Commit Graph

52 Commits

Author SHA1 Message Date
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
Turtle
dda02250f5 docs: reserve seam for complete capabilities 2026-08-09 17:26:57 +08:00
Tianyi Cui
a29f55881e Merge remote-tracking branch 'refs/remotes/origin/master' into worktree/retarget-pr961-20260808
# Conflicts:
#	.agents/notes/implemented/bug-fix/2026-07-27-stable-snapshot-refresh-volatiles.i18n.yaml
#	.agents/notes/implemented/bug-fix/2026-07-27-stable-snapshot-refresh-volatiles.zh.md
#	apps/web/tests/scaffold.ts
#	examples/tui-agent/tests/tui.snapshot.ts
#	packages/support/acp-snapshot/README.i18n.yaml
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/README.zh.md
2026-08-08 01:49:04 +08:00
Dudu-0223
431fb4b035 feat(subagent): add explicit child reports 2026-08-02 12:51:10 +08:00
Tianyi Cui
eb51d4c669 fix(acp-snapshot): retain unchanged message ids 2026-07-30 15:41:16 +08:00
Tianyi Cui
9c78a7df33 test(snapshot): share identical header sidecars 2026-07-28 17:26:03 +08:00
Tianyi Cui
8a7bb03aab fix(persistence): reconcile project session layout 2026-07-25 15:11:17 +08:00
Tianyi Cui
c09397f833 Merge branch 'master' into codex/session-directory-layout 2026-07-25 14:53:20 +08:00
Tianyi Cui
74d14f68bb fix(acp): accept baseline resource links and release a failed prompt slot
ACP v1 requires every agent to accept text AND resource_link prompt
content; the automation rewrite dropped the resource_link half of that
baseline. Restore the old bracketed-reference flattening in the codec,
reject only beyond-baseline blocks, and update the package contract and
Agent Note.

