宜博 / lemonboss

hire() now checks system_agents (source_kind='template') before provisioning a new
company agent: if the role has a shared template row, skip copying agent.md and
instead let AgentManager.getAgentConfig()/PromptBuilder.build() resolve the prompt
from the shared legacy_path at call time, with per-company context assembled from a
new company-context.md. Roles without a template row (including the 6 ids that exist
in both system/agents/ and system/templates/, e.g. evolver-youtube-crawler) fall back
to the existing full-copy behavior unchanged.

- server/services/graph-service.js (new): lookupSharedAgentMd(), upsertOrgGraphNode()
- server/services/company-service.js: hire() reference-mode branch, _provisionReferenceAgent()
- server/src/core/agent-manager.js: getAgentConfig() resolves prompt/companyContextPath
- server/src/core/prompt-builder.js: build() concatenates company-context.md
- unit + integration tests covering all 6 acceptance criteria from
  docs/todo/system-design/27-p1-virtual-reference.md §6, including a regression test
  against the real idearun:evolver-youtube-crawler naming-collision case

Full regression suite (587 tests) passes; independent adversarial review found 0
blocking/major issues.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds server/services/graph-db.js (new data/graph.sqlite: system_agents,
org_graph_nodes, org_graph_edges) and graph-seed-service.js, which scans
system/agents/, system/templates/, and data/companies/*/company.json into
seed rows without touching company-service.js's existing hire/copy path.

Real repo data diverged from the design doc's original estimates (8 not 10
global agents; 39 not 34 template dirs; system/agents/ and system/templates/
turn out to share 6 ids describing the "same" agent from two different
files) — documented in docs/todo/system-design/27-graph-agent-architecture.md
section 7 for P1/P2 to resolve.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Implements the §P2 acceptance gate from plan-migration.md: a single
POST /api/devloop/projects/:pid/run?only=todo-be drives the L1 inner
loop (Coder → Tester → fail → Coder → Tester → pass), with the second
Coder pass demonstrably reflecting on the first failure.

Mock protocol — stateful sequences:
- packages/acp-core/protocol/ClaudeCliProtocol.js
  * Mock fixtures now support `sequence: [{chunks,result,files}, ...]`.
    Each protocol.connect() + sendPrompt() consumes the next variant;
    sticks on the last entry after exhausted.
  * Static `ClaudeCliProtocol.resetMockState()` clears counters between
    test runs.

Fixtures:
- fixtures/devloop-mock/devloop-architect.json — units.json now has
  status:pending + retries:0 + retry_budget per unit, plus
  units/{todo-be,todo-db,todo-fe}/spec.json so Tester has acceptance
  criteria to read.
- fixtures/devloop-mock/devloop-coder.json — sequence: implement (with
  intentional missing 400 branch) → retry (reflective fix, coder.log
  attempt:2 has last_failure/last_cause/this_fix/rationale).
- fixtures/devloop-mock/devloop-tester.json — sequence: fail (1/3
  failure with hint pointing at missing body validation) → pass (3/3).

LoopController:
- server/src/core/devloop/loop-controller.js — adds:
  * runUnit(pid, unitId, opts) — drives the L1 loop via unit-registry
    FSM (pending → coding → testing → failed → coding → testing →
    passed/blocked). Calls Coder then Tester per attempt; on failure,
    builds a retry context summarizing prior coder.log + tester
    failures and feeds it into the next Coder prompt.
  * _buildRetryContext + _findLatestTesterResult helpers.
  * callAgent now rewrites units.json.project_id to the real pid after
    mock writes (so unit-registry validation passes).

Route:
- server/routes/devloop.js — adds POST /projects/:pid/run?only=<unitId>.
  Without ?only, returns 501 (full project run lands in P3).

