/remove-source-installer
cleanup: simplify source execution around pnpm dsh
2026-08-11 12:07:29 +08:00
Hypatia May
76cf6cbd0b feat(subagent): make final reports the continuable return contract
A continuable child could finish without giving its parent a usable
result: the report tool was described as optional and its default
delivery stayed quiet. Install the child-scoped report obligation (tool
description plus the tool:report prompt section), default reportDelivery
to wakeup, bind shipped subagent_fork delegations to one-shot so fork
keeps its prefix reuse, and extend the ACP snapshot harness to pin child
system prompts alongside child tool schemas.
2026-08-11 11:50:39 +08:00
creatixchu
5265fd084d fix(snapshot): use rescoped Cordis package 2026-08-11 11:23:49 +08:00
creatixchu
9186824e87 feat(session): refuse session logs a build cannot faithfully read
Old runtimes meeting a newer session format now fail loud instead of
misreading: version refusal names the direction (newer: upgrade the
harness; older: no upgrade path) and points at the raw JSONL log, and an
event type outside the generated known vocabulary refuses resume unless
its envelope carries the new ignorable: true marker (default: required,
so a forgotten marker over-refuses instead of silently resuming a gutted
session). gen-persistence-catalog now also emits
KNOWN_SESSION_EVENT_TYPES; SQLite stores the marker in a dedicated
column (SCHEMA_VERSION 15). The versioning design (monotonic integer,
n->n+1 upgrader chain, migrate-on-continue) is recorded in the
session-log-version-mechanism Agent Note.
2026-08-11 11:23:48 +08:00
Turtle
ee9465e4b3 build before source dsh launch 2026-08-11 11:22:08 +08:00
Turtle
d4ccfbd80f refactor(cli)!: complete app-owned profile startup 2026-08-10 23:45:04 +08:00
Hypatia May
29c00d59a5 Merge remote-tracking branch 'origin/master' into fix/continuable-subagent-policy-inheritance
# Conflicts:
#	packages/subagent/subagent-inprocess/package.json
#	packages/subagent/subagent/package.json
#	pnpm-lock.yaml
2026-08-10 22:24:56 +08:00
imccyu
ec601ca13d build(vendor): rescope the vendored Cordis packages into @deepseek-ai
Machine-produced by `pnpm run rescope-vendor --apply` plus the regeneration it
prints: `pnpm install` for the lockfile, `pnpm run gen-third-party-notices`,
`verify-translation-pairing --write` for the touched bilingual pairs,
`gen-doc-graphs`, and one typert snapshot whose ids embed character offsets.
`pnpm run rescope-vendor --check` verifies the result.

Renames nine vendored packages (cordis, cosmokit, schemastery and the six
@cordisjs plugins) and every reference that resolves them: manifest names and
dependency keys, module specifiers including declare-module merges, cordis.yml
plugin names, tsconfig paths, every Markdown fence, and `docs/` prose.
Directory names, upstream versions, and dependency ranges are unchanged, so
vendor/README.md still reads as an upstream snapshot; its manifest table gains
an upstream-name column so THIRD_PARTY_NOTICES keeps MIT attribution pointed
at each fork's origin.

The tutorial tier follows the rename end to end: its yaml fences named plugins
the Loader can no longer resolve, its `ts ignore-check` fences disagreed with
the compiled fences beside them, and its prose quoted both. The contracts that
told readers to keep upstream names — the root convention and the vendoring
cookbook's tree comment and manifest invariant — now say to rescope instead.

