Plugin-contributed skills previously registered only a name for sessions and the dashboard, so their SKILL.md bodies were never actually loaded — fix threads real body paths through to both session creation and the Skills UI.
- Resolve each enabled plugin skill's body path via @fusion/core's resolvePluginSkillBodyPath and thread its body dir (plus parent dir) into every session-creating lane (executor primary/retry/verification-fix/step/child-agent, triage, reviewer, merger, agent-heartbeat, cron-runner) as additionalSkillPaths, unioned with existing CE skill dirs.
- Add collectPluginSkillNames/mergePluginSkills additionalSkillPaths plumbing in session-skill-context.ts so plugin skill discovery paths flow the same way as native/role-fallback skills.
- Update dashboard skills-adapter.ts to read plugin skill SKILL.md and reference files from disk (via the traversal-guarded reader) instead of returning a runtime-placeholder/"not found" response for plugin-sourced skills.
- Document the plugin skill body delivery mechanism in docs/PLUGIN_AUTHORING.md.
- Add regression coverage: plugin-skill-body-delivery.test.ts, expanded session-skill-context.test.ts and skills-adapter.test.ts.
- Add changeset fn-7857-plugin-skill-body-delivery.md (minor, fix).
Files changed:
.changeset/fn-7857-plugin-skill-body-delivery.md | 7 ++
docs/PLUGIN_AUTHORING.md | 3 +
.../dashboard/src/__tests__/skills-adapter.test.ts | 92 ++++++++++++++++------
packages/dashboard/src/skills-adapter.ts | 33 ++------
.../__tests__/plugin-skill-body-delivery.test.ts | 75 ++++++++++++++++++
.../src/__tests__/session-skill-context.test.ts | 84 +++++++++++++++++++-
packages/engine/src/agent-heartbeat.ts | 3 +-
packages/engine/src/cron-runner.ts | 2 +
packages/engine/src/executor.ts | 25 ++++--
packages/engine/src/merger.ts | 10 ++-
packages/engine/src/reviewer.ts | 2 +
packages/engine/src/session-skill-context.ts | 43 ++++++++--
packages/engine/src/step-session-executor.ts | 5 +-
packages/engine/src/triage.ts | 3 +-
14 files changed, 318 insertions(+), 69 deletions(-)
Fusion-Task-Id: FN-7857
Fusion-Task-Lineage: 9ba4c305-8b38-4ae8-85b3-4c87205ef767
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Bounds the execute->pause-abort->todo dispatch loop so a task can no longer requeue forever with no visible signal or terminal state.
- Track a progress-anchored `executeRequeueLoopCount`/`executeRequeueLoopSignature` pair on the task row (current step + step statuses) so slow no-progress requeue cycles are counted independently of the scheduler's wall-clock `dispatchStormCount` guard.
- Warn visibly in the task log at `EXECUTE_REQUEUE_LOOP_VISIBLE_THRESHOLD` (3) and terminalize non-paused, non-terminal tasks at `MAX_EXECUTE_REQUEUE_LOOP_CYCLES` (6) with `status:"failed"` and an `EXECUTION_DISPATCH_LOOP_EXHAUSTED:` error, preserving worktree/branch/step progress.
- Emit a new `task:execution-dispatch-loop-terminalized` run-audit mutation type with ids/counts/outcomes-only metadata.
- Reset the loop counters on real progress, manual retry, forward moves (in-review/done/archived), and unpause, in both the executor and scheduler.
- Add DB migration 142 (`executeRequeueLoopCount`, `executeRequeueLoopSignature` columns) plus store read/write/reset plumbing.
- Add reliability-interactions coverage for the new loop guard and extend store-persistence tests for the new columns.
- Document the new behavior in AGENTS.md and docs/architecture.md.
