Track illustrative scopes and retain their connectors so a contrastive
request or rejection for the current task ends the preceding example.
Preserve complete skill aliases, outer discussion guards, quoted task
qualifiers, and indirect citation protection for scored admission.
Invalidate older routing receipts and add resolver/launcher regressions
for request ordering, scope boundaries, aliases, and the reported P1.
Treat example-framing prefixes as indirect citations before checking
rejections, preserving genuine requests around illustrative instructions.
Keep e.g. together during clause splitting without rewriting e.g.js tokens.
Bump routing policy to v10 to invalidate v9 selections that loaded example
context. Cover resolver, launcher, instruction ordering, and receipt reuse.
Allow neutral imperative task preambles before an explicit skill request
without admitting final bare mentions, questions, or subject-led reports.
Keep rejection-list scoping intact and recognize must/ought questions.
Bump routing policy to v9 so an empty v8 receipt is reconsidered. Cover
resolver and launcher behavior and document the affected routing helpers.
Keep follow-up questions and reported instructions on the proposal path by
requiring recognized scopes and a direct request prefix for exact admission.
Preserve grouped rejections, personal negation, and genuine directives around
indirect discussion. Invalidate v7 receipts with routing policy v8.
Cover both Greptile reproductions and neighboring resolver/launcher cases,
including unlisted wording, nested reports, and grouped negative lists.
Limit negation to each independent directive after comma, and, or but.
Accept imperative requests with question punctuation while preserving true
questions, reported speech, and ordered rejections. Bump routing policy to
v7 so prior empty selections are reconsidered.
Add resolver and launcher regressions for the individual cases and their
combinations, including cached selections and actual context injection.
Resolve six conflicts:
- hooks/hooks.metadata.json: keep this branch's gateguard description and
fingerprint, add upstream's hookify-runtime entries.
- package.json: keep both gateguard-report.js and github-coordination.js.
- scripts/hooks/gateguard-fact-force.js, tests/hooks/gateguard-fact-force.test.js,
skills/gateguard/SKILL.md: upstream added a simpler session denial cap; this
branch already has the fuller one (cap threaded through
markCheckedAndCountDenial, malformed-value warning, miss and target notes),
so keep it. Upstream's taskset and su wrapper handling, fail-closed
recursion limit and soft-hyphen sanitising merged cleanly and their tests pass.
- manifests/context-packs/skill-triggers@1.json: take upstream's file and
recompute registryDigest for the merged registry.
Treat non-2xx activity responses as feed errors, preserve non-Markdown Copilot agent assets, and apply the reviewed reference escape parity correction with regenerated bindings. Allow the test runner to drain piped output on its existing success or failure exit status. Validate installed workflows and bounded real Node20/24 pipe regressions.
- A build interrupted while writing the index leaves a partial file under
its digest name before the pointer exists. The next build rejects those
bytes ("content changed under its digest") and cannot repair the index.
- A skill edited after the entries are read leaves an index that still
matches the stored generation, and the next build reports that
generation stale. This pins the current behavior: the index is bound to
the generation, not to live sources.
plugin-hook-bootstrap (shell mode) and observe-runner probed a bare
`bash.exe`. On Windows that resolves to the first match on PATH, and
%SystemRoot%\System32 normally sits ahead of Git's bin directory, so the
pick was System32\bash.exe: the WSL launcher. The existing guard (require
a clean probe exit) only catches it when no distro is installed. With one
installed, the probe passes inside Linux, then the hook script is handed
over by a Windows path (C:\...) or a Git Bash path (/c/...), neither of
which exists in WSL. The hook exits 127 instead of running, and
observe-runner's continuous-learning observation fails on every call.
Resolve bash candidates on Windows to absolute paths from PATH, skipping
bash.exe in System32, SysWOW64, Sysnative, and the WindowsApps alias
directory, so a native bash later on PATH (Git's) is used. With none
available, the existing "no bash binary found" skip applies. An explicit
BASH override still wins, and other platforms keep bare names.
