Wire the two internal tools from parts 1-2 end-to-end:
- `invokeInternalTool` RPC method added to RuntimeBridge; worker tool
`execute` calls route here, handler dispatches by tool name via the
new `agent-runtime/internal-tools/router.ts`.
- `InternalToolCallbacks` (`onApprovalCreated` / `onApprovalResolved`
/ `onDomainChanged`) are late-bound on the bridge via
`setInternalToolCallbacks`; `wire-api-server` now cross-wires the
same callbacks used by the HTTP approval route so thread integration
/ automation fire identically across both entry points.
- `RunJob.internalTools` (new field) carries the per-run tool list
main decides at dispatch time via `orchestration/internal-tool-
selector.ts`. Selection rule: `hire_agent` → any agent with
`canRequestHire` authority; `file_approval` → CEOs only (scoped to
the `approve_ceo_strategy` use case).
- Worker `createPiAgent` call site now assembles `codingTools +
internalTools` before handing to pi. Exhaustiveness guard on the
switch catches new tool names at compile time.
No prompt-level wiring yet — the `initial-user-turn` and
`team-building.en.md` updates ship in parts 4 and 5 so this commit
only adds the tool surface without changing the CEO's observable
behaviour (the existing HTTP path is still the one the prompt tells
the CEO to call).
tests: pnpm typecheck + pnpm test:unit (529) + pnpm test:eval (8/8) green
Rewrite ~525 call sites from `db.<method>()` to `db.<module>.<method>()`
for tasks and agents domains (including `getAgent`/`findAgent`/`getTask`
which live on the `entityCrud` field). Delete the corresponding
pass-through methods on AppDatabaseBase. Structural types that narrowed
`db` to a bag of flat methods (CapabilityMatchDb, EscalationDeps,
SweepStaleReviewsDeps) are reshaped to match the new namespace. Internal
callback references inside database.ts/database-base.ts now invoke the
owning module directly (e.g. `this.agents.saveAgent`) rather than the
deleted pass-through.
The codemod lives at scripts/codemod/remove-appdatabase-passthrough.mjs
and filters by owning module + optional explicit method list. It is
idempotent and does not re-rewrite already-namespaced calls.
Before this commit `createDocumentWithLifecycle` enqueued ledger rows
inside the save transaction but consumed them from an in-memory
`pendingSideEffects` array straight after commit. A crash between the
commit and the drain stranded rows as `pending` forever; a crash mid
handler left them as `running`; and there was no retry budget.
The new `DocumentLifecycleProcessor` is the single drainer. It:
- claims work via `claimPendingBatch`, an atomic `UPDATE … RETURNING`
that flips rows from `pending` to `running` while incrementing
`attempts`, so two drainers cannot race onto the same row;
- dispatches each row through a handler registered by `hookType`,
parsing the frozen `payload_json` back into the call arguments;
- records `succeeded` / `failed` / `retryable` outcomes through the
ledger, so a transient failure stays on the queue until the attempt
cap expires, after which it is marked `failed` for operators;
- reclaims rows stuck in `running` past `staleRunningMs` back to
`pending` on every sweep tick plus at startup, so a crashed process
never leaves a row orphaned;
- runs a periodic sweep so every document — including those whose
immediate post-commit drain failed — is eventually advanced.
`createDocumentWithLifecycle` now only enqueues and then calls
`lifecycleProcessor.drainForDocument` for the immediate happy-path pass.
Handlers live in `document-lifecycle-handlers.ts` so the processor stays
free of service-graph knowledge. The processor is constructed in
`bootstrap-application`, started there, and stopped on `before-quit`.
Desktop IPC saves used to fire only automation and the reviewer wake,
while HTTP API saves fired automation, thread integration, checkpoint
engine, deliverable-review approval, and the reviewer wake. Two
divergent paths produced two different lifecycle states for the same
document, and a future fix to either branch would miss the other.
Introduce `document-lifecycle.ts` as the single owner of document
creation side effects: save, derive task binding from the originating
run, fan out to automation/thread/checkpoint, wake the reviewer, then
raise a deliverable-review approval when the document qualifies. The
HTTP route and the IPC handler both call the pipeline — the API
server's `onDocumentCreated` callback is replaced with a
`createDocument` hook that delegates to the pipeline.
Wire `checkpointEngine` through `bootstrap-application` →
`main-runtime` → `main-runtime-support` so the IPC handler bag carries
both thread integration and the checkpoint engine required by the
pipeline. The document-run-provenance integration test harness is
updated to pass a `createDocument` implementation backed by the same
pipeline the production path uses.
Incoming messages (human → agent, agent → agent, channel broadcast)
persisted to the inbox and were only projected into the recipient's
transcript on the next `prepareRun`. When the recipient was already
running, every message waited for the next wake — a Slack-like
system operating at heartbeat cadence, not in real time.