Files changed:
AGENTS.md | 1 +
docs/architecture.md | 2 +
packages/core/src/__tests__/store-persistence.test.ts | 45 +++++
packages/core/src/db.ts | 17 +-
packages/core/src/manual-retry-reset.ts | 1 +
packages/core/src/store.ts | 22 ++-
packages/core/src/types.ts | 11 ++
.../execute-requeue-loop-guard.test.ts | 188 +++++++++++++++
packages/engine/src/executor.ts | 67 +++++++-
packages/engine/src/run-audit.ts | 2 +
packages/engine/src/scheduler.ts | 8 +-
11 files changed, 355 insertions(+), 9 deletions(-)
Fusion-Task-Id: FN-7863
Fusion-Task-Lineage: db40507f-5851-435e-8854-c1ed695b4154
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Pausing an in-progress task never stuck: the pause teardown re-queued the
row to todo with a plain engine move, and the reopen block wiped
paused/pausedByAgentId/pausedReason. The graph-failure classifier then saw
an unpaused row, misread the hard-cancel as an engine-internal abort, and
auto-continued the session (graphResumeRetryCount 1/2, 2/2); once the
budget was exhausted the benign re-queue left the row dispatchable and the
scheduler re-dispatched it seconds later — an indefinite pause/resume
bounce, burning a fresh worktree + pnpm install per cycle.
- store: new moveTask option `preservePause` keeps the pause park across a
reopen-to-todo/triage move (flag-ON trait hook + flag-OFF legacy inline,
kept in sync). It never SETS a pause, only prevents clearing one.
- executor teardown: when the pause that caused the abort is still in
force, move with preservePause so the row lands in todo still parked
(scheduler skips paused/userPaused rows until explicit unpause).
- classifier: a live task pause is labeled operator intent, never
"engine abort during pause/resume"; the benign log now says
"parked … awaiting explicit unpause" instead of the contradictory
"cleared for normal scheduling" for parked rows.
Surfaces covered by tests: flag-ON hook (preserve + never-set + default
clear), classifier no-auto-continue for task-pause/user-pause/global-pause
rows in todo, provenance labels.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Video was registrable but effectively unusable, and HTML/PDF deliverables
had no first-class path from agents to the gallery.
- media route now serves HTTP byte ranges (Accept-Ranges, 206 +
Content-Range, 416 on unsatisfiable) so <video>/<audio> seeking works
and Safari plays media at all
- video attachments (mp4/webm/mov, 100MB cap vs 5MB for other types)
bridge into the artifact registry like images; multer transport ceiling
raised to 100MB with per-type caps enforced in the store
- fn_artifact_register path payloads are signature-validated for video
(ftyp box / EBML header) and PDF (%PDF- prefix), mirroring images
- HTML doc artifacts (mimeType text/html) render as live sandboxed
iframe previews by default in the doc viewer, with a Preview/Source
toggle and the same FileEditor edit mode
- executor/heartbeat/planning prompts and tool descriptions now cover
the full type matrix: images, videos, audio, HTML mockups, PDFs, and
markdown docs, each with the registration recipe
Verified live: range requests (200/206/416) via curl, an ffmpeg-generated
mp4 playing to completion in the gallery lightbox, and an interactive
HTML mockup rendering in the sandboxed preview.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Agents could never get screenshots/wireframes/mocks into the Artifacts view:
fn_artifact_register was gated on assignedAgentId (never set in default
ephemeral mode), the only image payload source was inline base64, and no
prompt ever told agents to register visual deliverables.
- always expose fn_artifact_register to executor sessions ("executor" author
fallback), resolve relative paths against the task worktree, and default
taskId to the executing task (heartbeat task lane too)
- add a `path` payload source: file read with 50MB cap, extension MIME
inference, PNG/JPEG/GIF/WebP signature + SVG sniff validation, persisted
through managed artifact storage
- executor/heartbeat/planning prompts + engine-tools reference now instruct
agents to register screenshots, wireframes, mockups, and recordings
- new ArtifactsGallery: Images/Docs/PDFs/Videos/Audio/Other category sections
and filter chips, visual tile grid + lightbox, embedded PDF viewer, audio
player rows, download rows; mobile-responsive down to the 768px breakpoint
- doc artifacts open a full viewer rendered as markdown by default with an
in-place edit mode using the shared CodeMirror FileEditor; persisted via new
GET/PATCH /api/artifacts/:id + TaskStore.updateArtifact and live-refreshed
through the new artifact:updated SSE event
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Replace the boolean isGitRepository() check with a tri-state Git detection so environmental git failures (dubious ownership, missing git binary, timeouts) are no longer misreported as "not a Git repository", which previously blocked all task execution in valid repos and survived engine restarts.
