Commit Graph
5103 Commits
Author SHA1 Message Date
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
Tianyi Cui 73c7e3c276 Merge branch 'code-mode-ui/live-parallel' into code-mode-ui/dispatch-spill 2026-07-26 13:25:12 +08:00
Tianyi Cui 06556237f4 fix(tools): close scheduler coverage gaps; regen persistence catalog
The coverage gate flagged three untaken paths in the bridge scheduler:
- the exclusive-head inFlight re-check was dead (the shared guard above
  already returns for an exclusive head with any in-flight sibling) — removed;
- the commit-cursor undefined-dispatched break was structurally unreachable
  once entries join commitQueue only after start() ran synchronously —
  reordered the pump so the invariant holds by construction, annotated;
- the finish (final-result) commit arm and the pump re-entry guard gain a
  covering test (throwing tools/pre-execute listener) and a defensive
  annotation respectively; mid-run unregistration test renamed to match its
  actual post-result settlement path.

Also covers the direct-construction maxParallelSubCalls default (index.ts)
and commits the regenerated persistence catalog for the new dispatch pair.
2026-07-26 13:24:34 +08:00
Tianyi Cui a84acca298 Merge branch 'code-mode-ui/live-parallel' into code-mode-ui/dispatch-spill 2026-07-26 12:30:14 +08:00
Tianyi Cui 6333b51f2f Merge branch 'code-mode-ui/web-ui-v1' into code-mode-ui/live-parallel 2026-07-26 12:30:03 +08:00
Tianyi Cui 9bf0318690 Merge branch 'code-mode-ui/host-foundation' into code-mode-ui/web-ui-v1 2026-07-26 12:29:56 +08:00
Tianyi Cui 9785f0e2a0 fix: actually compact the cordis-dynamic fixture's request/header line
The previous hygiene fix re-serialized with json.dumps defaults (spaced
separators), leaving the line byte-identical; explicit compact
separators make the header-scrub guard pass.
2026-07-26 12:29:16 +08:00
Tianyi Cui 5780577dc8 Merge branch 'code-mode-ui/live-parallel' into code-mode-ui/dispatch-spill 2026-07-26 11:52:00 +08:00
Tianyi Cui fc2d65fa20 test(snapshots): refresh code/both-mode fixtures against the replay model pins
The re-records for the SDK-prompt change had harvested live v4-pro
headers while every replay overlay pins v4-flash, so keyless replay
diverged on provenance; keyless refresh reconciles the affected
scenarios (dispatch-start pairs preserved).
2026-07-26 11:51:32 +08:00
Tianyi Cui 7b58346b3c fix: address review — log shaping off the program-facing path
ds-review-bot finding: awaiting shapeDispatchLog before resolving the
binding let a slow spill backend delay the program and occupy a
dispatch slot. The settle now resolves the program immediately; the
shaped append runs as tracked side work (logWork) drained at run
settlement, so every tool/code-dispatch event still lands inside the
open turn. New spec pins the contract: with a hung spill backend the
second dispatch starts and the program completes both calls, and both
settle events land once released.
2026-07-26 10:40:03 +08:00
Tianyi Cui f02641e8e5 Merge branch 'code-mode-ui/live-parallel' into code-mode-ui/dispatch-spill
# Conflicts:
#	packages/core/tools/src/code-mode.ts
2026-07-26 10:38:50 +08:00
Tianyi Cui a786911293 fix: address review — non-vacuous error assertion, package contracts
ds-review-bot findings: the browser e2e's error-state check now requires
at least one error sub-row (was >= 0); the runtime README documents the
codeDispatches snapshot contract and the ui-conversation README the code
variant + nested sub-row semantics.
2026-07-26 10:36:35 +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 52f6de60d6 Merge branch 'code-mode-ui/live-parallel' into code-mode-ui/dispatch-spill 2026-07-26 10:21:50 +08:00
Tianyi Cui 86819ecbbb Merge branch 'code-mode-ui/web-ui-v1' into code-mode-ui/live-parallel
# Conflicts:
#	.agents/notes/implemented/feature/2026-06-15-code-mode.i18n.yaml
2026-07-26 10:21:01 +08:00
Tianyi Cui e542a89db7 Merge branch 'code-mode-ui/host-foundation' into code-mode-ui/web-ui-v1 2026-07-26 10:20:06 +08:00
Tianyi Cui 99a9fa8509 fix: address review — python smoke caller, contract prose, fixture header hygiene
ds-review-bot findings: the packaged Python runtime smoke's scripted
run_code call gains the required description; the ToolDefinition JSDoc
and the Code Mode foundation note (both languages, pair re-recorded) now
state both required parameters; the cordis-dynamic-toolchain fixture's
request/header line is re-compacted so the header-scrub hygiene guard
passes (my earlier patch had re-spaced it). The TUI terminal fixture was
already regenerated from keyless replay in the previous commit.
2026-07-26 10:18:53 +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 366419862f Merge branch 'code-mode-ui/web-ui-v1' into code-mode-ui/live-parallel
# 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/code-mode-workspace-context/session.jsonl
#	examples/tui-agent/tests/snapshots/code-mode/terminal.expected.txt
2026-07-26 08:59:36 +08:00
Tianyi Cui d0a45d9f2f Merge branch 'code-mode-ui/host-foundation' into code-mode-ui/web-ui-v1 2026-07-26 08:58:50 +08:00
Tianyi Cui abfc7b7ed1 test(snapshots): reconcile scripted run_code fixtures with the required description
The scripted (non-recorded) fixtures' run_code calls predate the required
description parameter, so replay rejected them at validation before any
dispatch: patch the scripted programs' args (tool/call, message blocks,
and chunk deltas together) and refresh goldens keylessly. Also picks up
the v4-pro re-records of the code-mode scenario pair whose live model
drifted from the overlay pin, and drops tmp-path churn.
2026-07-26 08:58:04 +08:00
Tianyi Cui 8a79679489 feat(tools): live dispatch lifecycle + native-contract parallel sub-calls in Code Mode
The bridge replaces its serialization queue with a pool that reuses the
native concurrency contract: submissions classify through
registry.executionMode (fail-closed isConcurrencySafe), start strictly in
submission order, overlap up to the validated maxParallelSubCalls config
(default 10; 1 restores serial), and exclusive calls drain the pool, run
alone, and bar later calls. Each started sub-call logs a
tool/code-dispatch-start event at pool entry; the existing
tool/code-dispatch settles the pair (started ⇔ settles exactly once;
abandoned queued calls log neither). SDK prompt guidance now states the
true Promise.all contract — re-recorded across every code/both-mode
snapshot (plus the stale cordis-dynamic-toolchain fixture gaining the
required description arg).

