Commit Graph
534 Commits
Author SHA1 Message Date
LogosVeritas 00a007d833 Merge branch 'master' into feature/minimal-compact-image 2026-10-13 10:32:01 +08:00
fz 88a0be8486 Merge master after separating plugin-manager fix 2026-10-12 13:04:25 +08:00
LogosVeritas 444692d1ca feat(preset): add image reading and compaction to sdk-minimal
Reuse read_image and automatic compaction in the standalone profile without
adding SDK slash-command handling. Update profile guidance, upgrade steps,
and startup and recorded-session coverage.
2026-10-12 12:11:18 +08:00
imccyu e4410b2764 perf(client): read each tsdown preset's own package manifest
The client tsdown presets found a package's own manifest by name: a glob of
every packages/*/*/package.json, parsed until the name matched. tsdown's
native config loader imports each package config without module cache, so
the module-level cache never hit and all 82 configs repeated the glob
(40-125 ms each) synchronously on tsdown's main thread, where it delayed
every other package build. It was 34.5% of the client pass's main thread.

- clientBundle, staticLinked and clientLibrary take the package directory
  (import.meta.dirname at every call site) and read <dir>/package.json
  once; the package name, loader id and externals come from that manifest.
- A missing, unreadable or nameless manifest throws an actionable error.
- The glob, the name search and the module-level caches are removed.

tsdown client pass 12.78 s -> 8.73 s (median of 3 interleaved runs each,
-31.7%); all 11,566 lib outputs byte-identical; all 82 configs resolve the
same externals and banners.

Refs #5852
2026-10-11 18:19:23 +08:00
imccyu 1c6078dca6 perf(build): declare React type packages only at the workspace root
TypeScript builds a synthetic signature for every JSX intrinsic element and
computes a module specifier for @types/react (index and jsx-runtime) per
importing file. computeModuleSpecifiers visits every symlinked location of
that file and scans all 491 tsconfig paths for each; pnpm gave 65 packages
their own node_modules/@types/react link. Client test-aggregate Check
followed 26.9 + 0.494 * N seconds for N locations.

- Remove @types/react and @types/react-dom from all 67 workspace manifests
  and declare them once in the root devDependencies; packages keep declaring
  the react and react-dom they import (ui-slots gains react).
- verify-package-dependencies rejects either package in any workspace
  manifest and requires the root declaration, so a new package cannot add
  the link back.
- packages/client/AGENTS.md states the rule.

Client aggregate Check 59.1 s -> 26.5 s; the 76 client-only package
projects 54-57 s -> ~44 s wall. File set (2,613) and diagnostics unchanged.

Refs #5852
2026-10-11 18:19:21 +08:00
Tianyi Cui 9d385cd0d9 Merge master into persistent PTC
Preserve the persistent runtime package description with master's alpha.2 version and locale exports. Refresh the two PTC prompt snapshots for the current plan-tool result type.

Validation: full build, 434 focused tests (one skipped), two built-runtime tests, two selected snapshots, package metadata, and all 43 doc-sync checks passed.
2026-10-10 21:55:44 +08:00
Yichen Yan 23c29d067a fix(web): persist authenticated browser preferences on the Host (#4201)
* Persist authenticated browser preferences through the Host
* test(settings): cover recovery and remote preference refresh
* test(settings): read Host preferences from a fresh browser context
* test(settings): verify remote ConfigForm refresh at plugin entry
2026-10-09 19:27:00 +08:00
07akioni e2c410ef84 release(dsh): 0.2.1-alpha.2 2026-10-09 15:13:40 +08:00
creatixchu 244ca73755 fix(ptc): keep policy cleanup waits inside PTC 2026-10-09 15:02:01 +08:00
fz e493fd40dc fix(jobs): use short UUIDs for visible job ids 2026-10-08 21:04:58 +08:00
creatixchu b7dbd7bb03 Merge master into feat/persistent-ptc 2026-10-08 20:58:22 +08:00
turtle1999 39821cdc67 Merge remote-tracking branch 'origin/master' into fix/snapshot-title-event-wait-diagnostics 2026-10-08 19:45:16 +08:00
creatixchu 87013959f8 test(ptc): pin cancellation replay and resource cleanup branches 2026-10-08 17:25:50 +08:00
fz 5e6b0a5c53 Merge origin/master into fix/5520-job-session-timestamps 2026-10-08 16:56:04 +08:00
creatixchu 49f7919762 test(ptc): cover policy changes during nested tool execution 2026-10-08 16:55:32 +08:00
creatixchu 6885d662d2 refactor(ptc): move mode-change coordination into sandbox policy 2026-10-08 16:43:00 +08:00
fz 54c13688a8 fix(jobs): use one durable job id and ordered shutdown 2026-10-08 16:17:52 +08:00
Turtle cdf2f4c4b6 Merge pull request #5839 from deepseek-harness/turtle/revert-preset-insert-80a9ec3a652f
revert(plugin): drop preset-scoped profile patches; ship optional tools as global Host rows
2026-10-08 15:36:24 +08:00
fz 2be7329142 fix(jobs): preserve lifecycle order and headless settlement 2026-10-08 12:47:48 +08:00
turtle1999 188880962d test(snapshot): retain title and event wait timeout diagnostics
waitForTitleAfterTurnEnd and waitForEventAfterTurnEnd now name the session,
expected record, and deadline when the deadline passes before the first log
harvest settles, and keep the vi.waitFor failure as cause. Previously they
surfaced Vitest's generic 'Timed out in waitFor!', which failed the title
diagnostic spec on the macOS Sandbox lane at master 090348e4.

