Commit Graph

1294 Commits

Author SHA1 Message Date
kingwl
9aaa4a871f policy: reject out-of-range seed boundaries; carry baselines through session-query
Review fixes (ds-review-bot on #623):

- overrideOf (both knobs) rejects a seedLength past the log end before
  slicing: a malformed durable boundary would otherwise empty the
  own-switch slice until the log outgrew it, letting a wide baseline
  shadow a REAL later tightening. Malformed durable metadata fails loud,
  never open.
- The session-query derived index carries the two baseline fields end to
  end: schema columns on both session tables (SESSION_QUERY_SQLITE_SCHEMA
  _VERSION 6 — derived, rebuilds in place), inserts, header selects, the
  candidates CTE, rowHeader, sameHeader, and the cross-source
  assertSessionHeadersCompatible — so a search hit's header keeps the
  child's inherited confinement and conflicting live/persisted baselines
  reject.

Red-first: out-of-range seedLength tests in both policy suites;
baseline round-trip and live/persisted baseline-conflict tests in the
session-query sqlite suite.
2026-07-26 23:31:01 +08:00
kingwl
99f5fab7bc policy: scope seed-boundary slicing to delegation children
Review fix (ds-review-bot on #623): the unconditional slice regressed the
public SessionStore.fork path — a generic fork child gets seedLength but no
policy baseline, so slicing discarded its seed-carried sandbox/approval
switches and silently widened it to the deployment defaults (a forked
read-only/never parent produced a workspace-write/ask child).

overrideOf now branches on baseline presence: with a header baseline (a
delegation child) the fold covers only own post-seed switches — the
baseline captured from the parent's FULL log subsumes seed history; without
one, the whole log — seeded switches ARE the replayed inherited truth. The
permission preset fold scopes the same way. Red-first: generic-fork
seed-carried override tests in both policy suites.
2026-07-26 23:06:15 +08:00
Tianyi Cui
d167af3fb7 Merge branch 'master' into worktree-tasks-service-seam 2026-07-26 22:57:38 +08:00
Tianyi Cui
c50b899015 refactor(llm-deepseek): replace hand-rolled SSE parser with eventsource-parser
Implements the approved simplification Agent Note: sse.ts now pipes the
response body through TextDecoderStream and EventSourceParserStream
(eventsource-parser/stream) and keeps only the DeepSeek protocol shim —
yield each event's data, terminate on [DONE], throw
LlmError('STREAM_CLOSED') on EOF without the sentinel. The SSE
spec-conformance tests are deleted; sse.spec.ts pins only the
[DONE]/STREAM_CLOSED/EOF contract, including the new spec-strict verdict
that an unterminated trailing event is truncation (the old parser
flushed it — a robustness nicety no real provider shape needs).

eventsource-parser@^3.1.0 becomes llm-deepseek's second runtime
dependency (already in the lockfile transitively via the MCP SDK).

Docs: the Agent Note moves proposed/ → implemented/ and is rewritten per
the lifecycle contract; the rejected NIH roll-up note's inbound links
follow. The twin-adapters note, dsh-llm LlmAdapter JSDoc (and its
type-equiv fences), cookbook, group/package READMEs, root AGENTS.md
layout line, sdk-helper comments, and the regenerated config catalog
drop the "hand-rolled fetch + SSE" claim in both languages; all eight
touched pairs re-recorded.
2026-07-26 22:45:33 +08:00
Tianyi Cui
e2882f486b fix(review): harden web replay verification
Validate replay sidecars and cross-copy failure facts, make browser console tripwires and macOS temp paths deterministic, and wait for asynchronous TUI resume details. Keep the owning docs, translations, and generated catalog aligned.
2026-07-26 22:38:33 +08:00
Tianyi Cui
1b9d66eaac Merge branch 'worktree-process-service-seam' into worktree-subprocess-consumers
# Conflicts:
#	docs/core-data-structures/subprocess.md
#	packages/subagent/subagent-subprocess/README.md
#	packages/subprocess/README.md
#	packages/subprocess/subprocess-local/README.md
#	scripts/translation-pairing.manifest.json
2026-07-26 22:04:14 +08:00
kingwl
f505bd9258 policy: resolve every knob consumer through the shared override chain
Review fixes (ds-review-bot warnings on #623):

