Operator report: with project policy "Ephemeral agent follow-up tasks = Deny",
an executing agent filed ten follow-up tasks — five parallel fn_task_create
calls it reported as timed out, then five sequential retries.
Two defects:
1. Deny was advisory. fn_task_create was registered for every session and only
refused inside execute(), so the model still saw the tool, planned around it,
and retried it. The pi extension's isEphemeralCallerAgent also failed OPEN
whenever the caller id did not resolve to an agent row — which is the normal
shape of an ephemeral task-worker — so on that lane Deny was a no-op.
2. The deterministic content-fingerprint duplicate window was 60s, which only
covered concurrent in-flight creates. A retry two minutes later saw nothing
and filed a second task.
Fixes: isAgentTaskCreateToolAvailable() withholds the tool from ephemeral
sessions under Deny in both engine lanes (outer execution session, per-step
workflow session); isEphemeralCallerAgent fails closed on an unresolvable
caller id; the fingerprint window goes 60s -> 10m (clamp ceiling 5m -> 1h).
upon_validation keeps the tool, and permanent-agent and human/chat callers are
unaffected.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Unusable-worktree recovery preserved task.worktree whenever the failing path
differed from it, treating the difference as proof the recorded worktree was
live. The reported strand had both gone: an AI-merge clean room refused as an
"incomplete worktree" while the task worktree had already been removed, so
every requeue re-dispatched into a missing directory ("Working directory does
not exist … Cannot execute bash commands") until the retry budget burned out
and the card parked failed in review. Preserve the recorded worktree only when
it is still a usable checkout; otherwise clear it so the next dispatch builds a
fresh one from the branch.
Also splits the planning-stage guard: only the DURABLE replan parks
(needs-replan, plan-review-unavailable) outrank sticky execution stamps.
"planning" is the transient planner claim, so a stamp landing on it still means
execution won the FN-8361 race.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Plan Review REVISE rebounds a card to a planner lane with status
needs-replan, but hasAdvancedPastPlanning read the sticky
firstExecutionAt/executionStartedAt stamps as proof the card had left
planning. Triage discovery filters on that guard, so a rebounded card was
never re-admitted and sat in triage/needs-replan forever ("stuck in
planning"). An explicit planning-stage status now outranks the stamps in
both planner lanes; a triage card stamped with no planning status is still
excluded so self-healing's advanced recovery keeps owning it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Re-pin the execSync allowlist after self-healing/executor line shifts, capture
implementation-session tools under the graph-owned pause harness, treat
worktree alone as not past planning for replan targets, and age starved-
refinement fixtures past the post-escalation cooldown window.
Planning sessions run in the task's own worktree with the coding tool
surface, but the spec path handed to the planner is relative
(.fusion/tasks/<id>/PROMPT.md) while finalization reads it against
rootDir. A planner using the generic write tool instead of
fn_task_prompt_write stranded the spec inside the worktree, where
finalization could not see it and worktree disposal destroyed it.
project.tasks also has no `prompt` column, so PROMPT.md was
filesystem-only and the project checkout was the sole durable copy of
every plan.
Add plan-artifact-writeback.ts:
- reconcileWorktreePlanArtifact copies a worktree-stranded PROMPT.md
back into the main project .fusion folder through
store.updateTask({ prompt }), keeping File Scope validation, the root
write, and the task.json sync atomic. Empty, absent, and identical
worktree copies are no-ops so a correct spec is never clobbered.
- mirrorPlanToProjectDb mirrors the authoritative plan into the `plan`
task document, which triage already reads as a planning-draft
fallback, making that recovery path DB-backed. Identical content is
skipped so revisions do not churn.
Both are best-effort: a failure never turns a good planning pass into an
error. Wired at the reconcile-before-finalize-read seam, at finalization
with the post-hygiene accepted content, and inside fn_task_prompt_write.
Covers the invariant rather than the repro: tests assert worktree-
stranded, root-only, empty worktree file, absent file, identical
content, persistence failure, redundant-mirror skip, and mirror failure.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
fn_task_promote can now pass force:true to start execution when a task is still
waiting on planning or plan review, matching the dashboard's promote override.