`RuntimeMessageInjector` closes the gap: it looks up the recipient's
active run through `RuntimeBridge.findActiveRunForAgent`, projects
the persisted `AgentMessageRecord` via the existing inbox-projection
helper, and posts a `steer-run` ParentMessage into the worker. The
worker's runner enqueues the projection on the Agent's steering
queue; pi drains it at the next turn boundary and emits the usual
`message_end` → `persistMessage` sequence, so the session store
shadow is preserved without double-writing.
`dispatchAgentMessage` gains an optional `injectRuntimeMessage` hook
used by every API-side dispatch. Injection succeeds → we mark the
inbox row delivered and skip `wakeAgentIfPossible`. Injection fails
(no active run) → the legacy inbox + wake path still fires, so
sleeping agents continue to receive their messages on the next turn.
The injector is owned by the service graph alongside `workerService`
and `piRuntimeRef`, which gives it both the worker postMessage
channel and the RuntimeBridge active-run map without additional
coupling. Internal dispatch call sites (sweepStaleReviews,
automation actions) leave the hook unset; those system messages
target idle agents by design and do not need the runtime path.
The Co-Founder beforeToolCall hook (introduced in 77f81a7) gated every
non-readonly pi tool call as a `dangerous_command` approval. Because
agents call `POST /api/companies/:id/messages`, `/agents` (hire), and
every other company mutation via bash→node/curl, the first bash call in
every Co-Founder run got parked on a 30-minute approval timeout. Users
observed it as "agents never talk to each other" and "every bash command
waits for approval"; both symptoms are the same bug.
The business-level approval flow (`hire_agent`, `document_review`,
`plan_review`, etc. in execution-policy.ts) already gates the events
users actually care about, at the HTTP route layer where the event
originates (routes-agents.ts:368 for hiring, document routes for
deliverables). Stacking a pi-level hook on top was duplicate gating with
the wrong taxonomy.
Removed:
- src/main/agent-runtime/approval-hook.ts (entire file, 137 LOC)
- `beforeToolCall` conditional in worker-runner.ts and the
corresponding RPC method in worker-types.ts and runtime-bridge.ts
- `approvalHook` field + `resolveApproval` callback + shutdown
`cancelAll` in runtime-bridge.ts / service-graph-pi-runtime.ts /
wire-api-server.ts
Unchanged:
- `dangerous_command` approval type itself (still used by automation
workflows and routes-misc.ts)
- CEO mode (already never attached the hook)
- All business-level approval types and their wiring
An earlier cleanup deleted HumanApprovalHook wholesale on the rationale
that the body always returned {}. That was the stub implementation, not
the feature: 版本更新.md specifies AI Co-Founder mode as "human-reviewed
execution that pauses until human review arrives". With no beforeToolCall
attached, Co-Founder and CEO modes behaved identically — a silent
regression of the product's core differentiator.
Bring the hook back with real gating logic and split the Agent
construction path by execution mode so CEO runs pay zero IPC overhead.
- HumanApprovalHook.before(): create a `dangerous_command` approval row
for non-whitelisted tool calls, emit approval-updated, return a promise
that resolves when a human decides.
- AUTO_APPROVED_TOOLS whitelist: read/ls/glob/grep/find/tree. Anything
else (bash, write, edit, …) waits for human approval.
- approvalHook.resolveApproval(): invoked from wire-api-server's
onApprovalResolved *before* automation and thread follow-ups, so the
pi Agent unblocks the instant the human decides.
- approvalHook.cancelAll(): release every pending wait on shutdown so the
worker can drain cleanly; wired into service-graph-pi-runtime.release.
- worker-runner: attach beforeToolCall only when job.executionMode ===
"ai_cofounder". CEO mode constructs Agent with no hook, no RPC hops.
- WorkerRpcClient.invoke: accept per-call timeoutMs override so approval
RPCs can wait 30min instead of the 30s default.
- worker-types schema: restore beforeToolCall in the method enum.
- RuntimeBridge.handleRpc: restore beforeToolCall branch.
No changes to approval DB schema, approval lifecycle, or existing
automation/thread handling. CEO-mode runs retain zero-IPC-per-tool
behavior from the prior cleanup.
Splits the 391-line bootstrapApplication god function into a thin
orchestrator plus 7 focused modules under src/main/bootstrap/:
prepare-logger, prepare-database, prepare-services (service graph +
ipc wiring), wire-api-server (14-callback dictionary), recover-
scheduled-posts, run-startup-health-checks, recover-interrupted-tasks
(crash notification + clean-shutdown task resumption). Original
startup order, before-quit cleanup, and error handling are preserved;
the entry file drops to 153 lines.
ZacharyZhang-NY