Commit Graph
6936 Commits
Author SHA1 Message Date
Tianyi Cui 2481ad8eb6 docs(worktree): keep the capability seam translation paired 2026-10-06 01:39:47 +08:00
Tianyi Cui a1363f7f47 fix(worktree): offer GUI opt-in through official plugins 2026-10-06 01:39:47 +08:00
Tianyi Cui 171cf5d70f fix(experimental): align worktree fixtures and catalogs with current runtime 2026-10-06 01:39:47 +08:00
Tianyi Cui d26fe1ab4e fix(experimental): address worktree review findings 2026-10-06 01:39:46 +08:00
Tianyi Cui c67a2d6fdf feat(experimental): create and enter retained Git worktrees 2026-10-06 01:39:46 +08:00
Tianyi Cui 43928bf03f refactor(workspace): remove obsolete mutation path parser 2026-10-06 01:31:52 +08:00
Tianyi Cui f5b7fdcadb docs(system-prompt): align dynamic context evaluation contract 2026-10-06 01:31:52 +08:00
Tianyi Cui 96c4a89a72 docs(system-prompt): sync admission context API references 2026-10-06 01:31:52 +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 2489bbba16 test(session): acknowledge metadata and replay corrected directory state 2026-10-06 01:31:52 +08:00
Tianyi Cui ffd791a110 fix(session): use committed directories in hooks and consumers 2026-10-06 01:31:51 +08:00
Tianyi Cui df655fd11e fix(agent-loop): restore runtime context after compaction before request admission 2026-10-06 01:31:51 +08:00
Tianyi Cui caef1d5d5f docs(upgrade): explain current-directory migration 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 3f35ca7b5b test(session): align fixtures with awaited agent creation 2026-10-06 01:27:55 +08:00
Tianyi Cui b446e2e290 fix(web): start sidebar terminals in the session directory 2026-10-06 01:27:55 +08:00
Tianyi Cui 6f23c5dfd1 fix(session): align rebased documentation and SDK series output 2026-10-06 01:27:55 +08:00
Tianyi Cui 549c0b5e37 docs(session): clarify working directory ownership and migration 2026-10-06 01:27:55 +08:00
Tianyi Cui 79bd3d8da7 feat(session): centralize working directories and directory context 2026-10-06 01:27:54 +08:00
Tianyi Cui 8a7d5014bf Merge pull request #5716 from deepseek-harness/worktree/pr-ci-speed-independent-20261005
perf(ci): reduce repeated compilation without raising concurrency
2026-10-05 19:35:09 +08:00
Tianyi Cui 11a0f85b34 fix(ptc): apply shared sandbox policy to Python execution 2026-10-05 19:14:50 +08:00
Tianyi Cui 973a7fb8e4 Merge pull request #5677 from deepseek-harness/worktree/plugin-session-records-20261004
feat(session): add typed experimental plugin records and catalog
2026-10-05 18:53:22 +08:00
Tianyi Cui c954a07535 docs(session): separate experimental persistence catalogue 2026-10-05 18:09:01 +08:00
Tianyi Cui 9a4a750a05 Merge master into plugin record catalogue 2026-10-05 17:37:23 +08:00
Tianyi Cui 350dbb45df perf(ci): emit benchmark artifacts without repeated type checks 2026-10-05 17:28:27 +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 21d0c2e29c feat(agent-instructions): load the shared agents-root AGENTS.md
The user-global instruction scope now reads two roots: $DSH_HOME/AGENTS.md
first, then the shared agents root that other agent tools use
($DSH_AGENTS_HOME, else ~/.agents). Both resolve from the process environment
through @deepseek-ai/dsh-home-paths; no config field is added, because the
stack base (PR #5718) removed the per-row home override.

The two files are candidates of one candidate group: identical trimmed content
renders once from the harness home, an unobservable candidate preserves the
group's last-good state, and reconciliation probes both roots so external
edits, removals, and new files become visible change notices. A candidate
dropped as a duplicate keeps being reconciled, so deleting or changing the
retained candidate promotes it. The harness-home file keeps its recorded
`user-global` scope key; the shared file carries `agents-global`.