- One chain, every consumer: the override resolution (own post-seed
  switches ?? header baseline, closed-vocabulary validated) moves into pure
  exports (sandboxOverrideOf / approvalOverrideOf); the services delegate,
  and the permission presets consume them — current(session) and set()
  now see inherited baselines, so a child inheriting danger-full-access
  gets REAL knob switches when workspace-write is selected instead of a
  silent no-op, and a seed-carried preset selection is subsumed by the
  baseline. current(events) becomes current(session) (pre-release; the
  only callers were tests).
- Unconditional durable validation: a malformed header baseline fails
  loud on every read, no longer shadowed by an own switch.
- The two policy peers are declared optional (peerDependenciesMeta), so a
  thin spawn/fork deployment without policy plugins can consume the
  driver; verify-runtime-closure honors the flag.

Red-first: inherited-preset derive/switch-away and seeded-selection tests
in the permission suite; malformed-baseline-with-own-switch tests in both
policy suites.
2026-07-26 22:02:02 +08:00
Tianyi Cui
d3dc2b9fab Merge branch 'code-mode-ui/live-parallel' into code-mode-ui/dispatch-spill
Conflict resolution: scripts/type-equiv.manifest.json takes master's new
paired-derivative format (one primary entry per pair) and re-adds this
stack's CodeDispatchLog entry in that format. zh README pairs brought
along for the dispatch-log arm (spill-policy behavior/limitations bullets,
tools limitation bullet now pointing at the shipped bounding).
2026-07-26 21:35:03 +08:00
Tianyi Cui
709ac6b531 Merge branch 'master' into web-e2e-interactions 2026-07-26 21:29:34 +08:00
Tianyi Cui
fc38f8c813 Merge branch 'master' into code-mode-ui/live-parallel 2026-07-26 21:04:03 +08:00
Tianyi Cui
202582d600 Merge branch 'worktree-tasks-service-seam' into worktree-process-service-seam
# Conflicts:
#	packages/bash/bash-local/README.md
#	scripts/doc-budgets.manifest.json
#	scripts/type-equiv.manifest.json
2026-07-26 20:55:58 +08:00
Tianyi Cui
c3394d3012 Merge remote-tracking branch 'origin/master' into worktree-tasks-service-seam
# Conflicts:
#	packages/tasks/README.md
#	packages/tasks/tasks/README.md
#	scripts/translation-pairing.manifest.json
2026-07-26 20:28:37 +08:00
Tianyi Cui
c3c10820ba fix(tools): bound the shaped-append side channel; total error containment; recorded spill snapshot
Responding to ds-review-bot round 2 on #661:

- logWork is bounded: past maxParallelSubCalls pending shaped-append tasks
  the ordered commit lane holds (Promise.race drains one), so a slow spill
  backend backpressures the run instead of accumulating unbounded pending
  I/O and retained results. Tasks self-remove on settlement; run
  settlement still drains every task inside the open turn. New spill test
  drives three oversized reads against a hung backend at cap 1 and proves
  the third dispatch cannot start until a save drains.
- shapeDispatchLog's catch uses errorMessage() (total), so a thrown value
  with a throwing toString cannot escape the containment and lose the
  settle event.
- CodeDispatchLog.content documented as the RENDERED result projection
  (native tool/result vocabulary), not what the program received — the
  program gets the structured value; doc pair + type-equiv re-synced.
- New RECORDED tui-agent snapshot scenario code-mode-dispatch-spill: the
  real Loader-visible composition (worker runtime + spill-local + policy)
  drives an oversized bash sub-call end-to-end; replay proves the durable
  dispatch copy is bounded to preview + locator while the program value
  stays whole (the outer result carries just the line count).