The title diagnostic spec uses isolateDiagnosticTimeout like its siblings,
replacing the Windows-only 5s timeout.

Refs #5631
2026-10-08 11:58:06 +08:00
fz 672b384eea Merge master into job lifecycle timing and refresh owned fixtures 2026-10-08 11:02:16 +08:00
Turtle b173f3e2a2 revert(plugin): drop preset-scoped profile patches; ship optional tools as global Host rows
Remove the `{ preset, insert }` / `{ preset, id, ...override }` profile patch
operation added in #5773, together with the app-boot compiler and reload drain,
config-editor filtering, plugin-manager preset row inventory and retained-module
removal checks, the read-only preset rows on the Plugins page, and the
agent-preset-registry row identities that served them.

Session search, Ralph, persistent terminals, Codex, and Claude Code bundles now
insert ordinary Host rows whose tools register in the global tool layer, like the
earlier optional bundles. Every preset, including minimal, sees them, and toggling
a bundle updates live Agents without new composition generations.
2026-10-07 20:46:37 +08:00
Tianyi Cui 1150a874fc chore(deps): update protocol and image security dependencies 2026-10-07 19:07:44 +08:00
Tianyi Cui e99d38af9d chore(deps): update source and build tools 2026-10-07 18:08:01 +08:00
Tianyi Cui a2501d0779 Merge pull request #5828 from deepseek-harness/worktree/deps-20261007-test-tools
chore(deps): update test and lint dependencies
2026-10-07 18:07:52 +08:00
Tianyi Cui b931f1f9f7 Merge pull request #5713 from deepseek-harness/worktree/session-title-reasoning-20261005
fix(llm,session-title): configure prepared calls from model capabilities
2026-10-07 18:02:41 +08:00
Tianyi Cui eff2f8a92b chore(deps): update test and lint dependencies 2026-10-07 16:57:54 +08:00
Tianyi Cui 5969359dc4 chore(deps): update mature runtime utilities 2026-10-07 16:41:17 +08:00
Tianyi Cui c56fdb023e refactor(llm): configure prepared calls with explicit controls 2026-10-07 16:10:26 +08:00
Tianyi Cui 6e894e4bea fix(llm-replay): reject undeclared minimum efforts 2026-10-07 14:37:09 +08:00
Tianyi Cui ffb88d331e feat(llm): resolve minimum reasoning during call preparation 2026-10-07 14:33:23 +08:00
Tianyi Cui 2aa95755f1 test(plugin): replay native subagent bundle delivery through PTC 2026-10-07 01:26:00 +08:00
Tianyi Cui fbb95c0f16 fix(plugin): preserve final pinned composition and browser inventories 2026-10-06 23:48:59 +08:00
Tianyi Cui 3aa1cab43a feat(plugin): compose optional bundles inside agent presets 2026-10-06 23:48:58 +08:00
Tianyi Cui a3cb678875 Merge master current-directory support into subagent activations
Integrate the observed master checkpoint 7ab215e23e5d977aae7eb5d4fb91782d39969dbb without rewriting the earlier published checkpoints. Master adds current-directory events, directory-aware consumers, and retained Git worktrees; its old subagent startup paths overlapped the unified activation implementation.

Resolve directory selection within managed startup after acquiring parent ownership. Preserve the original Session origin while setting each new local child directory, retain persisted directory state on cold resume, and pass a required absolute cwd to external providers. Keep unified local/external ownership, full completion notices, parked-input host completion, SDK wait/error/shutdown behavior, and ACP cancellation semantics. Retain removal of the old in-process driver and continuation managers.

Combine SDK wait with the new directory requests, preserve the new master directory/worktree fixtures, regenerate derived catalogs from the combined sources, and refresh only the four stale prompt/schema sidecars. Preserve every protected historical schema, archived note, catalog-v2 acknowledgement, and recorded predecessor input.