Acceptance:
- scripts/phase2-verify.js — 6 steps:
  1. POST /projects (PM + Architect)
  2. POST /run?only=todo-be returns ok=true, attempts=2, final=passed
  3. FSM trail matches expected 6-step transition sequence
  4. coder.log second entry has all 4 reflection fields
  5. runs/ has ≥2 result.json with first.ok=false, last.ok=true
  6. sandbox cross-unit + prd writes blocked by ToolSandboxError

Tests (5 new cases):
- server/tests/devloop/run-unit.test.js (4) — FSM trail, coder.log
  reflection, runs/ result chain, sandbox enforcement.
- server/tests/devloop/routes.test.js (+3) — POST /run validation,
  full P2 loop, 404 on unknown unit.

Results:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- phase2-verify: 6/6
- vitest devloop+acp-core: 181/181 (was 174 → +7)

Specs:
- docs/prd/newfunction/_spec/plan-migration.md · P2 验收
- docs/prd/newfunction/_spec/loops-l1.md (retryWithReflection)
- docs/prd/newfunction/_spec/agents-coder.md
- docs/prd/newfunction/_spec/agents-tester.md

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Implements the §P1 acceptance gate from plan-migration.md: a single
POST /api/devloop/projects produces a runnable todo-demo project with
multi-page PRD/SDD sites, units.json, integration spec, agent-state,
and history snapshots — all via mock agents (no real Claude CLI cost).

Code additions:
- packages/acp-core/protocol/ClaudeCliProtocol.js
  * mock mode now emits an extra `mock/files` acp_event when the fixture
    contains a files[] array. LoopController applies it to the project
    root, letting mock agents produce real outputs.
- server/src/core/devloop/loop-controller.js (now ~280 lines)
  * callAgent(pid, agentName, prompt, opts) — single-agent invocation:
    reads system/templates/{agent}/prompt.md, runs mock protocol,
    applies fixture files[], timeline-logs, auto-commits.
  * runDocsPhase(pid, requirement) — orchestrates PM → Architect with
    `docs.complete` timeline marker.
  * getProjectState(pid) — returns project.json + units + prd_rev/sdd_rev
    + timeline tail for the GET /state endpoint.
- server/routes/devloop.js (new)
  * POST /api/devloop/projects — createProject + runDocsPhase
  * GET  /api/devloop/projects
  * GET  /api/devloop/projects/:pid/state
- server/index.js / server/agent-server.js — mount /api/devloop.

Mock fixtures (drive the full acceptance file tree):
- fixtures/devloop-mock/devloop-pm.json
  * 14 files: prd/{index,reading-guide,product/*,feature/*,flow/*,prototype/*}.html,
    prd/assets/{shell.css,shell.js,search-index.json},
    agent-state/{pm.json,pm-todo.json}, history/prd-rev-001.html.
- fixtures/devloop-mock/devloop-architect.json
  * 13 files: sdd/{index,mvcp/*}.html, sdd/assets/*,
    units.json (3 units, DAG), integration/spec.json,
    agent-state/{architect.json,architect-todo.json}, history/sdd-rev-001.html.

Acceptance:
- scripts/phase1-verify.js — spins ephemeral express app, POSTs the
  todo-demo project, asserts 23 expected paths exist + 3 units with
  l2_rounds/l2_budget + git ≥4 commits + timeline events.

Tests (12 new cases):
- server/tests/devloop/loop-controller.test.js (7) — callAgent +
  runDocsPhase + state.
- server/tests/devloop/routes.test.js (5) — POST validation, full
  POST, GET state, 404 on unknown pid.

Results:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- vitest devloop+acp-core: 174/174 (was 162 → +12)

Specs: docs/prd/newfunction/_spec/plan-migration.md · P1 Docs MVP

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Final P0 deliverables to make the system bootable in mock mode and
pass `scripts/phase0-verify.js` + `scripts/phase0-test-call.js` end-to-end.

ClaudeCliProtocol (mock mode):
- LEMONBOSS_CLAUDE_MODE=mock or { mock: true } in constructor enables
  mock mode. connect() becomes a no-op; sendPrompt reads fixtures from
  fixtures/devloop-mock/{agentName}.json and emits scripted session_update
  chunks + session/result(mock=true). Falls back to default.json.