The shared resolver lives in scripts/lib/windows-bash.js with a
platform-independent test. A Windows integration test puts System32 ahead
of Git's bash and requires the .sh hook to actually run. Upstream's
bootstrap fails that scenario with exit 127 ("/bin/bash: C:Users...hook.sh:
No such file or directory"); this one prints the hook output.
Carry forward the final scoped delta of PR #3119 at 60e82f95. Keep required dependency closure and select only modules reachable from successful requests; refresh the unchanged 293-skill registry binding.
Carry forward PR #3115ef475c79 and 780dfb78 onto current main. Preserve the newer hook-consent transforms during install and repair. Main already includes the source import fix from #3167.
On a Windows machine with Claude Code installed natively, Git for Windows,
and the ECC plugin installed, `node tests/run-all.js` on main fails 44 tests
in 7 files. Linux CI never sees them. Three of the four causes are test
isolation gaps, fixed here (43 tests):
- claude-plugin-setup, claude-scope-migration, setup (38): fixtures put a
fake claude.cmd first on PATH, but on Windows spawning a bare `claude`
resolves only .com/.exe, so a native ~/.local/bin/claude.exe ran instead
of the fake. Fixture PATHs now drop entries holding claude.exe/claude.com.
- ecc-universal-bin, eval-harness-package (4): tar received an absolute
C:\ archive path, which Git Bash's GNU tar reads as a host:path remote
spec ("Cannot connect to C: resolve failed"). Extract from inside the
destination with a relative, forward-slash archive name, which both GNU
tar and bsdtar accept.
- harness-audit (1): the cache-layout test overrode HOME only, while
findPluginInstall also reads USERPROFILE and os.homedir(), so the real
installed plugin won over the fixture. Override USERPROFILE too.
The two helpers live in tests/lib/helpers/windows-test-env.js with a
platform-independent test, so Linux CI holds both invariants too.
The 44th failure, plugin-hook-bootstrap's no-bash test, is a production
bug rather than a test leak: System32\bash.exe launches an installed WSL
distro, which passes the bash probe. It gets a separate fix.
Keep the operation lock while validating bigint file identity and reuse
only snapshots produced by successful trusted static SELECTs. Avoid
reloading and exporting unchanged databases on repeated public reads.
Retain conservative comparison for generic SQL, including RETURNING and
PRAGMA writes, and invalidate reuse after transactions, exports or errors.
Cover cache invalidation, cross-process visibility, Windows device IDs,
reentrant partial writes, lock contention and independent result objects.
Validate 188 focused tests per environment on WSL Node 22.22.3 and native
Windows Node 22.15.0/24.16.0, plus 38 related WSL tests. Paired warm-read
benchmarks show 7.6-18.1x point-query speedup on 160 KiB/1.28 MiB databases.
Handle Windows Node path stats that report dev=0 for the same file whose
open descriptor reports a volume serial. Keep bigint inode checks strict,
retain device comparisons whenever both are known, and leave POSIX strict.
Cover zero-device identity cases, high inode precision, replacement and
file-type safeguards. Verify 164 focused tests each on native Windows
Node 22.15.0 and 24.16.0, plus WSL Ubuntu Node 22.22.3.
Compare the completed snapshot after get/all queries so RETURNING and
prepared PRAGMA writes survive reloads and reopening. Export only after
the outer operation or transaction succeeds; unchanged read snapshots
still avoid disk writes. This adds one export/byte comparison per read
snapshot without relying on SQL parsing or private sql.js APIs.
Add 18 regression cases covering multi-row INSERT/UPDATE/DELETE RETURNING,
standalone and transactional get/all, no-row PRAGMA writes, and rollback.
The unfixed adapter fails 16 of these cases. Strengthen read-only checks.
Validation: 148 focused tests pass on WSL Node 22 and Windows Node 24;
the general state-store suite passes 20/20 on WSL and 19/20 on Windows,
where the existing file-symlink fixture is denied by Windows permissions.
