Commit Graph

515 Commits

Author SHA1 Message Date
Tianyi Cui
29ce2df315 Merge remote-tracking branch 'origin/master' into web-capability-seam
# Conflicts:
#	docs/architecture.md
#	docs/cordis-catalog/events-and-services.md
#	docs/module-graph.md
#	packages/README.md
#	tsconfig.base.json
2026-07-01 17:00:44 +08:00
Tianyi Cui
2fa16c16a4 Merge pull request #126 from deepseek-harness/codex/sync-docs-with-implementation
docs: sync implementation docs and doc gates
2026-07-01 13:18:34 +08:00
Tianyi Cui
0478f5965a docs: address review sync gaps 2026-07-01 12:56:13 +08:00
kingwl
643b77dabf docs: sync implementation docs and doc gates 2026-07-01 10:29:47 +08:00
Tianyi Cui
3f85f522ea Merge pull request #117 from deepseek-harness/drop-catalog-count-prose
docs(cordis-catalog): omit exact event/service counts from catalog prose
2026-06-29 22:10:30 +08:00
Tianyi Cui
dcf8e10e5a docs(cordis-catalog): drop merge-conflict-prone count sentences
The Events intro carried "The harness declares N events across M scopes."
and the Services intro "The N `ctx.<key>` services the harness provides."
Both embed counts the generator recomputes from source, so every branch
that adds an event or service rewrites that one line — a guaranteed merge
conflict against any sibling branch that also touched the catalog, for
prose that adds nothing a reader can't get by scanning the page.

Remove the count clauses from the generator's render() and regenerate the
catalog. The freshness gate (verify-cordis-catalog) stays green.
2026-06-29 22:04:37 +08:00
Tianyi Cui
08522c2c3f Merge pull request #116 from deepseek-harness/worktree-todo-write-tool
feat: add the todo_write tool (model task list as session state)
2026-06-29 21:46:05 +08:00
Tianyi Cui
9f1caf7c5b fix(todo): address todo_write review feedback 2026-06-29 19:44:38 +08:00
Dudu-0223
bb8f7799ce fix: drop unreachable WebError rethrow in exa/perplexity search
The `if (error instanceof WebError) throw error` guard is dead code in the
exa and perplexity providers: their mappers (mapExaResponse /
mapPerplexityResponse) never throw a WebError — a wrong-shape body throws a
TypeError, which the catch correctly translates to WEB_PROVIDER_ERROR. The
guard was added for symmetry with the deepseek provider, whose mapper DOES
throw a WebError in strict mode (no web_search_tool_result block), so it
keeps the rethrow. The unreachable lines tripped the per-file 100% coverage
gate.
2026-06-29 17:39:52 +08:00
Dudu-0223
8395722db5 fix: address codex review findings on web seam
- search providers (exa/perplexity/deepseek): map the parsed response
  INSIDE the parse try, so a well-formed body of the wrong shape surfaces
  as WEB_PROVIDER_ERROR instead of escaping as a raw TypeError; a WebError
  the mapper throws on purpose is re-thrown untouched
- web-fetch-local: validate numeric limits at plugin construction (positive
  finite caps; non-negative integer maxRedirects) rather than constructing a
  provider with nonsensical values
- web-fetch-local: enforce the redirect budget BEFORE resolving each hop, so
  maxRedirects:N follows exactly N redirects and an over-limit hop reports
  "exceeded the maximum" rather than misdiagnosing a cross-origin block
- drop the stale dsh-tool-web/search and /fetch path aliases (the package no
  longer declares those subpath exports)
- strip trailing EOF blank lines flagged by git diff --check

