699 Commits

Author	SHA1	Message	Date
xiaoju	be92cb2dd2	feat: agent-claude-code reports real $usage from stream-json output ... - Map parsed numTurns, inputTokens, outputTokens, durationMs to Usage type - Add @united-workforce/protocol dependency + tsconfig reference - 747 tests pass Fixes #77 Refs #68	2026-06-04 22:36:44 +00:00
xiaoju	7681e8b8e2	feat: agent-hermes reports $usage (turns + duration) ... - Count assistant turns from session messages - Measure wall-clock duration per prompt call - inputTokens/outputTokens remain 0 (ACP protocol doesn't expose token data yet) - Both runPrompt and continueHermes report usage Fixes #76 Refs #68	2026-06-04 22:30:14 +00:00
xiaoju	248ac710fd	feat: agent-mock emits fixed $usage stats ... - Mock agent returns {turns:1, inputTokens:0, outputTokens:0, duration:0} - E2E test 1 (linear workflow) asserts usage in CAS step nodes - 747 tests pass Fixes #75 Refs #68	2026-06-04 22:19:29 +00:00
xiaomo	172c232e61	Merge pull request 'feat: add $usage field to adapter protocol' (#80) from feat/74-usage-in-protocol into main ... feat: add $usage field to adapter protocol (#80)	2026-06-04 22:14:12 +00:00
xiaoju	99f40c2488	feat: add $usage field to adapter protocol ... - Add Usage type to protocol (turns, inputTokens, outputTokens, duration) - Add usage to StepRecord, StepNodePayload, StepEntry, STEP_NODE_SCHEMA - Thread usage through util-agent extract pipeline (writeStepNode → persistStep → createAgent) - All adapters return usage: null as placeholder (mock, hermes, claude-code, builtin) - 746 tests pass, no breaking changes (usage not in schema required array) Fixes #74 Refs #68	2026-06-04 15:41:07 +00:00
xingyue	bf489c59a5	fix: agent bin fields point to dist/cli.js instead of src/cli.ts ... All three agent packages had bin pointing to ./src/cli.ts (bun-era leftover). Node cannot execute .ts files directly, causing ERR_MODULE_NOT_FOUND when spawning agents. Closes #78	2026-06-04 23:25:39 +08:00
xingyue	83bcda60ff	refactor(prompt): rename subcommands and add frontmatter output ... - Rename: user→usage-reference, author→workflow-authoring, adapter→adapter-developing - Remove: developer (content lives in CLAUDE.md) - All prompts output complete SKILL.md with YAML frontmatter - Setup instructions simplified: uwf prompt bootstrap > SKILL.md - Remove all bun references, use pnpm/npm - Fix CLAUDE.md: fixed→independent versioning - Delete old reference files (user/author/developer/adapter) Closes #66	2026-06-04 22:46:11 +08:00
xiaoju	3401873051	chore: rebranding cleanup — reset versions to 0.1.0, bun→pnpm in docs ... - All 9 packages reset to version 0.1.0 - CLAUDE.md: bun→pnpm, fixed→independent versioning, proman commands - docs/architecture.md: bun→pnpm in toolchain table - docs/sync-readme.md: bun→pnpm in conventions	2026-06-04 13:05:26 +00:00
xiaoju	18170a4313	refactor: extract validateCount, replace CLI spawn with direct import ... - Extract validateCount() from cmdThreadExec (throw instead of process.exit) - 5 validation tests now import validateCount directly (no subprocess) - Only --help tests still spawn CLI (need Commander output) - Test time: 1.7s → 475ms Fixes #61	2026-06-04 12:31:17 +00:00
xiaoju	8bf5b88172	chore: remove integration tests, clean up CI exclusion ... Deleted: - acp-client.integration.test.ts (3 cases) - resume-e2e.integration.test.ts (1 case, already skipped) These tests spawn a real hermes CLI and hit live LLM, belonging to the eval layer (#34), not CI. ACP protocol parsing is already covered by unit test acp-client.test.ts. Also removed the --exclude integration/ hack from test:ci. Fixes #60	2026-06-04 12:19:24 +00:00
xiaoju	66c2e2a79b	fix: use node dist/cli.js instead of npx tsx in thread-step-count tests ... npx tsx hangs in CI Docker (30s+ timeout). node dist/cli.js runs in <2s.	2026-06-04 11:57:32 +00:00
