- done=true means all files created, build+lint pass
- done=false means progress made, continue next iteration
- Updated both sense-generator and workflow-generator coder prompts
- Split 500-line monolith into roles/{planner,coder,tester,committer}/
- Each role: index.ts (build function) + prompt.ts (pure function)
- Use createCursorRole/createLlmRole/createHermesRole factories
- DIP: env vars read in index.ts, injected via build.ts
- esbuild bundle to dist/index.js (24kb)
- Moderator logic preserved: planner→coder→tester→committer with retries
Fixesxiaoju/nerve-workspace#3
- Move index.js → src/index.ts with proper types for all 4 senses
- Move schema.ts → src/schema.ts
- Add package.json with esbuild build script per sense
- Bundle to index.js at sense root (daemon loads this)
- Update sense-generator coder prompt with TypeScript conventions
Fixes#224
- Add esbuild build script to package.json
- Add .gitignore for dist/
- Remove stale tsc-generated .js files (now bundled)
- Include sense files generated by workflow run (hermes-gateway-health update, worker-process-metrics)
- Clean up nerve.yaml (remove deleted workflows, migrate reflexes to interval)
- Remove nerveYaml injection from planner (skill has it)
- Remove sensesDir/nerveRoot from coder and tester (skill has conventions)
- Prompts now just say 'read the skill' instead of inlining knowledge
- BuildSenseGeneratorDeps reduced to { provider, cwd }
- index.ts drops getNerveYaml(), SENSES_DIR, readFileSync
Every role is self-contained (types.ts, prompt.ts, index.ts).
No shared.ts, no cross-role imports. All dependencies injected:
index.ts — wiring (resolve env, call buildSenseGenerator)
build.ts — buildSenseGenerator(deps) → WorkflowDefinition
moderator.ts — pure routing, composes meta from role types
roles/planner/ — buildPlannerRole(deps), self-contained
roles/coder/ — buildCoderRole(deps), self-contained
roles/tester/ — buildTesterRole(deps), self-contained
Workflow is now reusable: buildSenseGenerator() can be called with
any provider/paths, not hardcoded to this machine.
小橘 🍊（NEKO Team）
attempt is a deterministic fact (count of tester steps), not something
an LLM should guess. Removed from tester meta schema, moderator counts
it directly from context.steps.
小橘 🍊（NEKO Team）
Replaced 122-line hand-written smoke test with createHermesRole.
Hermes runs the full lifecycle check autonomously via terminal:
files → nerve.yaml → sense list → trigger → query → logs on failure.
All 3 roles now use factories:
planner: createCursorRole (ask mode)
coder: createCursorRole (default mode)
tester: createHermesRole (e2e verification)
小橘 🍊（NEKO Team）
- planner/coder: replaced 80+ lines hand-written agent calls with createCursorRole()
- SenseMeta slimmed to routing signals only (senseName, filesCreated, passed/attempt)
- Roles read context from thread via nerve thread <id>, not from previous role's meta
- tester stays hand-written (pure CLI logic)
- Re-exported spawnSafe from workflow-utils for helper use
Refs uncaged/nerve#210
小橘 🍊（NEKO Team）
Workflow: pr-code-reviewer
User request (summary): Create a code-reviewer workflow that: 1) Takes a PR URL (supporting Gitea git.shazhou.work, GitHub, and Gitee) as input. 2) A fetcher role detects the platform from the URL, authenticates using ava...
Reviewer (summary): npx tsc --noEmit passed and nerve.yaml contains the workflow entry
Staged paths:
- nerve.yaml
- workflows/pr-code-reviewer/index.ts
- workflows/pr-code-reviewer/package.json
- workflows/pr-code-reviewer/pnpm-lock.yaml
- workflows/pr-code-reviewer/tsconfig.json
Auto-generated by workflow-generator itself. After reviewer passes,
committer creates a feature branch, stages workflow files, commits
with a meaningful message, and pushes to origin.
小橘 🍊（NEKO Team）
llmExtract returns {} as T in dryRun mode, causing .map() on undefined.
Each role now returns mock data immediately when dryRun is true.
小橘 🍊（NEKO Team）
4-role workflow (analyst → architect → coder → reviewer) that generates
new workflows from natural language descriptions. Uses cursorAgent for
analysis/design/code generation and llmExtract for structured extraction.
小橘 🍊（NEKO Team）
