Commit 2d40baac (PR #2304) renamed `_ecc_*` -> `_clv2_*` but missed this
single call site. The launcher sources `scripts/lib/homunculus-dir.sh` which
only exports `_clv2_resolve_homunculus_dir`, so any user enabling the
observer (`observer.enabled: true`) gets:
start-observer.sh: line 40: _ecc_resolve_homunculus_dir: command not found
The hook (`observe.sh`) uses the correct name and writes observations, but
the lazy-start path fails silently via nohup, so the symptom is
"observations grow forever, no new instincts". Confirmed on
affaan-m/ECC@40927950c (HEAD of main).
Default `observer.enabled: false` masks the bug for new users. Opt-in
users hit it on first manual `start-observer.sh start` or first lazy-start
after enabling.
Fix: rename the single call to `_clv2_resolve_homunculus_dir` to match
the lib export and every other caller in the skill.
The 'Parallel Task Execution' rule encourages agents to spawn subagents,
but defines no completion contract. Observed failure mode: subagents
followed the rule, spawned their own children, and returned 'waiting
for background agents' as their final answer. All children completed
successfully, but their results were orphaned because a parent whose
turn has ended cannot receive completion notifications - leaving
zombie 'running' tasks and lost work.
Adds three rules that apply at every delegation depth:
1. Your final message IS the deliverable (never end with 'waiting')
2. If you delegate, you own collection (no fire-and-forget)
3. Decompose only when work cannot fit in one context
* refactor(hooks): consolidate PostToolUse hooks into sync/async dispatchers
Replace 10 individual PostToolUse entries in hooks.json with two
consolidated dispatcher entries (post:dispatcher:sync /
post:dispatcher:async). The dispatcher's internal registry preserves
every hook ID, matcher, and profile, so ECC_DISABLED_HOOKS and
ECC_HOOK_PROFILE gating behave exactly as before.
Performance (Edit event, actual hooks.json commands spawned in
parallel like the harness does, median of 7 runs):
- Blocking hook latency: 81ms -> 49ms (~40% faster; 7 blocking
processes -> 1 sync dispatcher)
- Node processes per tool call: 10 -> 2 (7 blocking + 3 async
-> 1 sync + 1 async)
- observe-runner now runs in-process (~370ms) inside the async
dispatcher, which stays backgrounded (async: true, timeout 45s),
so it adds no user-facing latency.
Also:
- dashboard-web lists dispatcher-managed child hooks so the hook
inventory stays complete
- post-edit-console-warn refactored to export run() for in-process
dispatch while keeping standalone stdin behavior
- dispatcher stdin reading is multi-byte safe (StringDecoder) and
child hook exit codes propagate to the dispatcher exit code
* test(hooks): replace emoji literal with unicode escape for CI unicode safety check
* fix(hooks): adopt explicit cli() entrypoint and merge multi-hook stdout
Address Greptile review on #2494:
- Replace the non-standard 'require.main === undefined' guard with an
explicit exported cli(). The hooks.json bootstraps now call
require(s).cli(), so merely requiring the module (dashboard-web,
test runners, Jest, worker threads) can never trigger dispatch,
attach stdin listeners, or set process.exitCode.
- Replace last-writer-wins stdout with mergeHookStdout(): when several
hooks emit additionalContext envelopes they merge into a single
PostToolUse envelope; non-mergeable raw stdout keeps the last hook's
output and emits a stderr warning naming the dropped hook IDs, so
nothing is lost silently.
Also includes local formatter reformatting of the dispatcher and its
test file (no behavioral changes beyond the above).
* fix(hooks): keep post:bash:dispatcher phase reachable in minimal profile
The Greptile P1 premise was partially incorrect: sub-hooks without
explicit profiles default to standard,strict via parseProfiles()
(scripts/lib/hook-flags.js), so audit/cost logs never ran under the
minimal profile on main either — there is no user-visible regression.
However, main did spawn the bash dispatcher phase unconditionally and
let each sub-hook gate itself. Restore that semantic by opening the
outer registry gate to minimal,standard,strict so a future sub-hook
that opts into minimal is not silently blocked at the phase level.
Adds the previously missing minimal-profile async dry-run test.
* test(hooks): assert failing hook exit code propagates to real process status
Spawns the actual dispatcher subprocess with an injected failing hook
and asserts the OS-level exit status, stderr diagnostic, and suppressed
pass-through — closing the E2E gap CodeRabbit flagged on #2494.
* chore: retrigger CI (flaky windows powershell bootstrap test)
* fix: make the installer runtime pass strict supply-chain vetting
Remediate the four enterprise supply-chain vetting blockers from
affaan-m/ECC#2502 so the installer runtime (package.json + manifests +
scripts/lib/**) passes strict exact-pin evidence policy:
1. Remove the package.json `postinstall` lifecycle script (it only echoed a
post-install banner) and move that banner to an explicit opt-in
`npm run welcome` command. No install-time lifecycle script remains.
2. Exact-pin every dependency in package.json (dependencies + devDependencies)
to the versions already resolved in package-lock.json; no ^/~ ranges.
3. Replace non-ASCII characters on the installer runtime script/config surface:
em-dashes (U+2014) in scripts/lib/{path-safety,install-executor,
install/link-rewrite}.js comments and the two "Itô" (U+00F4) occurrences in
manifests/{install-components,install-modules}.json descriptions become
ASCII, so strict-surface Unicode scanners are clean.
4. Drop the bare `require("ajv")` from scripts/lib/install-state.js; the file
already carries a complete hand-rolled validator enforcing the same
schemas/install-state.schema.json (ecc.install.v1) constraints, so the
installer closure is dependency-free (zero non-builtin bare requires).
Refs affaan-m/ECC#2502
* fix: avoid unpinned welcome invocations
Signed-off-by: Samar Tomar <samar_tomar@hotmail.com>
* fix: validate translated skill frontmatter
Signed-off-by: Samar Tomar <samar_tomar@hotmail.com>
* fix: repair skill frontmatter YAML
Signed-off-by: Samar Tomar <samar_tomar@hotmail.com>
* fix: add MIT license to core skill manifests; pin verification-loop tsc invocation
* fix: preserve tsc/pyright exit status in verification-loop type-check (set -o pipefail)
* chore(deps): sync lockfiles with exact-pinned package.json
Regenerate package-lock.json and yarn.lock so the pinned dependency
specs are reflected in both lockfiles. npm ci and Yarn's --immutable
install now pass the sync check. The resolution tree is unchanged
(231 yarn resolutions, byte-identical set; zero npm transitive drift);
only the root descriptor strings move from ranges to the versions
already resolved in the committed lockfiles.
Addresses the Codex P1 on #2503.
---------
Signed-off-by: Samar Tomar <samar_tomar@hotmail.com>
Co-authored-by: Samarjeet Singh Tomar <samartomar@gmail.com>
* fix(project-detect): parse Python deps pinned with ~= and @ direct references
* test(project-detect): cover ~= compatible-release and @ direct-reference parsing
* test(project-detect): cover direct references
* fix(project-detect): skip bare VCS/URL requirement lines in getPythonDeps
A requirements.txt line like git+https://host/repo.git#egg=pkg carries
no leading package name, so the delimiter split recorded the whole URL
fragment as a dependency. Skip names that start with git+ or contain a
URL scheme, and tighten the test assertions so any leaked URL, scheme,
or @ delimiter fails loudly.
* fix(plan-canvas): stop dropping list items when a block's first item is over-indented
* fix: address greptile findings for PR #2501 - list-type detection and outdent nesting
- plan-canvas markdown: fix nested list rendering where outdented runs (indent
6→4) create duplicate sibling UL blocks instead of sharing parent (#2501)
- transcript-context: add LARGE_WINDOW_NATIVE_MODEL_IDS array for models whose
default context window is 1M but do NOT carry the [1m] marker (fixes#2497)
- Add test coverage for transcript-context and shell-substitution modules
- Add test coverage for project-detect module (#2498)
* fix(plan-canvas): handle outdented list runs
* fix(plan-canvas): start a new list when marker type changes at the same indent
CommonMark treats a marker-type change (bullet to ordered or back) at
the same indentation as the start of a new list. buildList previously
absorbed the run into the current list, so mixed runs rendered under a
single wrong tag. Stop the run on a tag change and let buildListBlock
render the next run as a sibling list with its own tag.
* fix(llm/providers/claude): attach cache_control to system block, not top-level
The Anthropic Messages API does not accept `cache_control` as a top-level
request parameter — it is a per-content-block field. Passing it at the top
level raises `TypeError` in the Python SDK (which validates kwargs against
`messages.create()`'s signature) or a `400 unknown_parameter` from the API,
so every ClaudeProvider.generate() call fails.
Move `cache_control: {"type": "ephemeral"}` onto the last system-prompt
block so ephemeral prompt caching still works when a system prompt is
present, and drop it when there isn't one (nothing to cache).
Existing tests didn't catch this because `FakeMessages.create(**_params)`
accepted anything and ignored the kwargs. FakeMessages now records
`last_params`, and two regression tests assert that:
- `cache_control` never appears as a top-level param, and
- when a system prompt is set, `cache_control` rides on the last block.
Fixes#2512
* test(claude_provider): split composite isinstance+truthiness assertion (PT018)
Ruff PT018 flagged the combined `isinstance(system, list) and system` check
in `test_generate_does_not_pass_cache_control_as_top_level_param`. Split
it into two focused asserts (`isinstance(system, list)` then `assert system`)
so a failure points at the exact violation instead of a compound condition.
Behavior unchanged; 6/6 tests still pass.
Addresses CodeRabbit review on #2515.
* feat: add Plan Canvas - browser annotate-and-approve review for plan artifacts
- scripts/plan-canvas.js CLI (open/await/end/stop/server; bin ecc-plan-canvas)
- loopback server + ECC-styled chrome + annotation SDK + zero-dep markdown renderer
- Approve/Request-changes verdicts wired to the /plan confirmation gate
- plan-canvas skill, /plan-canvas command, SessionStart hook surfacing open reviews
- shared scripts/lib/loopback-guard.js extracted from control-pane (API re-exported)
- 121 new tests incl. full-workflow E2E; registered in manifests, catalog, registry
Inspired by lavish-axi (https://github.com/kunchenguid/lavish-axi) by @kunchenguid;
original ECC-native implementation, not a port.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor(plan-canvas): invoke via ecc-plan-canvas bin so the skill works from any project
Skill/command referenced a cwd-relative `node scripts/plan-canvas.js`, unusable
outside the ECC root. Switch to the ecc-plan-canvas bin (and $CLAUDE_PLUGIN_ROOT
fallback) and align CLI next_step hints so an agent can run it as a skill in any repo.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(plan-canvas): render Mermaid diagrams + ship Codex cross-harness surface
- markdown renderer emits <pre class="mermaid"> for ```mermaid blocks (source
entity-escaped so the browser decodes it for the renderer while blocking injection)
- artifact template loads a pinned Mermaid build only when a diagram is present,
themed to ECC dark, securityLevel strict, graceful offline fallback to source
(ECC_PLAN_CANVAS_MERMAID_URL overrides for a local mirror)
- skill teaches Mermaid-for-diagrams and states the CLI+JSON loop is harness-agnostic
- add .agents/skills/plan-canvas (Codex) with agents/openai.yaml interface manifest
- register in install-modules workflow-quality paths; docs updated
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(plan-canvas): add demo screenshot
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(ci): sync yarn.lock with new bin; add contributor checklist
- yarn.lock records the ecc-plan-canvas bin so Yarn hardened-mode install no
longer wants to modify the lockfile on public PRs
- PR template + CONTRIBUTING gain a pre-push checklist covering the lockfile
trap and the full skill/command/CLI registration surfaces
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Haley Chen <2022hachen@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Replaces 54 predictable os.tmpdir()+Date.now() test-home paths in
tests/hooks/hooks.test.js and the pid-based transcript files in
tests/lib/llm-summary.test.js with fs.mkdtempSync. The 22
claude-tool-count-* sites are left as-is: they intentionally mirror
the path the production hook computes. Clears all 16 open code-scanning
alerts (#256-#271).
