Handle logEntry failures after in-place parking without falling back to executor requeue and tighten the reliability assertion for STUCK_LOOP_EXHAUSTED.
Preserve incomplete task progress after stuck-kill budget exhaustion while marking the task failed and paused for manual intervention instead of making it scheduler-runnable again.
Refresh stored Claude OAuth credentials before reporting dashboard auth status or resolving model auth so users do not need to repeatedly re-login after access-token expiry.
Coalesce concurrent refresh attempts, prevent stale refreshes from overwriting newer logins, and route CLI dashboard/serve/daemon/onboard auth wiring through the shared refresh-capable storage.
Correct scheduler dispatch diagnostics so capacity decisions use consistent non-negative slot counts.
- Clamp excess semaphore releases at zero and warn once when a slot is returned without an active holder.
- Recompute dispatch capacity at each queue decision, including tasks started earlier in the same scheduler tick.
- Update scheduler and semaphore tests for true binding gates, non-negative diagnostics, and workflow-step env stability.
- Add a patch changeset for the scheduler capacity fix.
Files changed:
.changeset/fn-6423-scheduler-capacity.md | 5 +
packages/engine/src/__tests__/concurrency.test.ts | 32 ++++++
.../src/__tests__/executor-step-session.test.ts | 10 +-
packages/engine/src/__tests__/scheduler.test.ts | 122 ++++++++++++++++++++-
packages/engine/src/concurrency.ts | 29 ++++-
packages/engine/src/scheduler.ts | 117 ++++++++++----------
6 files changed, 248 insertions(+), 67 deletions(-)
Fusion-Task-Id: FN-6423
Fusion-Task-Lineage: a6b2e668-a822-46e9-9cd8-ac267fbde804
Update the non-progress churn reliability test to match the Move-Task contract for never-user-paused tasks.
- Treat undefined userPaused as not user-paused instead of requiring false.
- Document why engine rebounds should not write userPaused for never-user-paused tasks.
Files changed:
.../src/__tests__/reliability-interactions/non-progress-churn.test.ts | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
Fusion-Task-Id: FN-6394
Fusion-Task-Lineage: 59554c89-4e32-490f-88eb-d22ee7fdca31
Workflow context-limit recovery prompts now direct agents to read task attachments from the project root.
- Pass the project root into reduced workflow step prompts so attachment directories can be absolute when available.
- Replace the autonomous-agent "ask for context" wording with direct file-reading guidance for attachments.
- Cover root-aware, fallback, placement, and context-limit recovery attachment prompt behavior.
- Add a patch changeset for the published Fusion package.
Files changed:
.../fn-6375-workflow-attachment-recovery-prompt.md | 5 ++
.../src/__tests__/step-session-executor.test.ts | 70 +++++++++++++++++++---
packages/engine/src/step-session-executor.ts | 8 ++-
3 files changed, 72 insertions(+), 11 deletions(-)
Fusion-Task-Id: FN-6375
Fusion-Task-Lineage: ed9a5367-1623-49cb-9c7f-116c59ce5117
Resolves the onLoad conflict in the compound-engineering plugin by keeping both
the bundled ce-* persona-def install (this branch) and main's
recoverStaleSessionsForContext call.
Also addresses PR #1672 review feedback:
- executor: sentinel resume now guards on !live.paused (mirrors
runAwaitInputNode) so a still-paused task can't consume a reply and re-enter
the skill early.
- TaskCard: make the Answer-questions button text/title/aria-label fallbacks
consistent ("Answer questions") for label-in-name a11y; update test.
- ce-work: replace the unshipped `skill: ce-worktree` reference with the real
git worktree commands so Option B can't dead-end.
- ce-resolve-pr-feedback: invoke bundled scripts by absolute path via the new
FUSION_CE_SKILLS_DIR env (sessions run with cwd=projectRoot); add the Fusion
await-input sentinel path instead of AskUserQuestion for workflow steps;
normalize whitespace-only review bodies like PR comments.
- plugin: expose FUSION_CE_SKILLS_DIR (installed skills root) to step sessions.
- plan doc: add language to fenced block (markdownlint MD040).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
main's workflow-graph-executor now collapses the merge-policy region
(merge-gate, branch-group-*, merge-attempt) into a single synthetic
`merge` node. Reconcile the S05 work-item-driver test's visitedNodeIds
assertion to match, and union the `observed` recording-primitive fields
from both branches (executedTasks + merge attempt/run/workflow ids).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
When a skill in a graph workflow step emits ===FUSION_AWAIT_INPUT===,
runGraphCustomNode now parks the task awaiting-user-input with the
question (reusing the runAwaitInputNode pause/watermark model so the
dashboard input banner + task-card button surface it), and halts the
walk. On resume the node re-runs; the resume check consumes the user's
steering reply and lets the skill continue with the answer.
Pure sentinel parser unit-tested (6 cases). End-to-end pause/resume
through the graph interpreter needs verification on a running board.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Keep triage planning from advancing or continuing work after a task is paused.
- Abort active triage sessions and reviewer subagents when task updates mark the task paused.