Validation: full build; 59 CI static gates; 855 subagent tests with 100% coverage on changed core/external sources; affected consumer suites including 119 repaired-fixture tests; SDK 11 and headless 16 recorded scenarios; two local headless expected cases; six built nested SDK/ACP cases; lint, strict cast inventory, workspace constraints, and whitespace checks. Native Windows worker diagnostics remain additive and require the next CI run to classify the original crash.
2026-10-06 10:52:35 +08:00
Tianyi Cui 9c679b21f4 fix(agent-loop): refresh provider context at actual request admission 2026-10-06 01:31:52 +08:00
Tianyi Cui 03a0165f59 test(compaction): pin synthetic directory context
Seed a fixed POSIX effective directory before the first request and disable ambient instruction discovery in the two pressure fixtures. Preserve the original project and existing output, headroom, retention, and summary limits while keeping shadowed token counts independent of temporary workspace path length.
2026-10-06 01:31:51 +08:00
Tianyi Cui 0c6b1ef7bb fix(session): port directory consumers and fixtures to current runtime 2026-10-06 01:31:51 +08:00
Tianyi Cui 92713fcdbd fix(session): complete working directory consumers and validation 2026-10-06 01:27:54 +08:00
Tianyi Cui 79bd3d8da7 feat(session): centralize working directories and directory context 2026-10-06 01:27:54 +08:00
Tianyi Cui 6f0174b5a2 fix(subagent): consume accepted input before structured completion
A structured local activation now accepts continuation messages, but its
terminal predicate checked only delegated children. A correction accepted
during the model request could therefore remain in either Inbox queue while
the earlier response committed structured_output. The loop later consumed
the correction, but the terminal tool guard prevented revising the captured
value, so callers could receive the obsolete answer as completed work.

Require both Inbox queues to be empty as well as all owned children to be
released before staging a structured result. Keep input admission closed
from that synchronous staging point through authoritative result policy,
including the enclosing PTC result. Derive this admission state from the
existing staged, pending, and captured records instead of introducing a
second lifecycle controller. Failed results delete their stage and reopen
input; successful capture keeps the existing terminal behavior. Caller-owned
delivery, complete final text, descendant ownership, and cold resume remain
unchanged.

Add deterministic barriers for accepted steering and queued input, and for
Native/PTC post-execute acceptance and rejection. All six new cases failed
against the unchanged runtime for stale results or incorrectly accepted
late input, then passed with the fix. Extend the authored headless structured
scenario to reject answer 41, consume a parent correction, and commit 42.
Its two own schema sidecars also need the current master bash/edit/write
definitions: retaining their previous definitions fails verifyHeaders on
this pinned base. Update the owning bilingual result-admission documentation.

Validation:
- pnpm run build:native-system
- pnpm exec vitest run packages/subagent/subagent/tests/structured.spec.ts
  packages/subagent/subagent/tests/continuation.spec.ts
  packages/subagent/subagent/tests/external-activation.spec.ts (214 passed)
- pnpm run test:snapshot:refresh snapshots/session/headless.snapshot.ts
  -t subagent-structured-parent
- pnpm run test:snapshot snapshots/session/headless.snapshot.ts
  -t subagent-structured-parent (1 selected scenario passed)
- pnpm run test:docs (21 gates passed)
- pnpm run doc-sync (42 gates passed)
- pnpm run lint completed its host build; after correcting test deferred
  generic types, pnpm run lint:contracts-ready passed
- git diff --check
2026-10-06 00:26:32 +08:00
Tianyi Cui 9dcc8fa985 Merge master into unified subagent activations
Integrate master 78ae4fc2d4d8ecaebb4b674028f781a358b92cc9 after the four
independent review fixes. Keep this base update separate from those fixes
and from subsequent review changes so the integration is independently
reviewable and the observed-master checkpoint remains preserved.

Retain activation-owned execution, caller-independent local discovery,
and unconditional parent final-answer delivery. Preserve master's preset
scoped scheduling tools and all delegated-child schedule deny rules. Move
the new scheduling regression from the removed driver package into the
surviving subagent package and run it through a real Spawn activation.

Preserve master's removal of runtime invariant plugins, dependencies,
exports, and test mounts. Keep context disposal before fixture directory
cleanup. Combine Python workflow ordering with activation/catalog events
without inventing unsupported source-plane import paths.

Keep all frozen Agent Note archives byte-for-byte identical to master;
do not accept Git's automatic edits to renamed archived notes. Retain
current lifecycle and delivery facts in active documentation, repair its
links, and regenerate catalogs/persistence schemas from merged source.
All 62 master persistence roots remain; only subagent/catalog gains the
PR's external membership extension. Keep master's third-party lock graph
and update only workspace dependency changes.