Also release the per-session prompt slot when agent.send() throws
synchronously (an agent disposed outside the bridge would otherwise
wedge the session into permanent 'already in flight' rejections),
drop the tautological version-negotiation branch, prove the scenario
env layer reaches the snapshot subprocess, pin bridge-side fail-closed
permission errors, and correct two overpromising test names.
2026-07-24 22:11:49 +08:00
Turtle
4e295221f3 refactor(persistence): group sessions in project directories 2026-07-24 19:52:47 +08:00
Tianyi Cui
e819a586b0 refactor(acp): reduce bridge to automation protocol 2026-07-24 01:40:25 +08:00
Tianyi Cui
ad4c37013a test(snapshot): await cancelled turn durability 2026-07-22 22:00:48 +08:00
Tianyi Cui
c1f259bd0d Merge branch 'master' into feat/plan-mode 2026-07-22 11:29:58 +08:00
Tianyi Cui
b024ebabed Merge origin/master into worktree-windows-runtime
# Conflicts:
#	.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md
#	packages/support/acp-snapshot/src/harness.ts
#	packages/support/acp-snapshot/src/normalize.ts
#	packages/support/acp-snapshot/tests/harness.spec.ts
#	packages/support/acp-snapshot/tests/normalize.spec.ts
2026-07-21 17:14:44 +08:00
Tianyi Cui
3947312432 Merge remote-tracking branch 'origin/master' into codex/pr239-parent-retarget-publish
# Conflicts:
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
2026-07-21 00:58:16 +08:00
Tianyi Cui
0246806fec Merge origin/master into feat/plan-mode 2026-07-20 23:28:07 +08:00
Tianyi Cui
30d2ec4a95 Merge branch 'codex/goal-commands' into codex/ralph-tool
# Conflicts:
#	examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json
#	scripts/gen-tool-catalog.ts
2026-07-20 21:05:05 +08:00
Tianyi Cui
78eb93f7e6 Merge branch 'master' into worktree-windows-runtime 2026-07-20 20:39:13 +08:00
Tianyi Cui
07058e527c fix(snapshot): isolate concurrent spill roots 2026-07-20 18:32:21 +08:00
Tianyi Cui
9b28ad785f test(acp-snapshot): emit current session headers 2026-07-20 18:17:25 +08:00
Tianyi Cui
41d3e78d3a test(snapshots): require explicit delegation depth 2026-07-20 17:59:13 +08:00
Tianyi Cui
46d60d6d90 fix(tool-subagent): enforce depth only at runtime 2026-07-20 17:58:57 +08:00
Yichen Jiang
f2a813b791 Merge remote-tracking branch 'origin/master' into fix/subagent-depth-budget 2026-07-20 15:15:31 +08:00
imccyu
3e9cb70c78 Merge remote-tracking branch 'origin/master' into worktree-windows-runtime
# Conflicts:
#	packages/session-persistence/session-persistence-jsonl/README.md
#	packages/session-persistence/session-persistence-jsonl/src/index.ts
#	packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts
#	packages/support/loader-smoke/tests/loader-smoke.spec.ts
2026-07-19 17:52:36 +08:00
Tianyi Cui
0893aaa7cb test: rename golden snapshot files to expected 2026-07-19 17:45:49 +08:00
Yichen Jiang
b0dc299508 Merge remote-tracking branch 'origin/master' into fix/subagent-depth-budget
# Conflicts:
#	examples/acp-agent/tests/acp.snapshot.ts
2026-07-19 17:42:52 +08:00
Yichen Jiang
d231f30024 test(acp-snapshot): cover the child-omission branches synthetically
The childToolOmissions comparison arms ran only through the examples
snapshot suites, which the unit coverage gate does not count. Add an
authored child-omission scenario to the synthetic replay suite: one
scripted child omits the declared tool (header pin minus the omission,
prompt pin skipped), one keeps the full set (pin and prompt compared
verbatim), restoring 100% branch coverage on suite.ts.
2026-07-19 17:34:10 +08:00
Tianyi Cui
a246afa33a test(acp-snapshot): detach the inherited-stdio fixture
Windows does not guarantee that an ordinary child process will continue after its parent exits. The fake ACP agent exited immediately after spawning its late-output descendant, so Windows could tear down that descendant and close the protocol stream before the delayed ACP update was written.

Launch the descendant in detached mode while continuing to inherit stdout and stderr, then unref it as before. This preserves the intended regression boundary: launcher shutdown must wait for descendant-held stdio and parse the final buffered frame after the direct ACP parent exits.
2026-07-19 14:14:00 +08:00
Tianyi Cui
97f9ec7c19 test(acp-snapshot): inherit descendant pipes portably
Use Node's explicit inherit stdio mode for the fake descendant instead of passing the parent process stream objects as child descriptors.

This keeps the grandchild's stdout and stderr handles open across the fake ACP parent's exit on Windows, so launcher shutdown must drain the late buffered update and stderr bytes just as it does on POSIX.
2026-07-19 13:29:31 +08:00
Tianyi Cui
d709a8a1a4 test(acp): await cancelled tool updates 2026-07-19 13:09:16 +08:00
Tianyi Cui
edaaa50fe3 test(acp): snapshot cancelled queued tool calls 2026-07-19 13:03:31 +08:00
Tianyi Cui
0f4bc645da test(acp-snapshot): inherit descendant stdio portably
Pass the fake descendant the parent process's stdout and stderr stream handles instead of Unix-style numeric file descriptors. This lets Windows duplicate the live ACP and diagnostic pipes so launcher shutdown can prove that inherited handles, buffered frames, and stderr all drain after the parent exits.