Agent registry:
- 6 entries added to system/templates/_registry.json (devloop-pm,
  devloop-architect, devloop-coder, devloop-tester, devloop-integrator,
  devloop-triager).
- Per-agent dirs system/templates/devloop-{role}/ with:
  * prompt.md   — auto-extracted from agents-{role}.html §2.2
  * config.json — cli.toolPolicy.allowedTools + sandbox.writeAllowList

Tooling:
- scripts/extract-agent-prompts.js  — regex-extracts §2.2 system prompts
  from 6 agent HTML pages to system/templates/devloop-{role}/prompt.md.
- server/src/tools/devloop/index.js — central export (tools Map,
  bashHooks, dispatch).
- server/src/core/devloop/loop-controller.js (P0 skeleton) — exposes
  createProject (sandbox alloc + git init + first commit + timeline) and
  commitAfterAgent (per-agent kind-routed git commit + timeline event).

Mock fixtures:
- fixtures/devloop-mock/default.json + devloop-pm.json

Acceptance scripts:
- scripts/phase0-verify.js   — 8 static checks (35 tools loadable,
  6 agents registered, prompt+config wired, bash guard exported, services
  require, fixtures present, git-vault interface, loop-controller).
- scripts/phase0-test-call.js — 7 end-to-end steps under mock mode
  (createProject → CLI connect → sendPrompt chunks → no-op commit returns
  null → real write commits → git log ≥2 → timeline has both events).

vitest.config.js: include packages/**/*.test.js so the mock smoke test
runs in the suite.

Results:
- 162/162 devloop + acp-core tests pass (up from 159).
- phase0-verify: 8/8.
- phase0-test-call: 7/7.

Specs: docs/prd/newfunction/_spec/plan-migration.md · Quick-Start step 7

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Adds the DevLoop Agent tool layer (CommonJS) under server/src/tools/devloop:
- _errors.js / _sandbox.js — shared infra (3 error classes + path allow-list w/ {unitId})
- tool-registry.js — loadAllTools / dispatch / listToolNames / getDevLoopTools
- persistence-tools.js (5) — write_todolist · update_todo_item · update_runtime_state · timeline_append · record_memory
- doc-tools.js (12) — bootstrap_prd_site · bootstrap_sdd_site · write_chapter · write_mvcp_page · archive_doc · diff_html · diff_units · echo_diff · update_search_index · validate_prd_site · validate_sdd_consistency · hash_contract
- coder-tools.js (3) — contract_bridge · sandbox_check · append_coder_log (retry fields required)
- tester-tools.js (5) — parse_vitest · hint_builder · bug_open · bug_transition · bug_list
- integrator-tools.js (6) — port_picker · spawn_units · health_wait · run_case · parse_placeholder · collect_stderr
- triager-tools.js (4) — extract_evidence · category_classifier · diff_contract_vs_impl · find_similar_bug
- bash-json-guard.js — preExecute hook blocking inline JSON in Bash (CLAUDE.md L91-99)

Total: 35 callable devloop tools.

Tests: 88 cases across 9 files, all passing; combined with P0.0 services
suite the project now has 159 green tests.

Specs:
- docs/prd/newfunction/_spec/arch-tool-registry.md
- docs/prd/newfunction/_spec/agents-{pm,architect,coder,tester,integrator,triager}.md

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

First concrete code commit for DevLoop. Implements all 7 services that
P0.A tools will depend on, per plan-migration P0.0.

Services (server/services/devloop/, ~900 lines):
- path-resolver.js   foundation — resolveProjectRoot + 12 derived paths;
                     sandbox + linked-new mode support; sensitive path
                     blacklist (with /tmp + os.tmpdir() exemptions);
                     ~/.devloop/linked-projects.json registry
- doc-store.js       PRD/SDD multi-file site IO + cheerio validateHTML +
                     validateUnitsSchema + canonical-JSON hashContract
                     + automatic history/ archival
- unit-registry.js   FSM (M-2: pending→coding→testing→passed/failed/blocked);
                     l2GateOpen; diffUnits (added/changed/removed);
                     reset semantics for L2 + L3
- bug-tracker.js     bugs.ndjson append-only + dedupKey + P-9 transition
                     state machine + list/stats/history aggregation
- timeline-logger.js M-13 ProcessTimeline — append/read/tail;
                     summary truncate to 280; payload oversize → ref form
- changelog-writer.js M-15 — append/read/latest for prd/sdd/units revs
- sse-broker.js      per-pid pub/sub + 25s heartbeat + stream.log replay
                     via Last-Event-ID; emit returns monotonic id
- git-vault.js       spawn-git wrapper — init/commit/tag/log/diff/status/
                     resetWorkingTree/revert/archive; per-pid mutex;
                     nothing-to-commit returns {skipped:true} not throw