The rejection message names the flag so a caller that hits the gate can decide,
and a forced release says the pending replan was cancelled rather than burying it.
Force stays opt-in per explicit promote request: the hold-release sweep and the
webhook event release have no force parameter, so FN-7648 still holds for every
automatic surface.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The reclaim sweep's tip-already-merged arm vetoed on the branch tip's foreign
Fusion-Task-Id trailer alone. A task branch cut from the base that never
committed anything (planning aborted, card moved back to todo) points at the
PREVIOUS task's landed commit, so the veto fired on inherited metadata: the card
kept stale worktree/branch/baseCommitSha and re-logged
"already-merged rejected ... reason=foreign-task-tip" every sweep.
Hoist the merge-base diff proof already used by already-merged and
branch-misbound recovery into a shared foreignTipRejection helper and route all
three callers through it. Rejection still fires when the branch carries unique
content or the base already has this task's own commit.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Promote on a held card printed the raw i18n key `board.rejection.unplannedForExecution`:
FN-8471 added the server-side code without a client case or catalog entry, so
translateRejection fell through to `t(messageKey, messageKey)`.
- Add the explicit rejection case (both translate helpers) plus the en catalog
entry and secondary-locale stubs.
- promoteHeldTask(..., { force }) waives ONLY the unplanned-for-execution gate;
hold membership, capacity and slot reservation still arbitrate. It clears a
needs-replan/plan-review-unavailable status so triage rediscovery cannot pull
the card back into the waived replan, and emits task:promote-forced-unplanned.
- POST /tasks/:id/promote accepts { force: true }; the board asks for explicit
confirmation first and only offers the override for this rejection.
Force stays operator-only — the sweep, the webhook release and fn_task_promote
never set it, so FN-7648 still holds for every automatic surface.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Withdrawing a card from planning (todo -> Ideas) now stops the work:
- triage aborts and disposes the planning session through the same path
pause/delete already use, and clears status:"planning" so the planning badge
goes away and the card reads as a plain idea again;
- the executor aborts in-flight graph work on any backward move out of
todo/triage, so a Plan Review does not keep streaming against a card the
operator pulled back;
- moving it back to todo needs no new code: the existing column wake fires and,
with the status cleared, the card is an ordinary planning candidate again.
Pre-execution worktrees (planning acquires one now) are reclaimed two ways: an
immediate release on an explicit withdrawal, and a self-healing sweep
`reconcile-pre-execution-worktrees`. The sweep is deliberately timid — 30 days
of complete inactivity, and it skips anything active or waiting (todo,
executing, in-review, done, paused, carrying any status, blocked, or scheduled
for recovery). Every real safety condition lives in the executor: never
executed, no live session, clean branch, nothing uncommitted.
hasAdvancedPastPlanning no longer reads a worktree as execution evidence.
Planning owns a worktree now, so that signal would have made every planning
write skip; execution timestamps carry the meaning instead.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Contention prevention (why tasks shared a path at all):
- Planning ran `tools: "coding"` at the repo root, so every planner had write
tools in the operator's checkout and all planners shared one path. Planning
now acquires the task's own worktree (TriageProcessor.acquirePlanningWorktree
-> TaskExecutor.ensureTaskWorktreeForPlanning).
- Graph nodes with no worktree acquired one instead of falling back to rootDir,
so Plan Review / Code Review / custom gates all run isolated. Plan Review
re-acquires when its recorded worktree is gone, replacing FN-7996's
run-from-the-repo-root degrade. Workspace projects are unchanged.
- Registration goes through acquireActiveSessionPath, which reclaims a leaked
entry whose holder is provably dead and aged past the FN-5256 floor. A live
holder still contends — real serialization is never clobbered.
Classification (the reported symptom):
- A lease held by another task is no longer a provider failure. It carries
SESSION_CONTENTION_HOLD_VALUE, classifies transient, is excluded from
isNonPlanDefectPlanReviewFailure, and stops burning the node's fast retries.