Each fix carries a regression test.
2026-06-29 17:32:26 +08:00
Tianyi Cui
55088d1cfc docs(AGENTS): require running the CI gates locally before marking a PR ready
Add a "Run the CI gates locally BEFORE marking a PR ready" subsection: the
CI-equivalent local command line, and the rule that `pnpm run test:coverage`
(per-file 100%, CI-enforced) — not `pnpm run test` — is the gating test command,
alongside hygiene/snapshot/doc-sync. A green `test` run can still fail CI on an
uncovered line, which is usually dead code the gate is correctly flagging.
2026-06-29 15:53:34 +08:00
Tianyi Cui
5269d2ac3d fix(tool-todo): drop the unreachable status re-check that broke the coverage gate
The registry's validateArgs rejects a bad `status` enum before execute runs, so
the in-body re-check (`status !== 'pending' && …` → throw) was unreachable dead
code — line 70 was uncovered, failing the per-file 100% coverage gate. Narrow
the registry-guaranteed value with `status as TodoItem['status']` instead of
re-validating it, mirroring tool-bash (which only checks what the DSL can't
express). The malformed-status test still passes — it exercises the registry's
rejection, the actual path. Coverage back to 100%.
2026-06-29 15:38:54 +08:00
Dudu-0223
b92a3c531a feat(web): add DeepSeek-backed web search provider
Add @deepseek-ai/dsh-web-search-deepseek: a WebSearchProvider that calls
DeepSeek's Anthropic-compatible Messages API with the native
web_search_20250305 server tool and parses the structured
web_search_tool_result blocks into the ctx.web seam's WebSearchResult.

- Namespace plugin (inject: ['web']), no default export — registers into
  ctx.web like dsh-llm-deepseek registers into ctx.llm.
- Strict mode: a response with no web_search_tool_result block throws
  WEB_PROVIDER_ERROR rather than scraping URLs from model prose.
- Reuses $DEEPSEEK_API_KEY; baseURL defaults to the Anthropic-compatible
  base (api.deepseek.com/anthropic/v1) and does NOT reuse
  $DEEPSEEK_BASE_URL, which belongs to the chat-completions LLM adapter.
- snippet joined from text-block citations; sources deduped by url.
- Two-stage build layout (outDir lib/types) matching the other web
  packages; registered in tsconfig.json, tsconfig.build.json, knip.json,
  and docs/module-graph.md.
2026-06-29 15:32:03 +08:00
Tianyi Cui
5f744e4fa6 test(tool-todo): guard that stored content is trimmed
Codex confirmation review: the trim-the-stored-content fix had no test that
would fail if it regressed (existing assertions use already-trimmed todos).
Add a focused test asserting "  plan the work  " appends content "plan the
work". Verified it fails red against the pre-fix code.
2026-06-29 11:06:41 +08:00
Tianyi Cui
93a6dc6716 test(todo): add the todo-plan ACP snapshot scenario and a with-key e2e
Record the `todo-plan` snapshot scenario: a real prompt drives the model to call
todo_write, and the golden captures the resulting `plan` sessionUpdate (three
entries, priority synthesized as medium, status 1:1) plus the persisted
todo/write event. Registered in SCENARIOS; replays deterministically keyless.

Add a with-key coding-agent e2e that verifies the WORLD — a real model call to
todo_write lands a todo/write event whose snapshot is a valid, one-in-progress
list — not the agent's self-report. Wire tool-todo into the e2e harness.
2026-06-29 10:56:55 +08:00
Tianyi Cui
e17c4b748d refactor(tool-todo): store the trimmed content, matching the dedupe key
toTodoList dedupes and length-checks on the trimmed content but stored the raw
item.content, so a todo with leading/trailing whitespace was deduped by its
trimmed form yet persisted untrimmed — the stored value and the uniqueness key
could differ. Store the trimmed content so the persisted list matches what was
validated.
2026-06-29 10:50:31 +08:00
Tianyi Cui
46e31d8481 feat(tool-todo): add the model-facing todo_write tool
Add @deepseek-ai/dsh-tool-todo (a new packages/todo/ group): a model-facing
todo_write(todos: [{content, status}]) tool with whole-list-replace semantics.
Each call appends the full list as a todo/write event to the calling agent's
session log; the current list is the most recent such event (last-write-wins).
Single-owner — a non-agent caller is rejected. Beyond the schema's
type/required/enum checks, execute rejects empty/duplicate content and more than
one in_progress task, narrowing the loosely-typed args into a real TodoItem[].