Rebuild of #2154 on current main, following the hermes/openclaw (#2433)
adapter recipe: 10-line kimi-project adapter (project kind, ./.kimi root),
registry + helpers ownership, SUPPORTED_INSTALL_TARGETS + legacy-compat
modules, kimi target on the 5 shared modules + .kimi in platform-configs
paths, both schema enums, npm files allowlist, help text, README stub.
Credit to @MoYiC6 for the original adapter design in #2154.
* feat: add Hermes and OpenClaw harness install targets
- Add scripts/lib/install-targets/hermes-home.js and openclaw-home.js
- Register new adapters in registry.js and helpers.js
- Add hermes/openclaw to SUPPORTED_INSTALL_TARGETS, schema enum, and install help text
- Add .hermes/ and .openclaw/ platform source directories with READMEs
- Update install-modules.json so rules/agents/commands/platform-configs cover the new targets
Verification:
- npx ecc doctor reports all 13 targets OK (including hermes-home and openclaw-home)
- install-targets regression guard passes for new targets
- Catalog check passes
* fix(install): register hermes/openclaw in install-modules schema enum + npm files allowlist
---------
Co-authored-by: Lxcardoza993 <265670745+Lxcardoza993@users.noreply.github.com>
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
The fact-forcing gate fires once per first-touched file per session. In
build-heavy sessions this costs a deny->retry round-trip on every new file,
including trees where the gate's questions ("who imports this? what schema?")
carry no signal: test files, generated artifacts, scratch dirs.
Add an opt-in, comma-separated glob allowlist read from GATEGUARD_EXEMPT_GLOBS.
A matching Edit/Write/MultiEdit target skips the first-touch gate; destructive-
Bash and routine-Bash gates are untouched. Default-off (unset => identical prior
behavior), fail-open (a malformed glob is dropped, never throws), and memoized on
the env value, matching the existing getExtraDestructiveRegex idiom.
"env": { "GATEGUARD_EXEMPT_GLOBS": "**/tests/**,**/scratchpad/**" }
Adds 4 tests; all 144 gateguard tests pass.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(continuous-learning-v2): standardize shell shebangs to env bash
Three scripts under skills/continuous-learning-v2/ used the hardcoded
`#!/bin/bash` shebang while the other four already used the portable
`#!/usr/bin/env bash`:
- hooks/observe.sh (runs on every hook invocation)
- scripts/detect-project.sh
- agents/start-observer.sh
The hardcoded interpreter path fails to execute on systems where bash is
not installed at /bin/bash (NixOS, some Homebrew layouts, FreeBSD).
Standardize all three to `#!/usr/bin/env bash`, matching the repo-wide
majority convention, and add a regression test that asserts shebang
uniformity for every shell script in this skill so the inconsistency
cannot reappear.
Fixes#2303
* test(continuous-learning-v2): harden shebang test runner
Address review feedback on the shebang-consistency regression test:
- firstLine() now splits on /\r?\n/ so a script checked out with CRLF
line endings does not leave a trailing carriage return that would
break the shebang comparison on Windows.
- The test() helper now surfaces the full error (stack trace, not just
the message) on failure and writes pass/fail lines via
process.stdout/stderr so diagnostics are preserved.
* test(continuous-learning-v2): skip hidden dirs in shebang scan
The recursive shell-script scan now skips hidden directories (e.g. the
observer's runtime `.observer-tmp`). This keeps the shebang-consistency
check deterministic: only committed skill scripts are examined, and an
untracked local artifact left over from an observer run can no longer
cause a false failure.
* feat(session-start): make instinct injection count and confidence threshold configurable
Expose ECC_MAX_INJECTED_INSTINCTS and ECC_INSTINCT_CONFIDENCE_THRESHOLD so
operators can tune SessionStart instinct injection without editing source.
Defaults are unchanged (6 instincts, 0.7 confidence floor).
The two previously hardcoded constants become DEFAULT_-prefixed fallbacks,
resolved through getMaxInjectedInstincts() and getInstinctConfidenceThreshold(),
mirroring the existing getSessionRetentionDays() /
getSessionStartMaxContextChars() env-override pattern already in this file.
Invalid or out-of-range values fall back to the defaults.
Adds subprocess coverage in tests/hooks/hooks.test.js and documents both
variables in the README Hook Runtime Controls section.
Implements part (a) of #2371.
* fix(session-start): reject partial env values for instinct injection knobs
Parse ECC_MAX_INJECTED_INSTINCTS and ECC_INSTINCT_CONFIDENCE_THRESHOLD with
Number() (after trim) instead of parseInt/parseFloat, so malformed values
like "3.9", "6abc", or "0.7x" fall back to the default rather than silently
accepting the numeric prefix (parseInt("3.9")=3, parseFloat("0.7x")=0.7).
Adds a regression assertion that a non-integer count falls back to 6.
* fix(session-start): validate decimal grammar for instinct injection env vars
Number() still accepts non-decimal numeric syntax, so
ECC_INSTINCT_CONFIDENCE_THRESHOLD=0x1 resolved to 1 and
ECC_MAX_INJECTED_INSTINCTS=1e2 to 100. Gate each value on a strict format
(/^\d+(\.\d+)?$/ for the 0-1 threshold, /^\d+$/ for the positive-integer
count) before converting, so hex/exponent/partial values fall back to the
default. Adds regression assertions for 1e2 and 0x1.
* fix(steering): add missing name attribute to auto-inclusion steering files
* docs: include name attribute on steering file example
---------
Co-authored-by: Jucelio Brandao Goncalves Junior <jbgjunior@simpress.com.br>
* fix(install): rewrite relative skill links for injected ecc namespace
Skill and rule markdown is byte-copied during a claude install, but the
home/project adapters inject an `ecc/` namespace segment
(skills/<id> -> skills/ecc/<id>, rules/<x> -> rules/ecc/<x>). Source-relative
links such as `../../rules/react/hooks.md` therefore broke after install: the
extra level changed what `../..` resolved to, and the link target itself moved
under rules/ecc/.
Rewrite relative links in namespaced markdown so they resolve to the file's
actual installed location, derived from the plan's own file placements (no
hardcoded namespace literal, so the links cannot drift from where files land).
Non-namespacing adapters and links to non-installed targets are left untouched;
URLs, anchors, absolute paths, and fenced code blocks are never rewritten.
Fixes#2340
* fix(install): keep non-namespaced markdown on the byte-for-byte copy path
Address review feedback: the markdown branch in applyInstallPlan diverted every
copy-file markdown operation through read+rewrite+write, so identity-mapped
markdown (source path == install path, no namespace injected) lost byte-for-byte
content and source mode bits even though no link rewrite was needed.
Gate the rewrite on isNamespacedSource() so only files whose install path
actually changed (e.g. skills/x -> skills/ecc/x) leave the copyFileSync path;
everything else is copied verbatim as before.
* test(install): emit failure stack in the link-rewrite test runner
Address review feedback: the local test() harness logged only error.message,
so a failing assertion lost its source line and diff. Print error.stack on
stderr on failure so broken rewrite cases stay diagnosable.
* fix(observer): replace hardcoded sleep 2 with PID file poll in start-observer.sh
Fixes#2295
The previous `sleep 2` after launching the observer loop has two
problems: on slow filesystems or loaded systems 2 seconds may not be
enough, producing a false-negative on the subsequent PID file check; on
healthy systems it adds unnecessary latency.
Replace with a poll loop that exits as soon as the PID file appears:
for _i in $(seq 1 50); do [ -f "$PID_FILE" ] && break; sleep 0.2; done
50 × 0.2s = 10s max wait (vs the previous fixed 2s), but typical startup
returns within the first iteration. No behavior change in the success
path — only the wait strategy changes.
Tests: `node tests/run-all.js` 2891 passed / 0 failed; `npm run lint`,
`catalog:check`, `command-registry:check` all clean.
* test(observer): add regression guard for sleep-2 → PID-file poll (#2295)
Asserts start-observer.sh never reverts to the fixed `sleep 2` wait and
keeps the 50 × 0.2s `$PID_FILE` poll in place. Sits next to the existing
observer-loop invariant block in tests/hooks/hooks.test.js, matching the
repo's pattern of guarding shell-script invariants via source-content
assertions.
Without this, any future "cleanup" that reintroduces a fixed sleep would
silently regress the slow-filesystem fix from the previous commit.
* fix(observer): loosen poll-regression assertions and document failure-path latency (#2356 review)
Addresses CodeRabbit + Greptile feedback on PR #2356:
- tests/hooks/hooks.test.js: split the over-specific positive assertion
(which pinned the exact `for _i in $(seq 1 50); … sleep 0.2; done`
line) into three intent-based assertions — bounded iteration count,
early-exit on $PID_FILE, sub-second interval. Valid refactors (rename
loop var, switch to `while`, retune to 100 × 0.1s) no longer false-fail
while the `sleep 2` regression remains guarded.
- start-observer.sh: extend the inline comment to record the trade-off
Greptile flagged — a loop that crashes before writing $PID_FILE is now
detected in ~10s instead of ~2s. Healthy startups still return in
iteration 1.
Tests: node tests/run-all.js (Node v22.18.0) → 2892 passed / 0 failed.
OpenCode ships override command files under .opencode/commands/ that
shadow the generic commands/*.md sources. The manifest install plan
recorded both writes against the same destination, so `ecc doctor`
reported perpetual drift for the 29 shadowed command files and `ecc
repair` "fixed" that phantom drift by copying the generic source over
the correct override, corrupting the installed command while never
clearing the warning.
Dedupe copy-file operations by destination in createManifestInstallPlan,
keeping the last writer to match the sequential apply order. install,
repair, and doctor all consume this one builder, so a fresh install is
clean and a single repair rewrites drifted state green.
Fixes#2414
SKILL.md and _promote_auto already use avg_conf >= 0.8; observer.md
(EN + zh-CN) was missed and still says per-instance. Same drift as
#2274.
Refs #2298.
The Hook Setup section told all users to wire
`node ~/.claude/scripts/hooks/suggest-compact.js` into settings.json.
That path only exists on manual `./install.sh` installs; for plugin
installs the hook is already registered by the plugin's hooks/hooks.json
(id `pre:edit-write:suggest-compact`, standard/strict profiles), so the
snippet fails silently and would double-register the hook.
- Add a plugin-install note (mirrors continuous-learning-v2 wording)
and scope the snippet to manual installs — applied to the canonical
skill, the .kiro mirror, and ja-JP/zh-CN/zh-TW/ko-KR translations
- ko-KR: also replace the settings.json snippet that used
`${CLAUDE_PLUGIN_ROOT}`, which does not resolve in user settings.json
Every other language pack (typescript, react, python, golang, vue, ...) scopes its rules with a paths: YAML frontmatter block, so Claude Code only loads them when matching files are in context. The 7 files in rules/web/ ship without frontmatter, and per the official rules-loading docs (https://code.claude.com/docs/en/memory) rules without a paths field load unconditionally into every session - ~15.5KB of always-on context even in projects with no frontend code.
Add the same frontmatter convention used by the react pack, scoped to web-facing file types (css/scss/sass/less/html/tsx/jsx/vue/svelte).
golangci-lint deprecated the govet `check-shadowing` setting in v1.57.0 and
later removed it; a config using it now errors. The current v1-format way to
enable the shadow analyzer is `govet.enable: [shadow]`.
Applies to the source skill and the ja-JP, zh-CN, zh-TW, ko-KR, tr translated
copies.