- The executor waits it out on a 10-attempt 5s->60s ladder and then leaves the
task cleanly queued. There is no terminal branch: contention always ends, so
parking would only ask a human to press Retry on a condition that fixed
itself.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Plan Review needs no worktree, so it runs rooted at the project root. The
activeSessionRegistry key was the bare root path, so the second task to reach
Plan Review hit ActiveSessionPathHeldByForeignTaskError ("path ... is held by
task FN-1398; task FN-1403 may not overwrite it"). That surfaced as a Plan
Review provider failure, burned the in-place retry budget against a hold no
retry could clear, and left the task parked.
Task-scope the registry key for any session rooted at rootDir, in every project
mode — the workspace fix already did this for the shared browse-root. Root
exclusivity protects nothing here: write-capable nodes are refused at the root
outright, and every isPathActive consumer guards removable worktree paths.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Quick-add "Start" collapses create+promote into one request: it submits the
workflow id AND the post-intake `todo` column together, so the card lands in
`todo` having never sat in the workflow's manual intake column. The intake test
in task-creation.ts only matched `triage` or the resolved intake column, so the
card got generateSpecifiedPrompt — whose hard-coded boilerplate steps
("Implement the required changes") no planner ever wrote.
That stranded the card permanently: triage's todo-discovery admits a card only
when its PROMPT.md reads as a seed, so the placeholder spec was classified
"already planned" and never planned, while nothing could execute it either
(steps: []). It sat in Todo forever with no log line in any lane. Observed on
FN-8587.
Creates into `todo` on a manual-intake workflow (resolved intake is not the
legacy `triage`) now get the bootstrap seed. The pinned contract for a plain
direct create into todo on the default workflow — which intentionally keeps
generateSpecifiedPrompt — is untouched, and both create sites are fixed in step.
Also instrument the hold/release sweep, which had reasons but no timings:
per-task held duration reported on release, a per-sweep summary breaking out the
prefetch cost (a sequential await per non-archived task, so it scales with board
size rather than with held cards), and a warn when a sweep exceeds 2s — so a
"ready card doesn't move" delay can be attributed between poll cadence, sweep
cost, and a card genuinely queued on capacity.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Closes the second half of the "started card does nothing" gap. Plan-in-place
workflows (Coding (Ideas)) finalize by clearing `status` in place — finalize
deliberately skips the triage->todo move — so a card that just became executable
emits only a bare task:updated. None of the scheduler's existing event wakes
(task:created, globalPause/enginePaused unpause, per-task unpause) fire for that
transition, so the operator paid one poll interval for planning to start and
another for execution to start.
Track ids seen with status "planning" and trigger a scheduling pass when they
return to a dispatchable state, mirroring the pausedTaskIds unpause tracker.
Guarded on !status, not paused/userPaused, and a schedulable column, so a
planning -> failed/awaiting-approval park does not trigger a pointless pass.
schedule()'s re-entrance guard drops the call if a pass is already in flight,
and the id is cleared on task:deleted alongside the other per-task sets.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Pressing Start on a Coding (Ideas) card only writes a column move — there is no
dispatch call in that path — so planning did not begin until the triage
processor's next timer tick, up to pollIntervalMs (15s default) later. The
"Started planning" toast was optimistic and the card just sat in Todo.
- Wake planning discovery on the store's task:updated/task:created event when a
task lands in todo/triage. Binding the wake to the store event rather than the
Start button covers every move surface (board drag, context menu, task detail,
List view, CLI, agent tools, POST /tasks/:id/move) by construction. The wake is
advisory: it only advances WHEN the poll runs, so every pause, seed-prompt,
dependency, and concurrency gate still applies.
- Admit a todo task whose PROMPT.md is missing instead of dropping it through a
silent `catch {}`. The scheduler KEEPS a candidate whose prompt it cannot read,
so such a card was invisible to planning while still visible to dispatch, with
no log line in either lane. Unreadable (non-ENOENT) prompts now log.
- Route the scheduler's dispatch filter through the shared isUnplannedSeedPrompt
predicate. Its open-coded strict bootstrap compare disagreed with triage on the
refinement-seed shape, leaving hold-release as the only thing between an
executor and a prompt containing just the operator's feedback text. The
predicate also normalizes line endings/trailing whitespace, so a CRLF or
trailing-newline round-trip no longer reclassifies an unplanned card as planned.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Global settings live in settings.json under the resolved global dir, which
falls back to the pre-rename ~/.pi/fusion and ~/.pi/kb dirs for installs that
never migrated. The reader hardcoded ~/.fusion, so on those installs the
operator's preference was silently ignored and resolution fell back to raw-key
precedence -- the same silent fallback the preference exists to remove.