Observe the pending update promise before initiating shutdown as well, preventing a missing late frame from becoming a transient unhandled rejection before the assertion reports the fixture failure.
2026-07-19 12:42:59 +08:00
Tianyi Cui
df2432cae2 Merge branch 'codex/simp-snapshot-fixture-inventory' into codex/simp-shared-acp-test-launcher
# Conflicts:
#	examples/acp-agent/tests/escalation.e2e.ts
#	packages/support/README.md
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/harness.ts
#	packages/support/acp-snapshot/tests/harness.spec.ts
2026-07-18 11:58:15 +08:00
Tianyi Cui
ce393ccb93 Merge master into codex/simp-session-log-representation 2026-07-17 21:51:36 +08:00
Tianyi Cui
4ee880a189 Merge remote-tracking branch 'origin/master' into feat/plan-mode
# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	packages/README.md
#	packages/bash/tool-bash/src/index.ts
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
#	pnpm-lock.yaml
#	scripts/doc-budgets.manifest.json
2026-07-17 21:22:16 +08:00
imccyu
5039c4ae40 fix(snapshot): include agent stderr in failures 2026-07-15 23:57:44 +08:00
kingwl
1f38b211be Merge origin/master (generic task runtime #219, single-exe closure, package renames)
Semantic resolutions beyond line merges:
- The bash seam keeps resolveMode + the bash/resolve-mode waterfall on
  master's task-free BashExecutor (run/start/resolve only; BashProcess
  handles); tool-bash consults it at its stamping site and escalation
  baseline on master's render/background split, with a waterfall test on
  the recording executor.
- dsh-mode's BASH_FAMILY narrows to ['bash']: bash_output/bash_kill are
  replaced by the kind-generic task_output/task_kill, which span every
  task kind and only observe or stop work, so the access cap withholds
  only the starter it can reason about.
- The plan-mode snapshot suite adopts master's pin grammar (tool-schema
  sidecars; the expectedHeaderSnapshots extension is gone — the exit
  transition deltas, and entering-before-turn-1 needs no second
  snapshot); modes-advertise joins the plan header class (no-model, so
  membership is vacuous). Fixtures re-recorded on the acp-demo bin;
  the replay overlay gains the passthrough sandbox runner.
- examples/plan-acp-agent rewires to @deepseek-ai/dsh-acp-demo and drops
  its tool-bash entry (the spine bundle now composes it); dsh-stdio (the
  renamed stdio-chat home) keeps its /mode command and gains the dsh-mode
  peer edge; the acp bridge keeps the modes surface beside master's
  permission presets.
- mode README gains the Model Experience / Known Limitations sections the
  new README gates require; AGENTS.md ceiling 1370 → 1440 for the kept
  mode/ layout line and Agent efficiency section.
2026-07-15 23:17:18 +08:00
Tianyi Cui
2ae7f6ac3f Merge branch 'codex/simp-snapshot-fixture-inventory' into codex/simp-shared-acp-test-launcher
# Conflicts:
#	packages/support/README.md
#	packages/support/acp-snapshot/README.md
2026-07-15 16:04:40 +08:00
Tianyi Cui
281eed3e57 Merge remote-tracking branch 'origin/master' into codex/simp-session-log-representation
# Conflicts:
#	docs/cordis-catalog/services.md
#	docs/rfc/INDEX.md
#	docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md
#	docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/normalize.ts
#	packages/support/acp-snapshot/src/suite.ts
#	packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl
#	packages/support/acp-snapshot/tests/suite.spec.ts
2026-07-15 15:53:56 +08:00
Tianyi Cui
8ffcef7db9 test(snapshot): split pinned schemas into sidecars 2026-07-14 23:11:21 +08:00
Tianyi Cui
66c2996b36 Merge branch 'codex/simp-snapshot-fixture-inventory' into codex/simp-shared-acp-test-launcher
# Conflicts:
#	docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md
#	examples/acp-agent/tests/acp.e2e.ts
#	examples/acp-agent/tests/escalation.e2e.ts
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/harness.ts
#	packages/support/acp-snapshot/src/index.ts
2026-07-14 18:40:49 +08:00
Tianyi Cui
78276c52a7 Merge branch 'codex/simp-session-dead-surface' into codex/simp-session-log-representation
# Conflicts:
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.md
#	docs/persistence-catalog.md
#	docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md
#	docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md
#	docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md
#	docs/rfc/implemented/feature/2026-07-06-sandbox.md
#	docs/rfc/implemented/feature/2026-07-07-session-prefix.md
#	packages/compact/compact-basic/src/index.ts
#	packages/compact/compact-basic/tests/compact-basic.spec.ts
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent-loop/src/request-log.ts
#	packages/core/agent-loop/tests/request-reconstruction.spec.ts
#	packages/core/agent/src/types.ts
#	packages/core/session/README.md
#	packages/core/session/src/request-header.ts
#	packages/core/session/src/surface.ts
#	packages/core/session/src/tool-pairing.ts
#	packages/core/session/src/types.ts
#	packages/core/session/tests/surface.spec.ts
#	packages/core/session/tests/tool-pairing.spec.ts
#	packages/llm/llm/src/call-config.ts
#	packages/support/acp-snapshot/src/suite.ts
#	packages/support/invariants/README.md
#	packages/ui/user-approval/README.md
2026-07-14 18:34:34 +08:00
Tianyi Cui
0b492e6e62 fix: drain ACP test launcher streams 2026-07-14 07:22:22 +08:00
Tianyi Cui
1123e946c0 refactor: simplify session log representation 2026-07-13 23:56:10 +08:00
Tianyi Cui
148046b9c8 docs: rebalance prose cleanup and add trimming skill 2026-07-13 23:27:00 +08:00
kingwl
88db403d9f Merge branch 'worktree-session-modes-rfc' (master: sandbox stack #169, skills #109, prompt snapshots #254)
The stack rebases onto a moved master through its base branch. Beyond
mechanical unions (both branches' demo scripts, example rows, service
roles, tool lists, acp deps, doc budgets — each side fit alone, the
union needs the higher ceilings), three semantic reconciliations:

- The ACP bridge now carries BOTH per-session surfaces: the sandbox
  stack's config options + approval answerer and this branch's session
  modes; session/new and session/load advertise modes AND configOptions
  side by side.
- The feature matrix supersedes the sandbox stance per the RFC's
  second-lander rule: session/set_mode and current_mode_update flip to
  shipped-by-dsh-mode, config-option rows stay as #169 wrote them, and
  §6 records both landed features under the picker-to-modes /
  knobs-to-config-options division.
- The snapshot pin grammar (#254: one header snapshot + declared deltas
  + a Markdown prompt golden) gains a symmetric declaration for what a
  delta cannot express: expectedHeaderSnapshots — a plan-mode flip
  resorts the canonical tool list, so its widening lands as a second
  full snapshot, now its own Markdown section. The pin-less-class and
  model-turn-only-pin amendments carry over; new fixtures cover the
  extended writer paths, and the plan-acp-agent scenarios re-recorded
  under the merged composition (the app now bundles the skill tool)
  with the suite's refresh mode wired through.
2026-07-12 20:08:09 +08:00
Tianyi Cui
75838e10b5 docs: trim generated prose 2026-07-12 03:36:43 +08:00
Tianyi Cui
da9cef381c Merge remote-tracking branch 'origin/master' into codex/system-prompt-snapshots
# Conflicts:
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/support/acp-snapshot/src/suite.ts
2026-07-11 22:48:14 +08:00
Tianyi Cui
9339622d3b test(acp): snapshot system prompts as Markdown 2026-07-11 22:24:20 +08:00
kingwl
80d8726601 feat(acp): the bridge approval answerer + scripted permission answers
The ACP bridge registers the first real approval answerer: an ask for an
agent it owns becomes session/request_permission attached to the already-
streamed tool call (one-shot allow_once/reject_once only), outcomes map
conservatively (unknown optionId never grants, client cancel → cancelled),
and foreign or call-less requests delegate down the waterfall. The snapshot
harness accepts scripted permissionAnswers (FIFO; an unscripted prompt
answers cancelled, fail closed) so recorded scenarios can drive the wire
keylessly.
2026-07-10 15:43:02 +08:00