Scoped adapter coverage is 90.13% lines, 82.73% branches, 100% functions.
ESLint, Unicode safety, and git diff --check pass.
LANGUAGE_RULES had no entry for Dart, and FRAMEWORK_RULES had no way to
detect Flutter, so any Flutter app (pubspec.yaml, lib/*.dart, android/,
ios/) was reported as primary: "unknown" by the SessionStart project-type
banner, despite ECC shipping a dart-flutter-patterns skill and a
dart-build-resolver agent for this exact stack.
Adds a 'dart' language rule (pubspec.yaml/pubspec.lock markers, .dart
extension) and a 'flutter' framework rule that checks pubspec.yaml for
the standard `flutter: / sdk: flutter` dependency shape, via a new
customCheck hook on FRAMEWORK_RULES entries. This distinguishes Flutter
apps from plain Dart packages, which don't depend on the Flutter SDK.
Closes#3469
Add Arabic (ar) localization guide and glossary, register the locale:ar component and docs-ar module across install manifests, and wire test coverage.
Contributed-by: @taljeri (taljeri)
Signed-off-by: taljeri <318237806+taljeri@users.noreply.github.com>
The ecc@ecc plugin namespaces agents, commands and skills as `ecc:<name>`.
A manual install (install-apply --target claude|claude-project) places the
same files at bare names under ~/.claude, so plugin-prefixed references in
copied markdown point at agents and commands that do not exist in that
layout (e.g. subagent_type "ecc:planner", frontmatter agent: ecc:...).
- Add plugin-namespace.js with stripPluginNamespace(), which removes the
`ecc:` prefix before an identifier and leaves `ecc@ecc`, URLs and words
ending in "ecc" alone.
- Apply it to markdown copy operations when the target is claude or
claude-project. Non-markdown files and other targets are unchanged.
- Reword the agents rule so it describes both install modes instead of
stating that agents only ship with the plugin.
- Cover the transform with tests/lib/install-plugin-namespace.test.js.
/astra-review now runs on Opus (model: opus). Opus verifies findings,
checks every diff, and runs the tests; fixes go to a Fable subagent.
When that Agent call fails with a rate_limit / HTTP 429 API error, the
command switches to Astra for the rest of the session:
- astra-review.js --fix-findings <file> sends confirmed findings to
Codex in a workspace-write sandbox with the review isolation intact
(no web search, MCP disabled, user config ignored, no API keys) and
/tmp, $TMPDIR, and the network excluded from the writable roots.
- New scripts/lib/astra-review/fix.js builds the fix prompt, validates
the structured fix result, and formats the report.
- codex.js shares one exec runner between review and fix; the sandbox
is allowlisted (danger-full-access is refused).
- The command snapshots git diff and untracked files before any writer
runs, so Opus reverts only the writer's hunks and never the user's
uncommitted work.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Under OpenCode the skill-health dashboard had no writer and no honest
fallback, so it reported every discovered skill as healthy (#2463).
Root cause: `post:skill:track` is only wired for Claude Code, where
`posttooluse-dispatcher.js` fans the event out to `skill-run-tracker.js`.
The OpenCode plugin re-implements the harness events instead of reusing that
dispatcher, so nothing ever wrote `skill-runs.jsonl` — and the tracker's
matcher only accepted the exact Claude Code tool name `Skill`, while OpenCode
calls the tool `skill`, so even wiring it would have dropped every event.
Commands that locate ECC through the inlined resolver in
`scripts/lib/resolve-ecc-root.js` also fell back to `~/.claude`, which does
not contain ECC, so they could not find their scripts.
Changes:
- `.opencode/plugins/ecc-hooks.ts`: dispatch `post:skill:track` from
`tool.execute.after`. The tracker module is imported lazily and behind
try/catch, matching the existing `changed-files-store` pattern: this file is
OpenCode's startup entry point, so a static import failure would crash the
session before any hook runs (#2530). The module is reused rather than
reimplemented, keeping its identifier validation, length bounds and
"never persist prompt text" guarantees.