xiaoju	58b58d511e	fix: add timeout to cmdThreadExec count logic tests	2026-06-04 11:48:46 +00:00
xiaoju	596c05bfcc	fix: use node dist/cli.js instead of npx tsx in prompt help test ... npx tsx fails in CI (tsx not found, npm tries to install it)	2026-06-04 11:32:09 +00:00
xiaoju	d26f54e8ea	fix: biome format + remove unused noConsole suppressions	2026-06-04 11:22:46 +00:00
xiaoju	883bd79bcb	fix: add timeout to CI-slow tests + check stderr for help output	2026-06-04 11:18:49 +00:00
xiaoju	63454a4cfd	fix: OCAS_DIR → OCAS_HOME in test helpers + exclude integration tests from CI ... - Remaining OCAS_DIR references caused test isolation failures - agent-hermes integration tests need 'hermes' CLI, skip in CI Fixes #58	2026-06-04 11:06:42 +00:00
xiaoju	9f5891169e	fix: add missing workflow destructure in current-role test ... The createMarker call used shorthand 'workflow' but the variable was not destructured from cmdThreadStart. Fixes #56	2026-06-04 10:56:44 +00:00
xiaomo	f56e24cf82	Merge pull request 'test: expand E2E coverage — suspend, count, mustache, completed resume' (#51) from test/33-more-e2e into main ... test: expand E2E coverage — suspend, count, mustache, completed resume (#51)	2026-06-04 09:04:09 +00:00
xiaoju	974c2b8f1b	test: add E2E tests for suspend/resume, --count, mustache, and completed resume (#33) ... 4 new E2E scenarios: 4. $SUSPEND → resume lifecycle (suspendedRole/suspendMessage metadata) 5. --count 3 runs entire pipeline in one invocation 6. mustache template variables rendered into edgePrompt 7. completed thread resume (衔尾蛇: end → start, CAS chain preserved) Total: 7 E2E scenarios, all passing.	2026-06-04 09:03:01 +00:00
xingyue	dbb7885ffd	chore: fix biome check errors (40 → 0) ... - Auto-fix: import sorting, formatting (17 files) - Unsafe auto-fix: unused vars, template literals (7 files) - Manual: nursery/noConsole → suspicious/noConsole suppression - Manual: suppress noExcessiveCognitiveComplexity for cmdThreadResume and parseWorkflowPayload - Manual: remove unused destructured vars in current-role tests Closes #48	2026-06-04 16:45:45 +08:00
xiaomo	cd7e4e77ff	Merge pull request 'feat: agent-mock package for deterministic E2E testing (#33)' (#44) from test/33-mock-agent into main ... feat: agent-mock package for deterministic E2E testing (#44)	2026-06-04 08:38:51 +00:00
xiaoju	80e8efb05e	test: E2E integration tests with uwf-mock agent (#33) ... Three scenarios testing the full CLI pipeline: 1. Linear workflow (planner → worker → $END): CAS chain integrity 2. Loop workflow (developer ↔ reviewer): moderator routing through cycles 3. Role mismatch detection: agent catches routing bugs Uses workflow add → thread start → thread exec with uwf-mock, verifying CAS state, thread lifecycle, and error handling. Updated assertions to use getThread().status === 'completed' (aligned with PR #45 unified thread storage). Refs #33	2026-06-04 08:06:22 +00:00
xiaoju	75fb752a82	feat: add agent-mock package for deterministic E2E testing (#33) ... New package @united-workforce/agent-mock (uwf-mock CLI): - Reads pre-scripted outputs from a YAML mock data file (--mock-data) - Counts existing CAS chain steps to determine step index - Validates expected role matches actual moderator routing - Stores minimal detail node in CAS for valid step refs - Zero LLM, instant execution, 100% deterministic Usage in config.yaml: agents: mock: command: uwf-mock args: ["--mock-data", "./fixtures/scenario.yaml"] Refs #33	2026-06-04 08:00:07 +00:00
xingyue	06af1dc668	fix: resolve workflow from CAS chain in collectCompletedThreads ... Instead of hardcoding workflow as empty string for completed/cancelled threads, use resolveWorkflowFromHead to get the actual workflow hash from the CAS chain, consistent with active thread handling. Closes #46	2026-06-04 15:35:08 +08:00