Tests (server/tests/devloop/, 71 passing):
- path-resolver.test.js  (17 cases) — sensitive path · sandbox alloc · linked-new
- doc-store.test.js      (12 cases) — validateHTML · validateUnitsSchema · hashContract
- unit-registry.test.js  (15 cases) — FSM transitions · l2GateOpen · diffUnits
- bug-tracker.test.js    (10 cases) — open dedup · transition · list filter · history
- timeline-logger.test.js (9 cases) — append/read/tail · summary truncate · oversize
- git-vault.test.js      (8 cases)  — init idempotent · commit · tag · status · archive

vitest config (`globals: true`) means tests use describe/it/expect globally,
no `require('vitest')` needed (and would fail under vitest 4).

Dep added: cheerio@^1.0.0 (used by docStore.validateHTML; HTML parsing).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

1. Evolver agent.md: Added token budget rules
   - No re-reading unchanged files between iterations
   - Use head/grep instead of cat for large files
   - Concise output only (scores + diff summary, no full SKILL.md)
   - Cap at 5 iterations per session (was 10)
   - Early stop if score change < 2 points for 2 consecutive rounds

2. agent-chat.js: System prompt size guards
   - MAX_PROMPT_FILE_SIZE = 15KB per file (auto-truncate with warning)
   - MAX_TOTAL_PROMPT_SIZE = 100KB total (safety net)
   - Prevents runaway files from inflating context ever again

When a task completes and triggers a callback to the parent agent,
previously it always created a new convId (callback-{taskId}), spawning
a fresh CLI process with full system prompt re-injection.

Now it checks the sessions pool for an existing connected session of the
target agent and reuses its convId. This avoids creating a new CLI
process and saves the system prompt overhead (~30K tokens for master).

Falls back to creating new session if no active one exists.

Layer 1 (P0): Per-agent session mutex
- heartbeat-service.js: skip heartbeat if previous session still active (30min safety valve)
- agent-chat.js: reject concurrent /chat requests for same agentId with different convId (429)
  Multi-turn conversations on same convId still work normally

Layer 2 (P1): Advisory file lock utility
- server/utils/file-lock.js: O_EXCL-based .lock file mechanism
  Auto-cleanup stale locks, graceful degradation on timeout

Root cause: HeartbeatService creates new convId per heartbeat, spawning
independent Claude CLI processes that concurrently write config.json and
SKILL.md, causing rollbacks and FRAUDULENT scores.

- New template: content-selector with skills, train data (hunt/digest/evolve)
- youtube-crawler: add workspace archive, digest_v2, evolve_v2, mock data
- Update agent todo/plan/SKILL files for digester, evolver, hunter, innovator, master
- Update server/routes/agent-chat.js
- Update .gitignore: exclude runtime data (memory, sqlite, __pycache__, temp files)

…day window, skip old files

…writes (4KB/1s), remove messages.log fallback in loadHistory

…to prevent EADDRINUSE

1. Workspace page: left file tree + right detail/editor panel
   - File info: name, path, size, created/modified timestamps
   - Three view modes: Code / Preview / Edit with save
   - HTML files auto-open in Preview tab (sandboxed iframe)

2. Backend APIs:
   - GET/PUT /:companyId/workspace/files (list + content + save)
   - PUT /:companyId/files/content (company file save)

3. Navbar: removed Skills/Jobs/Pipeline, added Workspace
4. All nav links open in new tabs (target=_blank)

- Added inline editing for template description and type fields
- Implemented Delete Template functionality (removes both file system and registry entry)
- Added confirmation safeguards for the destructive delete action