Refs: https://golangci-lint.run/docs/product/migration-guide/
* fix(clickhouse-io): use official @clickhouse/client instead of unmaintained clickhouse package
The example imported the third-party `clickhouse` (TimonKK) package and used
its API (new ClickHouse, .query().toPromise(), .insert().stream()). Migrate to
the official @clickhouse/client: createClient() and structured
clickhouse.insert({ table, values, format }). The structured values array also
removes the previous SQL string-interpolation anti-pattern.
Applies to the source skill and the ja-JP, zh-CN, zh-TW, ko-KR translated
copies (translated code comments preserved).
Refs: https://clickhouse.com/docs/integrations/javascript
* fix(clickhouse-io): migrate remaining insert calls to @clickhouse/client
Address review feedback: the earlier commit missed two spots that still used
the legacy clickhouse API.
- CDC example: clickhouse.insert('market_updates', [...]) ->
clickhouse.insert({ table, values, format: 'JSONEachRow' })
- Single-row insertTrade: map the row to the column shape (same as the bulk
path) instead of passing the raw trade object.
Applies to the source skill and the ja-JP, zh-CN, zh-TW, ko-KR copies.
* docs: add MRR-biased ECC Pro + AgentShield security roadmap
Output of a multi-agent survey + research pass: capability map of AgentShield
and ECC Pro, triage of every open PR/issue on both repos, and web research on
competitors, unbuilt ideas, and dev-tool demand. 17 items across 4 themes
(now/next/later) scored for free-to-paid conversion, each linked to the real
PRs/issues that implement it. Includes the reusable workflow script that
generated it.
Headline: ecc-agentshield is ~30K downloads/month with near-zero monetization
bridge, and the agent-proximity moat is computed but never rendered. Roadmap
removes trust blockers (FP cluster), makes the moat visible (PR #2320), then
productizes local CLI primitives into hosted Pro surfaces.
* docs(design): add hosted Pro fleet dashboard design (Sentry for agent security)
Implementation-ready architecture for the flagship 'next' roadmap item: a
hosted, multi-repo agent-security posture dashboard built on the existing
ecc-agentshield primitives (evidence-pack bundleDigest + operatorReadback,
watch/drift DriftResult, runtime NDJSON, baseline diff, policy promotion).
Covers free-vs-Pro scope, ingestion/query API grounded in real field names,
data model + time-series rollups, auth/RBAC + redaction guarantees, MVP build
order, and pricing hooks. Companion to ECC-PRO-SECURITY-ROADMAP.md.
* feat(control-pane): serve 3D agent-airspace viz + /api/proximity feed (#2320)
Adds the Layer 4 observability view to the control pane: a self-contained,
dependency-free 3D point-cloud of the agent airspace (positions from the
proximity embedding, sized by working set, colored by collision risk, links
for converging pairs) plus an XSS-safe advisory panel that polls every 5s.
- proximity-viz.js: renderProximityVizHtml() (canvas projection, no external JS)
- server.js: GET /proximity (page) + GET /api/proximity (snapshot.proximity feed)
- test: asserts both routes serve and the feed carries positions/links/advisories
* fix(clv2): escape $HOME before pgrep -f in migrate-homunculus.sh (#2339)
* fix(clv2): escape $HOME before pgrep -f in migrate-homunculus.sh
pgrep -f treats its argument as an extended regular expression, but the
running-observer guard interpolated $HOME unescaped. Paths containing regex
metacharacters (e.g. /home/user.name, /home/c++dev, /home/user (work)) made the
match over-broad or invalid, causing either a false negative (live observer
missed, migration proceeds and risks registry corruption) or a false positive
(migration blocked unnecessarily).
Escape the ERE metacharacters in $HOME via sed before building the pattern so
the home prefix is matched literally while the trailing .*observer-loop\.sh
regex is preserved. Portable across BSD and GNU sed.
Fixes#2301
* test(clv2): add regression test for migrate-homunculus.sh $HOME escaping
Guards the #2301 fix: extracts the script's sed escaping command and asserts
the resulting pgrep -f pattern matches the literal home path while no longer
over-matching a regex-expanded decoy (HOME=/home/user.name must not match
/home/userXname). Also pins that the guard uses escaped_home rather than $HOME
directly. Follows the existing clv2 shell-test convention in
tests/hooks/observe-entrypoint-allowlist.test.js.
Refs #2301
* test(clv2): skip migrate-homunculus escaping test on Windows
The test relies on POSIX bash/sed/grep -E semantics, which differ on the
Windows CI runners. Guard with the same process.platform === 'win32' early
exit used by tests/hooks/observe-subdirectory-detection.test.js so the
bash-dependent assertions only run on POSIX platforms.
Refs #2301
* fix(clv2): harden registry writes and project deletion (#2294, #2297) (#2323)
Two security-priority fixes in continuous-learning-v2/scripts/instinct-cli.py:
- #2294: _write_registry wrote projects.json without the advisory lock that
_update_registry holds, so concurrent 'projects delete/gc/merge' could race an
observe-time update and corrupt the registry. Extract the lock into a shared
_registry_lock() context manager and use it in both writers.
- #2297: _remove_project_storage called shutil.rmtree on PROJECTS_DIR/project_id
with no containment check. Add defense-in-depth: resolve the path and refuse to
delete anything that is not strictly inside PROJECTS_DIR (or is the root
itself), so a relaxed validator or future caller can never cause an
arbitrary-directory delete.
Adds 5 pytest regression tests (atomic write under lock, contained delete,
missing-dir no-op, traversal refused, root refused). Node integration suite
(tests/scripts/instinct-cli-projects.test.js) green 9/9.
* feat(workflows): add orch-review native Workflow pilot (#2363)
* feat(workflows): add orch-review native Workflow pilot
Port orch-pipeline Phase 5 (Review) to a native Claude Code Workflow
script. The gated outer loop stays in the main conversation; this script
owns only the autonomous review+verify segment between the two human
gates:
1. Review — reviewers fan out in parallel: ecc:code-reviewer always,
ecc:<language>-reviewer when args.language maps, ecc:security-reviewer
when the orch-pipeline security trigger matches the diff/paths.
2. Dedup — merge findings across dimensions keyed on the normalized
evidence snippet, since independent reviewers flag the same line.
3. Verify — each unique CRITICAL/HIGH finding goes to an independent
adversarial verifier; MEDIUM/LOW pass through as advisory.
The Review->Verify barrier is deliberate: deduping before verification
stops the verifier running N times on the same bug (local testing: 11
raw findings collapsed to 4 unique, ~halving verifier cost).
Existing ECC reviewer subagents are reused via agentType; reviewer
output is validated by JSON schema. args is accepted as an object or a
JSON-encoded string.
- workflows/orch-review.workflow.js — the workflow script
- workflows/README.md — invocation contract, returns shape, follow-ups
CI lint is scoped to scripts/ and tests/, so the script (validated with
node --check) and the README (passes markdownlint) are untouched.
* fix(workflows): fail closed on invalid args and lost review dimensions
Addresses the two safety findings from the PR bot review:
1. Lost review dimension (Greptile P1 / CodeRabbit Major): a reviewer
agent that returns null or rejects was silently dropped by
filter(Boolean), so an unreviewed security dimension could still
return APPROVE. Each dimension's outcome is now captured; failures
land in failedDimensions and force CHANGES_REQUESTED (incomplete).
2. Invalid args (CodeRabbit Major): an empty diff returned APPROVE and
bad JSON / non-array changedFiles threw inconsistently. Input is now
validated up front and rejected with a clear error — the gate fails
closed instead of approving an unreviewed payload.
Docs (header contract + README) updated for the new return fields
(incomplete, failedDimensions, stats.failed). Remaining bot nits
(evidence minLength, verify-label collision, verified->confirmed
rename, contract drift) deferred as follow-ups.
* fix(workflows): address remaining orch-review review nits
Follow-up to the bot review (deferred items from the safety pass):
- evidence: require minLength 1 in the schema, and fall back to a
title+line dedup key when evidence is empty, so empty-evidence
findings in one file no longer collapse onto a single key and drop
(CodeRabbit).
- verify label: include a slice of the normalized evidence so two
CRITICAL/HIGH findings from the same file get distinct labels and do
not alias under resumability (Greptile).
- stats.verified -> stats.confirmed to match the "confirmed" wording
used in the log and avoid ambiguity vs the refuted count (Greptile);
header contract and README updated to match.
Verified by running the workflow on a synthetic vulnerable diff:
dedup 12 raw -> 5 unique, stats.confirmed populated, fail-closed fields
(incomplete/failedDimensions) intact.
* fix(workflows): harden verify stage and diff-only verification
Addresses the second-round bot review:
- Verify stage now has the same failure guard as the review stage: a
rejected verifier no longer nulls out its slot (which crashed the
later filter). A null return is treated as unconfirmed; a rejection
keeps the finding as blocking (fail closed) so an unverifiable
CRITICAL is never silently demoted to advisory (CodeRabbit @221).
- verifyPrompt now instructs the skeptic to judge solely from the
provided diff text and not to refute merely because the referenced
file is absent from the working tree (the diff may be an unapplied
PR). Fixes the false-refute seen when testing on a synthetic diff.
CodeRabbit @81 (evidence minLength) was already addressed in the prior
commit; this is a stale re-post on the unresolved thread.
* fix(workflows): keep unverifiable blockers blocking; stop leaking error text
Second-round bot review (CodeRabbit):
- @218 Treat a null/failed verifier as `unverified`, not refuted. A
terminal verifier failure or skip no longer demotes a CRITICAL/HIGH
to advisory; it stays in `blocking` tagged "could not be verified"
(fail closed). Only a genuine isReal=false verdict is refuted. Adds
stats.unverified.
- @189 Do not return raw subagent error text. Review/verify failures
now log the raw message for operators and return only a bounded label
(failedDimensions[].error = "review agent failed").
Stale re-posts this round (@81 evidence minLength, @224 verify guard)
were already fixed in prior commits.
* docs(workflows): enumerate bounded failedDimensions.error labels
CodeRabbit (trivial): the public contract implied callers get
human-readable error text, but the implementation returns only bounded
labels. Enumerate them in the README returns block.
* Update yarn.lock (#2342)
* Add memxus configuration to mcp-servers.json (#2355)
* Add memxus configuration to mcp-servers.json
Added configuration for Memxus service with API key placeholder and description.
* Revise description in mcp-servers.json
Updated the description to include a note about reviewing stored memories to prevent prompt-injection.
* Update description in mcp-servers.json
Update description in mcp-servers.json
* Fix for docs: Scope Decision Guide table duplicated in SKILL.md and observer.md with minor drift (#2366)
#2306
Co-authored-by: angadsingh7666 <angdsingh7666@gmail.com>
* fix(llm): align Claude provider with current Anthropic API (#2133)
Replace invalid default model IDs (e.g. claude-sonnet-4-7) with current
claude-sonnet-4-6, claude-opus-4-8, and claude-haiku-4-5. Route system
messages to the API system field, enable ephemeral prompt caching, omit
temperature for Opus 4.7/4.8, and surface cache usage metrics. Update the
CLI model picker to match.
Co-authored-by: Vladimir Đuranović <vlada@MacBook-Pro.local>
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(release): derive approval gate paths from version (#2383)
Co-authored-by: jan <jan@w-saxs001.local>
* fix(release): derive video suite paths from version (#2384)
Co-authored-by: jan <jan@w-saxs001.local>
* ci: isolate OMP workflow verification (#2382)
Co-authored-by: jan <jan@w-saxs001.local>
* fix(tests): resolve 10 failing tests on Windows (#2307)
- resolve-formatter: stop findProjectRoot walk before os.homedir() to
avoid mistaking global dotfiles (e.g. ~/.prettierrc) for a project root
- instinct-cli-projects: detect python3/python binary at runtime; skip
gracefully when Python 3 is unavailable instead of crashing with null status
- command-registry: regenerate COMMAND-REGISTRY.json (was stale)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(hooks): quote args when probing Windows .cmd MCP servers via shell (#2343)
On Windows, when a bare-name MCP server command (e.g. codesys-mcp-sp21-plus)
falls back to the .cmd candidate, the probe sets shell:true to work around
Node 18.20+ CVE-2024-27980. However, passing an args array alongside
shell:true causes Node to concatenate the tokens without quoting (DEP0190),
so an arg containing a space (e.g. --codesys-path "C:\Program Files\...") is
re-split by cmd.exe at every space boundary. The child process receives a
truncated path, fails to launch, and the probe declares the server unavailable,
falsely blocking every MCP tool call to that server.
