Store the fully assembled prompt sent to each agent in CAS as a text
node, referenced from StepNodePayload.assembledPrompt. This enables
exact reproduction of what the agent received for debugging hallucinations.
Changes:
- workflow-protocol: StepRecord + STEP_NODE_SCHEMA add assembledPrompt field
- workflow-util-agent: AgentRunResult includes assembledPrompt, run.ts stores it
- workflow-util-agent: schemas register TEXT_SCHEMA for prompt storage
- workflow-agent-claude-code: return assembled prompt from buildClaudeCodePrompt
- workflow-agent-hermes: return assembled prompt from buildHermesPrompt
- workflow-agent-builtin: return empty prompt (no prompt assembly)
- cli-workflow: step read --prompt renders the stored prompt
- All test fixtures updated for new field
Legacy steps without assembledPrompt show 'Prompt not recorded' message.
小橘 🍊
- Enhanced Biome config with test file override for noConsole
- Applied Biome auto-fixes (8 files: formatting, template literals, optional chains)
- Updated all package repository URLs to git.shazhou.work/uncaged/workflow.git
- Added workflow-agent-claude-code to publish order in scripts/publish-all.mjs
- Added --ignore-scripts flag to publish command to bypass prepublishOnly guard
- Installed vitest in root devDependencies for test infrastructure
- Created vitest.config.ts for all 8 packages with passWithNoTests: true
- Fixed 3 test files to use vitest imports instead of bun:test
- Added test and test:ci scripts to packages missing them
- Added missing build step to .gitea/workflows/ci.yml
- Renamed CI job from 'test' to 'check' for clarity
- Created workflows/solve-issue.yaml with TDD-driven issue resolution workflow
- Registered solve-issue workflow with uwf (hash: 084YVM60BR8G6)
- Added packageManager: bun@1.3.14 to root package.json
- Added preinstall guard to block npm/pnpm/yarn
- Added prepublishOnly guard to root and all 7 public packages
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When mustache variables in edge prompts resolve to empty strings (because
upstream output lacks the fields), the engine now returns a Result.error
instead of passing an empty --prompt to the agent.
- evaluate.ts: check rendered prompt is non-empty after mustache.render()
- run.ts: improve parseArgv error message for empty --prompt
- Export parseArgv for testability
- Add 7 tests covering all cases from the spec
Implement thread-level and edge-level working directory management:
- Thread-level cwd (required, defaults to process.cwd())
- Captured at uwf thread start time
- Stored in StartNodePayload
- Inherited by all steps unless overridden
- Edge-level location (optional, supports mustache templates)
- New location: string | null field on Target type
- Resolved by moderator using previous step's output
- Example: location: "{{{repoPath}}}"
- Step audit trail
- Each StepNodePayload records actual cwd where agent executed
Changes:
- workflow-protocol: Add cwd to StartNodePayload & StepRecord, location to Target
- cli-workflow: Thread start captures cwd, moderator resolves location, step execution uses resolved cwd
- workflow-util-agent: Expose cwd in agent context
Tests:
- Protocol type tests (3 scenarios)
- Moderator location resolution tests (5 scenarios)
- Thread-location integration tests (3 scenarios)
All tests pass. Build successful. Backward compatible.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Breaking change: Store API keys directly in config.yaml instead of
environment variable names.
## Changes
### @uncaged/workflow-protocol
- Change ProviderConfig.apiKeyEnv: string → apiKey: string
- Update README to reflect new type
### @uncaged/workflow-util-agent
- extract.ts: Remove dotenv loading, use providerEntry.apiKey directly
- storage.ts: Update normalizeProviders to validate apiKey field
- Update error messages to reference apiKey instead of apiKeyEnv
### @uncaged/cli-workflow
- setup.ts: Write actual API key to config.yaml, not .env
- Remove apiKeyEnvName(), loadEnvFile(), saveEnvFile() functions
- Remove getEnvPath() function
- Update cmdSetup to not return envPath in result
- Update README to reflect config.yaml stores API keys
- Fix setup-validate.test.ts to not expect envPath in result
## Verification
- ✅ bun run build passes
- ✅ All tests pass (260/260 in cli-workflow, 55/55 in util-agent)
- ✅ bun run check passes (only pre-existing warnings)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two fixes for 'uwf thread start solve-issue' failures:
1. json-cas 0.5.2 (npm) was missing oneOf in ALLOWED_SCHEMA_KEYS.