- Add detectGitRepository() in worktree-pool.ts returning repo / not-repo / error (with reason: dubious-ownership, git-missing, timeout, unknown), classified from git's stderr; bound the git rev-parse call with a 10s timeout and maxBuffer; keep isGitRepository() as a backward-compatible wrapper
- Route the executor dispatch preflight guard through detectGitRepository(): only emit the original "not a Git repository / run git init" fatal on a positive not-repo verdict; on error, throw a distinct accurate error naming the real git failure, including the safe.directory remedy for dubious ownership
- Route the in-process runtime startup warning through the same tri-state detection so it only warns "not a Git repository" on a positive not-repo verdict
- Add a regression test locking extractWorktreeConflictInfo() to NOT misclassify a dubious-ownership git worktree add failure as not-git-repo
- Add targeted tests across worktree-pool, executor-worktree, and in-process-runtime test suites covering repo/not-repo/dubious-ownership/git-missing/timeout classifications on Windows OneDrive-style and POSIX paths
- Add changeset and a docs/solutions/logic-errors write-up of the false-negative root cause and fix
Files changed:
.changeset/fn-7799-git-detection-false-negative.md | 7 +++
.../logic-errors/git-detection-false-not-repo.md | 54 ++++++++++++++++
.../engine/src/__tests__/executor-worktree.test.ts | 61 +++++++++++++++++++
.../engine/src/__tests__/worktree-pool.test.ts | 71 +++++++++++++++++++---
packages/engine/src/executor.ts | 38 +++++++++---
.../runtimes/__tests__/in-process-runtime.test.ts | 53 ++++++++++++++--
packages/engine/src/runtimes/in-process-runtime.ts | 16 ++++-
packages/engine/src/worktree-pool.ts | 66 ++++++++++++++++++--
8 files changed, 334 insertions(+), 32 deletions(-)
Fusion-Task-Id: FN-7799
Fusion-Task-Lineage: 25a84283-bf47-472b-8a98-a10bf7e494de
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds fallbackThinkingLevel plumbing so, when Fusion swaps from a primary model to a configured fallback model (executor, validator/reviewer, merger, planning, title-summarizer, heartbeat, and workflow-step lanes), the fallback's own configured thinking level is applied instead of silently reusing the primary lane's level.
- Add fallbackThinkingLevel option to AgentRuntimeOptions (agent-runtime.ts), AgentOptions (pi.ts), and ReviewOptions (reviewer.ts)
- Add per-lane resolvers: resolveExecutorFallbackThinkingLevel, resolvePlanningFallbackThinkingLevel, resolveValidatorFallbackThinkingLevel, resolveTitleSummarizerFallbackThinkingLevel, resolveMergerFallbackThinkingLevel (agent-session-helpers.ts), each following fallback-provider precedence and falling back to the primary lane/default thinking level when unset
- Export new resolvers from packages/engine/src/index.ts
- Apply the resolved fallback thinking level in createFnAgent's applyThinkingLevelIfSupported once a session has swapped to the fallback model (pi.ts)
- Wire fallbackThinkingLevel through executor session creation (workflow-step, task validator, child-agent, and main executor session paths), merger session creation, and heartbeat session creation
- Promote the fallback thinking level alongside the fallback model/provider when the no-visible-key Grok CLI fallback is promoted to primary, so the cleared fallback pair doesn't leave the session on the superseded primary's thinking level
- Route workflow-step fallback thinking level by which fallback candidate (validatorFallback vs globalFallback) actually matched
- Document fallbackThinkingLevel runtime-swap behavior in docs/settings-reference.md
- Add minor changeset for @runfusion/fusion
- Add regression tests covering fallback thinking-level resolution and application (agent-session-helpers.test.ts, pi.test.ts) and a shared test helper (executor-test-helpers.ts)
Files changed:
.changeset/fn-7794-fallback-thinking-level.md | 7 ++
docs/settings-reference.md | 3 +
.../src/__tests__/agent-session-helpers.test.ts | 38 ++++++
.../engine/src/__tests__/executor-test-helpers.ts | 23 ++++
packages/engine/src/__tests__/pi.test.ts | 136 +++++++++++++++++++++
packages/engine/src/agent-heartbeat.ts | 3 +-
packages/engine/src/agent-runtime.ts | 5 +
packages/engine/src/agent-session-helpers.ts | 54 ++++++++
packages/engine/src/executor.ts | 31 ++++-
packages/engine/src/index.ts | 5 +
packages/engine/src/merger.ts | 7 +-
packages/engine/src/pi.ts | 16 ++-
packages/engine/src/reviewer.ts | 6 +
13 files changed, 327 insertions(+), 7 deletions(-)
Fusion-Task-Id: FN-7794
Fusion-Task-Lineage: c94d621a-ccbd-42b2-9fe6-cb619418ad90
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Task execution sessions previously ignored the assigned permanent agent's
runtimeConfig model whenever the executor was handed an agents-less
worktree AgentStore, silently drifting to the pi runtime's built-in
default model instead of the configured one.