A user-global delta states `These user-global instructions apply to all work.`
instead of naming its reconciliation scope, and a project path whose first
component would collide with a user-global scope directory renders with a
leading `.` so it keeps its own scope.
2026-10-05 17:20:30 +08:00
Tianyi Cui b603bd924e docs(agent-instructions): correct the home-removal scope and thread one home
Review follow-ups:

- The guide claimed the removed field was the last per-row home override;
  other providers (skill-filesystem, shell-env, credentials-local,
  subagent-dsh-sdk, attachment-local) keep their own fields, so it now states
  that the removal covers the instruction loader, and step 1 also names the
  home-level `$DSH_HOME/cordis.patch.yml` layer.
- `DiscoverOptions` regains an already-resolved `dshHome` that `apply()` passes
  from its mount-time `resolveConfig()`, so baseline discovery and
  reconciliation share one resolution point instead of reading the environment
  separately.
- The package README says the loader reads the process home rather than "the
  same home as sessions, skills, and storage", and the resolver Agent Note
  states what the skill provider's fields actually select.
- `discoverBaselineInstructionFiles` JSDoc no longer lists a removed option.
2026-10-05 17:20:28 +08:00
Tianyi Cui 25f1672095 refactor(agent-instructions): drop the per-row dshHome override
The agent-instructions row accepted `dshHome`, letting one consumer read a
different harness home than sessions, skills, and storage. Home is process
policy: the plugin now resolves `$DSH_HOME`, else `~/.dsh`, through
`resolveDshHome()` from `@deepseek-ai/dsh-home-paths`, and the config field and
the library's explicit-home option are gone.

Tests and both snapshot fixtures pin the home with `vi.stubEnv('DSH_HOME', ...)`
and the harness's existing `DSH_HOME` export instead of row configuration.
`dsh-skill-filesystem` keeps its own `dshHome`/`agentsHome` fields.

The removed cordis.yml key gets an upgrade guide.
2026-10-05 17:20:28 +08:00
Tianyi Cui dd302f718b feat(session): catalogue experimental plugin records 2026-10-05 17:20:26 +08:00
Turtle 7d89563970 Merge pull request #5554 from deepseek-harness/fix/deepseek-extension-preparation
fix(llm): keep plugin package metadata from blocking requests
2026-10-05 17:02:06 +08:00
Tianyi Cui 536aaef0b3 fix(ci): preserve workflow concurrency and portable artifact checks 2026-10-05 12:53:52 +08:00
Tianyi Cui 853ad0bb9f perf(ci): remove repeated aggregate compilation and gate work 2026-10-05 12:07:57 +08:00
Tianyi Cui d1d560ba4b fix(translator): apply endpoint defaults and bound upstream failures 2026-10-05 11:09:32 +08:00
Tianyi Cui dede7b20e2 fix(translator): default anonymous translation to Bing 2026-10-05 10:37:55 +08:00
Tianyi Cui f1250c6e36 feat(translator): add anonymous Google and Bing translation service 2026-10-05 09:55:25 +08:00
Tianyi Cui 1678f0f5f5 fix(session): address review of plugin records
- Make the record commit an ES private method, so appendPluginRecord()
  is its only runtime entry.
- Document PluginRecordType and PluginRecord on the session subsystem
  page, and state in the README and JSDoc that the V3-to-V4 edge renames
  unknown ignorable V3 events into the plugin: namespace and that plugins
  outside this repository must not call the writer.
- The caller gate parses only files that contain the name or a \u
  escape, documents that wildcard re-exports are not reported, and its
  spec reads a temporary repository instead of this checkout.
- Cover Session.fromRestore in the record test and name SessionEventMap
  in the catalog generator's diagnostic.
2026-10-05 08:57:58 +08:00
Tianyi Cui 75542dd10a feat(session): let experimental packages append plugin records
Add appendPluginRecord(), which appends one ignorable event whose type is
`plugin:` followed by lowercase slash-separated segments, and
pluginRecordOf(), which reads such an event back. Records are not
SessionEventMap members, so the persistence catalog is unchanged; a build
that does not recognize one retains and skips it, and records never enter
the model-visible surface. Resume and fork carry them with the log, and a
format migration keeps them on a best-effort basis.

Only production source under packages/experimental/ may call the writer.
The verify-plugin-record-callers hygiene gate checks every reference in
repository sources, and the persistence catalog generator rejects a
SessionEventMap member in the plugin: namespace.

