Commit Graph

54 Commits

Author SHA1 Message Date
Tianyi Cui
a30660a63f 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
2026-07-14 15:26:34 +08:00
Tianyi Cui
2ef709a496 Merge branch 'codex/simp-session-log-representation' into codex/simp-snapshot-fixture-inventory 2026-07-14 15:25:36 +08:00
Tianyi Cui
443526285e Merge branch 'codex/simp-session-dead-surface' into codex/simp-session-log-representation
# Conflicts:
#	docs/persistence-catalog.md
#	packages/bash/bash/src/session-mode.ts
2026-07-14 15:25:26 +08:00
Tianyi Cui
7e9bf9b951 refactor: remove impossible ACP drain branch 2026-07-14 15:06:33 +08:00
Tianyi Cui
2027c70a17 fix: drain failed ACP launches 2026-07-14 12:38:32 +08:00
Tianyi Cui
85a1bbc7d5 Merge branch 'codex/simp-snapshot-fixture-inventory' into codex/simp-shared-acp-test-launcher 2026-07-14 12:36:59 +08:00
Tianyi Cui
287041e39e fix: preserve malformed snapshot fixtures 2026-07-14 12:35:25 +08:00
Tianyi Cui
795371a209 Merge branch 'codex/simp-snapshot-fixture-inventory' into codex/simp-shared-acp-test-launcher
# Conflicts:
#	examples/acp-agent/tests/acp.e2e.ts
#	examples/acp-agent/tests/escalation.e2e.ts
#	examples/acp-agent/tests/hooks.e2e.ts
#	packages/support/acp-snapshot/src/harness.ts
2026-07-14 11:53:45 +08:00
Tianyi Cui
fd5ee06a97 Merge branch 'codex/simp-session-log-representation' into codex/simp-snapshot-fixture-inventory 2026-07-14 11:49:56 +08:00
Tianyi Cui
4d5fb2cb1d Merge branch 'codex/simp-session-dead-surface' into codex/simp-session-log-representation
# Conflicts:
#	docs/core-data-structures/session.md
#	docs/rfc/implemented/feature/2026-07-06-sandbox.md
#	examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md
#	examples/sandbox-acp-agent/tests/acp.snapshot.ts
#	examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl
#	packages/core/session/README.md
#	packages/core/session/src/index.ts
#	packages/core/session/src/surface.ts
#	packages/core/session/tests/surface.spec.ts
#	scripts/type-equiv.manifest.json
2026-07-14 11:49:46 +08:00
Tianyi Cui
a50e8bc1f3 Merge remote-tracking branch 'origin/master' into codex/model-experience-readmes-20260712
# Conflicts:
#	packages/bash/bash-sandbox/README.md
#	packages/sandbox/sandbox-local/README.md
2026-07-14 11:28:08 +08:00
Tianyi Cui
3e2ba3f557 fix: stop ACP teardown when fallback kill fails 2026-07-14 10:13:05 +08:00
Tianyi Cui
a8c0e8a03c test: cover successful ACP cleanup failure 2026-07-14 09:55:15 +08:00
Tianyi Cui
6b59b6050e fix: preserve ACP scenario cleanup failures 2026-07-14 09:43:12 +08:00
Tianyi Cui
d4c96deac3 refactor: share ACP callback cleanup 2026-07-14 09:19:02 +08:00
Tianyi Cui
e784e4dce5 fix: await ACP client callbacks during shutdown 2026-07-14 09:12:32 +08:00
Tianyi Cui
0b492e6e62 fix: drain ACP test launcher streams 2026-07-14 07:22:22 +08:00
Tianyi Cui
e2a5a160d3 fix: settle ACP update waiters on shutdown 2026-07-14 07:00:10 +08:00
Tianyi Cui
140d32681e fix: make ACP test teardown failure-safe 2026-07-14 06:33:22 +08:00
Tianyi Cui
60ce23d77c fix: surface ACP launcher spawn failures 2026-07-14 06:07:37 +08:00
Tianyi Cui
9028c9b63b fix: contain ACP update predicate failures 2026-07-14 05:35:34 +08:00
Tianyi Cui
e3d7bb62d8 fix(permission): address human review feedback 2026-07-14 01:09:44 +08:00
Tianyi Cui
f0cad87492 Merge branch 'codex/simp-snapshot-fixture-inventory' into codex/simp-shared-acp-test-launcher 2026-07-14 00:49:27 +08:00
Tianyi Cui
6ad4b4fa42 fix: let snapshot recording create fixture inventory 2026-07-14 00:46:46 +08:00
Tianyi Cui
0e7d539bbc refactor: share the ACP test launcher 2026-07-14 00:18:00 +08:00
Tianyi Cui
e481288a3a refactor: derive snapshot session fixtures from disk 2026-07-14 00:04:11 +08:00
Tianyi Cui
1123e946c0 refactor: simplify session log representation 2026-07-13 23:56:10 +08:00
Tianyi Cui
7195d9eda2 docs: gate concise model experience summaries 2026-07-13 15:47:46 +08:00
Tianyi Cui
a08485fc80 Merge remote-tracking branch 'origin/codex/package-readme-limitations-audit-20260712' into codex/model-experience-readmes-20260712
# Conflicts:
#	docs/cookbook/adding-a-package.md
#	docs/rfc/INDEX.md
#	package.json
#	packages/AGENTS.md
#	packages/bash/bash-sandbox/README.md
#	packages/sandbox/sandbox-local/README.md
#	packages/sandbox/sandbox/README.md
#	packages/session-persistence/session-persistence-sqlite/README.md
#	packages/support/acp-snapshot/README.md
#	packages/ui/app-boot/README.md
#	packages/ui/user-approval/README.md
#	packages/workflow/tool-workflow/README.md
2026-07-12 02:48:49 +08:00
Tianyi Cui
027970043c docs: document package model experience 2026-07-12 02:12:36 +08:00
Tianyi Cui
9efdcce747 Merge remote-tracking branch 'origin/worktree-agent-scope-design' into codex/package-readme-limitations-audit-20260712 2026-07-12 01:46:59 +08:00
Tianyi Cui
ecb8aa5b8e Add a gated Known Limitations and Deferred Work section to every package README
Every packages/*/* README now carries a canonical '## Known Limitations and
Deferred Work' section: condensed, evidence-backed bullets for consumer-visible
gaps (unimplemented features, platform caveats, MVP cuts) and consciously
postponed work (TODO/FIXME/XXX markers, RFC deferrals still open). The ten
pre-existing ad-hoc variants ('What is NOT here (TODO)', 'Deferred',
'Limitations (MVP)', 'Known limitations (tracked TODOs)', ...) are normalized
into the canonical heading.

