* fix(git): don't delete a branch that still has open dependent PRs
Root cause of the run-zombifying "integration branch gone from origin" wedge.
_delete_remote_branch_best_effort deleted a merged PR's head branch
unconditionally, so:
- merging a cell->root PR deleted the cell branch while a sibling leaf PR was
still targeting it as base, and
- the CEO's root->master merge deleted the feature/main_pm/{root} integration
branch.
The dependent PRs lost their base, every later git op against the vanished
branch failed, and the task zombified (a51c3d31 only made the post-merge sync
non-fatal; this removes the cause).
The remote-branch delete chokepoint (the single path all merge/close/cancel
deletions funnel through) now first checks _branch_has_open_dependents: any OPEN
PR targeting the branch as its base marks it an active integration target and
preserves it. Fails safe (any error => keep the branch; cleanup is best-effort,
stranding is not). True leaf branches with no open dependents are still cleaned
up. Adds 6 unit tests for the guard + the probe.
* fix(git): recover a drifted shared clone on resume instead of BRANCH_MISMATCH
A dev/documenter/QA clone is shared across that agent's tasks. On a
respawn/resume it can sit on a sibling task's branch, or a re-provisioned clone
can lack the task branch as a local ref (commits only on origin). The
fresh-claim path git-resets the clone clean, but resume deliberately
short-circuits before it (_dev_reentry), so the agent's next commit hit
_assert_on_task_branch's BRANCH_MISMATCH, failed, and the task wedged in a
blocked respawn loop (the documenter that could never land its doc commit).
_assert_on_task_branch now recovers instead of only rejecting: fetch + checkout
the task branch (recreating a missing local ref from origin via `git branch
<b> origin/<b>`), and raise only when the switch genuinely can't happen
(uncommitted changes block it). Never discards work — checkout, not reset — so
a resumed agent's unpushed commits are preserved. Updates the RAG troubleshooting
+ developer docs to describe the auto-recovery. Adds 5 unit tests.
* fix(runtime): re-adopt running agent containers on restart (no double-spawn)
An orchestrator restart loses the in-memory _instances registry while the agent
containers keep running. The reaper already had a Docker-liveness fallback
(_assignee_container_running), but the spawn gate (_is_agent_active) did not, so
right after a restart it saw a live agent as inactive and could launch a second
container onto work the forgotten-but-running one was already doing.
start() now calls _readopt_running_agents() after _reconcile_orphan_claims_on_startup
and before the dispatcher/reaper loops launch: it probes each known agent slug's
container (AGENT_IMAGES, reusing _inspect_container_state — the same docker
inspect the reaper uses) and registers a minimal AgentInstance(state=ACTIVE) for
any that is running and not already tracked. Inert when nothing runs (cold start
unchanged); best-effort (a probe error leaves that slot for the reaper's own
fallback). This is the gateway-health spec's Task 4 / the orchestrator-state
spec's Phase 3 (_instances reconcile). Adds 4 unit tests.
* fix(git): treat an already-merged PR as idempotent success on merge
A merge PUT against an already-merged PR returns the same 405 as a genuine
"not mergeable" conflict, so _merge_with_retry raised MergeConflictError and the
completion path tried to rebase / close-superseded / escalate a PR that had
already landed (a prior cycle, a sibling, or the CEO merged it) — the
cell_pm_complete block<->unblock respawn loop.
_merge_with_retry now disambiguates before raising: a new _pr_is_merged probe
(GET the PR, check merged==true) returns success on an already-merged PR so
completion proceeds idempotently; a genuinely-unmerged 405 still raises the
conflict. Best-effort probe (False on any error → falls through to the existing
conflict handling). Adds 4 unit tests.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
* docs: sync prompts/RAG/CLAUDE + bump to 0.11.0 for the run-hardening wave
Documentation + version sweep for everything shipped since 889f3689 (the 0.11.0
wave: MegaTask + #249-#253 run-hardening). Closes the doc drift behind the live
incidents — agents had no branch-behind-master guidance, so a Main PM invented
a bogus "rebase subtask".
Agent guidance (the headline gap):
- main_pm / cell_pm / developer prompts: a task branch is made current at CLAIM;
there is NO rebase/pull/merge verb at the agent layer. Never create a "rebase
subtask" or improvise git surgery; escalate a behind-base branch
(developer: i_am_blocked; PM: escalate_up). "A rebase subtask is always a mistake."
- board prompt: Board has no unblock verb; a blocked task assigned to it is a
mis-assignment -> escalate_to_ceo immediately, never sit on it (respawn loop).
- developer prompt: the shared clone is git-reset on a fresh claim; push/open_pr
target the task branch by name regardless of the current checkout.
- RAG (git-errors, blocked-tools, pr-creation): branch-behind-base, "src refspec
does not match any", and non-fast-forward recovery -> escalate, don't improvise.
CLAUDE.md: 9 shipped behaviors synced (session-limit parking, one-active-work-
session + migration 047, push/PR-by-name + origin ref recovery, fresh-claim
workspace reset, Board never owns a coordination root, verb-runner per-action
INVALID_STATE re-check, note fire-and-forget RAG indexing,
ROBOCO_GATEWAY_HEALTH_ENABLED flag, learnings not broadcast to human roles).
Version 0.10.0 -> 0.11.0: pyproject, roboco/__init__, config.app_version +
agent-image-tag example, panel/package.json, uv.lock, README/deploy examples;
CHANGELOG [Unreleased] cut to [0.11.0] - 2026-06-24.
* docs(site): document session-limit parking + the branch-behind-base operator flow
User-facing docs site updates for the 0.11.0 wave (the run-hardening behaviors
that are operator-visible):
- models/resilience.md: the Claude session-limit (5-hour usage window) parks
and auto-revives like an overload, not just per-request 429s / 5xx overloads.
- troubleshooting/common-issues.md: same session-limit note on the parked-
provider entries; plus a new "task stuck on a branch behind its base" entry —
agents have no rebase verb so they escalate it; the operator rebases from the
panel Git tab (auto-rebase-at-spawn is the roadmap cure).
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
Markdown and editors soft-wrap on their own, so the manual ~75-char line
breaks across the docs added nothing but noise. Join wrapped prose, list
items, and paragraphs into single lines across 67 docs — README, CLAUDE.md,
deployment, usage, the RAG knowledge base, and the agent role prompts.
Whitespace-only: code fences, tables, and blockquote alerts are byte-identical
and the change is token-verified (no content altered). Applied with a
deterministic reflow tool (committed separately).
Also lands two doc edits that were awaiting commit: the measured under-load
resource numbers in usage.md and the pr_reviewer additions to the
org-structure RAG doc.
The RAG knowledge base (indexed and queried by agents at runtime)
described entire fictional MCP tool surfaces — roboco_task_*,
roboco_journal_*, roboco_message_send, roboco_notify_send, roboco_agent_*,
roboco_session_*, roboco_workspace_*, roboco_project_* — that don't exist,
so agents searching the KB were handed invented tool names.
Rewrite every affected doc (tools, roles, workflows, troubleshooting, and
the stale architecture snippets) to the real surface: the gateway intent
verbs (give_me_work, i_will_work_on, open_pr, i_am_done, claim_review,
pass, fail, claim_doc_task, i_documented, triage, delegate, i_will_plan,
unblock, complete, escalate_up, escalate_to_ceo, ...) and content tools
(commit, note(scope=...), say, dm, evidence, notify*, open_session,
channels). Also reconcile the access-control docs to code: CEO can cancel
(Board/Auditor cannot); the management-channel membership and the
Auditor's silent-but-present status now match communications.py.