- Add TaskExecutor.getAuthoritativeAssignedAgent(): falls back to the
authoritative project `.fusion` AgentStore when the live executor's
worktree AgentStore has no record of the assigned agent, so
runtimeConfig resolution matches chat-session behavior.
- Replace direct `this.options.agentStore.getAgent(...)` lookups across
step-session, workflow-graph, and legacy execution paths with the new
authoritative lookup helper.
- Warn and audit (`noModelResolved` / `runtimeBuiltInFallbackModel`) when
a non-mock, non-test-mode session resolves no provider/model pair and
falls back to the runtime's built-in default, so the drift is visible
instead of silent.
- Add regression tests covering assigned-agent runtime-config resolution
and the new runtime-resolved audit fields.
- Add changeset (patch) and update docs/settings-reference.md and
AGENTS.md.
Files changed:
.changeset/fuzzy-fable-fallback.md | 7 +++
AGENTS.md | 1 +
docs/settings-reference.md | 2 +-
.../executor-assigned-agent-runtime-config.test.ts | 68 ++++++++++++++++++++++
.../run-audit-session-runtime-resolved.test.ts | 44 ++++++++++++++
packages/engine/src/agent-session-helpers.ts | 31 +++++++---
packages/engine/src/executor.ts | 43 +++++++++-----
7 files changed, 174 insertions(+), 22 deletions(-)
Fusion-Task-Id: FN-7787
Fusion-Task-Lineage: 40fccad5-2e67-4ee2-8199-4548ce9025c6
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Fixes autoMerge=false being bypassed for engine-created branch-group member tasks whose branch group had already dissolved/finalized.
- Add isLiveSharedBranchGroupMemberIntegration(task, group) in @fusion/core, requiring the branch group's status be "open" before the shared-branch-member exemption bypasses the global/task autoMerge:false hold.
- Export the new helper from packages/core/src/index.ts and index.gate.ts.
- Thread the live-group check through packages/engine/src/project-engine.ts (allowInReviewMergeProcessing, enqueueEligibleInReviewTasks, merge-confirmed fast-path branch routing, and merge handoff paths).
- Add TaskExecutor.isLiveSharedBranchGroupMember helper in packages/engine/src/executor.ts and use it in retryable pre-merge remediation, no-op finalize, benign pause-abort classification, and merge-processing gates.
- Keep self-healing.ts's solo no-op finalize predicate on the pure branchContext-shape check (isSharedBranchGroupMemberIntegration) intentionally, so stale shared-group members stay excluded from solo finalize regardless of group liveness.
- Add regression tests covering the executor and project-engine auto-merge-hold behavior for stale/dissolved branch groups.
- Add a patch changeset documenting the fix.
Files changed:
.../fn-7750-automerge-hold-stale-branch-group.md | 7 ++
packages/core/src/__tests__/task-merge.test.ts | 42 +++++++++--
packages/core/src/index.gate.ts | 1 +
packages/core/src/index.ts | 1 +
packages/core/src/task-merge.ts | 13 +++-
...cutor-live-branch-group-auto-merge-hold.test.ts | 85 ++++++++++++++++++++++
.../engine/src/__tests__/project-engine.test.ts | 37 +++++++++-
packages/engine/src/executor.ts | 22 ++++--
packages/engine/src/project-engine.ts | 32 +++++---
packages/engine/src/self-healing.ts | 1 +
10 files changed, 214 insertions(+), 27 deletions(-)
Fusion-Task-Id: FN-7750
Fusion-Task-Lineage: d61f8847-0b09-49b5-b66a-00018c8738bb
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Fixes tasks in auto-merge-off manual merge hold getting incorrectly marked failed by a benign pause/resume abort, which blocked Merge & Close.