Validation before this checkpoint: 683 focused tests passed, seven
Windows-only cases skipped; 2,772 archived artifacts verified. Generated
catalog and active-pair checks passed. Fresh artifact build and remaining
build-dependent documentation checks continue before publication.
2026-10-05 23:49:47 +08:00
Tianyi Cui 0516f66d83 fix(agent-instructions): preserve groups when hidden candidates fail
A content-deduplicated shared file has no visible change record. If its
metadata became unavailable while the harness-home winner changed or vanished,
the reconciler skipped the failed candidate and still published the winner's
replacement or removal. Guidance that remained in the shared file disappeared
from the model's effective instructions. Content-read failures had the same
partial-group behavior even when metadata probing succeeded.

Rollback the probed candidate group whenever any metadata probe is unavailable
or its bounded content read cannot complete. Include candidates without a
visible predecessor and candidates previously removed as duplicates. Reuse
one rollback operation for proposed messages, deferred version updates,
metadata mutations, and retained digest bookkeeping, so a later successful pass
can reconstruct the complete group independent of cache warmth.

A filesystem path can also appear as a project instruction when the Harness
home is the project root. Releasing observed paths on rollback let that later
alias publish the very content withheld by the failed global group. A transient
failure of the first member also left failed and unvisited paths unreserved.
Factor the existing scope-to-file path calculation and reserve every eligible
member's absolute path for the rest of that pass when its group rolls back.
Project aliases therefore cannot bypass group preservation, without additional
filesystem operations. The shared resolver keeps probing and rollback path
calculations identical. Add metadata, content-read, and one-shot first-member
failure regressions for this supported same-file layout and its recovery.

Keep cancellation propagating to the caller. Keep explicit baseline-budget
exclusions outside observation rollback, because their removals are deliberate
policy decisions. No new session fields, baseline identities, polling, retries,
or process-global state are needed. Clarify the metadata/content and hidden
candidate guarantee in the bilingual README.

Add four real-plugin outage/recovery tests for metadata or content failure while
the retained home file is edited or deleted, plus a cold-cache reconciliation
regression. Add an authored headless session scenario with instance-local
provider failure injection: request two keeps baseline A while shared metadata
is unavailable; request three receives the home B replacement and shared A
addition together after recovery. The fixture restores the provider method on
disposal and asserts the real home/shared files before restoring observation.
Declare its test-only filesystem dependency without changing runtime packages.

Regenerate the persistence catalog's source anchors after the shared path
helper import shifts AgentInstructionSource by one line. Its persisted fields
and SHA-256 type fingerprint remain unchanged; no type acknowledgement or
Session migration is required for a source-location-only update.

Validation:
- All five new regressions failed with the intended partial-group emissions
  before the source fix.
- pnpm exec vitest run packages/context/agent-instructions/tests/agent-instructions.spec.ts -t 'hidden duplicate has|cold global group|unavailable active candidate|unavailable scope': 8 passed.
- pnpm exec vitest run packages/context/agent-instructions: 174 passed.
- The focused authored headless snapshot refresh and replay passed.
- Restoring the early skip for an unavailable hidden candidate makes the
  headless snapshot fail with the premature harness-home replacement.
- README translations were updated together and their pairing rerecorded.
- Three project-alias regressions failed on the initial group rollback fix,
  then passed after reserving failed and unvisited candidate paths.
- pnpm exec vitest run packages/context/agent-instructions/tests/agent-instructions.spec.ts -t 'frozen across a project alias|hidden duplicate has|cold global group|caches a removed duplicate': 12 passed.
2026-10-05 17:20:30 +08:00
Tianyi Cui 910f97059f test(snapshot): retain goal and turn-start wait diagnostics 2026-10-05 10:30:04 +08:00
Tianyi Cui 22f034bd76 test(snapshot): retain inbox wait timeout diagnostics 2026-10-05 09:38:05 +08:00
Tianyi Cui ec48669f48 release(dsh): 0.2.1-alpha.1 2026-10-03 10:46:11 +08:00
Turtle 819eb8078e Merge origin/master into turtle/remove-invariants-ccf1396aaf61 2026-10-01 16:33:09 +08:00
Tianyi Cui c7f66d13a6 docs(notes): prune redundant active decision records 2026-09-30 23:20:22 +08:00
Turtle 4ac4e95460 Merge pull request #5394 from deepseek-harness/fix/bundle-only-metadata
fix(plugins): read package.json only for package-root plugins
2026-09-30 18:10:34 +08:00
fz f899e87a1e fix(jobs): persist owned job lifecycle timing in sessions 2026-09-30 15:25:24 +08:00