Client: CodeSubCall widens to RunningToolCall | ToolResultNode — starts
land the running shape (rows wear the native running ring), settles
replace in place preserving start order, callTime pairs to the start
time. Fixture emits start/settle pairs; jsdom pins the running sub-row;
runtime specs pin in-place settlement and out-of-order completion.
2026-07-26 06:02:36 +08:00
Tianyi Cui 526651cb88 docs(notes): finalize Chinese pair for the sub-call rows note 2026-07-26 04:24:13 +08:00
Tianyi Cui 13f7c62318 feat(web): render Code Mode sub-calls as native rows nested under the run_code row
The client indexes tool/code-dispatch events into
ConversationSnapshot.codeDispatches (parent callId -> ToolResultNode-shaped
sub-calls; live mux and history replay build the identical index). ChatView
renders each run_code parent as the new code variant (description summary,
program as the expanded monospace body) with its sub-dispatches as
always-visible indented rows — every sub-row dispatches through the SAME
keyed conversation.chat.toolview hole with the same GenericToolCard
fallback, so custom registrations (bash sample) take over sub-rows exactly
as top-level rows. The details panel resolves sub-callIds to full logged
args and complete output through the native path.

Evidence: fixture turn 64 + built-bundle jsdom snapshot, real-machinery
jsdom suites (nesting, error state, details, running parent, reference
stability), and a recorded code-mode browser e2e round (keyless replay +
aria golden). Scaffold gains a toolsMode patch knob.
2026-07-26 04:02:38 +08:00
Tianyi Cui 7f8c3cc6b8 docs(notes): add Chinese pair for the code-dispatch UI foundation note 2026-07-26 03:29:22 +08:00
Tianyi Cui d60dea9f55 feat(tools): run_code description param + native-parity dispatch logging + web code-mode seam
run_code gains a required bash-style description parameter: presentCall
titles the card with it and moves the program to rawInput, so every
surface gets a readable label. tool/code-dispatch now logs each
sub-call's complete content/isError (the tool/result vocabulary),
replacing the bounded resultSummary and deleting the summarize/cwd
machinery — a UI renders sub-calls through the identical path as native
results. The dsh config tree mounts the worker code runtime and reads
DSH_TOOLS_MODE (temporary seam until per-session mode selection lands).