- Add isBenignManualMergeHoldPauseAbort classifier in executor.ts: recognizes a hard-cancel pause-abort at a merge-region node while auto-merge is off (or processing is disallowed) as benign, and preserves the in-review row instead of failing/re-enqueueing it.
- Clear stale pause-abort status/error and suppress the failure notification when this benign manual-hold case is detected, per FN-5147's no-backward-move/no-reenqueue contract.
- Extend self-healing.ts recovery to handle this manual-hold case alongside existing paused-abort recovery paths.
- Add/extend tests in merge-node-paused-abort-retryable.test.ts and self-healing-paused-abort-recovery.test.ts covering the new benign classification.
- Document the fix in docs/architecture.md.
- Add changeset (patch) describing the user-facing fix.
Files changed:
.changeset/fn-7749-manual-merge-hold-false-failure.md | 7 +++
docs/architecture.md | 4 +-
packages/engine/src/__tests__/reliability-interactions/merge-node-paused-abort-retryable.test.ts | 50 +++++++++++++++++----
packages/engine/src/__tests__/self-healing-paused-abort-recovery.test.ts | 49 ++++++++++++++++++++-
packages/engine/src/executor.ts | 51 +++++++++++++++++++++-
packages/engine/src/self-healing.ts | 23 ++++++++--
6 files changed, 168 insertions(+), 16 deletions(-)
Fusion-Task-Id: FN-7749
Fusion-Task-Lineage: 6d90adc3-6cd9-463d-b9d0-7a5c3069c1a5
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Archiving a task from triage/planning/todo (not just in-progress) previously left leaked active-session-registry entries, so a successor task could hit ActiveSessionPathHeldByForeignTaskError and get blocked from Plan Review.
- Add an explicit `to === "archived"` branch in the task-move handler that awaits abort of in-flight task work and sweeps any leftover activeSessionRegistry paths for the task, checked before the narrower `from === "in-progress"` branch so direct in-progress→archived transitions are covered too.
- Deliberately exclude `to === "done"` / `to === "in-review"` from this sweep since those columns legitimately hold ai-merge / workspace-repo-land merge leases that must survive the transition.
- Add regression test coverage for archive releasing active sessions across originating columns.
- Add changeset and architecture doc note.
Files changed:
.../fn-7717-archive-active-session-release.md | 7 +
docs/architecture.md | 1 +
...xecutor-archive-releases-active-session.test.ts | 167 +++++++++++++++++++++
packages/engine/src/executor.ts | 35 +++++
4 files changed, 210 insertions(+)
Fusion-Task-Id: FN-7717
Fusion-Task-Lineage: 7cff6821-7bb3-4b75-b502-a26467ca7f51
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Agents that must edit files beyond a task's declared ## File Scope had no
way to keep the scope in sync, so those edits were stranded at merge (the
squash merge is scoped to ## File Scope, and cross-task overlap blocking +
the merge file-scope invariant both read it).
New executor tool fn_task_file_scope_add validates repo-relative
paths/globs with isValidFileScopeEntry, de-dupes against existing scope,
appends them to the ## File Scope section of PROMPT.md, and persists via
store.updateTask({ prompt }) (same validation + task.json/PROMPT.md sync as
fn_task_prompt_write). Registered in the main coding-agent tool list; the
base executor prompt now instructs the agent to call it when editing beyond
the declared scope. Merge-time peer-claim refusal is unchanged and remains
the cross-task backstop.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Agents were composing plans (e.g. reboot/wait-and-retry loops) that assumed they could keep acting even after the Fusion platform itself shut down, since prompts never told them they run inside Fusion. This adds a shared, docs-grounded self-awareness preamble prepended to chat, heartbeat, and executor base prompts so agents know their own runtime constraints.
