Commit Graph
4430 Commits
Author SHA1 Message Date
creatixchu 244ca73755 fix(ptc): keep policy cleanup waits inside PTC 2026-10-09 15:02:01 +08:00
creatixchu b7dbd7bb03 Merge master into feat/persistent-ptc 2026-10-08 20:58:22 +08:00
Yixiang Tu fad2076073 Clarify recorded compatibility decisions and review output 2026-10-08 20:26:57 +08:00
Yixiang Tu de4a771c72 Simplify same-version acknowledgements to explicit decisions 2026-10-08 20:26:57 +08:00
Yixiang Tu b2a93b6307 Accept todo identifiers in persistence review evidence 2026-10-08 20:26:57 +08:00
Yixiang Tu 5c5b51257a Allow reviewed same-version Session schema changes 2026-10-08 20:26:57 +08:00
Turtle bd097552fd Merge pull request #5868 from deepseek-harness/fix/snapshot-title-event-wait-diagnostics
test(ci): retain snapshot wait and coverage worker-exit diagnostics
2026-10-08 20:19:09 +08:00
turtle1999 e2766698df fix(coverage): keep attributing a worker exit that raced a teardown
An unexpected fork exit can close the worker's channel under a send, which
Vitest reports as a runner-level worker error instead of the clean exit. It
then tears the worker down before the ChildProcess exit event, and
DiagnosticForkWorker treated that teardown as an orderly shutdown: it cleared
the observer and marked the exit expected, so the coverage log lost the pid,
file, code and signal it exists to report.

A worker error observed before a stop now keeps the observer, and a stop
requested after that error no longer marks the exit as expected.

Vitest reports one such exit either as the clean exit path or as a
runner-level worker error, so the spec accepts both forms and compares the
record against whichever appeared.

Refs #5813
2026-10-08 19:59:17 +08:00
Yichen Yan ac080346f0 Support native HTTPS Web listeners 2026-10-08 19:49:01 +08:00
Yichen Yanandliukx0205 cb9a590c86 Support concrete Web listener bind addresses
Co-authored-by: liukx0205 <[email protected]>
2026-10-08 18:25:43 +08:00
creatixchu 6885d662d2 refactor(ptc): move mode-change coordination into sandbox policy 2026-10-08 16:43:00 +08:00
Dudu-0223 deda23bf69 Merge master into refactor/agent-team-direct-steer 2026-10-08 16:29:44 +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
Dudu-0223 e3c0599a47 Merge master into refactor/agent-team-direct-steer 2026-10-08 14:54:48 +08:00
creatixchu 801861b95e Merge latest master benchmark report updates 2026-10-08 14:29:46 +08:00
creatixchu bc2bd61f6f Merge master into feat/persistent-ptc 2026-10-08 14:17:51 +08:00
turtle1999 0e7e2ceb19 ci(bench): warn on a missing benchmark report and document the artifact
The upload warns instead of silently ignoring missing files, and the spec
pins the upload after the benchmark step. benchmarks/AGENTS.md and the
report Agent Note now name the artifact CI publishes.

Refs #5840
2026-10-08 11:55:08 +08:00
turtle1999 a646dabbe9 ci(bench): publish the scaled benchmark report as an artifact
The node-24-bench job uploads benchmarks/.dsh-report after the benchmark
step, including when a budget assertion fails, so the report the Vitest
globalSetup renders survives the runner. #5838 deferred this step because
the authoring token had no workflow scope.

Refs #5838
2026-10-08 11:32:17 +08:00
Turtle 849e9ebd8d feat(client): configure text, code, and terminal fonts and sizes independently
The General font-size row gains a More font settings disclosure that expands
a font field for each of text, code, and the sidebar terminal, plus code
(10-16 px) and terminal (10-20 px) size steppers. Font lists are normalized,
stored in the ui-theme namespace, embedded by the boot script, and placed
ahead of each role's built-in stack; the code size moves the code typography
tokens; the terminal applies font and size live and refits without replacing
the shell. ThemeRuntime adopts Host sections only after its own writes settle.