A new doc-sync gate, scripts/verify-readme-limitations.ts, enforces the shape:
exactly one limitations-like heading per package README, byte-equal to the
canonical h2, with at least one bullet; near-miss headings fail so variants
cannot creep back. Packages with genuinely nothing to declare (dsh-brand,
dsh-timeout, dsh-subagent-mock, dsh-app-boot) are whitelisted in the script and
must NOT carry the section; whitelist entries are validated against the scanned
package set so a rename fails loud.

Wired into the doc-sync chain (package.json) and the run-gates doc-sync leaf
set; the standing rule lands in packages/AGENTS.md and the adding-a-package
cookbook; decision record in
docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md
(RFC index regenerated).

Also fixes two stale '(deferred)' markers claiming dsh-compact-basic is
unimplemented (the dsh-compact seam README's package table and the seam's
module doc comment).
2026-07-12 01:46:34 +08:00
Tianyi Cui
bac97a5b2e test(acp-snapshot): cover the delta-insert trailing-newline branch
formatSystemPromptSnapshot's insert-join ternary had its already-newline-
terminated arm unexercised (a delta whose insert ends in a blank line),
failing the per-file 100% branch gate on suite.ts (99.24%).
2026-07-11 23:55:56 +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
3baaecc078 Merge remote-tracking branch 'origin/master' into codex/skill-system
# Conflicts:
#	docs/rfc/INDEX.md
#	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/README.md
2026-07-11 22:31:28 +08:00
Tianyi Cui
9339622d3b test(acp): snapshot system prompts as Markdown 2026-07-11 22:24:20 +08:00
Tianyi Cui
1e2d8014a5 Merge remote-tracking branch 'origin/master' into feat/sandbox-support
# Conflicts:
#	packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts
2026-07-11 21:43:10 +08:00
Yichen Jiang
386d4d3ec4 Merge branch 'master' into codex/skill-system 2026-07-10 22:58:15 +08:00
kingwl
ca39fd89b0 feat(example): sandbox-acp-agent — the live composition; RFCs to implemented
The three-entry cordis.yml (dsh-sandbox-local + dsh-bash-sandbox at a
read-only default + dsh-approval) served over ACP: the first live approval
composition. Recorded snapshot scenarios pin the wire end to end —
config-options advertisement, the mode-switching arc as the suite pinned
header (both switches, the prompt-section delta, one changed-by-the-user
notice per knob, a confined write landing under the switched mode), and
both escalation branches over scripted permissionAnswers (a grant runs
confined under workspace-write; a rejection executes nothing and pins the
fail-closed text). The with-key escalation e2e drives a real model +
real runner + the real bridge answerer, world-verified; ci.yml snapshot
lane and e2e.yml install bubblewrap so the confined replays actually
execute.