Mirror the legacy-aware lookup getModelRegistryModelsPath already does for
models.json rather than importing core's resolver, which throws under VITEST
when called without an explicit dir.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Audit of the class behind the planning bug: createFnAgent forwards no model
unless both defaultProvider and defaultModelId are set, after which
pi-coding-agent picks its own built-in default (anthropic/claude-opus-4-8).
Seven lanes resolved no pair at all, so they hit that path on every call --
a permanent 401 invalid x-api-key for custom-provider and subscription
operators, and a hole in test-mode forcing:
- milestone/slice interviews (no model plumbing at all)
- subtask breakdown, triage and streaming paths
- agent generation
- text refine and goal drafting
- agent reflection (optional ctor pair no production caller supplies)
Two more resolved the halves independently, which the runtime treats as
unset: research synthesis defaults and pr-conflict-resolver's hand-rolled
copy of resolveProjectDefaultModel (which also skipped test-mode overrides).
Add lane-session-model.ts as the shared resolver and a source ratchet that
fails when a dashboard session is constructed from an inline literal with no
model decision.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
An operator can hold a raw Anthropic API key and a Claude subscription OAuth
login at once, and the raw key always won silently. A stale or revoked saved
key therefore shadowed a working subscription and failed every direct Anthropic
call with 401 invalid x-api-key, while both Settings cards still read Active.
Add the global anthropicAuthPreference setting ("api-key" default, preserving
the historical precedence, or "subscription"), read in resolveAnthropicRuntimeApiKey
straight from ~/.fusion/settings.json so it applies without a restart and needs
no settings plumbing through createFusionAuthStorage. Neither value removes a
source: with one credential configured, resolution reaches it either way.
Settings -> Authentication now names the credential in use on the two Anthropic
cards and renders the control, but only when both are actually connected.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The proactive status narration printed the internal 0-based step index, so the
final step of a 13-step task announced "Starting Step 12" next to a card
showing "12/13". Display now uses index + 1 in both the engine builders and
the store-side updateStep narration; the 0-based tool/PROMPT.md contract is
unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Binary Release (v0.73.0-beta.5 was fully red):
- bun compile: mark chromium-bidi external — playwright-core@1.60 (feature-video)
optionally requires it and bun fails closed on unresolvable requires.
- Windows desktop EXE: quote -c.publish.channel=beta in release.yml; PowerShell
tokenizes the bare flag into `-c` + a path and electron-builder ENOENTs on it.
Full suite (all 4 shards red from stale-test drift, no product bugs found):
- engine: align mock stores/assertions with atomic store.moveTaskIf dispatch
(#2371), the fail-closed non-empty PROMPT.md artifact gate (#2390), oldest-
first admission (FN-8453), alreadyClaimed graph routing (#2393), startStep
step projection (#2403/FN-8464), structured retry presentation (FN-8503),
provider-lane pause reasons (#2339), typed column-boundary entry (#2378),
Type.Integer in CAS document schemas (#2375), bounded model-registry refresh.
- engine-no-blocking-shellout: re-pin 17 drifted allowlist line numbers and drop
the stale REBASE_HEAD entry whose execSync was removed.
- core: schema-applier expectations track migrations 0033-0035 (96 tables) and
the synthetic 0000 fixture gains workflow_work_items/mission_contract_assertions;
work-item terminal state is "succeeded" post-#2378.
Known follow-up (not addressed here): self-healing starved-refinement escalation
bumps task.priority, which FN-8453 oldest-first admission no longer consults.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Align MissionAutopilot expectations with autonomy-audit attribution: updateMission
carries the system actor options, and autopilot_disabled is recorded on the
mutation instead of a separate logMissionEvent mirror.
- usage-limit-detector + provider-health-monitor: make three bare listTasks()
callers explicit with { slim: true }, restoring the architecture-hot-paths
contract (they only read scalar pause/column/model-provider fields).
