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
When a role participates for the first time (e.g. committer), it previously
only received the system prompt + last step output, missing the full thread
history. This caused hallucination as the role had to guess what happened.
Changes:
- build-continuation-prompt.ts: detect first-time roles and include all
steps' meta + content for last 2-3 steps (within quota)
- context.ts: add isFirstVisit detection helper
- types.ts: add isFirstVisit field to AgentContext
- hermes.ts: pass isFirstVisit through to prompt builder
Fixes#473
Each agent now maintains its own session cache file instead of sharing
a single agent-sessions.json. This prevents session ID conflicts when
multiple agents operate on the same thread+role pair.
Changes:
- getCachePath() now takes agentName parameter
- getCachedSessionId/setCachedSessionId require agentName as first param
- Cache files named <agent>-sessions.json (e.g., hermes-sessions.json)
- Agent wrappers inject their agent name into cache calls
- Add comprehensive tests for session cache isolation
- Handle malformed JSON gracefully (treat as empty cache)
Fixes#461
- StepRecord adds edgePrompt field (backward compat: defaults to "")
- StepNode CAS schema includes edgePrompt
- writeStepNode persists ctx.edgePrompt
- buildHistory exposes edgePrompt in StepContext
- buildBuiltinMessages reconstructs multi-turn moderator↔agent conversation:
system = role prompt + output format (stable prefix)
per prior visit: user (edgePrompt + inter-step summary) + assistant (output)
current: user (edgePrompt + recent summary)
- Zero extra persistence — pure function of CAS chain
- Stable prefix for LLM prompt cache hits
- 10 builtin tests pass, all other package tests pass
buildOutputFormatInstruction now includes explicit language telling agents to
output ONLY schema-defined fields and to focus on their role's deliverable.
Fixes#394
Replace hardcoded 5-field example with schema-driven generation.
Now shows actual enum values, types, and required markers for
each role's frontmatter schema.
Fixes#389
小橘 <xiaoju@shazhou.work>
Replace hardcoded 5-field candidate with schema-driven extraction.
Now reads outputSchema properties and picks matching fields from
parsed frontmatter, supporting role-specific fields like plan,
approved, success.
Falls back to standard 5 fields when schema has no properties.
Fixes#388
小橘 <xiaoju@shazhou.work>
- Move generateCliReference() to @uncaged/workflow-util
- buildRolePrompt inlines CLI reference directly (no agent tool call)
- Fix Role terminology to use new field names
- Add maintenance comment in cli-reference.ts
- Fix test assertions
Breaking change per review:
- Remove systemPrompt from RoleDefinition entirely
- identity/prepare/execute/report are now required (string, not nullable)
- Remove all legacy fallback logic in buildRolePrompt
- Simplify validate.ts, workflow.ts materialize
- Migrate all test fixtures and example workflows
Refs #359
- New buildRolePrompt() in workflow-agent-kit: four-phase prompt assembly
with fallback to systemPrompt
- Export from agent-kit index
- Update uwf-hermes to use buildRolePrompt instead of raw systemPrompt
- Add tests for all modes: four-phase, legacy, mixed
Refs #359, #362
xiaoju
xingyue