Published json-cas 0.5.3 with the fix, bumped all packages to ^0.5.3.
2. Semantic validator only recognized oneOf-based multi-exit schemas.
Roles using $status with enum (e.g. enum: [approved, rejected]) were
incorrectly treated as single-exit. Added isEnumMultiExit() support.
Changes:
- validate-semantic.ts: isEnumMultiExit(), getEnumStatuses(), checkSingleExitMustache()
- All package.json: @uncaged/json-cas ^0.5.2 → ^0.5.3
- validate-semantic.test.ts: 5 new enum multi-exit tests (Suite 3b)
- solve-issue-tea-worktree.test.ts: updated for current workflow structure
小橘 🍊
- Add `content: string | null` to RoleStep type
- Resolve contentHash → text for the last step when building ThreadContext
- Update buildAgentPrompt to include <output> tag with step content
- Add 16k content quota with truncation
- Update tests
- buildOutputFormatInstruction(schema): auto-generates frontmatter
format guide from Zod schema, injected at top of system prompt
- Adapter prepends deliverable format before role's systemPrompt
- buildThreadInput reordered: Task → Steps → Parent → Tools
- Scope reminder: 'Focus exclusively on YOUR role's deliverable'
- 8 tests for buildOutputFormatInstruction
Refs #351
Phase 2 of RFC #351 — adapter tries frontmatter first (zero LLM cost),
falls back to runtime.extract() when frontmatter is missing/invalid.
- tryFrontmatterMeta(): parse → validate → schema.safeParse
- Happy path stores body (no frontmatter) in CAS
- Fallback stores full raw in CAS + LLM extract
- 5 tests covering both paths
Refs #351
Make AgentFn<Opt> always take a mandatory options argument, removing
the void conditional overload. Simplify createAgentAdapter, restore
exports needed by tests, and fix CLI test bundles to use cas.put
instead of disallowed @uncaged/* imports.
Co-authored-by: Cursor <cursoragent@cursor.com>
- scripts/publish-all.mjs: pins workspace:^ before npm publish, restores after
- Workaround for bun publish workspace:^ resolution bug in pre mode
小橘 🍊
- Remove llmProvider and workspace from CursorAgentConfig (now just command/model/timeout)
- extractWorkspacePath uses runtime.extract + runtime.cas instead of standalone reactor
- TextProducerFn signature gains runtime parameter: (ctx, prompt, runtime)
- develop-entry.ts hardcodes cursor-agent path, no more env var dependency
- Drop @uncaged/workflow-reactor dep from workflow-agent-cursor
- Update tests for simplified config
小橘 <xiaoju@shazhou.work>
- Remove Gitea npm registry, use npmjs.org
- changeset publish works natively with npmjs
- release script: build + test + changeset publish
- Remove custom release.sh, all via changesets
- All @uncaged/* packages → 0.4.0
- Internal deps: workspace:* → workspace:^ (resolves to ^0.4.0 on publish)
- Fix exports: add 'bun' condition for local dev (src), 'import' for consumers (dist)
- Remove stale 'main: src/index.ts' from 6 packages
- Fix publish.sh topo sort to match workspace:^ prefix
星月 <xingyue@shazhou.work>
Packages without exports.types pointed main/types to src/ which
doesn't exist in published tarballs. Now all packages have:
exports."." = { types: dist/index.d.ts, import: src/index.ts }
Bump to 0.3.18.
xingyue
xiaomo
xiaoju
Scott Wei