- pg-test-harness beforeEach: wipe <rootDir>/.fusion/tasks after TRUNCATE ...
RESTART IDENTITY so filesystem isolation matches the id reset; stale task
dirs from prior tests no longer collide with reused IDs (fixes
store-reservation-atomicity rollback assertions).
## Problem
With `pushAfterMerge` enabled (and `mergeStrategy` other than
`pull-request`), if `origin/<integration-branch>` advances externally
between the local squash-merge and the push, the divergence path opens a
clean-room `git pull --rebase` and an AI agent resolves and stages the
conflicts — but the flow could end there: no `git rebase --continue`, no
push, and no surfaced error.
Because finalize runs *before* the push, the task is already `done`, so
a reviewed, approved merge is silently left container-only, and every
subsequent merge on the project stalls the same way. Separately, an
abort mid-push (`MergeAbortedError`) was swallowed with only a
process-log warning — no task-log entry, no run-audit event.
## Change
- **Deterministic regression coverage** for the conflicting-divergence
path (real-git fixture) proving the rebase runs to completion and the
push lands (refs converge), plus abort/termination scenarios.
- **Recovery-branch safety net:** before the clean-room rebase starts,
the pre-rebase local squash is force-pushed to a per-task remote branch
`fusion/<task-id>-stranded`, so approved content is never container-only
— even across process death or abort. Deleted after a successful target
push; retained on failure/abort as the recovery source.
- **Never-silent outcomes:** every non-pushed outcome (failure or abort)
writes a durable task-log entry and a `push:origin` run-audit event. The
audit contract now documents `push:origin` as polymorphic (dashboard
Smart Push vs. automated post-merge push) and enumerates the automated
path's outcomes, including the new `"aborted"` shutdown case.
- **Cleanup hardening:** `isRebaseInProgress` now probes Git's
worktree-specific `rebase-merge`/`rebase-apply` state directories
(async, timeout-guarded) so a completed rebase can't receive a spurious
second `--continue`; unfinished rebases are cleaned up.
Out of scope by design: withholding the "merge confirmed" state until
the push succeeds — the `FNXC:MergePush` invariant ("a push problem can
never park or roll back a landed merge") is deliberate; the recovery
branch + surfacing satisfy the data-preservation intent without breaking
it.
## Files
`packages/engine/src/merger-ai.ts`, `packages/engine/src/merger.ts`,
`packages/engine/src/run-audit.ts`, new/updated tests under
`packages/engine/src/__tests__/`, `docs/settings-reference.md`,
`docs/dashboard-guide.md`, `AGENTS.md`, and a labeled changeset.
## Validation
`tsc --noEmit` clean; engine divergence + merger suites pass (41 tests);
rebased onto current `main` with no conflicts.
---
_Developed with Claude Code, under human supervision and review._
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Prevented approved post-merge pushes from becoming stranded when the
remote diverges by using a recovery-branch workflow and safer cleanup.
* Improved behavior and reporting when pushes are aborted or fail after
merge, including clearer non-fatal status and audit outcomes.
* **Documentation**
* Expanded push-after-merge and dashboard Smart Push documentation with
recovery-branch and `push:origin`/`push:recovery-branch` outcome
semantics.
* **Tests**
* Added end-to-end regression tests for divergent/conflicting AI
push-after-merge flows, including abort and worktree cleanup
verification.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Victor Cano <victortroz@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Render complete mission hierarchy details from the fn_mission_show agent tool.
- Format mission, linked-goal, milestone, slice, and feature metadata with IDs and statuses
- Link features to their tasks and bound verbose acceptance and verification text
- Cover populated and empty hierarchy responses with regression tests
- Add a patch changeset for the agent lookup fix
Files changed:
.changeset/fn-8540-mission-show-hierarchy.md | 7 ++
.../src/__tests__/agent-mission-tools.test.ts | 68 +++++++++++++++++++
packages/engine/src/agent-tools.ts | 77 +++++++++++++++++++++-
3 files changed, 150 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-8540
Fusion-Task-Lineage: f2282226-3f4e-4d9f-bd8e-d18ad9639c03
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Port the planning turn-admission invariant (FNXC:PlanningTurnAdmission,
2026-07-22) into the Compound Engineering orchestrator: at most one turn
(opening/answer/resume-rehydration) is admitted per CE session, reserved
synchronously and held until the turn settles — a re-entered mobile view
re-submitting a turn now gets CeTurnInProgressError (HTTP 409) instead of
displacing the in-flight turn's live agent, which surfaced as "Failed to
parse agent response: AI returned no valid JSON". cancel()/discard()
force-clear the reservation; releases are token-scoped so a stale release
can't drop a newer turn's slot.