Both UIs render off the existing session/event: the stdio UI prints a glyphed
checklist; the ACP bridge maps the list to a `plan` sessionUpdate (todosToPlan
synthesizes the priority ACP requires; status maps 1:1). Wired into the
coding-agent, acp-agent, and snapshot example configs with a system-prompt nudge.

Tests: unit (schema, validation, append/replace, no-agent rejection, presentCall,
HMR-safety, Loader export-shape guard), full-loop integration through the agent
loop, the ACP todosToPlan mapping + stream-update arm, the stdio render arm, and
a session/load replay that re-emits the plan. New-group TS wiring added to
tsconfig.base/json/build. RFC + a doc-inventory sweep (architecture, packages
README, AGENTS layout, cookbook group list, example READMEs) ship with it.

The todo-plan ACP snapshot scenario is recorded separately (needs an API key).
2026-06-29 10:30:52 +08:00
Dudu-0223
b62cf1a31c Merge branch 'master' into web-capability-seam 2026-06-29 10:28:04 +08:00
Tianyi Cui
4f09157612 docs(session): scope the todo/write JSDoc to the event's own contract
Codex Phase 1 review: the event JSDoc described Phase 2 consumers (the
todo_write tool, stdio printing, ACP plan mapping) as current state, and put an
@mode tag on a SessionEventMap member. @mode is for first-class Cordis
`interface Events` entries the catalog generator reads — this event rides the
existing session/event emit and has no catalog row, so the tag was wrong.

Trim the JSDoc to the event's own contract (snapshot data shape,
last-write-wins, not-a-surface-event) and drop @mode; phrase TodoItem in terms
of its own purpose rather than a not-yet-present tool.
2026-06-29 01:50:35 +08:00
Tianyi Cui
22a89847ac feat(session): add TodoItem + todo/write event vocabulary
Add the TodoItem type and a todo/write SessionEventMap variant carrying the
whole todo list as a snapshot (last-write-wins on replay). It is NOT a
SurfaceEventType: it produces no LLM message and never reaches
deriveMessages(), so it carries no surfaceOp and stays off the surface — it is
durable, replayable UI state that rides the existing session/event emit.

Tests cover the snapshot-clone-on-append contract, last-write-wins, the
not-on-surface guarantee, and a seeded replay round-trip. Docs: session.md
gains the TodoItem type-equiv block + the event member; core.md's variant count
goes to twelve; the type-equiv manifest gains TodoItem.
2026-06-29 01:39:25 +08:00
Dudu-0223
70a8b57738 fix: drop tool-web subpath exports, align with tool-bash single-entry shape
The web tool package exposed ./search and ./fetch as standalone subpath
plugins, but nothing consumed them, the RFC never called for them, and the
sibling dsh-tool-bash (also a multi-tool consumer) ships a single entry and
selects tools via config. The extra entries also tripped the workspace
constraints gate, whose expected `files` list covers single-entry and bin
packages but not a non-bin multi-entry one.