Fix: add a quoteWin() helper that double-quotes any token containing whitespace
or cmd metacharacters. In the useShell branch, build a single properly-quoted
command line string and pass it as the sole argument to spawn() with no separate
args array. The else branch (shell:false, all non-.cmd commands) is unchanged.
Regression test added: on Windows, creates a .cmd shim that echoes its first
positional argument to stderr, probes it with a space-containing path arg, and
asserts the probe succeeds and the arg was not split at the space boundary.
Co-authored-by: Karstein Phobic Nyvold Kvistad <karstein.kvistad@maritimerobotics.com>
* fix(hooks): guard doc-file-warning stdin listeners behind require.main (#2358)
* fix(hooks): guard doc-file-warning stdin listeners behind require.main
doc-file-warning.js registered process.stdin data/end listeners at module
scope while also exporting run(). run-with-flags.js require()s any hook that
exports run() for its in-process fast path, so importing this hook attached
stray stdin listeners to the dispatcher process, corrupting the PreToolUse
stdout JSON contract. This is the exact failure run-with-flags' own SAFETY
comment warns about, and 24 sibling hooks already guard against it.
- Move the stdin entrypoint into main() and gate it behind require.main === module
- pre-write-doc-warn.js now calls main() explicitly instead of relying on the
import side effect
- Add regression tests: require() attaches no stdin listeners, run()/main()
stay exported, and the pre-write-doc-warn shim still warns
* docs(hooks): add JSDoc for doc-file-warning main() entrypoint
Satisfies the docstring-coverage pre-merge check; documents the stdin
entrypoint and why it must not run on require().
* fix(windows): prefer PowerShell over bash to prevent zombie process accumulation (#2346)
* fix(windows): prefer PowerShell over bash to prevent zombie process accumulation
On Windows, ECC hook scripts were spawning bash.exe (MSYS2/Git Bash) on
every tool use via findShellBinary(). These processes were not reaped by
Windows, causing 40+ zombie bash.exe/conhost.exe processes per session with
noticeable system lag.
Changes to scripts/hooks/plugin-hook-bootstrap.js:
- Add isPowerShellBin(bin) helper: basename-based detection so full paths
like C:\Windows\...\powershell.exe are handled correctly
- findShellBinary(): check BASH env var first (preserves escape hatch),
then on win32 probe pwsh.exe -> powershell.exe -> bash.exe -> bash;
use correct probe args per shell type; cache result in _cachedShell
- findBashBinary(): separate cached bash-only finder used by spawnShell
.sh fallback; skips PowerShell binaries even if BASH points to one
- spawnShell(): use isPowerShellBin() to select -NoProfile -NonInteractive
-File args for PowerShell; .sh scripts fall back to findBashBinary()
with a skip-warning if no bash found on Windows
observe-runner.js is intentionally unchanged: it always invokes observe.sh
which is bash-only; routing it through PowerShell would silently break it.
The observe.sh -> observe.js migration is tracked separately.
Fixes#2345
* fix(windows): address CodeRabbit and Greptile review comments
- Add timeout: 30000 to all spawnSync probe calls in findShellBinary and
findBashBinary to prevent hangs on broken/stalled shell candidates
- Add -ExecutionPolicy Bypass to PowerShell -File invocation to fix
execution on machines with the default Restricted policy (Win10/11)
- Add PowerShell availability skip guard to PS selection test (mirrors
existing bash skip guard)
- Fix no-bash test to keep PowerShell on PATH so the .sh fallback branch
is actually exercised rather than hitting shell-unavailable early exit
* test: add timeout to spawnSync probes in Windows test skip guards
---------
Co-authored-by: Christopher J Diamond <diamondcj@leidos.com>
* feat(session): LLM-powered session summary via claude -p (#2388)
Replace mechanical text extraction in session-end.js and pre-compact.js
with LLM-generated summaries using `claude -p`. Summaries now capture
design decisions, resolved bugs, changed files, and carry-over context
rather than just truncated user message snippets.
- Add scripts/lib/llm-summary.js: generateSessionSummary, extractConversationText,
getContextRemainingPct, getContextThreshold, getLLMModel
- Update scripts/hooks/session-end.js: trigger LLM when context < 20% or
every 50 messages (env-configurable via ECC_LLM_SUMMARY_*)
- Update scripts/hooks/pre-compact.js: generate LLM summary right before
compaction and write it to the active session .tmp file
- Add tests/lib/llm-summary.test.js: 18 unit tests
- Update tests/hooks/hooks.test.js: 3 integration tests for new behaviour
Recursion guard: sets ECC_SKIP_LLM_SUMMARY=1 in subprocess env so Stop
hooks fired by the claude -p subprocess do not re-enter summarisation.
Requires no ANTHROPIC_API_KEY — reuses Claude Code's own authentication.
Co-authored-by: Hiroshi Tanaka <hiroshi_tanaka@MBAM3.local>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(deps): update anthropic requirement from >=0.25.0 to >=0.111.0 (#2329)
Updates the requirements on [anthropic](https://github.com/anthropics/anthropic-sdk-python) to permit the latest version.
- [Release notes](https://github.com/anthropics/anthropic-sdk-python/releases)
- [Changelog](https://github.com/anthropics/anthropic-sdk-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/anthropics/anthropic-sdk-python/compare/v0.25.0...v0.111.0)
---
updated-dependencies:
- dependency-name: anthropic
dependency-version: 0.111.0
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps): bump actions/checkout from 6.0.3 to 7.0.0 (#2328)
Bumps [actions/checkout](https://github.com/actions/checkout) from 6.0.3 to 7.0.0.
- [Release notes](https://github.com/actions/checkout/releases)
- [Commits](https://github.com/actions/checkout/compare/v6.0.3...v7)
---
updated-dependencies:
- dependency-name: actions/checkout
dependency-version: 7.0.0
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps): bump slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml (#2330)
Bumps [slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml](https://github.com/slsa-framework/slsa-github-generator) from 1.4.0 to 2.1.0.
- [Release notes](https://github.com/slsa-framework/slsa-github-generator/releases)
- [Changelog](https://github.com/slsa-framework/slsa-github-generator/blob/main/CHANGELOG.md)
- [Commits](68bad40844...f7dd8c54c2)
---
updated-dependencies:
- dependency-name: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml
dependency-version: 2.1.0
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps): bump cron from 0.16.0 to 0.17.0 in /ecc2 (#2333)
Bumps [cron](https://github.com/zslayton/cron) from 0.16.0 to 0.17.0.
- [Release notes](https://github.com/zslayton/cron/releases)
- [Commits](https://github.com/zslayton/cron/commits)
---
updated-dependencies:
- dependency-name: cron
dependency-version: 0.17.0
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps-dev): update pytest requirement from >=8.0 to >=9.1.1 (#2324)
Updates the requirements on [pytest](https://github.com/pytest-dev/pytest) to permit the latest version.
- [Release notes](https://github.com/pytest-dev/pytest/releases)
- [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/pytest-dev/pytest/compare/8.0.0...9.1.1)
---
updated-dependencies:
- dependency-name: pytest
dependency-version: 9.1.1
dependency-type: direct:development
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps-dev): update mypy requirement from >=1.10 to >=2.1.0 (#2326)
Updates the requirements on [mypy](https://github.com/python/mypy) to permit the latest version.
- [Changelog](https://github.com/python/mypy/blob/master/CHANGELOG.md)
- [Commits](https://github.com/python/mypy/compare/v1.10.0...v2.1.0)
---
updated-dependencies:
- dependency-name: mypy
dependency-version: 2.1.0
dependency-type: direct:development
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps-dev): update pytest-cov requirement from >=4.1 to >=7.1.0 (#2332)
Updates the requirements on [pytest-cov](https://github.com/pytest-dev/pytest-cov) to permit the latest version.
- [Changelog](https://github.com/pytest-dev/pytest-cov/blob/master/CHANGELOG.rst)
- [Commits](https://github.com/pytest-dev/pytest-cov/compare/v4.1.0...v7.1.0)
---
updated-dependencies:
- dependency-name: pytest-cov
dependency-version: 7.1.0
dependency-type: direct:development
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps): bump the actions-minor-and-patch group across 1 directory with 3 updates (#2325)
Bumps the actions-minor-and-patch group with 3 updates in the / directory: [actions/setup-node](https://github.com/actions/setup-node), [pnpm/action-setup](https://github.com/pnpm/action-setup) and [softprops/action-gh-release](https://github.com/softprops/action-gh-release).
Updates `actions/setup-node` from 6.3.0 to 6.4.0
- [Release notes](https://github.com/actions/setup-node/releases)
- [Commits](https://github.com/actions/setup-node/compare/v6.3.0...48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e)
Updates `pnpm/action-setup` from 6.0.8 to 6.0.9
- [Release notes](https://github.com/pnpm/action-setup/releases)
- [Commits](0e279bb959...0ebf47130e)
Updates `softprops/action-gh-release` from 3.0.0 to 3.0.1
- [Release notes](https://github.com/softprops/action-gh-release/releases)
- [Changelog](https://github.com/softprops/action-gh-release/blob/master/CHANGELOG.md)
- [Commits](b430933298...718ea10b13)
---
updated-dependencies:
- dependency-name: actions/setup-node
dependency-version: 6.4.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: actions-minor-and-patch
- dependency-name: pnpm/action-setup
dependency-version: 6.0.9
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: actions-minor-and-patch
- dependency-name: softprops/action-gh-release
dependency-version: 3.0.1
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: actions-minor-and-patch
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps): bump the cargo-minor-and-patch group across 1 directory with 3 updates (#2387)
Bumps the cargo-minor-and-patch group with 3 updates in the /ecc2 directory: [ratatui](https://github.com/ratatui/ratatui), [anyhow](https://github.com/dtolnay/anyhow) and [uuid](https://github.com/uuid-rs/uuid).
Updates `ratatui` from 0.30.1 to 0.30.2
- [Release notes](https://github.com/ratatui/ratatui/releases)
- [Changelog](https://github.com/ratatui/ratatui/blob/main/CHANGELOG.md)
- [Commits](https://github.com/ratatui/ratatui/compare/ratatui-v0.30.1...ratatui-v0.30.2)
Updates `anyhow` from 1.0.102 to 1.0.103
- [Release notes](https://github.com/dtolnay/anyhow/releases)
- [Commits](https://github.com/dtolnay/anyhow/compare/1.0.102...1.0.103)
Updates `uuid` from 1.23.3 to 1.23.4
- [Release notes](https://github.com/uuid-rs/uuid/releases)
- [Commits](https://github.com/uuid-rs/uuid/compare/v1.23.3...v1.23.4)
---
updated-dependencies:
- dependency-name: ratatui
dependency-version: 0.30.2
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: cargo-minor-and-patch
- dependency-name: anyhow
dependency-version: 1.0.103
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: cargo-minor-and-patch
- dependency-name: uuid
dependency-version: 1.23.4
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: cargo-minor-and-patch
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* chore(deps-dev): bump eslint from 9.39.2 to 10.6.0 (#2260)
Bumps [eslint](https://github.com/eslint/eslint) from 9.39.2 to 10.6.0.