Agent Note updated (both languages).
2026-07-26 18:29:09 +08:00
kingwl
e8d8589219 Merge remote-tracking branch 'origin/master' into feat/telemetry-otel-plugin
Resolutions: regenerate docs/capability-seams.md (the only conflict);
master widened the bilingual pairing scope to package READMEs, so this
merge adds the Chinese counterparts and i18n records for the three
telemetry READMEs and patches packages/README.zh.md with the telemetry
group row.
2026-07-26 16:58:35 +08:00
Tianyi Cui
3672cd25b4 feat(subprocess): migrate lsp-local, subagent-acp, and the env scrubs onto the seam
Review direction (tianyicui, PR #660): in a stacked PR, change all other
process-running places to use the new service.

- lsp-local: LspConnection spawns through ctx.subprocess (piped protocol
  streams + a no-spill collected stderr tail); its private process-tree
  helpers (POSIX group signalling, Windows taskkill, liveness polling) are
  deleted in favor of the seam's handle verbs, and its buildChildEnv now
  rides scrubbedParentEnv (LSP children also stop inheriting stale DSH_*).
  The plugin injects 'subprocess'; compositions/tests mount
  dsh-subprocess-local.
- subagent-acp: the ACP child spawns through the seam (piped ndjson streams,
  inherited stderr); spawn failure surfaces through done-rejection into the
  same startup race; disposal is handle.dispose with the plugin's configured
  graces. dsh-subagent-subprocess is DELETED — its dispose ladder and scrub
  are the seam's, and the isolated-config-dir helper had no consumer.
- mcp-client, pty-local, sdk-helper: adopt scrubbedParentEnv as the one
  scrub definition (their spawns stay put by ownership: the MCP SDK and
  node-pty own those calls; the SDK wizard runs outside any composition).
- Coverage: per-file 100% over every touched src file, with each v8 ignore
  carrying a platform or contract reason; new suites cover stdio
  dispositions, the dispose ladder tiers, injected-win32 tree semantics,
  waitForExit, settled-kill/terminate no-ops, and spawn-failure disposal.
- Docs: consumer-migration Agent Note (en; zh follows in this PR), seam note
  updated in place, subprocess.md rewritten for the reshaped vocabulary
  (type-equiv re-registered), READMEs and SERVICE_ROLES updated, taskkill
  added to knip ignoreBinaries.
2026-07-26 15:27:59 +08:00
Tianyi Cui
f936fea4a1 Merge remote-tracking branch 'origin/master' into web-e2e-interactions 2026-07-26 14:19:06 +08:00
Yichen Jiang
8c77ba6420 Merge remote-tracking branch 'origin/master' into worktree/web-model-request-retry 2026-07-26 14:09:43 +08:00
Yichen Jiang
a430207427 feat(web): retry transient model requests 2026-07-26 14:09:31 +08:00
Yichen Jiang
65aaf2eb98 Merge branch 'master' into worktree/llm-reasoning-effort 2026-07-26 14:03:34 +08:00
Yichen Jiang
15d6f4c085 feat(llm-deepseek): expose off as a dynamic reasoning effort 2026-07-26 13:42:02 +08:00
Tianyi Cui
ded5d01c6c docs: regenerate catalogs and register CodeDispatchLog type-equiv on this tree
The static CI gates run per-branch on the merged tree: the cordis
catalog/api, config-catalog, and type-equiv manifest updates for the
tools/code-dispatch-log waterfall and CodeDispatchLog payload previously
landed only on the shiki branch (09734f23b); this branch's own tree needs
the same regenerated outputs and manifest entries.
2026-07-26 13:40:02 +08:00
imccyu
0fe9ff888d Merge origin/master into worktree-websettings
ui-sidebar shell landed on master (#643: geometry-only shell, the
browsing region moved to the sidebar.workspaces slot); this branch's
sidebar.settings foot seat re-applies on top — the hardcoded foot row
becomes the seat, the seat rides the railIn crossfade, and the shell
spec's renderSlot stub key-splits region vs settings.
2026-07-26 13:15:57 +08:00
Yichen Jiang
eeab643ad9 Merge remote-tracking branch 'origin/master' into worktree/llm-reasoning-effort
# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/config-catalog.md
2026-07-26 13:13:31 +08:00
Yichen Jiang
73e7e27799 refactor(llm): resolve model metadata together 2026-07-26 13:07:27 +08:00
imccyu
fabc843c22 docs(gui): regenerate graphs for the returning ui-settings-general package 2026-07-26 12:48:30 +08:00
Tianyi Cui
fc566119a7 refactor(subprocess): rename the process seam to subprocess and address review
Review feedback (tianyicui): 'process' is a poor service name. The family is
now packages/subprocess/ — @deepseek-ai/dsh-subprocess (ctx.subprocess,
abstract SubprocessService, Subprocess* vocabulary) and
@deepseek-ai/dsh-subprocess-local (LocalSubprocessService) — renamed
throughout code, compositions, docs (en+zh, pairs re-recorded), catalogs,
and gates. 'subprocess' is the precise term for managed OS children (the
Python-stdlib sense), avoids colliding with Node's global process object,
and reads as one system beside dsh-subagent-subprocess.