- Added FUSION_RUNTIME_SELF_AWARENESS shared preamble in packages/core/src/agent-prompts.ts, exported via packages/core/src/index.ts
- Prepended the preamble to the chat system prompt (packages/dashboard/src/chat.ts)
- Prepended the preamble to the heartbeat session prompt (packages/engine/src/agent-heartbeat.ts)
- Prepended the preamble to the executor base prompt (packages/engine/src/executor.ts)
- Updated docs/agents.md and CONCEPTS.md to document the new self-awareness/capability-grounding behavior
- Added regression tests across core, dashboard, and engine covering the new prompt content
- Added changeset for @runfusion/fusion (minor, fix category)
Files changed:
.changeset/fn-7675-agent-runtime-self-awareness.md | 7 ++++
CONCEPTS.md | 4 +-
docs/agents.md | 17 ++++++++
packages/core/src/__tests__/agent-prompts.test.ts | 41 ++++++++++++++++++++
packages/core/src/agent-prompts.ts | 32 ++++++++++++++-
packages/core/src/index.ts | 1 +
packages/dashboard/src/__tests__/chat-system-prompt.test.ts | 17 ++++++++
packages/dashboard/src/chat.ts | 6 ++-
packages/engine/src/__tests__/executor-prompt.test.ts | 45 ++++++++++++++++++++++
packages/engine/src/__tests__/heartbeat-session-prompt.test.ts | 35 +++++++++++++++++
packages/engine/src/agent-heartbeat.ts | 10 +++--
packages/engine/src/executor.ts | 7 +++-
12 files changed, 213 insertions(+), 9 deletions(-)
Fusion-Task-Id: FN-7675
Fusion-Task-Lineage: 126d04a6-2c68-4347-9789-591b274277bf
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Executors could previously treat a pending approval as a normal turn end and go hunt for ungated workarounds instead of stopping. This change makes wait-for-approval a hard suspend point.
- wait-for-approval now suspends the in-flight executor session via awaitAbortInFlightTaskWork
- Dedupe identical pending approvals so repeated waits don't pile up
- Executor prompts now carve out awaiting-approval as a legitimate turn end (agent-prompts.ts)
- Extend provisioning-gate and agent-action-gate coverage for the new suspend/carveout behavior
- Add changeset (patch) documenting the fix for release notes
- Update docs/agents.md and docs/architecture.md to describe the new blocking behavior
Files changed:
.changeset/fn-7608-awaiting-approval-blocking.md | 7 ++
docs/agents.md | 1 +
docs/architecture.md | 1 +
packages/core/src/agent-prompts.ts | 5 +
.../engine/src/__tests__/agent-action-gate.test.ts | 82 +++++++++++++
.../executor-approval-gate-suspend.test.ts | 128 +++++++++++++++++++++
.../executor-approval-prompt-carveout.test.ts | 61 ++++++++++
packages/engine/src/agent-heartbeat.ts | 13 +++
packages/engine/src/executor.ts | 28 +++++
packages/engine/src/pi.ts | 22 +++-
.../sandbox/__tests__/provisioning-gate.test.ts | 29 +++++
packages/engine/src/sandbox/provisioning-gate.ts | 11 ++
12 files changed, 384 insertions(+), 4 deletions(-)
Fusion-Task-Id: FN-7608
Fusion-Task-Lineage: 9e42d8ee-bda7-4ef1-b159-46c2100bbc48
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
The Plan Review pre-merge gate could loop a task through triage↔plan-review
indefinitely (FN-7525 ran 13+ replans overnight with no operator visibility),
and its reviewer frequently produced "no PROMPT.md found / data lives in a DB"
non-verdicts that fed the loop.
Root cause of the non-verdicts: the reviewer runs readonly with cwd set to the
task worktree, but the spec lives at project-root .fusion/tasks/<id>/PROMPT.md —
outside the worktree — so telling it to "Read PROMPT.md" had it search the wrong
tree and give up. Four fixes:
1. Inject the PROMPT.md content (via readTaskArtifact, store-backed) directly
into the Plan Review reviewer prompt so the verdict never depends on the
agent locating the file.