Both RFCs move to implemented/ (Decision/Consequences form, deferred
phases tracked in their own sections), with every cross-reference flipped.
2026-07-10 15:44:38 +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
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
Tianyi Cui
af242dbae5 Preserve snapshot refresh seed boundaries 2026-07-10 01:04:06 +08:00
Tianyi Cui
9d2cf8ce82 Add keyless snapshot refresh mode 2026-07-10 00:48:27 +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
2da28e89eb Merge remote-tracking branch 'origin/master' into code-mode-tools
# Conflicts:
#	examples/AGENTS.md
#	examples/README.md
#	package.json
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
2026-07-09 22:58:58 +08:00
Tianyi Cui
673f20c990 Merge remote-tracking branch 'origin/master' into code-mode-tools
# Conflicts:
#	docs/event-producer-consumer.md
#	packages/support/acp-snapshot/tests/suite.spec.ts
2026-07-09 11:06:50 +08:00
Yichen Jiang
0d023b9aaa Merge remote-tracking branch 'origin/master' into agent-request-messages 2026-07-08 22:26:25 +08:00
Yichen Jiang
77333c0a19 fix(agent): correct session-prefix composition-order docs; scrub messagePrefix in snapshots
Two ds-review-bot findings:

The seam JSDoc claimed extending 'await next()' composes in
registration order — false for the append form: the waterfall unwinds
innermost-first, so appending places later-registered contributions
first. The canonical contribution is now documented as the PREPEND
'[mine, ...await next()]' (registration order on the wire), with the
append form's reverse-order behavior stated explicitly; the ordering
test now uses the canonical pattern in both listeners.

scrubRequestHeaders tokenized only system/tools, so a fixture recording
a composed session prefix would carry its raw text (workspace-specific
churn/leak). The scrubber now maps each header/delta messagePrefix
entry to a {{messagePrefix}} token — count stays a structural fact,
absence stays absent, the empty-array transition stays visible — with
normalize.spec coverage for the header, delta, absence, and odd-shape
paths.
2026-07-08 16:16:08 +08:00
Tianyi Cui
35ef649716 Merge branch 'code-runtime-worker' into code-mode-tools
Brings in the refreshed base (master merged through the stack after #203
and #205 landed), including the acp-snapshot extraction (#204), and
re-ports this PR's snapshot-suite extensions onto the extracted package:

- dsh-acp-snapshot's Scenario gains headerClass and configPath; the suite
  factory pins the request header PER CLASS (construction rejects a
  missing or duplicated class pin), forwards a scenario's configPath to
  the harness (RunOptions.configPath overrides AgentUnderTest.configPath),
  and a new fixtures meta-test asserts every pinning fixture carries
  exactly one request/header and no deltas.
- The acp-agent example's thin scenario table re-registers code-mode-turn
  and both-mode-turn with their overlay configs and per-class pins; the
  committed fixtures replay unchanged.
- The package's synthetic suites cover the new surface (explicit
  headerClass on one suite, the default on the other, a configPath
  override through the fake bin, and the two construction throws).
2026-07-08 15:55:29 +08:00
kingwl
93d5e4c560 test(acp-snapshot): replace the authored-implies-override guard with an explicit overridden flag 2026-07-08 14:24:20 +08:00