- [Release notes](https://github.com/eslint/eslint/releases)
- [Commits](https://github.com/eslint/eslint/compare/v9.39.2...v10.6.0)
---
updated-dependencies:
- dependency-name: eslint
dependency-version: 10.5.0
dependency-type: direct:development
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix(ci): unbreak main after dependabot batch (checkout SHA + lint) (#2393)
* fix(ci): track actions/checkout v7 SHA in supply-chain workflow test
Dependabot #2328 bumped actions/checkout v6->v7, changing the pinned SHA in
supply-chain-watch.yml; update the test's expected SHA to match.
* Revert "feat(workflows): add orch-review native Workflow pilot (#2363)"
This reverts commit 1031d312cc.
* feat: add ecc-recipes skill (#2319)
* feat: add ecc-recipes skill
Maps a described workflow to the right ECC command-group with run-order
and stop condition, and browses command-group recipe families. Fills the
gap between ecc-guide (flat catalog) and prompt-optimizer (single-prompt
match) by adding family grouping, run-order, and stop conditions.
Advisory only; reads commands/ live.
* fix(ecc-recipes): address review
- flatten frontmatter origin/author/version to top-level (repo convention)
- guard unset CMD_DIR before globbing; use find instead of ls
- show burn-warning explicitly in output template
* feat(ecc-recipes): add argument-hint for slash UI
* feat(skills): add mailtrap-email-integration skill (#2288)
Adds a new Tool Integration skill (mailtrap-email-integration) covering transactional email sending patterns: sandbox vs. production separation, API authentication, and domain verification. Focused on patterns that generalize beyond one vendor, per the repo's Skill Adaptation Policy.
* docs(code-tour): document ref-field semantics to prevent PR-tour file-not-found (#2273)
The code-tour skill mentioned the CodeTour 'ref' field only in an example,
with no explanation of its behavior. CodeTour resolves each step's file
content from the git revision named by 'ref' (not the working tree) whenever
ref differs from HEAD, so any file that does not exist at that revision fails
to open with 'The editor could not be opened because the file was not found'
- even though the file is present on disk.
This bit a generated PR tour where ref was set to the base branch (develop):
every file ADDED by the PR is absent on the base, so all new-file steps 404'd
while the tour tree and comments still rendered, making the cause non-obvious.
Adds a 'The ref Field' section explaining the resolution behavior and the
rule that PR tours must pin ref to the branch head (never the base), plus a
validation step to confirm every referenced file exists at the chosen ref.
* fix(gateguard): finish tool-agnostic checklist across edit gate and SKILL.md copies (#2274)
b3268fef (#2272) made the write-gate "confirm no existing file" item
tool-agnostic in the JS hook, but the rest of the checklist surface still
names Glob/Grep. On hosts without those tools the agent still hits a dead
tool call on:
- the edit-gate "list importers" item in the hook (scripts/hooks/gateguard-fact-force.js)
- both checklist items in all three SKILL.md copies (en, ja-JP, zh-CN)
Apply the same wording b3268fef introduced — "(search the tree — Glob/Grep,
or find/grep via Bash)" — to those five remaining spots so the whole gate is
consistent. Prose-only; no logic change.
Follow-up to #2272 / b3268fef.
* feat(skills): harden the file upload validation section in django-security (#2338)
* feat(skills): harden the file upload validation section in django-security
* Update skills/django-security/SKILL.md
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* add missing stuff to second code block
* add import to the top of the code block
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* docs(skills): update Prisma and Zod API patterns for cross-version compatibility (#2336)
* docs(skills): update Prisma and Zod API patterns for cross-version compatibility
- skills/prisma-patterns: show both adapter-based and direct PrismaClient
initialization side-by-side; update import paths with conditional notes;
rewrite version header to be release-agnostic
- skills/backend-patterns: fix ZodError.errors -> ZodError.issues
- skills/coding-standards: fix ZodError.errors -> ZodError.issues
- skills/security-review: fix ZodError.errors -> ZodError.issues
These API differences were discovered during implementation of a
full-stack health assessment project. The updated code samples show
both the new and old API forms so the skill remains useful regardless
of which Prisma or Zod version is installed.
Closes#2335
* fix(skills): revert Prisma client imports to '@prisma/client'
The 'prisma' npm package is the CLI tool, not the runtime client.
Using it as an import source would cause compile-time failures on all
versions. '@prisma/client' remains the correct import source for the
generated PrismaClient and Prisma namespace types.
Found by Greptile during PR review.
* feat(skills): make tdd-workflow test-runner aware (npm/pnpm/yarn/bun) (#2347)
* feat(skills): make tdd-workflow test-runner aware (npm/pnpm/yarn/bun)
Add "Step 0: Detect the Test Runner" so the RED/GREEN cycle no longer
hardcodes `npm test`. Distinguishes the package manager from the test
runner (a project can install with Bun yet run Jest/Vitest), adds a runner
command matrix, and warns about `bun test` (native bun:test runner) vs
`bun run test` (runs the package.json script) — a common ESM failure mode.
Adds a Bun native test pattern section and links the bun-runtime skill.
Applied to both the canonical skills/ copy and the .agents/skills/ Codex
subset (manual sync per CONTRIBUTING).
* docs(skills): apply <test>/<coverage> placeholders in tdd-workflow steps
Address review feedback on PR #2347: Step 0 instructs the agent to substitute
the detected runner command, but Steps 3/5/7, Run Coverage Report, Watch Mode,
Pre-Commit, and CI/CD still showed literal `npm test` / `npm run test:coverage`
— so an agent reaching those blocks could run npm test on a pnpm/bun project.
Replace them with the <test> / <test-watch> / <coverage> placeholders from
Step 0. Left untouched: the plan-handoff allowlist example and the Step 8
evidence-table samples (illustrative, not run-this instructions). Applied to
both the canonical and Codex-subset copies.
* docs(skills): make pre-commit lint runner-agnostic via <lint> placeholder
Follow-up to PR #2347 review (CodeRabbit): the pre-commit example still used
`npm run lint`, coupling it to npm after test/coverage were made runner-aware.
Add a `<lint>` column to the Step 0 runner matrix (npm run lint / pnpm lint /
yarn lint / bun run lint) and change the Pre-Commit Hook example to
`<test> && <lint>`. Applied to both the canonical and Codex-subset copies.
* chore: re-trigger CI (flaky windows/node20 npm cell)
* refactor(commands): remove duplicated content in skill-create and learn-eval (#2348)
skill-create: drop the "Example Output" section (53 lines) — it re-rendered
the same skeleton already defined by the Step 3 output template, just with
filled-in `my-app` values.
learn-eval: drop the "Next Action" column from the 5b verdict table — it
duplicated Step 6's "Verdict-specific confirmation flow". The table now
carries Verdict + Meaning, and a pointer to Step 6 as the single source for
each verdict's action.
No behavior, frontmatter, or design-rationale changes.
* chore(catalog): sync manifests after skill batch (#2319#2288#2273#2274#2338#2336#2347#2348) (#2394)
Regenerate catalog doc counts + command registry after merging the verified
skill/agent batch. Local full suite was green (2924/2924) with these applied.
* fix(clv2): align Python _update_registry schema with shell counterpart (#2369)
* fix(clv2): align Python _update_registry schema with shell counterpart
The Python `_update_registry` in instinct-cli.py wrote registry entries
without the `id` and `created_at` fields, while the shell counterpart in
detect-project.sh writes both. A projects.json entry could therefore have a
different shape depending on which path (Python CLI or shell hook) last
touched it.
Emit the same field set and order as the shell version: id, name, root,
remote, created_at (preserved from any existing entry), last_seen. Add
regression tests asserting field parity and created_at preservation.
Fixes#2299
* fix(clv2): guard _update_registry against a non-dict registry entry
A malformed projects.json (a non-dict value for the current project id, e.g.
null) would make existing.get("created_at", ...) raise and crash the update,
losing the old code's ability to self-heal a corrupt per-entry value. Normalize
existing to {} when it is not a dict so the entry is healed by the rewrite. Add
a regression test for the malformed-entry path.
* test(clv2): assert the first-write created_at == last_seen contract
The new _update_registry tests only checked both timestamps were truthy. On the
initial write both derive from the same `now`, so created_at must equal
last_seen; assert that explicitly so a later refactor that breaks the contract
is caught. Split the compound assertions into single-expression checks.
* fix(clv2): heal a non-dict top-level registry in _update_registry
A projects.json that is valid JSON but not a mapping (e.g. `[]` or a
string) previously crashed _update_registry on registry.get(), before
the per-entry guard could run, so the corrupt file could not be healed.
Guard the top-level shape right after the load and fall back to {} so the
rewrite repairs the file — matching the per-entry healing already in place.
Resolves the remaining CodeRabbit finding on #2299.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(clv2): serialize observer signal-counter to stop dropped increments (#2372)
observe.sh bumps the SIGUSR1 throttle counter in
${PROJECT_DIR}/.observer-signal-counter with an unlocked read-modify-write.
The hook runs on every tool call, so concurrent invocations read the same
value, both increment, and lose a write, signaling the observer at
unpredictable intervals and defeating the #521 throttle.
Serialize the read-modify-write under a lock, and only ever bump the counter
while that lock is held:
- Prefer flock with a bounded -w wait (the OS auto-releases it when the fd
closes or the process dies, so there is no stale lock and no lost increment);
on a timeout the tick is skipped rather than bumped unlocked.
- Fall back to an atomic mkdir lock on platforms without flock, with a bounded
spin. An EXIT trap cleans up on normal completion; INT/TERM traps release the
lock and exit, so a signal cannot drop the lock and then continue the
read-modify-write without ownership. If the lock cannot be acquired in the
budget the tick is skipped rather than raced. No hand-rolled PID stale-reclaim
(which is racy and can delete a live re-acquirer's lock).
- Guard the counter read against a corrupt (non-integer) file that would abort
the hook under set -e.
Add tests/hooks/observe-signal-counter-race.test.js: 20 concurrent observe.sh
invocations must not lose increments (exact under flock; at most one dropped on
the best-effort mkdir fallback), the runner rejects on any hook execution
failure or hang, plus content guards for the lock and the corrupt-counter
handling.
Fixes#2296
* fix(clv2): surface SIGALRM timeout drops in observe.sh (#2373)
* fix(clv2): surface SIGALRM timeout drops in observe.sh
The inline-Python observation writers in observe.sh arm a signal.SIGALRM
alarm (8s) so they self-terminate before the async hook's 10s timeout can
orphan them (#2278). The handler _ecc_bail called sys.exit(0) with no
logging, so when the alarm fired the in-flight observation was silently
dropped: nothing was logged, no partial write occurred, and the shell saw
a clean exit. There was no way to detect or count how many observations
were being lost.
Add a single stderr visibility line to both _ecc_bail handlers (the
parse-error fallback path and the main observation-writing path) before
sys.exit(0), using the repo's "[observe]" log prefix. Exit code stays 0:
in a Claude Code hook a non-zero exit signals a block, so changing it
would turn an internal timeout into a user-facing tool block. The warning
goes to stderr (not stdout) because both blocks redirect stdout into the
observations file.
Add tests/hooks/observe-signal-timeout.test.js: a static regression guard
that every _ecc_bail handler logs to stderr before exiting and keeps exit
0, plus a behavioral check that runs the real handler text extracted from
observe.sh and confirms a fired alarm exits 0 and emits the [observe]
warning on stderr only.
Fixes#2300
* test(clv2): exercise both _ecc_bail handlers end-to-end
The behavioral SIGALRM-fire test ran only handlers[0] (the parse-error
fallback path); the main observation-write path (handlers[1]) was covered
only by the static regex guard. The write path is the higher-value one to
verify end-to-end since it carries valid, parseable data that would succeed
given more time, so a silent drop there is the worst case.