ds-review-bot findings addressed:
- kill() on a settled handle is now a no-op (no signal to a possibly-reused
  pgid, no referenced grace timer delaying exit); pinned by a spy test.
- The moved DshEnvironmentKey/DshEnvironment/CollectedOutput types get
  drift-checked type-equiv blocks on the new subprocess.md page, restoring
  their manifest registration.
- subprocess.md is registered in the core.md sub-page index (en+zh).
2026-07-26 12:43:59 +08:00
Tianyi Cui
5bf4d573f7 fix: address review — staged scheduler, start-time reclassification, catalogs
ds-review-bot findings on the parallel bridge: sub-dispatches now run
through the registry's staged scheduler view (the loop's own seam) —
ordered prepare (pre-execute/guards) at submission-ordered start time,
only the dispatch/body stage overlapping, and a head-of-line commit
cursor running post-execute, context deferral, and the settle event in
submission order (new spec pins post order + context order under
out-of-order completion). Queued dispatches reclassify via
executionMode() immediately before starting, so a registry mutation
while queued flips them exclusive (native lazy-reclassification
semantics). Config and tool catalogs regenerated; the tool-catalog
metadata now names the start/settle pair and the scheduling contract.
2026-07-26 10:33:48 +08:00
Tianyi Cui
4987261d55 feat(spill): bound the durable copy of Code Mode sub-dispatch results
New tools/code-dispatch-log waterfall (run via registry.shapeDispatchLog,
contained — a throwing listener falls back to the unshaped content) lets
listeners reshape the tool/code-dispatch event's content before the
bridge appends it. dsh-spill-policy registers a second arm sharing the
model-facing arm's exact replacement pipeline (same maxInlineBytes cap,
preview + locator, within-cap invariant, best-effort fallbacks), with
artifacts labeled dispatch under the sub-call id. The program's value is
untouched; read sub-calls ARE bounded (a log copy is not model context,
and read produces the biggest logs). Resolves the tools README's
uncapped-dispatch-log Known Limitation.
2026-07-26 09:01:03 +08:00
Tianyi Cui
0d6bfd8856 refactor(process): split the process manager out of the bash executor
New process/ capability family: @deepseek-ai/dsh-process owns ctx.processes —
abstract ProcessManager.spawn(spec) over a fully-explicit ProcessSpawnSpec —
plus the shared DSH_* managed-environment and CollectedOutput vocabulary;
@deepseek-ai/dsh-process-local carries the former bash-local run.ts plumbing
(detached groups, tail-keep spill-backed output, credential scrub, kill
escalation, kill-and-join disposal) with no config of its own.

dsh-bash-local becomes a consumer: it keeps command defaulting, the fused
deadline timedOut/aborted classification, the model-friendly terminal env
(now merged through the ordinary env channel), and the [stderr]-marked
background read merge, and spawns through ctx.processes. Background-process
lifetime moves to the manager, so an executor reload no longer kills live
background work; a background spawn failure is injected once into the read
path instead of being buffered as fake stderr. dsh-bash re-exports the moved
vocabulary so bash consumers keep one import root; dsh-bash-sandbox only
redeclares the inherited inject.