Session format stays v0 (pre-release churn). Code-mode ACP/TUI fixtures
re-recorded; TUI presenter pin refreshed; catalogs regenerated. Keyless
web smoke pins the code-mode wire contract (tools=[run_code] + SDK
prompt section).
2026-07-26 02:43:34 +08:00
Tianyi Cui 6f50208ea3 Merge pull request #625 from deepseek-harness/worktree/llm-mock-fault-server
feat(llm): add scriptable mock fault server
2026-07-26 00:54:15 +08:00
Tianyi Cui 674d916ef8 Merge branch 'master' into worktree/llm-mock-fault-server 2026-07-26 00:45:44 +08:00
Tianyi Cui 5f04c92f15 Merge pull request #612 from deepseek-harness/web-e2e-lane
test(web): keyless browser e2e lane — replayed round trip + seeded cold resume
2026-07-26 00:40:13 +08:00
Tianyi Cui f1577d620e test(web): harden replay scaffold lifecycle 2026-07-26 00:33:46 +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 642cdc7b1d Merge pull request #608 from deepseek-harness/worktree/dsh-arg-parser
refactor(cli): unify dsh argv parsing and the dsh entrypoint
2026-07-26 00:08:23 +08:00
Tianyi Cui 8af3d2461b Merge branch 'master' into worktree/dsh-arg-parser 2026-07-26 00:05:16 +08:00
Tianyi Cui a519412b4d Merge pull request #599 from deepseek-harness/session-query-tool
Add model-facing session-query tools
2026-07-26 00:01:17 +08:00
Yichen Jiang badf7d1c63 fix(llm-mock-server): harden fault boundaries 2026-07-25 22:45:58 +08:00
Yichen Jiang 5446714177 Merge branch 'master' into worktree/llm-mock-fault-server 2026-07-25 22:27:29 +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
Hypatia May b78daaad8c fix(session-query): keep model tools opt-in 2026-07-25 18:14:36 +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
Tianyi Cui 84be7cc622 Merge pull request #613 from deepseek-harness/worktree-workspace-gui
feat(gui): workspace entity + intent mode — picker, guidance, durable titles
2026-07-25 17:52:48 +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 1f0d555f60 docs(missions): record workspace GUI closeout lessons 2026-07-25 17:46:05 +08:00
imccyu 1a9c1596b8 test(web): cover workspace UI branches 2026-07-25 17:46:05 +08:00
imccyu c06cb2deec test(web): stabilize workspace snapshots 2026-07-25 17:46:05 +08:00
imccyu 468c64a078 fix(web): keep composer add action attachment-only 2026-07-25 17:46:05 +08:00
imccyu 08ce02da2b docs(web): finalize workspace UI product flow 2026-07-25 17:46:04 +08:00
imccyu 9eb9c70a8a feat(web): add workspace-aware session flow 2026-07-25 17:45:26 +08:00
Turtle 67e2ef8ef2 chore: retrigger CI (synchronize event was missed) 2026-07-25 17:37:50 +08:00
Turtle 5a06b9e926 fix(cli): reject default-surface flags leaked onto the web subcommand
ds-review-bot: `dsh web -p task`, `dsh web --resume s`, and `dsh --config c.yml
web` reached the web action with those values in program.opts() but the action
ignored them and served — silently dropping mode-specific inputs. The web
action now reads the parent opts and fails loud (exit 1) on a leaked
--config/-p/--resume, matching the root mode's mixing guard. Covered in
args.spec.ts.

Also (ds-review-bot): tui-demo/README documented the removed `dsh
[path-to-cordis.yml]` positional form; corrected to bare `dsh` / `dsh --config
<path>`. Agent Note + Chinese pair note the web-leak guard.
2026-07-25 17:24:39 +08:00