Loop the behavioral check over every extracted handler so a regression that
silenced the second handler's stderr write is caught at runtime, not just by
the static guard.
* test(clv2): select timeout handlers by marker, not array index
The behavioral check looped over all extracted _ecc_bail handlers by index.
If an unrelated _ecc_bail were ever added to observe.sh, the loop would
either test the wrong block or be diluted. Filter the handlers to those
carrying the "[observe] SIGALRM timeout" marker so the live SIGALRM check
stays pinned to the two #2300 timeout handlers regardless of array order or
future additions.
* test(clv2): fail fast when python is missing in SIGALRM check
The behavioral test returned early when no python interpreter was found,
which the test harness records as a PASS — so the SIGALRM contract could go
entirely unverified yet still look green. Throw instead, matching the
existing insaits-security-monitor convention of failing when a required
Python runtime is absent, and drop the in-test console.log.
* test(clv2): add coverage for instinct-cli prune, projects ops, promote dry-run, normalize-url (#2374)
* test(clv2): cover instinct-cli prune, projects ops, promote dry-run, normalize-url
Add pytest coverage for previously-untested functions in
skills/continuous-learning-v2/scripts/instinct-cli.py:
- _normalize_remote_url: scp/https/file forms, credential + .git
stripping, network lowercasing, case-preserving local paths, idempotence
- _promote_specific dry-run: returns 0 and writes no global file
- projects delete/gc/merge: invalid-id, not-found, dry-run, and force
paths over registry + storage, asserting destructive ops are gated
- cmd_prune: dry-run keeps files; non-dry-run deletes only expired; quiet
Test-only change; no production code modified.
Fixes#2302
* test(clv2): assert dry-run storage no-op and quiet-mode stderr silence
Address CodeRabbit review on #2374:
- projects gc/merge dry-run tests now also assert on-disk storage is
untouched (empty1 project dir survives; nothing copied into dest
personal), closing the gap where a storage-mutating dry-run regression
would still pass.
- cmd_prune quiet test now asserts stderr is empty too, not just stdout.
* test(clv2): cover merge missing-destination and prune empty-pending branches
* fix(clv2): archive observations only after successful analysis in observer-loop (#2386)
analyze_observations moved observations.jsonl into observations.archive/
unconditionally, even when the Claude analysis failed (timeout, non-zero
exit, rate limit). Because the analyzer only reads the live file, a failed
batch was archived and never re-analyzed, silently dropping the instincts
it would have produced.
Return early on a non-zero analysis exit so the archive mv runs only on
success, retaining observations for the next cycle to retry. Resolve the
script's own directory from ${BASH_SOURCE[0]} (SCRIPT_DIR) so sibling
scripts (session-guardian.sh) and relative helpers resolve correctly under
both execution and sourcing, and add a source-guard so observer-loop.sh can
be sourced without starting the loop. Add a regression test covering both
the failure (retain) and success (archive) paths.
Fixes#2370
* feat(continuous-learning-v2): make observer model configurable via ECC_OBSERVER_MODEL (#2390)
* feat(continuous-learning-v2): make observer model configurable via ECC_OBSERVER_MODEL
The observer hardcoded `--model haiku`. Parameterize as "${ECC_OBSERVER_MODEL:-haiku}": the haiku default is preserved (no behavior change for existing users), but users can opt into a stronger model — e.g. `ECC_OBSERVER_MODEL=opus` — for higher-quality instinct extraction. Useful on subscription plans where model cost isn't the limiting factor.
* fix(continuous-learning-v2): address review — update wiring test + docs
- Update source-inspection test to assert the ${ECC_OBSERVER_MODEL:-haiku} defaulting behavior (was matching the literal `claude --model haiku`, which this PR changed). All 31 tests pass.
- Add guidance to raise ECC_OBSERVER_TIMEOUT_SECONDS for slower models (e.g. opus) so the 120s watchdog doesn't kill analysis mid-run.
- Fix now-stale 'Haiku session' comment -> 'observer session' (model is configurable).
* feat(rules,skills): add React Native / Expo rules pack and react-native-patterns skill (#2275)
* feat(rules,skills): add React Native / Expo rules pack and react-native-patterns skill
* fix(rules,skills): address review feedback — safeParse nav example, drop deprecated sentry-expo, memoize list renderItem, clarify New Architecture SDK support
* fix(rules,skills): drop deprecated Flipper, surface permission-denied state in location hook
* Add growth-log skill: methodology for effective learning capture (#2377)
* Add growth-log skill: methodology for writing effective, transferable growth log entries
* Add metadata.origin: ECC frontmatter per repo convention (Greptile feedback)
* Re-sign: apply GPG-verified commit to growth-log branch (rebase artifact, content unchanged)
* docs(growth-log): v1.1.0 — remove personal library structure, generic storage, delivery-gate optional companion
* Stop hook: verify thinking quality at session end — task completeness, assumptions, stale logs, disk space (delivery-gate) (#2378)
* Restore delivery-gate: Stop hook with learning capture enforcement (auto-closed by fork sync, now on clean branch)
* Fix bot findings: log level→INFO (DISK_REMIND dead code), count_edits full transcript (not truncated), memory-dir-absent warning (not silent pass), SKILL.md description accuracy
* Fix CodeRabbit feedback: treat missing memory-dir as all-stale on complex tasks (fail-close instead of fail-open)
* Trigger bot re-review (no logic changes)
* Fix: handle both stdin formats — raw transcript AND JSON with transcript_path (Greptile feedback)
* Add debug log for memory-dir lookup path
* Fix path encoding: replace colon with dash (not strip), matching Claude Code actual encoding on Windows
* Fix SKILL.md: update How It Works for JSON+transcript_path, add English translation to CLAUDE.md block (Greptile feedback)
* Fix: memory-dir absent → warn but don't block (prevents deadlock for new users per Greptile feedback)
* fix: restore daltino-approved voice (thinking quality/收尾铁律) with technical patches
Reverts 'session hygiene' rebranding. Preserves original approved framing
while keeping technical improvements:
- JSON transcript_path parsing documentation
- filesystem mtime staleness check
- 'skip tests for now' rationalization pattern
- disk critically low explicit block condition
* fix: remove stdout JSON echo — Stop hooks write feedback to stderr, not stdout
Previously sys.stdout.write(raw) echoed the raw hook JSON payload to stdout,
which Claude Code displays as the hook's response message. When the hook
blocked (exit 2), Claude saw {"transcript_path":"...","session_id":"..."}
instead of the actual blocking reason from stderr.
This made the gate functionally silent from Claude's perspective — it could
not guide Claude to the corrective action (update growth-log / free disk).
Fix per Greptile feedback: stop echo, let stderr messages reach Claude.
* fix: remove duplicate disk-critical log line
* docs(delivery-gate): v1.1.0 — accurate scope (deterministic checks, not reasoning), warning vs block table, CI/CD analogy, limitations section, self-audit pairing
* fix(delivery-gate): expand rationalization regex coverage (R3/R4) — match "we can fix" and "integration tests" variants
* chore: bump version to 1.1.1 to re-trigger CI checks
* feat: add loop-design-check skill (design + review goal-oriented agent loops) (#2381)
* chore(catalog): sync manifests + fix skill emoji (wave 2) (#2395)
* chore(catalog): sync manifests after skill batch (#2275#2377#2378#2381)
Update skill counts (273 -> 277) across catalog docs after the verified skill batch.
* fix(skills): replace emoji with ASCII in growth-log + loop-design-check
check-unicode-safety (pre-push gate) bans emoji in SKILL.md; the merged #2377
and #2381 slipped through run-all.js. Swap U+274C/U+2705 for 'Avoid:'/'Bad:'/'Good:'.
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316) (#2409)
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368) (#2410)
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368)
The inline node -e resolver blob was duplicated ~60x across hooks.json,
command docs, and translations. Each copy inlined the full ~700-char
plugin-root search using a spread over nested array literals
(p.join(d,'plugins',...s) over [['ecc'],...]), which breaks Windows hook
execution due to shell quoting (#2368).
Collapse every copy to a 250-char locator that loads the committed
resolve-ecc-root module and delegates to resolveEccRoot() — no spread, no
nested array literals, no escaped double quotes. The real search logic now
lives in one tested module. Also route session-start-bootstrap.js through
resolveEccRoot() instead of its own duplicated reimplementation, and fix
the auto-update.md 'marketplace' (singular) typo along the way.
Guard tests updated: discovery behavior is asserted against resolveEccRoot();
the inline is asserted to delegate and to contain no Windows-fragile
constructs.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(resolve-ecc-root): restore full env-unset discovery in inline resolver
Address Greptile review on #2410: when CLAUDE_PLUGIN_ROOT is unset the
delegating inline could only load the resolver module from ~/.claude,
returning ~/.claude without ever reaching the plugin/cache search. Restore
the old inline's discovery breadth (exact plugin roots + versioned cache)
Windows-safely (no spread, nested arrays, or escaped quotes), then delegate
the authoritative decision to resolveEccRoot(). Add regression tests for
plugin-subdir and versioned-cache bootstrap with env unset.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix: docs/COMMAND-REGISTRY.json check fails on fresh Windows clone (missing .gitattributes) (#2437)
* fix: add .gitattributes to force LF line endings for text files
npm run command-registry:check (part of npm test) fails on a fresh clone
on Windows with the common core.autocrlf=true setting: git checks out
docs/COMMAND-REGISTRY.json with CRLF, but generate-command-registry.js
always writes LF, so the strict string comparison in checkRegistry()
never matches. Forcing LF via .gitattributes makes checkouts consistent
across platforms regardless of a contributor's local autocrlf setting.
* fix: normalize CRLF line endings to LF per .gitattributes
pyproject.toml, src/llm/__init__.py, src/llm/prompt/builder.py,
src/llm/providers/claude.py, and tests/test_builder.py had CRLF line
endings committed to the repo, inconsistent with the rest of the
codebase. Renormalized via 'git add --renormalize .' now that
.gitattributes enforces eol=lf.
---------
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* feat(workflows): re-land orch-review workflow + add /orch-review command (#2400)
* feat(workflows): re-land orch-review workflow + add /orch-review command
Re-lands #2363 (reverted by #2393 to unbreak main's lint) and fixes the
root cause so it stays green:
- Restore workflows/orch-review.workflow.js + workflows/README.md.
- eslint.config.js: ignore 'workflows/**/*.workflow.*' and '.claude/workflows/**'
per the maintainer's note in #2393. Workflow DSL scripts use both top-level
export (ESM) and top-level return (the runtime wraps them in an async fn),
which no single eslint sourceType can parse — they must be excluded, not
lint-fixed. 'npx eslint .' is green with this ignore.
- Add commands/orch-review.md (the /orch-review surface) + regenerate
docs/COMMAND-REGISTRY.json.
Supersedes #2397 (command-only), which referenced the reverted workflow.
* fix(workflows): address orch-review bot review findings
- Verifier uncertainty no longer demotes blockers (Greptile P1 + CodeRabbit):
isReal=false only refutes when confidence >= 0.8; low-confidence 'false'
is treated as uncertain and kept blocking (fail closed).
- Treat the diff (and finding text) as untrusted input in both review and
verify prompts; ignore embedded directives (prompt-injection hardening).
- Validate changedFiles entries are strings, not just that it is an array.
- Enforce proof for HIGH/CRITICAL in FINDINGS_SCHEMA, not only in the prompt.
- Remove in-place mutation in dimension build + dedup merge (immutable).
- /orch-review: extract & validate a numeric PR id before shelling out to gh.
- Docs: complete the stats example, soften wording, refresh follow-up list.
* style(workflows): apply formatter to orch-review assembly
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316) (#2409)
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368) (#2410)
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368)
The inline node -e resolver blob was duplicated ~60x across hooks.json,
command docs, and translations. Each copy inlined the full ~700-char
plugin-root search using a spread over nested array literals
(p.join(d,'plugins',...s) over [['ecc'],...]), which breaks Windows hook
execution due to shell quoting (#2368).
