Commit graph

610 commits

Author SHA1 Message Date
hypatiamay
0c5aa8110f Merge pull request #2999 from deepseek-harness/perf/token-meter-surface-fold-plan-commit
perf(token-meter): commit the surface fold in place through a plan/commit pair
2026-08-25 10:28:11 +08:00
Dudu-0223
f76a225a7d Merge pull request #2663 from deepseek-harness/feat/subagent-provider
让 subagent 按需发现并选择子 Agent 模型
2026-08-24 18:23:42 +08:00
creatixchu
30704dc1df fix(attachment): budget master pixels and share the encoding ladder
Master dimensions move from a 2048 long-edge rule to a total-pixel
budget (normalizedImageMaxPixels, default 2048x2048) with an 8192
long-edge cap, so extreme aspect ratios keep short-edge resolution.
The shared quality ladder and lazy execution move to encoding.ts,
review-round doc fixes land across attachment and llm packages, and
the superseded facts in the unified-image-pipeline note now describe
the shipped routing.
2026-08-24 17:10:59 +08:00
Hypatia May
4db19c352e docs(token-meter): distinguish projection and measurement folds 2026-08-24 16:24:13 +08:00
Hypatia May
58a0e450b3 perf(token-meter): commit the surface fold in place through a plan/commit pair
foldSurfaceTokens rebuilt the priced surface on every surface event: an
append allocated [...nodes, node] and a replacement copied the whole
array before splicing, charging every well-formed event O(surface) for
an atomicity property only malformed events need. Benchmarks put the
copy at ~99.9% of an append's cost (100µs at a 50k-node surface vs
0.1µs for pricing) with O(S²) accumulation over a session, inside the
synchronous session/event publication path.

Split the fold into the session core's planSurfaceEvent/applySurfacePlan
shape: planSurfaceTokens performs every fallible step against the
read-only surface, commitSurfaceTokens applies the plan in place and is
infallible by construction. _foldEvent plans first, runs the remaining
fallible anchor validation, and only then commits, so retry identity is
preserved by ordering instead of by allocation. Appends drop to
amortized O(1) (100.3µs -> 1.9µs at 50k nodes); replacements keep their
O(surface) findIndex but stop paying the extra full copy (21µs -> 4.2µs).

A new regression test pins the one hazard this introduces: an event
whose surface plan is valid but whose later anchor validation throws
must leave the priced surface and running total uncommitted across
repeated failures.
2026-08-24 16:24:12 +08:00
creatixchu
ebb8010b56 Merge remote-tracking branch 'origin/master' into worktree/2885-image-compression
# Conflicts:
#	docs/config-catalog.i18n.yaml
#	docs/config-catalog.md
#	docs/config-catalog.zh.md
#	packages/llm/llm-deepseek/README.i18n.yaml
#	packages/llm/llm-deepseek/README.md
#	packages/llm/llm-deepseek/README.zh.md
#	packages/llm/llm-deepseek/src/adapter.ts
2026-08-24 16:23:34 +08:00
creatixchu
4863890535 fix(attachment): route image encoding by alpha over shared quality ladders
Delete the 5-bit colour-count classifier and palette PNG branch that
misrouted high-frequency photographic JPEGs (issue #2885 images 23/24)
into an encoder 100x slower with 4x larger output. Both normalization
and request-image encoding now route by the decoded alpha fact alone:
opaque sources down a JPEG ladder and alpha sources down a WebP
effort-0 ladder, each at qualities 85/75/60. Byte budgets become ladder
targets: the downscale retry loop is gone and a ladder-exhausted encode
keeps its smallest output, while provider byte caps stay enforced at
the transmitting route. Request transforms move to request-image-v5.
2026-08-24 16:14:32 +08:00
creatixchu
7bad88206b test(llm): 覆盖执行环境图片路径解析 2026-08-24 16:01:49 +08:00
creatixchu
558f08780c refactor(attachment): 分离宿主位置与模型访问路径 2026-08-24 14:51:03 +08:00
creatixchu
7f4cf99eeb 修正图片路径访问与只读存储 2026-08-24 13:11:04 +08:00
creatixchu
bd4e4173e7 feat(attachment): expose model-readable image paths 2026-08-24 12:08:26 +08:00
Yichen Jiang
05daf25e10 test(llm): pin includeShippedRoot off in the inventory roster
The spec landed on master before the roster gained the plugin-bundled
shipped root; its empty-roots harness now opts out explicitly, matching
every other exact-roster suite.
2026-08-24 10:17:11 +08:00
Tianyi Cui
c4f10577b5 test(llm): cover pi-ai upgrade compatibility 2026-08-24 01:57:18 +08:00
Tianyi Cui
76c3bf5f6f Merge origin/master into worktree/upgrade-pi-ai-0.84.2 2026-08-24 01:38:25 +08:00
Tianyi Cui
44bd9182ff chore(llm): bump pi-ai to 0.84.2 2026-08-24 01:19:01 +08:00
imccyu
e47c897f5f refactor(session): localize token delta detection 2026-08-23 23:29:38 +08:00
Tianyi Cui
9c7e142f79 refactor(session): send canonical events directly 2026-08-23 00:22:41 +08:00
Tianyi Cui
fe72ab42d1 feat(deepseek): upload incremental session logs 2026-08-22 22:55:02 +08:00
Tianyi Cui
c41c5f3959 Merge origin/master into todo-event-ownership-v2 2026-08-22 21:12:36 +08:00
Tianyi Cui
a2b415096d refactor(todo): own todo event vocabulary 2026-08-22 21:10:02 +08:00
Tianyi Cui
17f85bdbcd docs: trim CoT leakage from post-purge prose
Remove dead design-session citations, change narration, indexical
stamps, and review-adjacent justification found by the
dsh-trim-cot-leakage recall batteries in prose that landed after the
last purge. Bilingual README pairs are re-recorded.
2026-08-22 20:35:11 +08:00
Tianyi Cui
ea6f61f144 feat(deepseek): upload plugin package metadata (#2916)
* feat(deepseek): upload plugin package metadata

