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
Add comprehensive tests verifying that `uwf step show` produces valid
JSON output even when step detail nodes contain control characters
(newlines, tabs, carriage returns, etc.) in tool call args and content
fields.
Tests cover:
- Basic control characters (newlines, tabs, CR+LF)
- Backslashes and quotes
- Unicode control characters (U+0001-U+001F)
- Nested CAS refs with control characters
- Large steps with multiple tool calls
- Empty/null values
- YAML output format (unaffected by escaping)
The tests confirm that JSON.stringify() already handles control
character escaping correctly when serializing JavaScript objects
to JSON. No code changes needed - these tests serve as regression
guards to ensure the behavior remains correct.
Fixes#557
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add ThreadStatus type to workflow-protocol
- Update StepOutput type to include status field alongside deprecated done/background fields
- Implement status computation in cmdThreadShow (idle/running/completed/cancelled)
- Update cmdThreadStepOnce to include status in return values
- Add comprehensive test suite for thread show status scenarios
Fixes#559
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Exposes the existing cwd parameter from cmdThreadStart to the CLI layer,
allowing users to specify a custom working directory for thread execution.
- Added --cwd <path> option to uwf thread start
- Option defaults to process.cwd() when not provided
- Added comprehensive test suite with 4 test cases
- All 328 tests in cli-workflow package pass
Fixes#561
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>
- Add agentOverrides (minDepth 3) and modelOverrides (minDepth 2) to VALID_CONFIG_KEYS
- Support per-key minDepth instead of hardcoded 3
- No knownFields for either key (sub-keys are user-defined)
- Add 5 new tests covering valid/invalid paths for both keys
小橘 <xiaoju@shazhou.work>
- Add engines.bun >= 1.0.0 to workflow-agent-hermes package.json
- Update README to explain uwf-hermes is an adapter, not hermes itself
- Update uwf setup --agent help text to mention adapter concept
- Add tests for engines field, shebang, and adapter docs
- Patch uncaged-workflow-cli skill with Agent Adapters section
Adds 'uwf skill user' command for agents/humans using the uwf CLI.
Covers setup, workflow management, thread lifecycle, step operations,
CAS queries, logging, and global options with a Quick Start guide.
Refs #538
Adds 'uwf skill actor' command for agents executing workflow roles.
Covers the two things an actor needs to know:
1. Frontmatter output protocol (status field, schema-defined fields)
2. CAS operations (put, get, refs, walk, merkle DAG pattern)
Refs #540
- Remove unnecessary Promise.resolve() wrappers (sync function)
- Use try/finally for db.close() instead of manual close at each exit
- Flatten nested try/catch
Follow-up to #535 review nits.
小橘 🍊
When sessions.write_json_snapshots is disabled, Hermes only writes to
state.db (SQLite). loadHermesSession now falls back to reading from
~/.hermes/state.db when the JSON file is missing.
- Add getHermesDbPath() and loadHermesSessionFromDb() functions
- Use bun:sqlite with readonly mode, try-catch for graceful errors
- JSON file still takes priority (fast path)
- Filter messages to user/assistant/tool roles
- Convert unix timestamps to ISO 8601 strings
This commit addresses three related issues in the CLI config and setup commands:
1. Issue #531: Fix config list apiKey masking
- maskApiKeys() now checks for 'apiKey' instead of 'apiKeyEnv'
- Updated tests to use apiKey field throughout
2. Issue #532: Add config set key validation
- Reject unknown top-level keys with helpful error messages
- Reject unknown nested fields in providers/models/agents
- Reject incomplete paths and nested paths on scalar keys
- Added VALID_CONFIG_KEYS schema and validateConfigKey() function
3. Issue #533: Fix agent name double-prefix in setup
- mergeConfig() now uses _agentNameFromBinary() to normalize agent names
- 'uwf-hermes' input now produces 'hermes' key with 'uwf-hermes' command
- Added tests for prefixed agent names
All tests passing, no regressions.