xiaomo	bbea89c067	Merge pull request 'refactor: unified thread storage + resume completed threads' (#45) from refactor/39-unified-thread-storage into main ... refactor: unified thread storage + resume completed threads (#45)	2026-06-04 07:25:56 +00:00
xingyue	bda3e3a861	feat(cli): resume completed threads (衔尾蛇: end → start) ... uwf thread resume now supports completed threads: - Evaluates workflow graph from $START to find first role - Clears completed state (status → idle, completedAt → null) - Builds resume prompt with supplement context - Full CAS chain preserved for rich context Suspended resume behavior unchanged. Cancelled/idle threads still rejected. 425 tests pass. Part of #39, closes #43	2026-06-04 15:13:47 +08:00
xingyue	ca7b68ca5f	refactor(cli): unify thread storage, remove history prefix ... - store.ts: all threads in @uwf/thread/* with status tag - Remove HISTORY_VAR_PREFIX, ThreadHistoryLine, deleteThread - Add loadActiveThreads, loadHistoryThreads, completeThread - Add migrateHistoryVarsToThreadVars migration - thread.ts: replace deleteThread+addHistoryEntry with completeThread - shared.ts: remove findHistoryEntry fallback - Update all tests for unified storage model 422 tests pass. Part of #39, closes #41, closes #42	2026-06-04 15:01:20 +08:00
xingyue	23e2ae9eb4	refactor(protocol): add status + completedAt to ThreadIndexEntry ... - ThreadIndexEntry gains status and completedAt fields - createThreadIndexEntry defaults to idle/null - normalizeThreadIndexEntry backward-compat defaults - updateThreadHead resets to idle (衔尾蛇 resume prep) - markThreadSuspended sets status=suspended - New markThreadCompleted(entry, status, now) function - serializeThreadIndexEntry includes new fields Part of #39, closes #40	2026-06-04 14:42:14 +08:00
xiaoju	6b7636b088	refactor: unify env vars (UWF_HOME, OCAS_HOME) + env only in CLI (#37) ... Breaking changes: - UWF_STORAGE_ROOT → UWF_HOME - WORKFLOW_STORAGE_ROOT removed (no fallback) - OCAS_DIR → OCAS_HOME (aligned with ocas CLI) Library functions no longer read process.env: - util-agent/storage.ts: resolveStorageRoot(override), getGlobalCasDir(override) - agent-hermes: isResumeDisabled(flag) pure function, CLI reads env - agent-claude-code: CLI reads CLAUDE_MODEL and passes to agent Fixes #37	2026-06-04 05:12:05 +00:00
xiaoju	06e959e7a5	test: add unit tests for core modules (#35) ... Cover high-priority untested modules: - util: base32, result, refs-field, storage-root, log-tag - util-agent: storage (normalizeWorkflowConfig, resolveStorageRoot), run (parseArgv) - agent-builtin: tools (read-file, write-file, run-command), session, detail 627 → 719 tests (+92), all passing. Refs #35	2026-06-04 04:35:33 +00:00
xiaoju	90893b0aa8	chore: integrate proman scaffold ... - Add proman.yaml with 8 packages in dependency order - Add @shazhou/proman as devDependency - Replace root scripts: build/test/check/format → proman commands - Keep typecheck script for standalone tsc --build Fixes #27	2026-06-04 03:10:14 +00:00
xiaoju	d0ef2c4676	chore: upgrade @ocas/* to ^0.3.0, migrate better-sqlite3 → node:sqlite ... - @ocas/core and @ocas/fs upgraded from ^0.2.2 to ^0.3.0 - agent-hermes: replace better-sqlite3 with node:sqlite (DatabaseSync) - Remove better-sqlite3 and @types/better-sqlite3 dependencies - Fix remaining bun references in cli test helpers (execFileSync) Refs #28	2026-06-04 01:59:00 +00:00
xiaoju	fd33bf5ee1	fix: address PR review — await store.cas.put + bun shebang → node ... - Add missing await on store.cas.put() in run.ts:192 - Replace #!/usr/bin/env bun → #!/usr/bin/env node in all CLI bins - Update issue-551 test to assert node shebang	2026-06-03 14:58:23 +00:00