Collapse every copy to a 250-char locator that loads the committed
resolve-ecc-root module and delegates to resolveEccRoot() — no spread, no
nested array literals, no escaped double quotes. The real search logic now
lives in one tested module. Also route session-start-bootstrap.js through
resolveEccRoot() instead of its own duplicated reimplementation, and fix
the auto-update.md 'marketplace' (singular) typo along the way.
Guard tests updated: discovery behavior is asserted against resolveEccRoot();
the inline is asserted to delegate and to contain no Windows-fragile
constructs.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(resolve-ecc-root): restore full env-unset discovery in inline resolver
Address Greptile review on #2410: when CLAUDE_PLUGIN_ROOT is unset the
delegating inline could only load the resolver module from ~/.claude,
returning ~/.claude without ever reaching the plugin/cache search. Restore
the old inline's discovery breadth (exact plugin roots + versioned cache)
Windows-safely (no spread, nested arrays, or escaped quotes), then delegate
the authoritative decision to resolveEccRoot(). Add regression tests for
plugin-subdir and versioned-cache bootstrap with env unset.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix: docs/COMMAND-REGISTRY.json check fails on fresh Windows clone (missing .gitattributes) (#2437)
* fix: add .gitattributes to force LF line endings for text files
npm run command-registry:check (part of npm test) fails on a fresh clone
on Windows with the common core.autocrlf=true setting: git checks out
docs/COMMAND-REGISTRY.json with CRLF, but generate-command-registry.js
always writes LF, so the strict string comparison in checkRegistry()
never matches. Forcing LF via .gitattributes makes checkouts consistent
across platforms regardless of a contributor's local autocrlf setting.
* fix: normalize CRLF line endings to LF per .gitattributes
pyproject.toml, src/llm/__init__.py, src/llm/prompt/builder.py,
src/llm/providers/claude.py, and tests/test_builder.py had CRLF line
endings committed to the repo, inconsistent with the rest of the
codebase. Renormalized via 'git add --renormalize .' now that
.gitattributes enforces eol=lf.
---------
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* chore(catalog): sync command counts (92->93) + register orch-review in agent.yaml surface
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Boube <109886533+Cb2i@users.noreply.github.com>
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* docs: replace personal absolute paths with repo-relative agentshield/ paths
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Gaurav Dubey <gauravdubey0107@gmail.com>
Co-authored-by: JongHyeok Park <jonghyeok.park@unitblack.co.kr>
Co-authored-by: Daniel Nguyen <DANIEL@FINHUB.NET.AU>
Co-authored-by: Gabriel Pitrella <gabriel98_@hotmail.com>
Co-authored-by: Angad Singh Thind <angadsthind@gmail.com>
Co-authored-by: angadsingh7666 <angdsingh7666@gmail.com>
Co-authored-by: quadcent <vlada87ns@gmail.com>
Co-authored-by: Vladimir Đuranović <vlada@MacBook-Pro.local>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yang Cheng <ycg78@hotmail.com>
Co-authored-by: jan <jan@w-saxs001.local>
Co-authored-by: Tahiti18 <35585881+Tahiti18@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: phobicdotno <spamme.post@gmail.com>
Co-authored-by: Karstein Phobic Nyvold Kvistad <karstein.kvistad@maritimerobotics.com>
Co-authored-by: SSH._.WORLD <ssh97540@gmail.com>
Co-authored-by: ChrisD <cdiamond@diamond.net>
Co-authored-by: Christopher J Diamond <diamondcj@leidos.com>
Co-authored-by: Hiroshi Tanaka <viveregratis1982@gmail.com>
Co-authored-by: Hiroshi Tanaka <hiroshi_tanaka@MBAM3.local>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: KyawZinLatt <mr.kyawzinlattt@gmail.com>
Co-authored-by: Awa Dieudonne <dieudonneawa7@gmail.com>
Co-authored-by: Carlos Carvallo <carloscarvallo87@gmail.com>
Co-authored-by: Jun <39075334+mc856@users.noreply.github.com>
Co-authored-by: jvirgovic <jvirgovic@proton.me>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: weizhiyuan <104509245+m18897829375@users.noreply.github.com>
Co-authored-by: jack-finance-able <jack@finance-able.com>
Co-authored-by: Yeris Rifan <yerisrifan@gmail.com>
Co-authored-by: YuhaoLin2005 <lin_yuhao2005@163.com>
Co-authored-by: Seekers2001 <jiaxinleifm@outlook.com>
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Boube <109886533+Cb2i@users.noreply.github.com>
* feat(workflows): re-land orch-review workflow + add /orch-review command
Re-lands #2363 (reverted by #2393 to unbreak main's lint) and fixes the
root cause so it stays green:
- Restore workflows/orch-review.workflow.js + workflows/README.md.
- eslint.config.js: ignore 'workflows/**/*.workflow.*' and '.claude/workflows/**'
per the maintainer's note in #2393. Workflow DSL scripts use both top-level
export (ESM) and top-level return (the runtime wraps them in an async fn),
which no single eslint sourceType can parse — they must be excluded, not
lint-fixed. 'npx eslint .' is green with this ignore.
- Add commands/orch-review.md (the /orch-review surface) + regenerate
docs/COMMAND-REGISTRY.json.
Supersedes #2397 (command-only), which referenced the reverted workflow.
* fix(workflows): address orch-review bot review findings
- Verifier uncertainty no longer demotes blockers (Greptile P1 + CodeRabbit):
isReal=false only refutes when confidence >= 0.8; low-confidence 'false'
is treated as uncertain and kept blocking (fail closed).
- Treat the diff (and finding text) as untrusted input in both review and
verify prompts; ignore embedded directives (prompt-injection hardening).
- Validate changedFiles entries are strings, not just that it is an array.
- Enforce proof for HIGH/CRITICAL in FINDINGS_SCHEMA, not only in the prompt.
- Remove in-place mutation in dimension build + dedup merge (immutable).
- /orch-review: extract & validate a numeric PR id before shelling out to gh.
- Docs: complete the stats example, soften wording, refresh follow-up list.
* style(workflows): apply formatter to orch-review assembly
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316) (#2409)
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368) (#2410)
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368)
The inline node -e resolver blob was duplicated ~60x across hooks.json,
command docs, and translations. Each copy inlined the full ~700-char
plugin-root search using a spread over nested array literals
(p.join(d,'plugins',...s) over [['ecc'],...]), which breaks Windows hook
execution due to shell quoting (#2368).
Collapse every copy to a 250-char locator that loads the committed
resolve-ecc-root module and delegates to resolveEccRoot() — no spread, no
nested array literals, no escaped double quotes. The real search logic now
lives in one tested module. Also route session-start-bootstrap.js through
resolveEccRoot() instead of its own duplicated reimplementation, and fix
the auto-update.md 'marketplace' (singular) typo along the way.
Guard tests updated: discovery behavior is asserted against resolveEccRoot();
the inline is asserted to delegate and to contain no Windows-fragile
constructs.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(resolve-ecc-root): restore full env-unset discovery in inline resolver
Address Greptile review on #2410: when CLAUDE_PLUGIN_ROOT is unset the
delegating inline could only load the resolver module from ~/.claude,
returning ~/.claude without ever reaching the plugin/cache search. Restore
the old inline's discovery breadth (exact plugin roots + versioned cache)
Windows-safely (no spread, nested arrays, or escaped quotes), then delegate
the authoritative decision to resolveEccRoot(). Add regression tests for
plugin-subdir and versioned-cache bootstrap with env unset.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix: docs/COMMAND-REGISTRY.json check fails on fresh Windows clone (missing .gitattributes) (#2437)
* fix: add .gitattributes to force LF line endings for text files
npm run command-registry:check (part of npm test) fails on a fresh clone
on Windows with the common core.autocrlf=true setting: git checks out
docs/COMMAND-REGISTRY.json with CRLF, but generate-command-registry.js
always writes LF, so the strict string comparison in checkRegistry()
never matches. Forcing LF via .gitattributes makes checkouts consistent
across platforms regardless of a contributor's local autocrlf setting.
* fix: normalize CRLF line endings to LF per .gitattributes
pyproject.toml, src/llm/__init__.py, src/llm/prompt/builder.py,
src/llm/providers/claude.py, and tests/test_builder.py had CRLF line
endings committed to the repo, inconsistent with the rest of the
codebase. Renormalized via 'git add --renormalize .' now that
.gitattributes enforces eol=lf.
---------
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* chore(catalog): sync command counts (92->93) + register orch-review in agent.yaml surface
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Boube <109886533+Cb2i@users.noreply.github.com>
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* fix: add .gitattributes to force LF line endings for text files
npm run command-registry:check (part of npm test) fails on a fresh clone
on Windows with the common core.autocrlf=true setting: git checks out
docs/COMMAND-REGISTRY.json with CRLF, but generate-command-registry.js
always writes LF, so the strict string comparison in checkRegistry()
never matches. Forcing LF via .gitattributes makes checkouts consistent
across platforms regardless of a contributor's local autocrlf setting.
* fix: normalize CRLF line endings to LF per .gitattributes
pyproject.toml, src/llm/__init__.py, src/llm/prompt/builder.py,
src/llm/providers/claude.py, and tests/test_builder.py had CRLF line
endings committed to the repo, inconsistent with the rest of the
codebase. Renormalized via 'git add --renormalize .' now that
.gitattributes enforces eol=lf.
---------
Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor: consolidate duplicated hook-root resolver into shared resolveEccRoot() (#2368)
The inline node -e resolver blob was duplicated ~60x across hooks.json,
command docs, and translations. Each copy inlined the full ~700-char
plugin-root search using a spread over nested array literals
(p.join(d,'plugins',...s) over [['ecc'],...]), which breaks Windows hook
execution due to shell quoting (#2368).
Collapse every copy to a 250-char locator that loads the committed
resolve-ecc-root module and delegates to resolveEccRoot() — no spread, no
nested array literals, no escaped double quotes. The real search logic now
lives in one tested module. Also route session-start-bootstrap.js through
resolveEccRoot() instead of its own duplicated reimplementation, and fix
the auto-update.md 'marketplace' (singular) typo along the way.
Guard tests updated: discovery behavior is asserted against resolveEccRoot();
the inline is asserted to delegate and to contain no Windows-fragile
constructs.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(resolve-ecc-root): restore full env-unset discovery in inline resolver
Address Greptile review on #2410: when CLAUDE_PLUGIN_ROOT is unset the
delegating inline could only load the resolver module from ~/.claude,
returning ~/.claude without ever reaching the plugin/cache search. Restore
the old inline's discovery breadth (exact plugin roots + versioned cache)
Windows-safely (no spread, nested arrays, or escaped quotes), then delegate
the authoritative decision to resolveEccRoot(). Add regression tests for
plugin-subdir and versioned-cache bootstrap with env unset.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(plan-orchestrate): detect ecc@ecc marketplace + emit ecc: agent prefix (#2316)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): resync lockfiles with package.json (eslint 10) + migrate yarn.lock to Yarn 4 format
package.json requires eslint@^10.6.0 but the committed locks pinned 9.39.2, so
npm ci aborted and Yarn 4 hardened mode rejected the stale v1-classic yarn.lock
(YN0028). Regenerate package-lock.json and rewrite yarn.lock in Yarn 4 (berry)
format so npm ci and immutable yarn installs both pass.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(ci): require clean probe exit for Windows shell/bash detection; add pyyaml dev dep
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: affaan <affaan@itomarkets.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* chore(catalog): sync manifests after skill batch (#2275#2377#2378#2381)
Update skill counts (273 -> 277) across catalog docs after the verified skill batch.