In the engine interactive-ai-session seam: bump the reformat retry from
one to two attempts (non-Anthropic default models comply less reliably
with the JSON-only protocol), and log every failed parse with a bounded
raw-response snippet plus resolved provider/model — including a distinct
empty-assistant-message marker — so support can diagnose these reports
without a repro.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Code-review follow-up on 4413699de. Deleting an orphaned pending review
entry was a severity inversion: the merge gate blocks on pending/failed
results, not on an enabled step with NO result, so deletion silently
satisfied the gate and the task merged with its review skipped (verified
live: FN-8492 landed on main without Code Review re-running). Orphans are
now rewritten to status:"failed" — the gate stays closed and the
failed-pre-merge-steps recovery / FN-7720 operator-bypass paths own the
re-run decision.
Also from review: the sweep now runs in periodic maintenance too (a step
session can die without a restart), skips executor-owned in-progress rows
(resume is deferred ~30s at startup, so their liveness is unprovable when
startup recovery runs), re-reads the row immediately before the write so
the whole-array update cannot clobber a fresh lease, counts recovery on
the successful mutation rather than after the audit emit, and the new
audit event literal is registered in DatabaseMutationType (cast dropped).
Tests now cover all three liveness-triple legs, >500-row pagination,
in-progress skip, per-task write-failure isolation, and the never-delete
invariant; the needs-replan adoption row moved under a preserve-group
header.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
An engine restart that kills an in-flight pre-merge step session (FN-8492's
Code Review) left its pending workflowStepResult behind with no live session.
The merge gate read it as incomplete pre-merge steps, surfaced an identical
stall every 30 minutes, and the deadlock disposer parked the task failed two
hours later. resolveOrphanedPendingStepResults existed for exactly this but
shipped with no caller (same U9 gap as the adoption table).
Wire it: a startup sweep right after legacy adoption clears pending results
whose task has no live session (activeSessionRegistry / executingTaskLock /
isTaskActive), emitting task:reconcile-orphaned-pending-step-results with
ids/counts-only metadata. User pauses and live resumed sessions are never
disturbed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Instead of dropping a fallback-only grok-cli pair when no GROK_API_KEY is
Fusion-visible, defer it: the session runs the configured primary, and on
the first retryable model-selection failure it creates a session on the
Grok CLI runtime with the fallback model and re-issues the failed prompt
there; later prompts stay on the swapped session. Engagement reports
through onFallbackModelUsed and an ids-only
session:grok-cli-fallback-engaged run-audit event. The pair is dropped
(with audit flag) only when the Grok runtime plugin is unavailable.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A configured grok-cli fallback with no Fusion-visible GROK_API_KEY was
promoted to primary at session start (FN-7758 seam), so every planning
session silently ran grok-4.5 instead of the configured planning model.
The no-visible-key Grok CLI auto-route now fires only for a grok-cli
primary; a fallback-only grok-cli pair is dropped with a warning and an
audited grokCliFallbackDropped flag, and session:runtime-resolved now
records the post-transform model pair the session actually runs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
## Summary
- Fix a false-positive in `StuckTaskDetector` where legitimate long
single-step work (E2E debugging, iterative fix/test cycles) was
classified as a loop and kill/requeued.
- Root cause: loop meant “no step status transition for
`taskStuckTimeoutMs` + high activity volume,” conflating **step
progress** with **actual activity**. Agents can stay productively busy
on one step for 10+ minutes with zero repetition.