- `scripts/hooks/skill-run-tracker.js`: match the tool name case-insensitively
so `Skill` and `skill` are both accepted.
- `scripts/lib/skill-evolution/health.js`: split the summary into
measured/healthy/declining/unmeasured instead of deriving `healthy = total -
declining`, which turned "no telemetry" into "everything is fine" for every
skill.
- `scripts/lib/skill-evolution/dashboard.js`: show the breakdown and warn
explicitly when skills have no recorded runs, since absence of telemetry is
not a health signal.
Under OpenCode the resolver also needs `CLAUDE_PLUGIN_ROOT`, which only the
plugin can supply: `shell.env` exports it when a root is found, without
replacing a root the user set or one an earlier plugin already put in
`output.env`.
Root discovery is per capability and probes required runtime files — never
optional content. Probing for `skills/continuous-learning-v2` (the
`workflow-quality` module) rejected supported modular installs that ship the
plugin and tracker without that optional module, disabling telemetry and the
root export for exactly those users.
Also fixes an incidental bug: the compiled plugin bundle is ESM, where
`__dirname` is undefined, so the ECC version lookup silently fell back to its
default. The module directory is now derived from `import.meta.url`.
Tests: `tests/opencode-plugin-hooks.test.js` covers the telemetry dispatch
(skill tool recorded, other tools ignored, minimal profile respected), a
modular install without the optional skills module, the root export and both
override paths; `tests/hooks/skill-run-tracker.test.js` covers the
case-insensitive matcher; `tests/lib/skill-evolution.test.js` and
`tests/lib/skill-dashboard.test.js` cover the unmeasured bucket, the warning
and the aged-out-coverage wording.
Refs #2463, #2530
Brings in the three commits main gained since the branch's merge base: the 2.2.3
release, retiring the Everything Claude Code name for ECC, and the ja-JP sponsor
update. 227 files arrive from main; two conflicted.
CHANGELOG.md: the branch had added an Unreleased section and main a released
2.2.3 section, both at the top. Both are kept verbatim with Unreleased above
2.2.3, since none of the branch's entries shipped in that release.
manifests/context-packs/skill-triggers@1.json: both sides had recomputed
registryDigest from the same earlier value to different results, and neither is
the digest of the merged tree. It is recomputed with loadContextRegistry over the
merged tree and only that field changes; triggers and triggersDigest are
untouched on both sides. validate-context-profiles passes.
All twelve CI validators pass. The full suite reports 44 failures in seven files;
43 of them fail by name and count identically on an unmodified upstream/main, and
the remaining one, plugin-hook-bootstrap, fails only inside run-all and passes in
isolation on both trees. The merge introduces no failing test that main does not
already have.
Across 240 evaluation trials every question the gate raised was about code
structure - importers, callers, public API, data schemas - while every deciding
fact in the hidden-intent corpus was an external contract: a consumer's CSV
dialect, a reporting timezone, retry safety against a non-idempotent endpoint,
collation rules, a quota policy. Obtaining the deciding fact predicted the
outcome almost perfectly in both arms, and the gate did not reliably cause it.
Add an external-contract question for code targets whose change profile touches
data, beside data-schema rather than replacing it: data-schema asks what the
change touches, external-contract asks who decides what it has to be. It reuses
the existing touchesData signal, so it stays as selective as the question it
sits with and adds no new detection, and it therefore does not reach a change
with no data involvement - pure retry semantics, for instance - which is a known
limit to be measured rather than guessed at.
Code edits that touch data now ask four questions instead of three, so the
condensed hint for an unknown profile changes too. That string was pinned by a
test as legacy-stable; the pin is updated deliberately, because a hint that
names fewer questions than the gate asks is worse than a hint that changed.
Suites: target-class 31, fact-force 1019, scenario-gate 25, eval 15, and the two
effectiveness suites 29 and 26, all passing. The 23 relevantQuestions
annotations that listed data-schema now list external-contract as well.
Yann Roberto