Refs #5217
2026-10-08 10:26:16 +08:00
Turtle ddd15a1ffe Merge pull request #5841 from deepseek-harness/turtle/memory-pressure-bench-4bc6543c10da
test(bench): rerun memory-sensitive benchmarks under 4 GiB and 8 GiB caps
2026-10-08 10:13:55 +08:00
Tianyi Cui cdbb78d39d fix(ci): use the compatible pnpm setup action on Intel macOS 2026-10-07 23:17:10 +08:00
Tianyi Cui 59bd530aaf chore(deps): update GitHub Actions to mature release tags 2026-10-07 22:28:27 +08:00
Turtle a8e9e9b546 fix(plugin): address review on the preset-patch revert
Let a title provider replace one that is still draining, so switching the
titles bundle during an in-flight request no longer leaves no provider.
Omit group container rows from bundle inventories, since they have no
plugin entry to switch. Drop the obsolete preset-target product-use case,
fix the Claude Code row id example, and refresh stale Agent Note text.
2026-10-07 21:27:38 +08:00
Turtle 59fd47e451 test(bench): reject swap-enabled cgroups and record the memory-limit decision 2026-10-07 21:20:08 +08:00
Turtle 51e2e5630f test(bench): rerun memory-sensitive benchmarks under 4 GiB and 8 GiB cgroup caps 2026-10-07 21:04:13 +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 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 c56fdb023e refactor(llm): configure prepared calls with explicit controls 2026-10-07 16:10:26 +08:00
Tianyi Cui 36f12b6f6e Merge pull request #5800 from deepseek-harness/worktree/ptc-providers/remove-both
refactor(tools)!: remove unused mixed tool presentation
2026-10-07 15:34:35 +08:00
Tianyi Cui ffb88d331e feat(llm): resolve minimum reasoning during call preparation 2026-10-07 14:33:23 +08:00
Tianyi Cui b99a2c147f fix(scripts): address review findings in the local bundle registry
- The summary lists only the catalog roots as installable specs; the other 29
  archives stay in the run manifest, where the installer resolves them itself.
- Only a pnpm entrypoint receives pnpm's arguments, a catalog root counts as a
  required edge for platform admission, and a signal that stops packing reports
  the interrupted exit instead of an exception.
- The packed rehearsal names the Agent SDK's musl artifact on musl hosts again,
  and its comments match what the fixture does.
- The cache test registers its pnpm children for termination, and a new case
  keeps one profile and its real lockfile: pnpm refuses a new run's URL with
  ERR_PNPM_TARBALL_URL_MISMATCH until the stale resolution is cleared with
  pnpm's own `pnpm clean --lockfile` remedy, which the desktop README now
  documents for same-version iteration.
2026-10-07 14:07:28 +08:00
Tianyi Cui c26b658e61 test(cli): keep the packed rehearsal's primary failure visible
The teardown asserted the Web process's SIGTERM exit inside `finally`, so a
body failure was reported as a shutdown timeout instead of itself. The
assertions now run only when the body passed, the earlier failure is rethrown
after teardown, and the listener readiness became a named step that no longer
clones the release pack coordinator's listen idiom.
2026-10-07 14:07:28 +08:00
Tianyi Cui eac927e143 test(scripts): cover preparation cancellation and an abandoned client
Both are failure paths the registry owns: a signal that stops packing must
report as a cancellation rather than as a pack failure, and a client that
disconnects mid-tarball must not stop later requests. execa reports the first
either as a resolved canceled result or as a thrown error, so the packing step
now names both.
2026-10-07 14:07:27 +08:00
Tianyi Cui 73d853a9ae feat(scripts): serve locally built Official bundles from a loopback registry
A packaged application installs an Official on-demand bundle as
`name@<running DSH version>`, and the plugin manager asks a custom registry
alone, so the unsigned test DMG cannot install a locally built provider before
its release reaches npm: each packed manifest still names the rest of the
repository by version, and ordinary bundle tarballs therefore resolve against
a registry that does not have them yet.