Collapse to a single `.` entry: drop the ./search|./fetch exports and their
lib/*.js from package.json files, delete the per-package tsdown override (the
root config's lib/types/index.js entry now suffices), and remove the
plugin-shaped name/inject exports from search.ts/fetch.ts (renaming each
apply to its applyWeb{Search,Fetch}Tool helper, still composed by the root
plugin and re-exported from the index). Selective enablement stays via the
existing { search?, fetch? } config. Docs updated to match.
2026-06-28 17:02:06 +08:00
Tianyi Cui
185c09d6a5 Merge pull request #115 from deepseek-harness/worktree-ci-lint-heap
ci: fix lint OOM and surface.ts coverage gap (re-enabled CI)
2026-06-27 00:03:15 +08:00
Tianyi Cui
489a26e865 test(session): cover the isSurfaceEvent / isSurfaceEligibleType guards
The per-file 100% coverage gate flagged surface.ts line 46 — the
branch where a surface-eligible event type carries no surfaceOp marker
(isSurfaceEvent returns false). Exercise both guards directly: the
type-only eligibility check, the positive narrowing path, a
non-eligible type, and the markerless-but-eligible branch.
2026-06-26 23:47:54 +08:00
Tianyi Cui
0619ce62b6 ci: raise Node heap ceiling for type-aware ESLint lint step
Type-aware ESLint loads every package tsconfig through the project
service and peaks at ~3.4GB RSS. The default V8 old-space ceiling
(~2GB) OOMs it (FATAL ERROR: Ineffective mark-compacts near heap
limit, exit 134) on both node 24 and 26. Set NODE_OPTIONS with an
8GB ceiling for the Lint step, comfortably above the peak.
2026-06-26 23:38:53 +08:00
Dudu-0223
f843ea7701 fix: align web packages with master's two-stage build layout
The web packages were authored against the old single-stage layout where
tsc emitted directly to lib/. Master compiles declarations to lib/types/
via tsc -b, then bundles JS into lib/ via tsdown. Point every web package's
tsc outDir at lib/types, update package.json types/exports/files to the
lib/types declaration + lib/ bundle shape (matching dsh-bash/dsh-tool-bash),
and bundle tool-web's subpath entries from lib/types/*.js rather than src.
2026-06-26 19:30:08 +08:00
Dudu-0223
caef252905 chore: adapt web seam to master's tsconfig + regenerate catalogs
Register the five web packages in the root tsconfig.json project graph
(master's typecheck moved to `tsc -b tsconfig.json` and dropped the
separate tsconfig.typecheck.json), and regenerate the module graph and
cordis catalog so they reflect the web packages on master.
2026-06-26 19:18:46 +08:00
Dudu-0223
1cd3a454da fix: remove stale duplicate JSDoc on translateAbortOrNetwork
The function carried two consecutive JSDoc blocks; the first was an
outdated short version missing the timeout-recovery contract. Keep only
the accurate detailed block.
2026-06-26 19:14:30 +08:00
Dudu-0223
a1624530ee fix: address codex review round 3
Resource-lifecycle and error-classification fixes in the local fetch provider:

- Classify a timeout that fires DURING the body read as WEB_FETCH_TIMEOUT, not
  WEB_ABORTED: thread the controller signal into the body-read translate path
  and recover the timeout WebError from signal.reason, honoring the public
  WEB_FETCH_TIMEOUT contract for a stalled response body.
- Cancel the response body before every blocked-redirect throw path
  (cross-origin, invalid target, missing Location), so a rejected redirect with
  a large or streaming body does not leak the socket after the tool returns
  WEB_REDIRECT_BLOCKED.
- Cancel the body when charset validation fails, matching the
  unsupported-content-type and over-size paths (the round-1 charset check threw
  before readCapped owned the stream).
2026-06-26 19:14:30 +08:00
Dudu-0223
0930e483ec fix: address codex review round 2
- Preserve abort errors while parsing search responses: when the caller's
  AbortSignal fires after headers but during response.json() (both the success
  and HTTP-error body parses), surface WEB_ABORTED instead of wrapping it as
  WEB_PROVIDER_ERROR, so agent cancel/dispose is not misreported as a provider
  failure. Applied to both the Exa and Perplexity providers.
- Report a malformed baseURL as misconfigured in status() (URL.canParse), so
  selection diagnostics and execution agree (configured-unavailable up front
  rather than a late WEB_PROVIDER_ERROR). WebProviderStatus already had the
  reason.
2026-06-26 19:14:30 +08:00
Dudu-0223
567519184b fix: address codex review round 1
- Re-validate redirect targets through validateFetchUrl before following, so a
  same-origin Location carrying credentials (or a non-http(s)/over-long URL)
  cannot bypass the transport hygiene a direct request enforces.
- Treat only DROPPED bytes as truncation: a body exactly at maxResponseBytes is
  no longer falsely flagged truncated (which emitted a spurious footer).
- Honor the declared response charset: parse the Content-Type charset and decode
  with it (rejecting unsupported labels as WEB_UNSUPPORTED_CONTENT_TYPE) instead
  of always assuming UTF-8 and returning replacement characters.
- Catalog the web seam vocabulary in docs/core-data-structures/web.md with
  type-equiv blocks + manifest entries, per the core-data-structures rule.
2026-06-26 19:14:30 +08:00
Dudu-0223
d01f5f73b7 Add web capability seam: ctx.web, search/fetch providers, web tools
Introduce web access as a first-class capability seam so the model-facing
web tools stay stable while backends change. dsh-web owns ctx.web as a
provider registry with registration-order-independent selection and the
WebError taxonomy; dsh-web-search-exa, dsh-web-search-perplexity, and
dsh-web-fetch-local register capabilities into it; dsh-tool-web is the sole
owner of the model-facing web_search/web_fetch schemas, prompt sections, and
HTML-to-markdown presentation. Search and fetch are deliberately one seam.