- Skip approved-spec recovery and final approved-spec transitions while a task remains paused.
- Add regression coverage for paused planning, pause-driven aborts, and published package changeset metadata.
Files changed:
.changeset/pause-triage-planning.md | 5 +
.../src/__tests__/triage-pause-abort.test.ts | 237 +++++++++++++++++++++
packages/engine/src/triage.ts | 57 +++++
3 files changed, 299 insertions(+)
Fusion-Task-Id: FN-6361
Fusion-Task-Lineage: 33d849d5-1461-49ae-9fe0-be98b534ac35
Add an optional systemPromptOverride to spawnAgentParams. When non-empty,
the spawned child runs under that persona system prompt instead of the
generic child base prompt (executor instructions still appended), so a
caller can spawn a specific persona — the primitive the compound-
engineering reviewer/research fan-out needs.
Two spikes confirmed the need: fn_spawn_agent had no persona param, and
Fusion has no plugin agent-contribution channel — so the lightweight path
is a generic override here + plugin-local persona defs the skill reads and
passes inline (revised KTD-4/U2/U3 in the plan). Behavioral coverage lands
with U10.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
U1: workflow-step sessions now carry FUSION_WORKFLOW_STEP=1 (scoped to
the step session, not the main executor) so skills detect autonomous
context and surface questions via await-input instead of a dead blocking
tool.
U8: bundle ce-commit, ce-commit-push-pr, and ce-resolve-pr-feedback
(vendored from compound-engineering 3.9.4) so the CE merge/PR flow has
its skills. Registered in COMPOUND_ENGINEERING_SKILLS; manifest test
updated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Stabilize the cli-agent re-entry regression test by awaiting the original run after the replacement session succeeds.
- Keep the first cli-agent run promise instead of dropping it with void.
- Assert the active task session still points at the first PTY before simulating re-entry.
- Kill and await the first session at the end so no hub or store work outlives teardown.
Files changed:
packages/engine/src/__tests__/cli-agent-executor.test.ts | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
Fusion-Task-Id: FN-6341
Fusion-Task-Lineage: 3e365f21-0d05-496a-adec-aa782aa83503
Reconcile the FN-352 no-commit coordination guard skip with main's
independently-landed FN-424 work. Both branches added a no_commits
guard bypass at the same fn_task_done call site:
- FN-352 (this branch): getNoCommitEligibilityReason(task) covering
Review Level 1 coordination prompts with board-only scope and
explicit no-source intent (e.g. "Do not change product source").
- FN-424 (main): evaluatePromptDerivedNoCommitEligibility(...) plus
non-blocking audit logging of the skip.
Their prompt phrase-matching differs, so neither alone satisfies the
merged test file. Resolved by OR-ing both eligibility checks and
wrapping the skip in main's audit-logging block. Both helpers still
refuse the contradictory implementation+coordination prompt.
All 18 executor-task-done-invariant tests pass; engine typecheck clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Self-healing now resumes stranded assigned in-progress work when an agent has no active run or execution.
- Add a self-healing pass that groups stale assigned in-progress tasks by durable agent and calls the executor resume seam without moving tasks backward.
- Emit run-audit telemetry for reattached orphaned executions and wire the resume hook through the in-process runtime.
- Cover grace windows, pause/active-run/active-execution guards, task filtering, and registration order with engine tests.
- Document the recovery behavior and add a patch changeset for the published CLI package.
Files changed:
.changeset/fn-6336-reattach-orphaned-executions.md | 5 +
docs/agents.md | 2 +
docs/architecture.md | 2 +
...lf-healing-reattach-orphaned-executions.test.ts | 217 +++++++++++++++++++++
packages/engine/src/run-audit.ts | 1 +
packages/engine/src/runtimes/in-process-runtime.ts | 1 +
packages/engine/src/self-healing.ts | 122 ++++++++++++
7 files changed, 350 insertions(+)
Fusion-Task-Id: FN-6336
Fusion-Task-Lineage: 6d8519b9-d8b0-4726-9b45-bfa445b7883e
Resolve conflicts from main's FN-6232 single-source triage prompt refactor:
- Drop the inline FAST_TRIAGE_SYSTEM_PROMPT const removed by main; the fast
triage prompt now lives in agent-prompts.ts (planning-fast seam).
- Migrate the PR's no-commit/operational-routing heuristic edits into the
fast block of agent-prompts.ts (standard block already carried them).
- Point triage tests at FAST_PLANNING_PROMPT/TRIAGE_POLICY_PROMPT instead of
the removed const.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Quarantine unrelated engine test flakes so the gate avoids known unstable fixtures.
- Add the soft-delete blocker residue reliability test to the quarantine ledger and reliability interaction exclusions.
- Add the bubblewrap sandbox backend test to the quarantine ledger and engine-core exclusions.
Files changed:
packages/engine/vitest.config.ts | 6 +++++-
scripts/lib/test-quarantine.json | 10 ++++++++++
2 files changed, 15 insertions(+), 1 deletion(-)
Fusion-Task-Id: FN-6319
Fusion-Task-Lineage: 9a47ae20-76b8-47d8-8858-f4fe51ea807e