Architecture fix for long-running tool execution:

1. ClaudeCliProtocol: Two-tier idle timeout
   - Chat mode: 45s (detect API hang/silent rate limit)
   - Tool execution mode: 5min (Bash long tasks like pip install)
   - Automatically switches on tool_use_start / content_block_stop events

2. Provision API: POST /templates/:templateId/provision
   - Runs shell commands directly via child_process.exec
   - Bypasses Claude ACP entirely (no idle timeout issue)
   - 10min per-command timeout, security blocklist
   - Frontend button with prompt for custom commands

3. Template UI: Added 🔧 安装依赖 button (teal)

Fixed 4 hidden bugs where path.join(DATA_ROOT, "system", ...) was used instead
of direct path.resolve to root-level system/:

- agent-chat.js: billing log scan (line 804) and agent list scan (line 909)
- company-service.js: TEMPLATES_DIR and GLOBAL_AGENTS_DIR constants
- heartbeat-service.js: system agents scan directory

These were missed because they used path.join with a variable (DATA_ROOT)
rather than the literal string "data/system" that sed caught.

- Moved data/system/ → system/ (agents, templates, skills, data, workspace)
- Updated all server route/service path references
- Updated all script path references
- Updated all documentation references
- Restructured .gitignore for cleaner system/ vs data/ boundary

system/ = platform-shared assets (system agents, template library)
data/ = tenant-specific company instance data

…aruncreate skill paths

- Upload skill files to .claude/skills/ (Claude Code ACP reads from here)
- Add conversation type filter (user/callback/task/train) to AgentChat
- Parse messages.log for richer conversation history display
- Fix idearuncreate template & company agent skill directory structure
- Add adm-zip dependency for ZIP extraction
- Add fs/path top-level requires in company.js

- Add TaskTimeline.vue: two-pane dashboard with task list + message timeline
- Add task-service.js: aggregate cross-agent conversations into task tree
  - 4-strategy parent-child inference (explicit meta, time-overlap, conv→tpl, master→T)
  - Read messages.log for full tool call details (not just history.json)
- Add tasks.js API routes: GET /api/tasks, GET /api/tasks/:taskId/timeline
- Mount /api/tasks in agent-server.js
- Add 'Task Logs' nav entry in AppNav.vue after Templates
- Support taskId in URL (/tasks/:taskId?) for sharing/bookmarking
- Add --parent flag to CLI task dispatch for explicit parentTaskId
- Auto-detect parentTaskId in task/dispatch from sender's active task
- Add --instructions flag to template train CLI command
- Update master tools.md with new parameters

…ictly enforce empty shell company creation

…th time-based multi-dimension token tracking charts

…en costs across agents

- Updated `GET /api/agent/:agentId/info` to include heartbeat and cron configurations.
- Added `PUT /api/agent/:agentId/heartbeat` to update config.json and toggle service heartbeat on the fly.
- Added `PUT /api/agent/:agentId/cron` to update cron.json list.
- Updated AgentChat.vue detail panel UI to include interactive heartbeat toggles and a cron job management list.

- Updated `POST /api/company/create` to create an empty shell without bootstrapping CXO/HR automatically.
- Updated `master/agent.md` instructions so Master Agent handles all Template library hirings.
- Renamed 'MasterBot' navigation link to 'System Agents'.
- Updated AgentChat sidebar to only show System Agents when accessed via the System Agents link.

- GET /api/company/templates/:id/logs scans system agent conversations
- Logs stored in system agents (agent-creator/innovator), NOT in template dir
- Template directories stay clean for copying
- Collapsible log cards with status, time, message count, and output summary
- Auto-poll during generate/train actions (10s/15s intervals)

- POST /api/company/templates: scaffold new template via AgentScaffold
- POST /api/company/templates/:id/generate: trigger agent-creator to write definitions
- POST /api/company/templates/:id/train: trigger innovator FDE training pipeline
- PUT /api/company/templates/:id/files/content: save template file content
- TemplateAgents.vue: create form, action buttons, editable preview, status banner