Two rules read `@deepseek-ai/` as "another workspace plugin": the client bundle
purity gate now names the vendored libraries a browser bundle inlines, and the
files where a bare `cordis` is an agent-preset id keep that product data.
2026-08-10 22:04:13 +08:00
Hypatia May
76061417d9 Merge remote-tracking branch 'origin/master' into fix/continuable-subagent-policy-inheritance
# Conflicts:
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
2026-08-10 22:02:36 +08:00
Turtle
993550e6c8 refactor: remove repository plugin path 2026-08-10 21:32:13 +08:00
pku-xht
4eb0a52840 fix(workflow): close review and snapshot gaps 2026-08-10 19:25:21 +08:00
Hypatia May
501c3a8ab6 fix(subagent): pin delegated child approvals to 'never' within the inherited sandbox scope
A delegated in-process child now acts only within the sandbox scope fixed
at delegation: captureDelegatedPolicyOverrides still snapshots the parent's
explicit sandbox override but pins the child approval policy to 'never'
(instead of inheriting the parent's), so every child ask — sandbox_permissions
escalations included — is rejected deterministically by ApprovalService
before any answerer, with the audit pair still logged. Every in-process
child additionally receives the scoped subagent:delegation runtime-context
statement telling it to report a scope limitation instead of retrying.

Supersedes the approval half of the policy-inheritance decision (new Agent
Note cross-linked from both prior notes and the approval-seam Q&A); refreshed
child snapshot fixtures carry the pinned event, and
subagent-published-run-failure now persists a one-event child log.
2026-08-10 19:17:37 +08:00
Turtle
a27efdef36 docs: make technical prose concrete 2026-08-10 16:34:20 +08:00
Turtle
a7fc81d745 docs: replace front door terminology 2026-08-10 13:07:46 +08:00
Tianyi Cui
25dcd7293c docs: purge chain-of-thought leakage from prose
Delete design-session citations (decision/audit/plan ordinals, stack
positions), change narration, review choreography, and reviewer-addressed
justification from comments, JSDoc, docs, READMEs, Agent Notes, tests, and
generator templates; restate every affected fact as current-state contract
prose. Fix generated docs at their sources and regenerate the catalogs and
cordis-surface regions; re-paste type-equiv blocks; update every bilingual
counterpart and re-record the pairs. Record the citation rule in the
committed-artifact-citations Agent Note.
2026-08-09 21:10:59 +08:00
imccyu
522acc7432 test: update conversation assembly coverage and docs 2026-08-09 18:16:44 +08:00
Turtle
2f3821c232 Merge remote-tracking branch 'origin/master' into codex/concrete-provenance-prose 2026-08-09 15:51:40 +08:00
Turtle
9704749b01 docs: replace vague provenance prose with recorded facts 2026-08-09 15:35:02 +08:00
fz
57c9e077ce Merge remote-tracking branch 'origin/master' into codex/fix-deepseek-keepalive
# Conflicts:
#	.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml
#	examples/headless-agent/tests/fixtures/deepseek-defaults.cordis.yml
#	packages/llm/llm-deepseek/README.i18n.yaml
#	packages/util/timeout/README.i18n.yaml
2026-08-09 15:00:08 +08:00
Tianyi Cui
63b6e18f71 fix(headless): terminal model failures reach stderr 2026-08-09 13:44:44 +08:00
Tianyi Cui
9d5eb37638 fix(headless): dsh run is a direct core front door 2026-08-09 13:44:44 +08:00
Turtle
76b3353452 docs: call waterfall interception short-circuiting 2026-08-09 13:13:37 +08:00
xjt
acf75a8af3 Merge origin/master into xjt/incremental-proofreading-275-apply 2026-08-09 12:17:59 +08:00
Tianyi Cui
c8e0b0f3a7 test(repository-plugin): update keyless prepare fixture 2026-08-09 11:41:40 +08:00
Tianyi Cui
e00ec8e2aa test(repository-plugin): refresh prepared wrapper fixture 2026-08-09 11:41:40 +08:00
Tianyi Cui
033fa4b0b1 feat(repository-plugin): load trusted package code 2026-08-09 11:41:40 +08:00
Tianyi Cui
a9af1a33f0 test(repository-plugin): update prepared fixture metadata 2026-08-09 11:41:40 +08:00
xjt
5d46c11784 docs(i18n): reconcile source-drifted translations 2026-08-09 10:24:11 +08:00
Tianyi Cui
10fc9405c7 docs(e2b): re-home the overlay section on master's README
Master rewrote the headless README around the profile CLI and removed
cli-demo; the replay had resurrected the old body. The branch's claim is
the E2B overlay section alone, now inserted into master's text with the
credential-gated live composition e2e as the runnable instruction (the
config-file demo runner no longer exists).
2026-08-08 22:19:14 +08:00
Tianyi Cui
d488330ba4 fix(rebase): migrate the replayed E2B branch onto the rebased parent
The linear replay carried old-lineage content over parent-owned files;
this checkpoint restores them and adapts the branch to the parent's
post-rebase seam:

- restore all pty/lsp/subprocess/code-runtime surfaces to the parent's
  exact content (this branch claims none of them) and drop the net-zero
  code-runtime-e2b/pty-e2b/lsp-e2b residue and its registrations
- widen serializeRemoteEnvironment to the seam's NodeJS.ProcessEnv
  tombstone contract: an explicit undefined removes an ambient entry
- migrate the two E2B fixture Agent stubs to the Inbox-model interface
  and Session.create
- re-apply the branch's gen-doc-graphs roles, THIRD_PARTY_NOTICES e2b
  row, and packages/README group row (trimmed to the doc budget);
  regenerate catalogs and re-record bilingual pairings
2026-08-08 22:19:13 +08:00
Tianyi Cui
6e1ae76c9b test(e2b): satisfy the steer() receipt signature in Agent stubs
Master's steering-receipt API (agent.steer returns SteeringReceipt) reached
this branch through the parent sync; the two E2B live-fixture Agent stubs
return the same rejected-outcome receipt the pty test stubs use.
2026-08-08 22:19:13 +08:00
Tianyi Cui
f5866fc202 fix(e2b): address review round on cadence config, disposal, and SDK edge cases
- subprocess-e2b: the 20 ms remote poll cadence becomes a validated pollMs
  Config field (each tick is one control-plane request); the README documents
  the latency-versus-request-count trade.
- subprocess-e2b: extract src/remote.ts owning asError, signalOpts,
  commandOpts, delay, waitTick, and one tolerant signalRemoteGroups shared by
  the pgid-keyed process ladder and sid-keyed terminal ladder, so the two
  teardown paths keep identical error tolerance.
- subprocess-e2b: service disposal aggregates sibling cleanup failures into
  one AggregateError instead of discarding all but the first.
- subprocess-e2b: waitForProcessGroupId refuses published group ids <= 1, so
  a same-UID rewrite of the pid file cannot aim termination at kill -- -1;
  README documents the same-UID control-state limitation.
- subprocess-e2b: drain-grace expiry now releases an inherited-output E2B
  callback blocked on host backpressure before disconnecting, so the SDK
  settlement cannot stay pinned behind an unread host stream.
- subprocess-e2b: spawn/spawnTerminal stop validating typed spec fields
  (trust-TypeScript rule; pty-local validates its config before specs exist);
  resolveExecutable rejects separator-containing relative paths per the seam
  contract; terminal setups tracked as a Set of records.
- subprocess-e2b: PTY output push-without-backpressure is a documented
  contract (flowing consumer folds bytes; paused consumer buffers).
- fs-e2b: streamText normalizes the pinned SDK's empty-file '' return into an
  empty stream instead of throwing on getReader().
- e2b overlays: comment the one-world cwd invariant across e2b.cwd,
  workspaceRoot, and bash-local's implicit default workdir.
2026-08-08 22:19:13 +08:00
Tianyi Cui
26b18ba189 refactor(e2b): keep code runtime host-local 2026-08-08 22:19:13 +08:00
Tianyi Cui
de77310c6f refactor(e2b): narrow the sandbox POC 2026-08-08 22:19:13 +08:00
Tianyi Cui
bb0be75d85 refactor(e2b): drop obsolete host sandbox overlay 2026-08-08 22:19:12 +08:00