xiaoju	8cb74672bc	fix: resolve remaining agent-hermes test failures ... - Update issue-551 test: assert bun engines removed (not present) - Migrate session-detail tests from bun:sqlite to better-sqlite3 API (db.exec for DDL, db.prepare().run() for inserts) Refs #26	2026-06-03 14:39:20 +00:00
xiaoju	e5e6de2fad	chore: migrate from bun to pnpm + vitest + esbuild ... - Replace bun:test with vitest across all packages - Replace bun build with esbuild - Replace bun:sqlite with better-sqlite3 - Fix OCAS Store API: store.put/get → store.cas.put/get - Fix vitest vi.mock hoisting (vi.hoisted) - Add pnpm-workspace.yaml and pnpm-lock.yaml - Update all package.json test/build scripts WIP: 8 failures remain in agent-hermes (bun engines check + sqlite migration) Refs #26	2026-06-03 14:33:03 +00:00
xingyue	4306935dbc	refactor: remove legacy symlink migration code ... Remove migrateStorageIfNeeded() which created symlinks from ~/.uncaged/workflow → ~/.uwf and ~/.uncaged/json-cas → ~/.ocas. This was temporary migration support. Users who still have old paths can run a one-time copy manually. Zero 'uncaged' references remain in active codebase.	2026-06-03 00:22:13 +08:00
xingyue	87b893bd28	refactor: remove all uncaged codename references ... - Remove UNCAGED_CAS_DIR and UNCAGED_WORKFLOW_STORAGE_ROOT env var fallbacks - Tests updated to use OCAS_DIR / UWF_STORAGE_ROOT - All docs, READMEs, scripts, workflows, skills updated - Only symlink migration code retains .uncaged paths (functional requirement) Closes #12 (Phase 5 complete)	2026-06-03 00:08:45 +08:00
xingyue	e2098e7371	docs: update stale comments and prompts referencing old storage formats ... - architecture-reference.ts: threads.yaml/history.jsonl/registry.yaml → variable store, storage layout updated (~/.ocas/ + ~/.uwf/) - protocol types.ts: JSDoc comments updated - thread-index.ts: serialization comment updated - util-agent context.ts: buildContext JSDoc updated Only migration code in store.ts retains old file references (needed to read legacy files).	2026-06-02 23:59:07 +08:00
xingyue	5970456a54	refactor: align package folder names with npm package names ... Rename packages/ subdirectories to match their @united-workforce/* scope: cli-workflow → cli workflow-agent-builtin → agent-builtin workflow-agent-claude-code → agent-claude-code workflow-agent-hermes → agent-hermes workflow-dashboard → dashboard workflow-protocol → protocol workflow-util-agent → util-agent workflow-util → util Updated all tsconfig references, scripts, and active docs. Historical docs (docs/plans/, docs/superpowers/) left as-is. Closes #21	2026-06-02 23:45:45 +08:00
xingyue	34ce190e5f	fix: agent createAgentStore uses wrong CAS path (~/.uwf/cas instead of ~/.ocas) ... createAgentStore was calling getCasDir(storageRoot) which resolves to ~/.uwf/cas/, but since Phase 3 all CAS data lives in ~/.ocas/. getActiveThreadEntry already used getGlobalCasDir() correctly, causing a split where thread lookup succeeded but CAS node reads failed. Found during e2e walkthrough after Phase 0-5 migration.	2026-06-02 23:19:14 +08:00
xingyue	3e12e6ebc0	refactor: migrate thread history from JSONL to ocas variable store (Phase 4c)	2026-06-02 22:53:24 +08:00
xingyue	93b96987a3	refactor: migrate threads index from YAML to ocas variable store (Phase 4b) ... - Replace loadThreadsIndex/saveThreadsIndex with granular variable API: loadAllThreads, getThread, setThread, deleteThread - Variable: @uwf/thread/<thread-id>, value=head hash, tags=suspend metadata - Auto-migration: threads.yaml → variables, renames to .migrated - Updated ~20 call sites in thread.ts, step.ts, shared.ts - workflow-util-agent: getActiveThreadEntry reads from variable store - New test helper: seedThread/seedThreads - biome fix: removed unused imports - 22 files changed Ref #11	2026-06-02 22:22:38 +08:00
