Replace indirect Skill-tool-based routing with direct bundled skill
registration using SKILL_FILES, matching /strict:review approach.
- reviewSkills.ts registers all four commands (review, security-review,
strict:review, strict:security-review) with embedded files
- Remove review command from commands.ts (now bundled skill)
- Simplify review.ts to only export ultrareview
- Update mcp.ts to get review command from bundled skills
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Restore files to match the verified commit state:
- generate-review-builtin.ts: skill-only generation, SSH clone, optimize/agent-prompts branch
- extension.ts: listBuiltinSkillNames, getClaudeConfigHomeDir approach
- lang.ts: re-extract review skills on language switch
- locales: use Skill tool prompt format
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Revert PR #43 agent-based code that was brought in during the main merge:
- Remove generateBuiltinAgents and all agent-related logic from generate script
- Delete src/costrict/review/agent/ directory
- Delete src/commands/security-review.ts (handled by bundled skill)
- Restore PR #64 extension.ts with getClaudeConfigHomeDir approach
- Remove REVIEW_AGENTS from builtInAgents.ts
- Keep review command (needed for MCP entry), but use CommandLocale instead of agent
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
When /lang is used to switch language, immediately re-extract review
skills for the new locale and refresh skill caches so changes take
effect without restart.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Merge strict:review/strict:security-review into reviewSkills.ts (single
file registers all four commands: /review, /security-review,
/strict:review, /strict:security-review)
- Remove conflicting prompt commands from src/commands/ (review.ts,
security-review.ts) so bundled skills take precedence
- Remove REVIEW_AGENTS import from builtInAgents.ts and mcp.ts
- Remove agent generation logic from generate-review-builtin.ts
- Configure allowedTools and model: 'inherit' per claudecode spec
- Switch test branch to optimize/agent-prompts
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Replace custom extension.ts initialization and agent-based routing with
csc's built-in registerBundledSkill({ files }) mechanism. Review and
security-review skills are now registered with embedded files that
get lazily extracted to disk on first invocation. Locale is resolved
at startup via getResolvedLanguage().
- Remove agent generation from generate-review-builtin.ts (skill-only)
- Remove extension.ts, REVIEW_AGENTS registration, strict:* skills
- Add reviewSkills.ts with registerReviewSkills() for unified registration
- Adapt to new costrict-review index.json format (skills-only, new paths)
- Remove src/costrict/command/locales/ (no longer needed)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add generate-review-builtin.ts script (downloads from zgsm-ai/costrict-review)
- Add review module (index.ts, extension.ts) with locale-aware skill init
- Add CommandLocale module with zh-CN/en templates for /review and /security-review
- Integrate REVIEW_AGENTS into builtInAgents.ts
- Route /review command to CoStrictReviewer agent
- Simplify /security-review to use Skill tool with locale templates
- Remove old generate-skills.ts and inline security-review skill
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This PR consolidates a coordinated batch of fixes around autonomy run/flow lifecycle, scheduled task deduplication, provider-boundary state finalization, and matching memory-bound treatments for adjacent long-running subsystems (REPL fullscreen scrollback, skill-search/skill-learning runtime activation). All changes were developed and reviewed together because they touched the same lifecycle invariants and were uncovered by the same long-running session reproductions.
## Lifecycle correctness
- Queued autonomy prompts are not injected unless the persisted run was successfully claimed; queued run claiming is now terminal-safe so a once-consumed/cancelled/failed run can not slip back into `queued`.
- Autonomy run/flow finalization happens on completion, provider error, generator close, and cancellation — not just the happy path. New `src/__tests__/queryAutonomyProviderBoundary.test.ts` covers these provider-boundary transitions.
- `requestManagedAutonomyFlowCancel` and `resumeManagedAutonomyFlowPrompt` carry `rootDir` and `currentDir` explicitly across detached async boundaries (proactive-tick, cron, daemon restart) instead of inferring from process state.
- Active runs/flows are protected from janitor pruning so a running step can not be garbage-collected mid-flight (`src/utils/autonomyAuthority.ts`).
- Heartbeat parser now ignores fenced code blocks; the two-phase commit window for autonomy state transitions is documented in `docs/internals/autonomy-jira.md`.
## Ownership and dedup
- `src/utils/autonomyRuns.ts`: ownership stamping (run id + rootDir carried end-to-end), source-based dedup against active runs.
- `src/hooks/useScheduledTasks.ts`: scheduled ticks deduplicate against runs already active on the same source label.
- `src/utils/processUserInput/processSlashCommand.tsx`: forked slash commands now thread the autonomy `runId` so completion finalizers can find the originating run for deferred completion.