Providers ship as namespace plugins that register into ctx.web (like an
LlmAdapter into ctx.llm), not key-owning services, since multiple search
providers cannot each own the key. Tool registration follows product
enablement, not backend availability, so load order/credentials never enter
the model contract; the seam resolves the provider at execution time and
surfaces a structured WebError otherwise.

Moves the RFC to implemented/ amended to match what shipped. Example/app
configs are intentionally not wired yet (RFC migration step 6).
2026-06-26 19:12:13 +08:00
Dudu-0223
a4091daa3d docs: propose web capability seam 2026-06-26 19:04:23 +08:00
hypatiamay
32462f42bd Merge pull request #97 from deepseek-ai/compact-interface
feat(compact): compaction capability seam — abstract CompactService interface
2026-06-26 10:00:06 +08:00
hypatiamay
6cd446da2f Merge pull request #49 from deepseek-ai/session-surface
feat(session): add session surface — a linked list over the event log for message derivation
2026-06-26 08:57:33 +08:00
Hypatia May
4c1b7191f3 Merge branch 'session-surface' into compact-interface 2026-06-25 10:07:37 +08:00
Hypatia May
b955c7d18d Merge remote-tracking branch 'origin/master' into session-surface 2026-06-25 09:50:37 +08:00
Hypatia May
cf70141486 Merge branch 'session-surface' into compact-interface
# Conflicts:
#	docs/core-data-structures/core.md
#	packages/README.md
#	scripts/type-equiv.manifest.json
#	tsconfig.base.json
#	tsconfig.typecheck.json
2026-06-25 09:10:50 +08:00
Tianyi Cui
329371a529 Merge pull request #61 from deepseek-ai/codex/fix-stdio-readline-terminal
fix(examples): enable terminal editing in demo agents
2026-06-24 22:09:45 +08:00
Hypatia May
828c3f85c9 fix review findings: skip collided SCHEMA_VERSION 3; reject marker-less surface events
P1: both merge parents shipped SCHEMA_VERSION=3 for different layouts (surface
columns vs seed_length), so an on-disk 3 was ambiguous and wrongly accepted.
Bump to 4 (merged layout) so the version check rejects both sibling v3s.

P2: a surface-eligible event with no surfaceOp lands in the log but vanishes
from deriveMessages() (surface is the sole derivation path). The typed append
overload enforces the marker only when the type arg is a literal; it collapses
to optional when widened to the union (a caller iterating raw events). Guard at
runtime in both append() and the seed constructor — no backward-compat for
surface-less logs. Shared seed fixtures carry surfaceOp explicitly and the
appendLog helper forwards it verbatim (no synthesized default). Exports
isSurfaceEligibleType. Regression tests for all three, each verified to fail
on the unfixed code.