Session.append() and the record writer share one commit path, so a record
follows the same reentrancy, detach, and observer-containment rules. The
ignorable-events decision, the session README, the format-version
cookbook, and the plugin-author practices describe the records.
2026-10-05 08:57:58 +08:00
Tianyi Cui e166240405 docs(session): keep release status in the published state 2026-10-03 11:55:48 +08:00
Tianyi Cui 7c22428471 docs(session): record the published V4 format 2026-10-03 11:37:09 +08:00
Tianyi Cui da00f7f535 Merge pull request #5623 from deepseek-harness/feat/experimental-claude-code-mods-20261002
feat(experimental): add Claude Code mods bridge
2026-10-03 07:44:05 +08:00
Tianyi Cui 233032b8f4 fix(experimental): close the mods bridge review findings
- Disposal cancels detached runs before the engine waits for timer callbacks,
  so a callback parked in a $ call ends instead of blocking unload.
- A forgotten band wakes and ends its watch streams; a refresh asked for
  during a pass joins one more pass that settles after it; the Web band drops
  an ended stream so the next subscriber opens a fresh one.
- $ has Claude Code's namespaces: an unserved member rejects with
  'no implementation for <namespace>.<member>' instead of a TypeError.
- A .catch handler's next makes the rewrite check; a tool rename is refused
  like an argument rewrite; a null op answer is reported as no answer;
  defineMod returns its disposer from apply; the live turn record is copied
  before the chain freezes it; prompt.submit is raised only for batches with
  a human message and names the submitting mod as origin.
- $.http.fetch bounds the body while streaming; bandColumns/bandRows are
  Config; the client package drops its stale gateway edges; the source
  overlay lives in the package and anchors its entries to the file, and the
  dsh installation no longer depends on the experimental packages.
2026-10-03 05:18:32 +08:00
Tianyi Cui 2db0c83e86 docs(experimental): compatibility page, READMEs, and catalogs for mods as plugins
docs/subsystems/claude-code-mods.md lists every way a mod behaves
differently through the bridge than under Claude Code 2.1.287 — packaging,
events, the chain, $ members, drawing, testing, and the example mods,
including the four official mods assessed by reading. The bridge README
describes defineMod, the band, and the test kit; the band package gets its
README; the group index, release families, config and client catalogs,
module and seam graphs, and the Cordis API catalog are regenerated.
2026-10-03 03:19:43 +08:00
Tianyi Cui f1715c67ec refactor(experimental): make mods DSH plugins and drop the persistence change
A mod is now a plugin built with defineMod() around its register(on,
options); the bridge is the ClaudeCodeMods service (ctx.claudeCodeMods)
that keeps the loaded mods and raises their events. The plugin.json /
hooks.json loader, pluginDirs, and dynamic imports are gone.

prompt.submit context becomes text blocks appended to the human's own
prompt message and $.prompt.submit queues a user-sourced message, so the
bridge adds no message source kind: the persistence record and the
regenerated schema are removed and the artifacts match master again.

Engine correctness from the review round: next() is memoized and every
started run beneath is awaited before a hook's answer settles; a rewritten
tool argument skips the hook with a report pointing at the pre-tool input
rewrite proposal; timers belong to the session whose event started them;
$.tool.call injects a tool's deferred contexts; $.clock.sleep honors the
event signal; a built-in tool answered with { result } is validated against
its output schema before it becomes an error-shaped result; hooks on events
this host never raises are reported at load.

Examples: the three mods from the Claude Code blog post under examples/,
Token Weather and its test unchanged, Blast Radius and Replay Theater
completed from the published fragments, run by their own tests through a
claude-code/testing alias over the new test kit ($.ui.mount/find/press).
2026-10-03 01:38:21 +08:00
imccyu b1c5f861b6 fix(hmr): preserve loaded entry identities across manifest changes 2026-10-02 13:54:51 +08:00
imccyu 6fe4a2e184 fix(hmr): invalidate changed package manifests 2026-10-02 13:51:41 +08:00
Turtle 31fbe85ec5 Merge pull request #5626 from deepseek-harness/turtle/unrun-build-dep-bc6bf626ae0d
fix(build): reject Node processes without TypeScript type stripping
2026-10-02 13:40:47 +08:00
Tianyi Cui 600034d653 fix(experimental): harden the mods bridge after review
- prompt.submit sees and rewrites only the human's own messages, gains the
  rewritten text on an image-only prompt, and keeps only typed result fields
- a mod's $.tool.call reaches only the mods loaded before it, attributed to
  the caller, instead of re-entering every mod through the pipeline
- a .catch handler shares the failed hook's beneath state so nothing beneath
  runs twice; a late next from an abandoned handler is ignored
- hook results are validated before use; detached runs report rejections
- session.end keeps $.state readable until its hooks settle; agent creation
  cancellation abandons a waiting session.start hook; agents is read lazily
- a success a hook marks isError becomes a failure; replacement entries clear
  on tools/result; per-agent registrations drop with the agent
- $.store writes are serialized per plugin and bounded in UTF-8 bytes;
  $.http.fetch bodies are bounded; timers refuse rescheduling after unload
  and unload awaits running callbacks; regex matchers reset lastIndex
2026-10-02 13:18:17 +08:00
Turtle 500614c0d5 fix(build): pin tsdown to the native config loader
Root build scripts, the desktop bundle and the dev:web watcher pass the
native loader so tsdown never selects the undeclared unrun fallback. A spec
covers the build.ts rejection path.
2026-10-02 12:48:01 +08:00
Turtle f3013b2d8d fix(build): reject Node processes without TypeScript type stripping
Without process.features.typescript, tsdown falls back to the undeclared
unrun loader, which fails to import and, once installed, resolves
import.meta.url in packages/client/tsdown.client.ts to the entry config.

Refs #5622
2026-10-02 12:31:36 +08:00