`pnpm run dev:bundle-registry` validates the Official catalog and the workspace
inventory, builds the official artifacts, packs the catalog's complete local
dependency closure with the release families' own payload and manifest checks,
records the run in `dist/test-bundles/<run-id>/bundle-registry.json` as its
completion marker, and only then serves it from 127.0.0.1 on an allocated port
under a fresh namespace. Repository-owned names are answered from this run or
refused locally; third-party packages keep npm's real metadata and bytes
through a fixed redirect. The run publishes nothing, changes no global
npm/pnpm configuration, and leaves DMG packaging untouched.

The packed installer rehearsal now installs that closure into an isolated
profile with no `file:` override, checkout link, ignore list, or scoped
registry standing in for a package the registry should answer, and it asserts a
transitive repository package served only by this run.
2026-10-07 14:07:27 +08:00
Tianyi Cui c4bda67252 test(python): own dynamic tool fixture instructions and homes 2026-10-07 14:06:44 +08:00
Tianyi Cui 19d36f602b test(python): isolate dynamic tool snapshots from log export 2026-10-07 13:53:19 +08:00
Tianyi Cui a46412bd53 fix(scripts): keep Python runtime deployment isolated and deduplicated 2026-10-07 13:51:48 +08:00
Tianyi Cui 5529a5014a fix(ci): skip the verification install when rebuilding Linux node-pty
pnpm 11.28.5 runs verifyDepsBeforeRun before a script, so `pnpm run install`
inside the installed node-pty directory first installed node-pty's own
dependencies into the package and ran its `prepare` build. Both reached the
packaged payload: the SEA blob then carried a node-gyp tree and tripled pkg's
file records, and postject aborted while injecting it. The step now runs the
package's install script alone, as it did with pnpm 11.7.0.
2026-10-07 13:10:09 +08:00
Tianyi Cui 4260fd2451 fix(scripts): keep the Python runtime payload out of its own deploy root
pnpm's legacy deploy links the deployed project into the target's node_modules
when the target sits inside that project. Materializing that link copies the
payload into itself and fails with ERR_FS_CP_EINVAL, which broke the
release-shaped Python runtime matrix on Linux and Windows. The staged payload
never carries the project source, so the staging tree's owner drops the entry
and leaves the deploy root's files alone.
2026-10-07 12:58:25 +08:00
Tianyi Cui aeb166c42e test(ptc): refresh ordinary snapshots without extra retention 2026-10-07 03:53:15 +08:00
Tianyi Cui 4359d3ee17 refactor(tools): remove mixed tool presentation 2026-10-07 01:57:57 +08:00
Tianyi Cui e9a68b2484 fix(plugin): clarify on-demand recovery and preserve package diagnostics 2026-10-07 01:26:00 +08:00
Tianyi Cui f730199b94 test(plugin): classify on-demand composition and document mock events 2026-10-07 01:26:00 +08:00
Tianyi Cui 8ed0b530ed feat(plugins): offer official bundles through on-demand installation 2026-10-07 01:26:00 +08:00
Tianyi Cui ed0376f172 fix(plugin): clarify on-demand recovery and preserve package diagnostics 2026-10-06 23:50:43 +08:00
Tianyi Cui f59c3196bf test(plugin): classify on-demand composition and document mock events 2026-10-06 23:50:43 +08:00
Tianyi Cui 72aa4966cd feat(plugins): offer official bundles through on-demand installation 2026-10-06 23:50:10 +08:00
Tianyi Cui 2b0dd1567d fix(plugins): preserve Creator drafts and refresh bundle validation 2026-10-06 23:48:59 +08:00
Tianyi Cui 55dfd3bab1 fix(plugins): narrow optional bundles and create fresh session agents 2026-10-06 23:48:59 +08:00
Tianyi Cui fbb95c0f16 fix(plugin): preserve final pinned composition and browser inventories 2026-10-06 23:48:59 +08:00