Gates: typecheck, test (1115), snapshot (14), doc-sync, lint, build, hygiene green.
2026-06-24 17:45:48 +08:00
Hypatia May
9cc8dc371e Merge remote-tracking branch 'origin/master' into session-surface
Reconciles the session-surface work (surfaceOp/sourceEventSeqs provenance as
the sole derivation path) with master's worktree-subagent series (fork-seed
boundary + out-of-process subagent backends).

Semantic reconciliations beyond the textual auto-merge:
- SQLite SCHEMA_VERSION: both sides bumped 2->3. Merged to a single v3 carrying
  BOTH column families — master's seed_length on `sessions` and surface's
  source_event_seqs/surface_op on `events`. writeRow + both INSERT sites bind
  the full set; the schema doc lists all three added columns as the v2->v3 gap.
- agent-loop runStep request: master's `sessionId: session.id` and surface's
  per-append surfaceOp/sourceEventSeqs coexist (different regions).
- Fork seed + surface: a fork seeds the child from the parent's LIVE events,
  which now carry surfaceOp, so the child's surface rebuilds correctly. Verified
  end-to-end — the subagent-fork replay recalls the inherited "SAFFRON" codeword
  through the seeded prefix.
- Subagent snapshot fixtures (recorded pre-surface) re-enriched via KEYLESS
  deterministic replay: only surfaceOp/sourceEventSeqs added onto existing
  recorded lines (matched by seq), no recorded value changed. Not re-recorded
  against the live API.

Gates: typecheck, test (1112), test:snapshot (14), doc-sync, lint, build,
hygiene all green.
2026-06-24 10:48:01 +08:00
Tianyi Cui
4cfa22f997 Merge pull request #101 from deepseek-ai/worktree-subagent-fork-scenario
Subagent seam (follow-up): record fork + mixed spawn/fork snapshot scenarios
2026-06-23 23:40:36 +08:00
Tianyi Cui
e6de8d1e9d Merge remote-tracking branch 'origin/master' into worktree-subagent-fork-scenario 2026-06-23 23:40:05 +08:00
Tianyi Cui
ddb240f3b1 Merge pull request #100 from deepseek-ai/worktree-subagent-fork-replay
Subagent seam (follow-up): persist the seed boundary so fork-child replay routes correctly
2026-06-23 23:39:14 +08:00
Tianyi Cui
cdfbf6f631 Merge remote-tracking branch 'origin/master' into worktree-subagent-fork-replay 2026-06-23 23:38:54 +08:00
Tianyi Cui
91d9b5e415 Merge pull request #95 from deepseek-ai/worktree-subagent-seam-pr3
Subagent seam (PR3): ACP backend (out-of-process delegation)
2026-06-23 23:38:15 +08:00
Tianyi Cui
18a56f041d Merge remote-tracking branch 'origin/master' into worktree-subagent-seam-pr3 2026-06-23 23:37:57 +08:00
Tianyi Cui
3e2b90fe7d Merge pull request #94 from deepseek-ai/worktree-subagent-seam-pr2.5
Subagent seam (PR2.5): per-session snapshot replay for nested agents
2026-06-23 23:37:31 +08:00
Tianyi Cui
7152184342 Merge remote-tracking branch 'origin/master' into worktree-subagent-seam-pr2.5 2026-06-23 23:37:07 +08:00
Tianyi Cui
e945219df4 Merge pull request #92 from deepseek-ai/worktree-subagent-seam-pr2
Subagent seam (PR2): in-process spawn + fork backends
2026-06-23 23:36:49 +08:00
Tianyi Cui
921362364c Merge remote-tracking branch 'origin/master' into worktree-subagent-seam-pr2 2026-06-23 23:36:26 +08:00