- Loop now requires thrash evidence on top of volume + no step progress:
- **repetitive tool fingerprints** (`toolName` + primary-arg detail in a
sliding window), or
- **elevated ignored step-update rebuffs** (≥ 10)
- Wire tool name/detail from `AgentLogger` → executor / step-session
into `recordActivity(...)` so novelty is measurable.
- Document the thrash-evidence rule in `docs/architecture.md`.
## Test plan
- [x] `pnpm --filter @fusion/engine exec vitest run
src/__tests__/stuck-task-detector.test.ts
src/__tests__/reliability-interactions/non-progress-churn.test.ts`
- [x] Regression: high-volume **diverse** iterative activity (174
events) does **not** classify as loop
- [x] High bare text/heartbeat volume without tools does **not**
classify as loop
- [x] Repetitive identical tool fingerprint + timeout **does** classify
as loop
- [x] Ignored step-update thrash (≥10) with volume **does** classify as
loop
- [x] Existing FN-5168 no-progress-churn + FN-6598 verification
suppression paths still pass
- [ ] CI gate green
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Improved stuck/loop classification by requiring explicit “thrash
evidence” (repetitive tool fingerprints and/or elevated ignored progress
rebuffs), reducing false positives for busy but diverse work.
* Updated loop evidence tracking to incorporate tool name plus
summarized tool-argument detail.
* Cleared loop evidence appropriately after verification, progress
updates, and task resumption.
* Extended tool-start telemetry/callbacks to include optional tool
detail.
* **Documentation**
* Refined loop-classification criteria to match the new evidence gates.
* **Tests**
* Updated/expanded stuck/loop and churn scenarios to validate the
evidence-based behavior and callback ordering.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Summary
Chat-driven `fn_task_create` rejected freeform intake with `Approved
mission_lineage is required` even though the tool schema marks
`mission_lineage` as optional. That was FN-8307 mission admission
over-applied beyond autonomous heartbeat patrol.
This restores freeform chat/board-equivalent creates while keeping
idle-heartbeat mission-lineage enforcement.
## What changed
- **`fn_task_create` / `fn_delegate_task`**: omit `mission_lineage`
succeeds for user-directed surfaces; hard-require only when the tool is
registered with `requireMissionLineage` (idle heartbeat patrol).
- **Gates**: missing lineage is policy-governed (`allow` /
`require-approval` / `block`) instead of a hard pre-block, so
permanent-agent chat can create freeform tasks under normal policy.
- **Heartbeat no-task delegate**: also sets `requireMissionLineage:
true` so freeform off-mission work cannot bypass admission via
`fn_delegate_task`.
- Supplied lineage is still fully validated (Feature → Slice → Milestone
→ Mission) on every surface.
- Parent inheritance still applies when not in require mode.
## Test plan
- [x] Unit: freeform `fn_task_create` without lineage creates a task
with no `missionId`/`sliceId`
- [x] Unit: freeform `fn_delegate_task` without lineage succeeds
- [x] Unit: `requireMissionLineage: true` still hard-fails without
lineage
- [x] Unit: gates treat missing lineage as policy disposition, not hard
block
- [ ] CI gate green
## Symptom
**Original:** chat tool call `{ description: "Create a red button",
priority: "high" }` → `ERROR: Approved mission_lineage is required; no
task was created.`
**Expected after fix:** task is created freeform without mission fields.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **Bug Fixes**
- Freeform chat task creation and delegation can now proceed without
`mission_lineage`.
- Permission policies continue to govern these actions, including
approval requirements.
- Autonomous idle patrols still require approved mission lineage before
creating or delegating tasks.
- Task creation no longer receives mission-specific metadata when no
lineage is provided.
- **Tests**
- Expanded coverage for freeform and mission-linked task creation,
delegation, and policy-gating scenarios.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Summary
Ordered task steps can no longer appear active ahead of unfinished
predecessors. Step starts now use the same dependency-aware ordering
guard as completions, while steps explicitly declared independent remain
parallelizable. Rejected executor updates explain that the lifecycle
transition was suppressed instead of implying completed work was
overwritten.
## Validation
- Reproduced the FN-8490 concurrent update sequence and verified later
steps remain pending.
- Passed 15 PostgreSQL step-order tests, the focused executor response
test, core and engine typechecks, changeset validation, and `pnpm
verify:fast` including boot smoke.