Every composition loading a bash executor now loads dsh-process-local (CLI,
examples, python bundled runtime, create-sdk bash feature, inline test
configs).
2026-07-26 06:59:01 +08:00
Tianyi Cui
698b391bd6 refactor(tasks): split the task registry into seam and local implementation
The tasks/ family now matches the capability-seam shape: @deepseek-ai/dsh-tasks
keeps the abstract TaskService (ctx.tasks contract, vocabulary types, snapshot
invariant companion) and the new @deepseek-ai/dsh-tasks-local carries the
process-local registry (LocalTaskService: in-memory store, settlement,
owner-cleanup effects, teardown, TASK_WAIT_TIMEOUT). Compositions and test
harnesses now load dsh-tasks-local; producers, TaskKindMap merges, and
dsh-tool-tasks keep importing the seam only.

Producer misconfiguration diagnostics name dsh-tasks-local because loading the
implementation is the fix. The registry behavior suite moves to tasks-local;
the seam keeps a stub-subclass registration test and the probe-based invariant
suite.
2026-07-26 05:13:39 +08:00
Tianyi Cui
07770f90f9 Merge remote-tracking branch 'origin/master' into web-e2e-interactions
# Conflicts:
#	.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.i18n.yaml
#	.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md
#	.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.zh.md
#	apps/web/tests/scaffold.ts
2026-07-26 04:10:37 +08:00
Tianyi Cui
90d91c3cf9 docs(llm-replay): cover the patches form in the overrideFile contract
The ReplayConfig.overrideFile JSDoc still described only whole-script
replacement; it now names both sidecar forms and links ReplayOverrideDoc
(config catalog regenerated: source line shifted).
2026-07-26 03:31:21 +08:00
Tianyi Cui
2e52c0670c feat(llm-replay): indexed override patches for error injection
The override sidecar now accepts { patches: [{ at, entry }] } alongside the
legacy whole-script ReplayEntry[] replacement: the JSONL-derived script is
kept and only the named call indexes are swapped (at == length appends, for
a retry attempt following an injected transient throw). Out-of-range or
non-integer indexes fail loud with the derived length in the diagnostic.
This is the mock-LLM error capability the web e2e scenarios drive: 'call N
throws AUTH/SERVER, everything else replays as recorded'.
2026-07-26 03:26:41 +08:00
imccyu
a3ee5dd8a0 docs(gui): regenerate graphs and sync the note's English pair
Generated docs follow the ui-models rename and the removed
ui-settings-general package; the English note side picks up the
feature-owner self-registration doctrine.
2026-07-26 02:54:29 +08:00
Tianyi Cui
a07d727cba Merge latest master into codex/consolidate-agent-notes 2026-07-26 02:11:13 +08:00
Turtle
61eb2014a2 Merge remote-tracking branch 'origin/master' into codex/provider-retry-policy
# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/config-catalog.md
#	packages/support/llm-replay/README.md
2026-07-26 01:40:19 +08:00
Turtle
19a1aec89e refactor(llm-retry): simplify policy history validation 2026-07-26 01:16:41 +08:00
Tianyi Cui
cd15711079 Merge latest master into codex/consolidate-agent-notes
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-21-tui-no-banner.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-21-tui-no-banner.md
#	.agents/notes/implemented/feature/2026-07-21-tui-no-banner.zh.md
#	.agents/notes/implemented/simplification/2026-07-20-retire-readline-front-door.i18n.yaml
#	.agents/notes/implemented/simplification/2026-07-20-retire-readline-front-door.md
#	.agents/notes/implemented/simplification/2026-07-20-retire-readline-front-door.zh.md
2026-07-26 00:57:51 +08:00
imccyu
b1b180e098 fix(gui): CI gate repairs — docs, coverage, HMR re-registration
Regenerate the module-graph/config-catalog/event-graph docs for the
locale rename and new packages; allowlist the three settings READMEs;
complete the RFC code block and add its English pair. Cover the
ThemeService media-query paths (stubbed matchMedia) and mark the
unreachable registry fallback. General section re-registration now
judges presence on the slot ledger instead of a local disposer, which
went stale when an HMR collapse removed the entry.
2026-07-26 00:57:21 +08:00
Tianyi Cui
674d916ef8 Merge branch 'master' into worktree/llm-mock-fault-server 2026-07-26 00:45:44 +08:00
Tianyi Cui
882bd4a591 Merge origin/master into web-e2e-lane
# Conflicts:
#	tsconfig.host.json
2026-07-26 00:16:12 +08:00
Tianyi Cui
8af3d2461b Merge branch 'master' into worktree/dsh-arg-parser 2026-07-26 00:05:16 +08:00
Yichen Jiang
5446714177 Merge branch 'master' into worktree/llm-mock-fault-server 2026-07-25 22:27:29 +08:00
Yichen Jiang
478376acaf Merge remote-tracking branch 'origin/master' into worktree/llm-reasoning-effort
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml
#	docs/architecture.i18n.yaml
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/session.i18n.yaml
#	docs/event-producer-consumer.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
2026-07-25 22:24:25 +08:00
Hypatia May
729485216d Merge remote-tracking branch 'origin/master' into session-query-tool
# Conflicts:
#	docs/capability-seams.md
#	packages/host/runtime/README.md
#	packages/host/runtime/package.json
#	packages/host/runtime/src/boot.ts
#	packages/host/runtime/tests/host-runtime.spec.ts
#	packages/host/runtime/tsconfig.json
#	pnpm-lock.yaml
2026-07-25 18:27:39 +08:00
Tianyi Cui
ee25ccf38b Merge remote-tracking branch 'origin/master' into web-e2e-lane
# Conflicts:
#	vitest.web.config.ts
2026-07-25 18:19:22 +08:00
Turtle
e996aabf47 Merge branch 'master' into worktree/dsh-arg-parser
Integrate the Commander adapter with master's `dsh web --workspace-root`
(workspace-aware session flow).

