Commit Graph

22 Commits

Author SHA1 Message Date
xiaoju 4d85a2eebb refactor: split test suites — test:ci for unit tests, test for all
- 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
2026-05-25 10:27:46 +00:00
xiaoju a11d76264a chore: open-source readiness — LICENSE, CONTRIBUTING, templates, package metadata
- Add MIT LICENSE
- Add CONTRIBUTING.md with setup, conventions, PR workflow
- Add GitHub issue/PR templates
- Add repository/homepage/bugs/license to all package.json files
- Add Install section to README before Quick Start

Fixes #510

小橘 🍊(NEKO Team)
2026-05-25 10:13:36 +00:00
xiaomo 6e8dedeb2f docs: move cursor rules to docs/, add project rules to CLAUDE.md
Also bump @uncaged/json-cas* to ^0.5.2
2026-05-25 09:54:45 +00:00
xiaoju 2b8cd99100 fix(agent-claude-code): use buildContinuationPrompt for step context
Replace custom buildHistorySummary with shared buildContinuationPrompt
from workflow-agent-kit. This aligns claude-code agent with hermes agent:

- First visit: includes step content (within 32k quota)
- Re-entry: shows only steps since last visit (meta only, session has context)

Previously developer could not see reviewer's detailed feedback on
re-entry, only {"approved":false}. Now gets full review text.

Fixes #486
2026-05-25 02:01:57 +00:00
xiaoju 39f6ae692b feat(cli): add filtering and pagination to thread list command
Implements enhanced filtering and pagination for the `uwf thread list` command
to support workflows with large numbers of threads.

Changes:
- Add --page, --page-size parameters for pagination (default: page 1, size 20)
- Add --since, --until time filters supporting multiple formats (ISO8601, relative like "2h", "1d")
- Add --workflow filter to show threads for specific workflow
- Add --sort parameter (newest-first, oldest-first, alphabetical)
- Add pagination metadata in JSON output (page, pageSize, totalThreads, totalPages, hasMore)
- Implement parseRelativeTime() for human-friendly time expressions (1h, 30m, 2d, 1w)
- Add comprehensive unit tests for filters, pagination, and time parsing
- Update CLI help text with new parameters and examples

Fixes #471
2026-05-24 14:44:30 +00:00
xiaoju 1d174ee5c9 fix(agent-kit): separate session cache per agent
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
2026-05-24 09:16:06 +00:00
xiaoju 8ca7708a12 fix: add cas_ref format to claude-code-detail turns schema
The turns array items in CLAUDE_CODE_DETAIL_SCHEMA were missing
format: 'cas_ref', so expandDeep in step-details couldn't resolve
turn hashes to their payloads. Hermes schema already had this.

小橘 <xiaoju@shazhou.work>
2026-05-24 04:17:29 +00:00
xingyue 221919448e refactor: reduce cognitive complexity in session-detail and acp-client
Extract helper functions to bring parseClaudeCodeStreamOutput (37→≤15)
and handleSessionUpdate (24→≤15) within complexity limits. Add tests.

Fixes #448
2026-05-24 00:41:39 +08:00
xingyue 68b82c9574 style: use dot notation for process.env.CLAUDE_MODEL 2026-05-24 00:25:08 +08:00
xingyue 6481fc0cc5 refactor(cli): reduce cognitive complexity in thread.ts
Extract helper functions (resolveThreadId, getThreadHead, listThreadSteps,
displayStepDetails, displayThreadRead) to reduce nesting and improve
readability. Also adds test coverage for the refactored functions.

Fixes #446
2026-05-23 23:47:54 +08:00
xiaoju ffc31a8c19 docs: sync all README.md files with current codebase
- Root README: add all 9 packages to table, update architecture diagram,
  refresh CLI reference from uwf --help
- New READMEs for 8 packages (cli-workflow, workflow-protocol,
  workflow-moderator, workflow-agent-kit, workflow-agent-hermes,
  workflow-agent-builtin, workflow-agent-claude-code, workflow-dashboard)
- Updated workflow-util README to match current exports
- All API sections verified against src/index.ts exports