- The full `executor-prompt.test.ts` run retains five pause-behavior
expectation failures that reproduce unchanged on `origin/main`.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Enhanced the step start hook to support an awaited “pre-start
projection” that can reject startup via `false` (sync or async),
preventing step-session creation/completion.
* Added a step-start “verdict” so steps can be started or blocked
deterministically (including “resumed” behavior).
* **Bug Fixes**
* Prevented ordered/dependency steps from transitioning out-of-order by
enforcing guards for both in-progress and done transitions, including
concurrent update attempts.
* Improved integrity/out-of-order warning behavior and suppression
details when persisted status doesn’t match expectations.
* **Tests**
* Added/updated PostgreSQL and engine regression coverage for
blocked/resumed start and start-rejection control flow.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Summary
Project workflow model lanes now apply to tasks on every workflow
instead of only tasks using the active default workflow. Model selection
consistently resolves task-specific choice -> project workflow baseline
-> global lane -> selected-workflow value -> project/global default for
primary models, fallback models, and thinking levels.
The active default workflow remains the storage owner for backward
compatibility, while runtime resolution keeps its project baseline
distinct from lower-priority selected-workflow values. Non-model
workflow policies remain isolated to their selected workflow.
## Validation
- Core workflow/model resolution: 60 tests passed
- Engine effective settings and session resolution: 59 tests passed
- Reviewer: 85 tests passed
- Scheduler: 154 tests passed
- Heartbeat: 90 tests passed
- Settings UI: 67 tests passed
- Workspace lint and core/engine/dashboard typechecks passed
- `pnpm verify:fast` passed workspace builds, the published CLI build,
and real `/api/health` boot smoke
---
[](https://github.com/EveryInc/compound-engineering-plugin)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added **Project workflow model lanes** to establish a project baseline
for model selection and thinking levels across workflows.
* Updated model/fallback resolution to account for task overrides,
project baselines, global lanes, and selected-workflow values.
* **Bug Fixes**
* Improved effective settings merging so project baselines are applied
correctly (including scheduled/idle and heartbeat flows) while
preserving selected-workflow provenance.
* **Documentation**
* Refreshed settings and dashboard guidance for workflow lane
inheritance and resolution precedence.
* **Tests**
* Expanded unit test coverage for lane precedence, fallback detection,
and thinking-level behavior.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Summary
Re-lands the completed Fusion board task FX-005 on current upstream
`main`, stacked on #2374 (FX-004).
- adds a narrowly authorized additive publication path for archived task
documents
- preserves archived task and mission state and keeps ordinary
replacement/deletion writes rejected
- exposes retained archived current/revision reads
- requires project-scoped revision/hash CAS for publication
- maps malformed, unauthorized, missing, inconsistent, and stale states
safely
- rebases preserved dashboard drafts explicitly after CAS conflicts
## Why
Operators need to append a correction or evidence revision to an
archived task without unarchiving it or weakening ordinary archived-task
immutability.
## Dependency
This branch contains #2374 plus the eight FX-005 commits because
cross-fork PRs cannot target a fork-only base branch. After #2374 lands,
this PR should be rebased or refreshed so its diff collapses to FX-005
only.
## Validation
- PostgreSQL task-store and archived-default suites: 33/33
- dashboard route and editor suites: 321/321
- agent document tools: 22/22
- core, dashboard, and engine typechecks pass
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added optimistic concurrency controls for task document creation and
editing using revisions and content hashes.
* Added safe, authenticated append-only corrections for documents
retained on archived tasks.
* Archived documents and revision history remain available for direct
reading.
* Agent and dashboard tools now report conflicts clearly and support
explicit draft rebasing.
* **Bug Fixes**
* Prevented stale updates from overwriting newer document content.
* Preserved archived-task immutability while allowing controlled
corrections.
* **Documentation**
* Updated CLI, dashboard, storage, task-management, and agent guidance
for these workflows.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: fusion-merge-train <merge-train@topkoli.local>
Co-authored-by: Fusion <noreply@runfusion.ai>
Co-authored-by: v <v@v.speedport.ip>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
