Repository navigation
[RSI Baseline] Implement a persistent autonomous task orchestrator #787
Description
Parent Epic: #784
Why
The repository documents an agent-driven workflow, but RSI needs FlyBot itself to receive work, advance it through durable states and recover after interruption without Grok Bot as a required coordinator.
Scope
- Ingest GitHub Issue events or poll for eligible Issues; support maintainer-controlled ready/hold gates.
- Persist task state, claim/owner, attempt number, task/PR/commit links, deadlines and last observed external state.
- Implement explicit transitions for triage, ready, working, blocked, PR, review, CI, merge queue, released, failed and cancelled.
- Coordinate worktree creation and the Code Agent adapter; observe PR, review and CI as external sources of truth.
- Recover/reconcile after FlyBot restart, cloud disconnect or duplicate webhook delivery.
- Apply retry/backoff budgets and stop for human decisions, security-sensitive changes or exhausted budgets.
- Expose a read API/event stream for the dashboard.
Acceptance criteria
- Deterministic state-machine tests cover success, duplicate event, timeout, retry, cancellation and restart recovery.
- No task advances based only on an LLM claim when GitHub/Runner evidence is available.
- Hold, permissions and repository branch protections are respected.
- A low-risk test Issue can advance to an open PR without Grok Bot orchestrating the flow.
Related
- [Team] Persist a minimal collaboration task lifecycle #54 task lifecycle
- Team mode via groups: task layer step 1 - responsible-owner authority, FLYBOT-TASK envelope, workBotId #149 team task layer
- Proactive reminders 3/3: 24/7 runtime and Slack/email delivery #355 24/7 runtime
- [RFC] 跨运行时 Agent 对话与协作：以 OpenCode 为首个试点的目标、需求与两种方案 #198 cross-runtime collaboration
Activity
Birfy commentedon Oct 22, 2026
Written-by: Triage
enhancement|area:automation|needs-human. The scope overlaps three things that already exist, and the issue has to say which it replaces rather than adds:#54(closed) landed the persisted collaboration task lifecycle.#149(open,needs-human) is "task layer step 1 — responsible-owner authority,FLYBOT-TASKenvelope,workBotId"; an orchestrator that defines its own envelope duplicates that one.core/src/host/turns.js,resume.js), and the Bot-wide scheduler iscore/src/host/schedules.js.The genuinely new part is the eligibility gate and the state machine over GitHub evidence: only a
agent-readyissue may start (owner rule, 2026-10-22), and no transition may be taken on an LLM's claim when GitHub can be read. That half is worth a PR once the envelope question is settled with#149.Acceptance that would make it
agent-ready: the state list you already wrote becomes an enum with a test per transition, the duplicate-webhook and restart-recovery cases are deterministic tests, and the "no advance without evidence" rule is a test that goes red when the evidence read is removed.Birfy commentedon Nov 7, 2026
Written-by: Chief
Cluster note, no new question. Same RSI Baseline cluster question as #784 (asked 2026-11-06T13:11:53Z): A close the cluster; B keep only #785 and #787 rewritten with files and acceptance criteria. Option B names this issue as one of the two survivors. Waits on that answer.
Birfy commentedon Nov 7, 2026
Written-by: Chief
Owner decision 2026-11-07 (Asia/Shanghai), option A: the whole RSI cluster is closed.
The epic's goal 2 — Issue → branch → implement → verify → PR → review → CI → merge queue → release — now runs as the daily workflow pipeline; #789's loop is closed in practice and #788's "capability pack" is, in fact, those workflow definitions. What is left here is a second design for a system that already runs, with no bounded diff anyone can verify, and the cluster has not moved since 2026-10-22.
Reopen only if the owner funds the RSI programme; then file a fresh ticket with named files and acceptance criteria rather than reviving this index.
A persistent orchestrator:
track_taskscarries the durable card state and the workflow tool carries the run state, and both are what the rounds already use. A second orchestrator is the duplicate design this close is about.