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>
Add configuration management commands to uwf CLI:
- uwf config list: display all config values (masks API keys)
- uwf config get <key>: retrieve specific value using dot notation
- uwf config set <key> <value>: update config value with auto-creation
Implementation:
- New file packages/cli-workflow/src/commands/config.ts with helper functions
- Comprehensive test coverage (32 tests) in config.test.ts
- Supports nested path navigation via dot notation
- Auto-creates intermediate objects when setting new paths
- Masks apiKeyEnv values in list output for security
Resolves#526
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- moderator-reference: use nested map graph format matching evaluate.ts
- yaml-reference: use goal/procedure/output/capabilities/frontmatter fields
matching actual WorkflowPayload, not fabricated system/outputSchema
- skill.test.ts: replace hardcoded absolute path with __dirname-relative
- skill.test.ts: assert 'frontmatter' instead of 'outputSchema'
Closes#519
The ACP protocol's tool_call updates only carry a display title (not a
structured tool name) and omit rawInput for polished tools, making the
reconstructed messages unusable for step read/show.
Changes:
- hermes.ts: storePromptResult reads ~/.hermes/sessions/session_{id}.json
via loadHermesSession() instead of using ACP-reconstructed messages
- acp-client.ts: strip message/tool-call collection logic, keep only
text chunk accumulation for final response extraction
- step.ts: TurnData gains role + toolCalls fields; formatTurnBody
renders them in step read markdown output
- README: document sessions.write_json_snapshots requirement
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 agent discovery step to cmdSetupInteractive flow
- _promptAgentSelection: discover uwf-* binaries, auto-select if only one,
prompt user to choose if multiple, show install hints if none found
- mergeConfig: always write selected agent entry, update defaultAgent
- Known agent labels for hermes, claude-code, cursor, builtin
- 10 new tests for _agentNameFromBinary, _printAgentMenu, cmdSetup agent config
Fixes#424
The test used a fake CasRef string as frontmatter, which fails
putSchema validation when loading from YAML files. Replace with
a proper JSON Schema object.
Fixes pre-existing failures in workflow-resolution, cas-exit-code,
and thread-step-count tests.
- Move hermes ACP integration tests to __tests__/integration/
- Add test:ci script to all packages (excludes integration/)
- CI workflow uses test:ci instead of test
- bun test still runs everything (unit + integration)
Refs #510
- Remove hardcoded ~/repos/workflow paths from procedure text
- Use .worktrees/ relative to repo root instead of global path
- Add developer failed → $END exit for unrecoverable situations
- Add worktree field to reviewer rejected variant
- Fix test workflowPath to use import.meta.dirname
Refs #506
BREAKING CHANGE: StepRecord now requires startedAtMs and completedAtMs fields.
StepEntry now requires durationMs field. Old CAS data without these fields is invalid.
- Add startedAtMs/completedAtMs to StepRecord and StepNodePayload
- Add durationMs to StepEntry (computed: completedAtMs - startedAtMs)
- Update STEP_NODE_SCHEMA to require timing fields as integers
- Record Date.now() before/after agent execution in createAgent
- Show duration in thread read headers (formatStepHeader)
- Update existing test fixtures with timing fields
buildOutputFormatInstruction now detects discriminated union schemas
(oneOf with shared const/ property) and renders separate YAML
example blocks per variant, so agents see exactly which fields belong
to which outcome instead of a flat merge.
Non-discriminated oneOf/anyOf schemas fall back to the existing flat
merge behavior.
Refs #502
- evaluate() reads $status instead of status, defaults to _ when missing
- Update all YAML examples and .workflows to use $status
- Update cli-workflow resolveEvaluateArgs to use $status
- 10 moderator tests pass including new default _ test
- Single-exit roles no longer need to declare status field
Phase 1 of #499 (closes#500)
Replace all JSONata/ConditionDefinition/ConditionalEdge references with
status-based routing terminology across 8 files:
- README.md, CLAUDE.md: moderator description, key terms
- docs/architecture.md: dependency jsonata→mustache, evaluate signature
- docs/wf-stateless-design.md: type definitions, routing context
- packages/workflow-moderator/README.md: full rewrite for new API
- packages/workflow-protocol/README.md: Target type, remove Transition
- packages/workflow-dashboard/context.md: StatusEdge, graph type
- docs/builtin-agent-research.md: stale JSONata references
xiaoju
xiaonuo
xingyue
xiaomo