xingyue	8052473728	refactor: migrate workflow registry from YAML to ocas variable store (Phase 4a) ... - UwfStore gains varStore: VariableStore (SQLite at ~/.ocas/variables.db) - loadWorkflowRegistry reads from @uwf/registry/* variables - saveWorkflowRegistry writes individual @uwf/registry/<name> variables - Auto-migration: workflows.yaml → variables on first run, renames to .migrated - Updated callers in workflow.ts and thread.ts - Tests updated and passing Ref #11	2026-06-02 21:58:58 +08:00
xingyue	1aacf11ad9	refactor: remove uwf cas subcommand, use ocas CLI ... - Remove entire 'uwf cas' command group from CLI - Delete commands/cas.ts (only used by CLI + tests) - Delete cas.test.ts and cas-exit-code.test.ts - Update workflow YAMLs: uwf cas get/has/refs/walk → ocas - Update e2e-walkthrough script to use ocas - Update docs and reference files - Keep store-global-cas.test.ts (internal CAS store tests) CAS operations now go through 'ocas' CLI exclusively. Agent text storage handled internally by uwf pipeline. Closes #10	2026-06-02 21:30:59 +08:00
xingyue	eb8e98f67f	refactor: migrate storage paths ~/.uncaged/workflow → ~/.uwf ... - Default storage root: ~/.uncaged/workflow → ~/.uwf - Default CAS root: ~/.uncaged/json-cas → ~/.ocas - Env var priority: UWF_STORAGE_ROOT → WORKFLOW_STORAGE_ROOT → UNCAGED_WORKFLOW_STORAGE_ROOT (legacy) - CAS env var: OCAS_DIR → UNCAGED_CAS_DIR (legacy) - Auto-migration: symlink old paths on first run + deprecation warning - Updated all comments, JSDoc, reference docs, CLAUDE.md - New test: store-storage-root.test.ts Closes #9	2026-06-02 21:14:48 +08:00
xingyue	e067a2f25a	refactor: rebrand npm packages @uncaged/* → @united-workforce/* ... Package mapping: - @uncaged/cli-workflow → @united-workforce/cli - @uncaged/workflow-protocol → @united-workforce/protocol - @uncaged/workflow-util → @united-workforce/util - @uncaged/workflow-util-agent → @united-workforce/util-agent - @uncaged/workflow-agent-hermes → @united-workforce/agent-hermes - @uncaged/workflow-agent-claude-code → @united-workforce/agent-claude-code - @uncaged/workflow-agent-builtin → @united-workforce/agent-builtin - @uncaged/workflow-dashboard → @united-workforce/dashboard Changes: - 8 package.json name + dependency refs - 82 files: import statements updated - .changeset/config.json updated - CLAUDE.md updated - bunfig.toml restored for preload CLI command (uwf) and directory names unchanged. Closes shazhou/united-workforce#8	2026-06-02 20:56:06 +08:00
xingyue	e65e2aec72	refactor: migrate test runner from vitest to bun:test ... - Replace vitest with bun:test across all 8 packages (47 test files) - vi.spyOn → spyOn, vi.restoreAllMocks() → mock.restore() (3 files) - toHaveBeenCalledOnce → toHaveBeenCalledTimes(1) (bun:test compat) - Delete all vitest.config.ts files - Remove vitest from devDependencies - Add preload.ts for process.exit mock (cli-workflow) - Fix import ordering (biome check --write) All tests pass. Closes #601	2026-06-02 18:55:17 +08:00
xiaomo	fa188ddf21	Merge pull request 'feat: rename skill subcommand to prompt, add usage/setup' (#599) from feat/prompt-subcommand into main	2026-06-02 05:46:44 +00:00
xingyue	61ee22f647	feat: rename skill subcommand to prompt, add usage/setup ... Rename `uwf skill` → `uwf prompt` to align with ocas CLI convention. Changes: - `uwf prompt usage` — combined output of all references (for skill installation) - `uwf prompt setup` — agent-facing setup instructions - `uwf prompt list` — list available prompt names - `uwf prompt <name>` — individual reference (user/author/developer/adapter/bootstrap) - Removed: commands/skill.ts, __tests__/skill.test.ts - Added: commands/prompt.ts, __tests__/prompt.test.ts Ref #598	2026-06-02 13:41:46 +08:00
xiaomo	7b13e7deb4	Merge pull request 'feat: thread list/show displays suspended state and message' (#596) from feat/591-thread-list-suspended into main	2026-06-02 05:12:12 +00:00