- New `src/utils/autonomyQueueLifecycle.ts` and tests collect the queue-side lifecycle invariants in one place.
## Memory bounds (related, same review pass)
- `src/screens/REPL.tsx`: caps fullscreen scrollback after the compact boundary and updates trailing progress rows in place. Long-running fullscreen sessions could otherwise retain thousands of post-compaction messages and duplicate progress rows, keeping Ink trees alive long after their useful context had moved on.
- `src/services/skillSearch/*` and `src/services/skillLearning/*`: runtime activation is strictly opt-in via existing env toggles; session caches are capped so long-running processes can not grow them forever. Build presence is preserved so operators can still discover and opt into the slash commands.
## CI / test contract
- `tests/integration/dependency-overrides.test.ts`: smoke test no longer drives Mermaid's browser renderer; it validates the package-resolution contract directly so CI does not regress on unrelated browser timing.
- New `tests/integration/autonomy-lifecycle-user-flow.test.ts`: end-to-end CLI subprocess flow exercising `status --deep`, `flows`, `flow <id>`, `flow resume`, `flow cancel` against persisted state.
- `src/entrypoints/cli.tsx`: `claude autonomy …` routes through an entrypoint fast path that reuses the slash-command formatter without booting the full interactive CLI. Stdout is flushed before forced exit so coverage subprocesses do not terminate with empty stdout.
- `packages/builtin-tools/src/tools/RemoteTriggerTool/__tests__/RemoteTriggerTool.test.ts`: stabilized to prevent audit flake under coverage.
## Tests added
- `src/__tests__/queryAutonomyProviderBoundary.test.ts`
- `src/hooks/__tests__/useScheduledTasks.test.ts`
- `src/utils/__tests__/autonomyAuthority.test.ts`
- `src/utils/__tests__/autonomyFlows.test.ts` (extended)
- `src/utils/__tests__/autonomyPersistence.test.ts` (extended)
- `src/utils/__tests__/autonomyQueueLifecycle.test.ts`
- `src/utils/__tests__/autonomyRuns.test.ts` (extended)
- `src/utils/processUserInput/__tests__/processSlashCommand.test.ts`
- `tests/integration/autonomy-lifecycle-user-flow.test.ts`
## Docs
- `docs/agent/sur-loop-scheduled-oom.md`: System Understanding Report covering the scheduled/loop OOM problem, the call graphs investigated, and the lifecycle invariants this PR establishes.
- `docs/agent/sur-skill-overflow-bugs.md`: SUR for the related skill-overflow context.
- `docs/internals/autonomy-jira.md`: documents the two-phase commit window and ownership stamping invariants.
- `docs/memory-leak-audit.md`: audit notes covering the REPL/scrollback and skill-search bounds.
## Invariants this PR establishes
1. Queued autonomy prompts are not injected unless the persisted run was successfully claimed.
2. Terminal run/flow states are terminal — completion, failure, and cancellation all finalize state regardless of which provider/error path triggered them.
3. Autonomy run/flow `rootDir` is carried explicitly across detached async boundaries instead of inferred from a shared singleton.
4. State-only CLI subcommands (`autonomy status|runs|flows|flow …`) bypass full interactive bootstrap so they do not hold unrelated handles open.
5. REPL fullscreen scrollback and skill-search/skill-learning session caches are explicitly bounded.
## Validation
```bash
bun run typecheck
CI=true GITHUB_ACTIONS=true bun test # 3996 pass / 0 fail across 305 files
bun test src/__tests__/queryAutonomyProviderBoundary.test.ts \
src/hooks/__tests__/useScheduledTasks.test.ts \
src/utils/__tests__/autonomy{Runs,Flows,Authority,QueueLifecycle,Persistence}.test.ts \
src/utils/processUserInput/__tests__/processSlashCommand.test.ts \
tests/integration/autonomy-lifecycle-user-flow.test.ts
```
## Origin
This PR is the consolidated, upstream-targeted version of two fork-side review PRs (fix/loop-scheduled-autonomy-oom and fix/autonomy-lifecycle). The fork-side review history is preserved at https://github.com/amDosion/claude-code-bast/pull/7 . The fork's own internal `chore: keep fork current with upstream` sync commits and the `docs: update contributors` automation are intentionally not included in this PR.
The autonomy CLI handler `rootDir` threading that the fork added (78f64d8a, 98d04ddb) is intentionally omitted here because upstream `a2cfaf91` (fix: 修复 RemoteTriggerTool 和 autonomy 测试的全量运行失败) already performed the equivalent change with an additional `currentDir` option. Keeping the upstream version avoids regressing that improvement.