- args.ts: add `--workspace-root <path>` to the web subcommand; WebInvocation
  carries workspaceRoot.
- web.ts: keep the adapter-parsed signature, take (host, port, dev,
  workspaceRoot) and pass workspaceRoot through to AppCLIEntry (drop master's
  re-added parseArgs and CLI host/port validation — the schema owns those).
- bin.ts forwards invocation.workspaceRoot; args.spec + the Agent Note pair note
  the flag.
2026-07-25 18:05:39 +08:00
Turtle
17147df200 Merge remote-tracking branch 'origin/master' into codex/consolidate-agent-notes 2026-07-25 18:00:37 +08:00
Turtle
2243023575 Merge branch 'master' into worktree/dsh-arg-parser
Integrate the Commander adapter with master's headless rework (dsh -p now boots
through AppCLIEntry — the same cordis.yml composition as dsh web, web-observable
while it runs — via toFetchHandler(ctx.apiProxy)).

- headless.ts: keep master's AppCLIEntry-based body but take the adapter's
  pre-parsed `task` (drop the re-added parseArgs). Old startHost path and the
  now-deleted packages/host/runtime dependency are gone.
- remove the stale packages/host/runtime dir left on disk by master's deletion
  (mirrors the earlier packages/ui/acp cleanup).
2026-07-25 17:48:21 +08:00
imccyu
9eb9c70a8a feat(web): add workspace-aware session flow 2026-07-25 17:45:26 +08:00