* feat(deepseek): apply metadata review feedback

* docs(deepseek): specify request wire extensions

* docs(notes): record inventory cache benchmark

* docs(site): keep DeepSeek wire spec repository-only
2026-08-22 20:03:23 +08:00
Tianyi Cui
934976732d docs: purge residual chain-of-thought leakage 2026-08-22 13:10:23 +08:00
Turtle
6b3e971805 docs: remove implementation narration from prose 2026-08-21 22:22:23 +08:00
imccyu
0bee546177 feat(util): mint UUIDs without crypto.randomUUID in every context 2026-08-21 20:35:34 +08:00
imccyu
aa6c361a97 release(dsh): 0.1.1-rc.2 2026-08-21 19:48:58 +08:00
creatixchu
d618bfebb4 fix(deepseek): decouple files and stream timeouts 2026-08-21 18:34:16 +08:00
creatixchu
1b389798dc fix(llm-deepseek): fall back when Files resolution fails 2026-08-21 18:14:46 +08:00
creatixchu
2491e12fd8 refactor(attachment): normalize image storage API 2026-08-21 15:06:24 +08:00
creatixchu
724783b024 refactor(image): remove region reads 2026-08-21 15:06:24 +08:00
creatixchu
0c9a664223 test(deepseek): print vision failure facts 2026-08-21 15:06:11 +08:00
creatixchu
703ce4a3d6 test(deepseek): expose Files API e2e failures 2026-08-21 15:06:11 +08:00
creatixchu
d65e2a9e8a test(images): close unified pipeline coverage gaps 2026-08-21 15:06:11 +08:00
creatixchu
48a58b9090 fix(images): address unified pipeline review 2026-08-21 15:06:10 +08:00
creatixchu
c09a42ccb5 fix(images): parse listed missing Files ids 2026-08-21 15:05:55 +08:00
creatixchu
c0dd8ec820 chore(images): align merged runtime closure 2026-08-21 15:05:54 +08:00
creatixchu
d29855f97c feat(images): unify master and Files request pipeline 2026-08-21 15:05:54 +08:00
creatixchu
8f83853b60 refactor(attachment): saveImage returns the canonical ref beside source facts
AttachmentStore.saveImage now resolves SavedImageAttachment: the durable
reference paired with the submitted raster's intrinsic facts, so a store may
persist a canonical re-encoding while callers keep the source dimensions for
coordinate mapping. saveImages keeps returning refs; every fake store and the
cordis API catalog follow the new signature.
2026-08-21 15:01:45 +08:00
imccyu
3ec5e8f8c4 release(dsh): 0.1.1-rc.1 2026-08-21 14:11:09 +08:00
Yichen Jiang
708a25a8a9 fix(llm-deepseek): address vision catalog review 2026-08-21 11:28:14 +08:00
Yichen Jiang
246caaba77 Merge remote-tracking branch 'origin/master' into worktree/deepseek-vision-model-catalog
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.i18n.yaml
#	docs/config-catalog.i18n.yaml
#	packages/llm/llm-deepseek/README.i18n.yaml
2026-08-21 10:34:51 +08:00
pku-xht
84cbec28e9 Merge remote-tracking branch 'origin/master' into codex/localized-chinese-doc-links
# Conflicts:
#	.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml
#	.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md
#	.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md
#	.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.i18n.yaml
#	.agents/notes/implemented/bug-fix/2026-07-29-pnpm-setup-runner-isolation.zh.md
#	.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.i18n.yaml
#	.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.zh.md
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md
#	.agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-21-cross-session-references.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-21-cross-session-references.zh.md
#	.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md
#	.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-31-permission-default-for-new-sessions.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.zh.md
#	.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md
#	.agents/notes/implemented/feature/2026-08-05-agent-teams.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-05-agent-teams.zh.md
#	.agents/notes/implemented/feature/2026-08-11-workspace-sidebar-order-and-folding.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml
#	.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.i18n.yaml
#	.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.zh.md
#	.