- agent.plan emits plan_updated; system prompt asks for a plan first and updates while executing
- agent.propose_options registers a decision and suspends the run (waitForFact, no worker slot);
the answer or timeout (recommended/stop) resumes it as the tool result
- console-session runs get inline approvals for plan-bound capabilities: approve replays the call
with the approval, reject fails it with the reason and records it on the decision
- proposeFirst blocks execute capabilities until an option is chosen; E12 covers all paths
Co-Authored-By: Claude Opus 5.5 <[email protected]>
agent.await and agent.spawn{await:true} now return immediately when
children are still running: the session closes, runAgent registers a
wake signal in agent_run.await_wake and waits with waitForFact without
holding an io/agent worker slot. A child that settles (terminal or
waiting) signals the parent's registered fact, so the parent resumes at
once instead of polling; the suspended call replays and the child
report becomes the tool result. agent.spawn is registered replay-safe;
a suspended spawn is recorded as failed in the ledger so the replay
re-runs it against the same child.
Migration 0037 also adds the admin_recovery_code, admin_passkey and
webauthn_challenge tables used by the account work.
E11 asserts the parent is suspended with no run held by any worker
while it waits, and covers spawn{await:true} end to end.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
When children are still running, agent.await records the wait, closes
the session (the tool call stays pending in the JSONL) and drive returns
suspended. runAgent waits with waitForFact for the children to settle,
the deadline, or cancellation, then reopens the session; agent.await is
replay-safe, so resume replays it and the model gets the real result.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
no_match resources (and lookup failures after auto-review gives up) now
open a decision in the inbox with options to set a TMDB ID, pick a local
work, or dismiss; ambiguous decisions get the same manual options.
Resolve accepts identity {tmdb | mediaEntityId} and assigns with a manual
lock. The inbox option dialog collects the TMDB type/ID or searches local
works; the identity pool links each pending item to its inbox filter.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- agent_run gains depth / spawn_reason (0029); agent_run_event types
subagent_spawned / subagent_event / subagent_completed
- agent.spawn (propose, medium, replay never): allowlist ⊆ parent, mode not
above parent, budget carved from parent's remainder, idempotent per run+input;
settings.pi.subagents {enabled, maxConcurrent, maxDepth} (subagentsEnabled kept as alias)
- child runs claim a concurrency slot under an advisory lock (waitForFact while
queued); agent.await polls business tables without calling the model
- parent abort cascades to all descendants; parent runtime budget counts
descendant usage; child events mirrored into the parent stream by parent seq
- authorize caps every child call by all ancestors' allowlists/kinds
- session page shows parent link, inherited info and the subagent tree
- e2e E11; runbook section on subagents
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- /pi/providers, /pi/upstreams CRUD, test (auth-only by default, no cost), models
- subscription login via pi models.login with a suspended interaction: browser mode
waits for the pasted redirect URL, device mode polls server-side; per-provider
login lock, readable callback-port-in-use errors
- credential store locks the pi_upstream row (select for update) so api and worker
refreshes never double-write a rotated refresh token
- refreshPiTokens task: refresh before expiry; failure marks expired and opens a
relogin decision, closed again after a successful login
- runAgent picks upstreamId > agent_run.upstream_id > default upstream > legacy
settings; credentials injected by the server, never logged
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- downloads.ts observe: re-read download_task FOR UPDATE inside the tx and merge
from the locked row; qB sync could overwrite imported back to importing when
verifyAndImport committed between the sync read and write (E8 flake).
- agent finalize: accept summaryPrefix so the recovery verdict is written with
the terminal status in one update (E6 read a budget_exceeded run before the
"未恢复:…" annotation landed); recover-summary step kept, now idempotent no-op.
- organize.ts: drop local slotComplete and the once-subscription completion
write; completion/history are decided only by applySlotEvent(verify_passed)
(W5-C follow-up, removes double write). Manual slot organize uses the shared
subscriptions.slotComplete.
- vitest: server split into unit (parallel) and pg (file-serial, groupOrder 1)
projects; packages/tasks file-serial; explicit worker concurrency in e2e.
- docs: W6 stabilization record in 04-v0.1-acceptance.md.
Test expectations unchanged. Full `deno task ci` x3 green: 369s / 341s / 337s.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- settings.agent.autoInvestigateMode investigate|recover, investigateMaxAttempts, recoverVerifySec
- new capability download.recheck (execute, replay never): qB force recheck / resume, no source swap/delete
- autoInvestigate moves to agent/investigate.ts: recover mode runs execute with a recovery allowlist
only when an active grant (published policy if bound) covers the recovery actions; otherwise degrades
to read-only investigation and leaves suggestion + recheck option on the decision
- runAgent verifies recovery against business facts (download_task/task/source_release) before finalize;
verified -> decision resolved by system:auto-recover, run summary '已恢复(系统核实)'; otherwise stays
awaiting_user; per-root-cause attempt cap
- e2e E6: missingFiles -> download_failed -> recheck -> verified; no grant degrades; swap rejected;
dedupe; attempts exhausted; budget exceeded keeps attention
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- Capabilities: all 14 registered (AO: inventory.query, download.plan/submit, organize.plan/execute,
policy.preview/apply; agent: task.inspect/retry/cancel); startup asserts count == 14.
Registry injects server-side authorize (automation_grant by action/scope/policy version/budget,
one-shot approval bound to plan id + payload hash + revision + expiry; model claims ignored;
automation switch), audit_event, server idempotency keys and a capability_invocation op ledger
(migration 0021) used for crash reconciliation. download.plan creates draft plans only;
download.submit promotes draft -> reserved after authorization.
- Agent session API: POST/GET /agent/runs, GET /agent/runs/{id} (events by seq, messages, report),
POST .../messages (wake), POST .../abort; automation-grants, approvals, capabilities invoke, tasks.
- runAgent task: Pi or fake provider from settings (apiKey via secrets), events persisted to
agent_run_event then published, resume + ledger reconciliation when pendingOperations > 0,
waits for goal-linked downloads/imports and reports from business tables (submitted != imported).
- Background triggers: decision.created -> bounded plan_only investigation (dedupe per decision);
decision.updated(resolved) -> resolveDecision executes chosen option.
- W2 closure: all OpenAPI routes registered in contracts api.ts (+ subset test); TMDB key from
settings secret_ref with env fallback; PUT /sites/{id}/credentials documented as alias of
/site-accounts; completion events documented as existing status events.
- e2e (real PG + OpenWorkflow + testkit mocks): RSS->library, agent delegation with grant/deny,
background continuation, worker kill -9 recovery (single qB add), auto investigation dedupe.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
root