小橘 🍊(NEKO Team)
2026-05-23 15:00:05 +00:00
xiaomo c1f04929f4 Merge pull request 'feat(builtin-agent): persist ReAct loop turns as session JSONL' (#434) from feat/turn-jsonl-session into main 2026-05-23 10:48:49 +00:00
xingyue 1abc3b4cf4 chore: fix all biome lint errors across monorepo
- Fix import ordering (organizeImports) across multiple packages
- Replace forEach with for...of loops (noForEach)
- Replace non-null assertions with fallback values (noNonNullAssertion)
- Add biome-ignore comments for justified noExplicitAny usages
- Remove parameter properties, use explicit class properties (noParameterProperties)
- Fix string concatenation to template literals (useTemplate)
- Fix format issues (CSS, TypeScript)
- Add tailwindDirectives CSS parser config in biome.json
- Replace var with const (noVar)

Result: 0 errors, 12 warnings (all cognitive complexity, acceptable)
2026-05-23 18:39:02 +08:00
xiaoju 211f38bc8d fix(claude-code): include edge prompt in agent prompt as Current Instruction
buildClaudeCodePrompt was dropping ctx.edgePrompt entirely — the graph
transition instruction (e.g. 'Implement the plan') never reached the agent.
Now appended as '## Current Instruction' at the end of the prompt.
2026-05-23 09:46:17 +00:00
xingyue 080792a6c0 feat: builtin agent session resume via deterministic message reconstruction (#426)
- 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
2026-05-23 17:34:49 +08:00
xiaoju d16ce44bc3 feat(claude-code): enrich step details with per-turn breakdown
Switch from --output-format json to stream-json --verbose to capture
per-turn data. Detail now includes:
- model name
- usage (input/output/cache tokens)
- stopReason
- turns[] as individual CAS nodes with role, content, tool calls

Also addresses PR #421 review fixes:
- sessionId guard: skip cache write when sessionId is empty/undefined
- silent catch: log resume failures with debug tag 5VKR8N3Q
- atomic write: session cache uses temp+rename for crash safety

Closes #422
2026-05-23 08:16:47 +00:00
xiaoju 1afaeacd57 feat: extract session cache to agent-kit, add resume to claude-code agent
Move getCachedSessionId/setCachedSessionId from workflow-agent-hermes
into workflow-agent-kit so all agent adapters can share the same
session cache logic.

Add cross-process session resume to workflow-agent-claude-code:
on re-entry (isFirstVisit=false), look up the cached sessionId and
use 'claude --resume' to continue with full conversation history.

Cache file renamed from hermes-sessions.json to agent-sessions.json
to reflect its shared nature.

Refs #418
2026-05-23 07:44:02 +00:00
xiaoju 4b45f4e6d1 feat: replace edgePrompt null check with isFirstVisit (Phase 2)
- Add isFirstVisit: boolean to AgentContext
- Compute from steps history: !steps.some(s => s.role === role)
- hermes.ts: use isFirstVisit for first-entry vs re-entry logic
- buildInitialPrompt: always append edgePrompt as Moderator Instruction
- edgePrompt is never blanked — always the real moderator instruction
- New tests for first-visit, re-entry, and fallback scenarios

Refs #405, #407, #404
2026-05-23 04:54:11 +00:00
xiaoju 3d6399c0e3 feat: make edge prompt required (Phase 1)
- Transition.prompt: string | null → string
- EvaluateResult.prompt: string | null → string
- AgentContext.edgePrompt: string | null → string
- CLI YAML validation rejects missing prompt
- All tests updated

Phase 2 will replace edgePrompt === null checks with findLastRoleIndex.

Refs #405, #406, #404
2026-05-23 04:28:58 +00:00
xingyue 4dff320d5c fix: throw on non-JSON Claude Code output instead of fallback 2026-05-22 18:57:07 +08:00
xingyue 176844d7f5 fix: add sessionId to raw fallback, fix test meta→frontmatter+description 2026-05-22 18:42:27 +08:00
xingyue 31695e89a8 feat: add workflow-agent-claude-code package
Claude Code CLI adapter for the workflow engine, mirroring
workflow-agent-hermes architecture. Spawns `claude -p` with
`--output-format json` for structured output parsing.

Refs #391
2026-05-22 18:38:18 +08:00