* fix(skills): replace emoji with ASCII in growth-log + loop-design-check
check-unicode-safety (pre-push gate) bans emoji in SKILL.md; the merged #2377
and #2381 slipped through run-all.js. Swap U+274C/U+2705 for 'Avoid:'/'Bad:'/'Good:'.
* Restore delivery-gate: Stop hook with learning capture enforcement (auto-closed by fork sync, now on clean branch)
* Fix bot findings: log level→INFO (DISK_REMIND dead code), count_edits full transcript (not truncated), memory-dir-absent warning (not silent pass), SKILL.md description accuracy
* Fix CodeRabbit feedback: treat missing memory-dir as all-stale on complex tasks (fail-close instead of fail-open)
* Trigger bot re-review (no logic changes)
* Fix: handle both stdin formats — raw transcript AND JSON with transcript_path (Greptile feedback)
* Add debug log for memory-dir lookup path
* Fix path encoding: replace colon with dash (not strip), matching Claude Code actual encoding on Windows
* Fix SKILL.md: update How It Works for JSON+transcript_path, add English translation to CLAUDE.md block (Greptile feedback)
* Fix: memory-dir absent → warn but don't block (prevents deadlock for new users per Greptile feedback)
* fix: restore daltino-approved voice (thinking quality/收尾铁律) with technical patches
Reverts 'session hygiene' rebranding. Preserves original approved framing
while keeping technical improvements:
- JSON transcript_path parsing documentation
- filesystem mtime staleness check
- 'skip tests for now' rationalization pattern
- disk critically low explicit block condition
* fix: remove stdout JSON echo — Stop hooks write feedback to stderr, not stdout
Previously sys.stdout.write(raw) echoed the raw hook JSON payload to stdout,
which Claude Code displays as the hook's response message. When the hook
blocked (exit 2), Claude saw {"transcript_path":"...","session_id":"..."}
instead of the actual blocking reason from stderr.
This made the gate functionally silent from Claude's perspective — it could
not guide Claude to the corrective action (update growth-log / free disk).
Fix per Greptile feedback: stop echo, let stderr messages reach Claude.
* fix: remove duplicate disk-critical log line
* docs(delivery-gate): v1.1.0 — accurate scope (deterministic checks, not reasoning), warning vs block table, CI/CD analogy, limitations section, self-audit pairing
* fix(delivery-gate): expand rationalization regex coverage (R3/R4) — match "we can fix" and "integration tests" variants
* chore: bump version to 1.1.1 to re-trigger CI checks
* feat(rules,skills): add React Native / Expo rules pack and react-native-patterns skill
* fix(rules,skills): address review feedback — safeParse nav example, drop deprecated sentry-expo, memoize list renderItem, clarify New Architecture SDK support
* fix(rules,skills): drop deprecated Flipper, surface permission-denied state in location hook
* feat(continuous-learning-v2): make observer model configurable via ECC_OBSERVER_MODEL
The observer hardcoded `--model haiku`. Parameterize as "${ECC_OBSERVER_MODEL:-haiku}": the haiku default is preserved (no behavior change for existing users), but users can opt into a stronger model — e.g. `ECC_OBSERVER_MODEL=opus` — for higher-quality instinct extraction. Useful on subscription plans where model cost isn't the limiting factor.
* fix(continuous-learning-v2): address review — update wiring test + docs
- Update source-inspection test to assert the ${ECC_OBSERVER_MODEL:-haiku} defaulting behavior (was matching the literal `claude --model haiku`, which this PR changed). All 31 tests pass.
- Add guidance to raise ECC_OBSERVER_TIMEOUT_SECONDS for slower models (e.g. opus) so the 120s watchdog doesn't kill analysis mid-run.
- Fix now-stale 'Haiku session' comment -> 'observer session' (model is configurable).
analyze_observations moved observations.jsonl into observations.archive/
unconditionally, even when the Claude analysis failed (timeout, non-zero
exit, rate limit). Because the analyzer only reads the live file, a failed
batch was archived and never re-analyzed, silently dropping the instincts
it would have produced.
Return early on a non-zero analysis exit so the archive mv runs only on
success, retaining observations for the next cycle to retry. Resolve the
script's own directory from ${BASH_SOURCE[0]} (SCRIPT_DIR) so sibling
scripts (session-guardian.sh) and relative helpers resolve correctly under
both execution and sourcing, and add a source-guard so observer-loop.sh can
be sourced without starting the loop. Add a regression test covering both
the failure (retain) and success (archive) paths.
Fixes#2370
* test(clv2): cover instinct-cli prune, projects ops, promote dry-run, normalize-url
Add pytest coverage for previously-untested functions in
skills/continuous-learning-v2/scripts/instinct-cli.py:
- _normalize_remote_url: scp/https/file forms, credential + .git
stripping, network lowercasing, case-preserving local paths, idempotence
- _promote_specific dry-run: returns 0 and writes no global file
- projects delete/gc/merge: invalid-id, not-found, dry-run, and force
paths over registry + storage, asserting destructive ops are gated
- cmd_prune: dry-run keeps files; non-dry-run deletes only expired; quiet
Test-only change; no production code modified.
Fixes#2302
* test(clv2): assert dry-run storage no-op and quiet-mode stderr silence
Address CodeRabbit review on #2374:
- projects gc/merge dry-run tests now also assert on-disk storage is
untouched (empty1 project dir survives; nothing copied into dest
personal), closing the gap where a storage-mutating dry-run regression
would still pass.
- cmd_prune quiet test now asserts stderr is empty too, not just stdout.
* test(clv2): cover merge missing-destination and prune empty-pending branches
* fix(clv2): surface SIGALRM timeout drops in observe.sh
The inline-Python observation writers in observe.sh arm a signal.SIGALRM
alarm (8s) so they self-terminate before the async hook's 10s timeout can
orphan them (#2278). The handler _ecc_bail called sys.exit(0) with no
logging, so when the alarm fired the in-flight observation was silently
dropped: nothing was logged, no partial write occurred, and the shell saw
a clean exit. There was no way to detect or count how many observations
were being lost.
Add a single stderr visibility line to both _ecc_bail handlers (the
parse-error fallback path and the main observation-writing path) before
sys.exit(0), using the repo's "[observe]" log prefix. Exit code stays 0:
in a Claude Code hook a non-zero exit signals a block, so changing it
would turn an internal timeout into a user-facing tool block. The warning
goes to stderr (not stdout) because both blocks redirect stdout into the
observations file.
Add tests/hooks/observe-signal-timeout.test.js: a static regression guard
that every _ecc_bail handler logs to stderr before exiting and keeps exit
0, plus a behavioral check that runs the real handler text extracted from
observe.sh and confirms a fired alarm exits 0 and emits the [observe]
warning on stderr only.
Fixes#2300
* test(clv2): exercise both _ecc_bail handlers end-to-end
The behavioral SIGALRM-fire test ran only handlers[0] (the parse-error
fallback path); the main observation-write path (handlers[1]) was covered
only by the static regex guard. The write path is the higher-value one to
verify end-to-end since it carries valid, parseable data that would succeed
given more time, so a silent drop there is the worst case.
Loop the behavioral check over every extracted handler so a regression that
silenced the second handler's stderr write is caught at runtime, not just by
the static guard.
* test(clv2): select timeout handlers by marker, not array index
The behavioral check looped over all extracted _ecc_bail handlers by index.
If an unrelated _ecc_bail were ever added to observe.sh, the loop would
either test the wrong block or be diluted. Filter the handlers to those
carrying the "[observe] SIGALRM timeout" marker so the live SIGALRM check
stays pinned to the two #2300 timeout handlers regardless of array order or
future additions.
* test(clv2): fail fast when python is missing in SIGALRM check
The behavioral test returned early when no python interpreter was found,
which the test harness records as a PASS — so the SIGALRM contract could go
entirely unverified yet still look green. Throw instead, matching the
existing insaits-security-monitor convention of failing when a required
Python runtime is absent, and drop the in-test console.log.
observe.sh bumps the SIGUSR1 throttle counter in
${PROJECT_DIR}/.observer-signal-counter with an unlocked read-modify-write.
The hook runs on every tool call, so concurrent invocations read the same
value, both increment, and lose a write, signaling the observer at
unpredictable intervals and defeating the #521 throttle.
Serialize the read-modify-write under a lock, and only ever bump the counter
while that lock is held:
- Prefer flock with a bounded -w wait (the OS auto-releases it when the fd
closes or the process dies, so there is no stale lock and no lost increment);
on a timeout the tick is skipped rather than bumped unlocked.
- Fall back to an atomic mkdir lock on platforms without flock, with a bounded
spin. An EXIT trap cleans up on normal completion; INT/TERM traps release the
lock and exit, so a signal cannot drop the lock and then continue the
read-modify-write without ownership. If the lock cannot be acquired in the
budget the tick is skipped rather than raced. No hand-rolled PID stale-reclaim
(which is racy and can delete a live re-acquirer's lock).
- Guard the counter read against a corrupt (non-integer) file that would abort
the hook under set -e.
Add tests/hooks/observe-signal-counter-race.test.js: 20 concurrent observe.sh
invocations must not lose increments (exact under flock; at most one dropped on
the best-effort mkdir fallback), the runner rejects on any hook execution
failure or hang, plus content guards for the lock and the corrupt-counter
handling.
Fixes#2296
* fix(clv2): align Python _update_registry schema with shell counterpart
The Python `_update_registry` in instinct-cli.py wrote registry entries
without the `id` and `created_at` fields, while the shell counterpart in
detect-project.sh writes both. A projects.json entry could therefore have a
different shape depending on which path (Python CLI or shell hook) last
touched it.
Emit the same field set and order as the shell version: id, name, root,
remote, created_at (preserved from any existing entry), last_seen. Add
regression tests asserting field parity and created_at preservation.
Fixes#2299
* fix(clv2): guard _update_registry against a non-dict registry entry
A malformed projects.json (a non-dict value for the current project id, e.g.
null) would make existing.get("created_at", ...) raise and crash the update,
losing the old code's ability to self-heal a corrupt per-entry value. Normalize
existing to {} when it is not a dict so the entry is healed by the rewrite. Add
a regression test for the malformed-entry path.
* test(clv2): assert the first-write created_at == last_seen contract
The new _update_registry tests only checked both timestamps were truthy. On the
initial write both derive from the same `now`, so created_at must equal
last_seen; assert that explicitly so a later refactor that breaks the contract
is caught. Split the compound assertions into single-expression checks.
* fix(clv2): heal a non-dict top-level registry in _update_registry
A projects.json that is valid JSON but not a mapping (e.g. `[]` or a
string) previously crashed _update_registry on registry.get(), before
the per-entry guard could run, so the corrupt file could not be healed.
Guard the top-level shape right after the load and fall back to {} so the
rewrite repairs the file — matching the per-entry healing already in place.
Resolves the remaining CodeRabbit finding on #2299.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Regenerate catalog doc counts + command registry after merging the verified
skill/agent batch. Local full suite was green (2924/2924) with these applied.
skill-create: drop the "Example Output" section (53 lines) — it re-rendered
the same skeleton already defined by the Step 3 output template, just with
filled-in `my-app` values.
learn-eval: drop the "Next Action" column from the 5b verdict table — it
duplicated Step 6's "Verdict-specific confirmation flow". The table now
carries Verdict + Meaning, and a pointer to Step 6 as the single source for
each verdict's action.
No behavior, frontmatter, or design-rationale changes.
WinterSold1er
黄云龙
someiyoshino-lab
fletcherm-hub
JongHyeok Park
Samarjeet Singh Tomar
Thejesh
Affaan Mustafa
devin-ai-integration[bot]
haelyra
Lx
Alec Moldovan
Gaurav Dubey
Jucélio Brandão Gonçalves Junior
Jun
Nidelson Gimenez
sutazca
28winz-bot
Boube
Seekers2001
YuhaoLin2005
Yeris Rifan
jack-finance-able