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml
#	.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md
#	.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml
#	.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md
#	.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.zh.md
#	.agents/notes/implemented/testing/2026-07-30-web-browser-snapshot-ci-gate.i18n.yaml
#	.agents/notes/implemented/testing/2026-07-30-web-browser-snapshot-ci-gate.zh.md
#	.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml
#	README.i18n.yaml
#	README.zh.md
#	docs/architecture.i18n.yaml
#	docs/architecture.zh.md
#	docs/development.i18n.yaml
#	docs/development.zh.md
#	docs/persistence-catalog.i18n.yaml
#	docs/persistence-catalog.zh.md
#	docs/subsystems/README.i18n.yaml
#	docs/subsystems/README.zh.md
#	docs/subsystems/agent-team.i18n.yaml
#	docs/subsystems/agent-team.zh.md
#	docs/subsystems/client-modules.i18n.yaml
#	docs/subsystems/client-modules.zh.md
#	docs/subsystems/commands.i18n.yaml
#	docs/subsystems/commands.zh.md
#	docs/subsystems/persistence.i18n.yaml
#	docs/subsystems/persistence.zh.md
#	docs/subsystems/session-reference.i18n.yaml
#	docs/tool-catalog.i18n.yaml
#	docs/tool-catalog.zh.md
#	docs/user/guide/providers.i18n.yaml
#	docs/user/guide/providers.zh.md
#	packages/README.i18n.yaml
#	packages/README.zh.md
#	packages/bundle/web-app/README.i18n.yaml
#	packages/bundle/web-app/README.zh.md
#	packages/client/README.i18n.yaml
#	packages/client/README.zh.md
#	packages/client/connection/README.i18n.yaml
#	packages/client/connection/README.zh.md
#	packages/client/ui-conversation/README.i18n.yaml
#	packages/client/ui-conversation/README.zh.md
#	packages/client/ui-primitives/README.i18n.yaml
#	packages/client/ui-primitives/README.zh.md
#	packages/client/ui-sidebar/README.i18n.yaml
#	packages/client/ui-sidebar/README.zh.md
#	packages/client/ui-workspace/README.i18n.yaml
#	packages/client/ui-workspace/README.zh.md
#	packages/context/README.i18n.yaml
#	packages/context/README.zh.md
#	packages/core/agent-loop/README.i18n.yaml
#	packages/credentials/README.i18n.yaml
#	packages/credentials/README.zh.md
#	packages/experimental/agent-team/README.i18n.yaml
#	packages/experimental/agent-team/README.zh.md
#	packages/experimental/tool-agent-team/README.i18n.yaml
#	packages/experimental/tool-agent-team/README.zh.md
#	packages/host/frontend-static/README.i18n.yaml
#	packages/host/frontend-static/README.zh.md
#	packages/host/webserver/README.i18n.yaml
#	packages/host/webserver/README.zh.md
#	packages/interaction/commands/README.i18n.yaml
#	packages/interaction/commands/README.zh.md
#	packages/plan/plan-mode/README.i18n.yaml
#	packages/plan/plan-mode/README.zh.md
#	packages/sandbox/sandbox-local/README.i18n.yaml
#	packages/sandbox/sandbox-local/README.zh.md
#	packages/session/README.i18n.yaml
#	packages/session/README.zh.md
#	packages/session/session-persistence-sqlite/README.i18n.yaml
#	packages/session/session-persistence-sqlite/README.zh.md
#	packages/session/session-projection-cache/README.i18n.yaml
#	packages/session/session-projection-cache/README.zh.md
#	packages/shell/tool-pwsh/README.i18n.yaml
#	packages/shell/tool-pwsh/README.zh.md
#	packages/subagent/subagent-codex/README.i18n.yaml
#	packages/subagent/subagent-codex/README.zh.md
#	packages/subagent/subagent/README.i18n.yaml
#	packages/subagent/subagent/README.zh.md
#	packages/web/tool-web/README.i18n.yaml
#	packages/web/tool-web/README.zh.md
#	scripts/snapshots/translation-prompt-v4/request-response.expected.json
2026-08-20 19:15:33 +08:00
Yichen Jiang
120097e266 chore(sync): restore the image-budget README merge on llm-pi-ai 2026-08-20 17:58:39 +08:00
Yichen Jiang
0b2bc3d651 fix(llm-pi-ai): stub both home spellings in the tilde-expansion test
os.homedir() reads HOME on POSIX and USERPROFILE on Windows; stubbing
only HOME left the Windows lane expanding ~ into the real profile
directory and failing the fileExists assertions.
2026-08-20 17:58:38 +08:00
Yichen Jiang
9eaaeaeb96 fix(credentials,authorization,llm-pi-ai): harden the auth seams per review
Review findings on #2509, all confirmed:

- Every writer of .credentials.yaml now waits out the record-mutation
  lock (DOCUMENT_LOCK_WAIT_MS): refs and records share one file and one
  lock, so a reference write or record delete contending with an OAuth
  refresh must not fail at the 2s file-work default.
- api-key records are admitted before they are rendered: an empty key,
  a non-POSIX env name, or an empty env value is refused at the write
  instead of persisting a document the next boot rejects wholesale.
- llm-pi-ai no longer lets the credential-key grammar reject legal
  route ids: reads answer "nothing stored" via isCredentialKeySegment
  (new dsh-credentials export), deletes have nothing to remove, and only
  a write refuses, as LlmError UNSTORABLE_PROVIDER_ID; flow registration
  skips a future catalog id outside the grammar instead of failing the
  mount.
- authorization/settled fans out with contained listener failures on
  the credentials seam's terms (INVARIANT still rethrows), so a broken
  watcher can never turn a finished attempt into a failure.
- notify() is fire-and-forget at the seam: a surface that cannot render
  a notice loses the notice, never the attempt.
- A declined prompt is an outcome: interactions reject with the new
  AuthorizationDeclinedError and the attempt settles cancelled instead
  of failed.
- NOT_COMMITTED now confirms a commit observed during the attempt
  (credentials/record-updated for the flow's key), so a re-auth cannot
  pass a stale record off as fresh; a flow that deletes its record is
  refused on the same code.

READMEs, the subsystem/event/config catalogs, and the Agent Note follow
the shipped behavior; memory.ts carries the dedup TODO.
2026-08-20 17:58:38 +08:00
Yichen Jiang
57c5f017ac feat(llm-pi-ai): sign in to a provider instead of withholding it
pi-ai's auth model reaches this adapter through three translations, all
of which live here: a CredentialStore over the harness credential
records, an AuthContext over the credential plane and the host
filesystem, and one authorization flow per installed provider that
ships a login. The seams they consume name nothing from pi-ai, so a
second adapter family can arrive with a different auth model and share
them.

Every collection is now built with the store and the context rather
than with nothing, which is what makes a signed-in provider stay signed
in across the collection rebuild a configuration change causes. With a
posture that works, the configurable-provider directory no longer
withholds OAuth-only routes and `openai-codex` is offered again; the
predicate that withheld it is gone.

The credential plane stays optional. Reads answer "nothing stored"
without a credentials service because such a composition genuinely
holds no credential, while writes refuse by name — a login whose grant
evaporated would report success and then fail every request. Flow
registration is scoped to the authorization seam, so a headless or ACP
composition mounts with no sign-in and everything else unchanged.

Two fixes found while wiring this up: pre-release credential fixtures
in the llm suites still used the flat document the record work
replaced, and a flow that ignores its cancellation signal would have
held its key for the life of the process — withdrawal now settles the
attempt either way.
2026-08-20 17:58:38 +08:00
_Kerman
83a3457b4a Merge remote-tracking branch 'origin/master' into dshw/pr-deepseek-harness-deepseek-harness-2730 2026-08-20 10:04:04 +08:00
imccyu
f1f7dc36fa release(dsh): 0.1.0-rc.8 2026-08-19 23:00:28 +08:00
Yichen Jiang
583894f7ae fix(llm-deepseek): pass reasoning content back on every reasoned turn
An assistant turn that answered without calling a tool serialized no
reasoning_content, so a gateway re-encoding the conversation for another
vendor had no chain of thought to hash and lost that turn's upstream
thinking signature.
2026-08-19 22:02:36 +08:00
creatixchu
ff88d3dd00 Merge remote-tracking branch 'origin/master' into worktree/abort-partial-finalize 2026-08-19 14:55:32 +08:00