2. Self-retry a malformed reviewer response once on the primary model when no
fallback model is configured, so a single fumbled response gets a second
chance instead of feeding the replan loop.
3. A malformed (advisory_failure, no parsed verdict) plan-review result can
never trigger a triage replan — it is an infra failure, not a plan defect.
4. Cap the unbounded plan-review replan default at 15 attempts; past the cap it
emits a loud halting log entry and leaves the task for a human instead of
looping forever. Explicit numeric operator budgets are unchanged.
Tests: cap halts at 15 / still replans at 14 / malformed never replans. Existing
Plan Review replan and malformed-verdict-gate tests still pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add workflow nodes for mid-flow user reach-out and early exit from a workflow run.
- Add `ask-user` IR node kind that reuses the await-input park/resume mechanism and surfaces the question in the task chat for brainstorming/clarification.
- Add `exit-gate` IR node kind that terminates the workflow early, with an optional condition.
- Wire both node kinds through the engine executor and workflow-node-handlers, including a new exit-gate-runner.
- Update the WorkflowNodeEditor palette, node summaries, and node help text for the two new node types.
- Extend workflow-flow-mapping to support the new node kinds.
- Keep `prompt`+`awaitInput` as a back-compat alias.
- Add core/engine/dashboard tests covering the new node kinds.
- Document the new nodes in docs/workflow-steps.md.
- Add changeset for the new minor feature.
Files changed:
.changeset/fn-7579-ask-user-exit-gate-nodes.md | 7 +
docs/workflow-steps.md | 28 ++++
packages/core/src/__tests__/workflow-ir.test.ts | 120 ++++++++++++++
packages/core/src/workflow-ir-types.ts | 12 +-
packages/core/src/workflow-ir.ts | 47 ++++++
.../app/components/WorkflowNodeEditor.tsx | 181 ++++++++++++++++++++-
.../app/components/__tests__/node-summary.test.ts | 43 +++++
.../__tests__/workflow-flow-mapping.test.ts | 49 ++++++
.../app/components/nodes/WorkflowNodeTypes.tsx | 14 +-
.../dashboard/app/components/nodes/node-help.ts | 24 +++
.../dashboard/app/components/nodes/node-summary.ts | 28 ++++
.../app/components/workflow-flow-mapping.ts | 4 +
.../workflow-graph-executor-handlers.test.ts | 115 +++++++++++++
.../src/__tests__/workflow-node-handlers.test.ts | 66 ++++++++
packages/engine/src/executor.ts | 23 ++-
packages/engine/src/workflow-node-handlers.ts | 18 +-
.../src/workflow-node-runners/exit-gate-runner.ts | 81 +++++++++
17 files changed, 849 insertions(+), 11 deletions(-)
Fusion-Task-Id: FN-7579
Fusion-Task-Lineage: 9a89ff49-200d-4a6c-b97c-15d219349ee5
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Reviews no longer fail on formatting. Three changes to how reviewer/gate
verdicts are parsed and how retries reset state:
- Approval leniency: a review that clearly approves in prose passes even
without a structured verdict (proseSignalsClearApproval, with a
revise/reject/negated-approval guard so a rejection is never flipped). Any
APPROVE*/APPROVAL verdict token classifies as approved. Shared by the
reviewer/plan-review parser and the code-review/browser-verification gate.
- Prose + trailing JSON: extractJsonObjectCandidates does a string-aware
balanced-brace scan and prefers the last object, so a model that emits
reasoning prose then a trailing {"verdict":...} payload parses correctly.
An explicit "Verdict:" heading/line still takes precedence over an
incidental/example JSON object.
- Malformed handling: executeWorkflowStep retries the fallback model on
malformed output (not just timeout); malformed gate output becomes a
non-blocking advisory (a genuine parsed REVISE still blocks).
- Retry clears prior terminal step failures (incl. optional gate nodes like
code-review) after the task leaves the mergeable in-review column, so a
retry starts clean without an auto-merge race.
Fail-closed merge / PR-review / mission-verification gates are unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add TaskExecutor.blockOuterDispatchWhenEphemeralDisabled, gating all three
workflow dispatch paths (graph / authoritative / work-engine) on
ephemeralAgentsEnabled at the top of execute(). Previously the toggle was
enforced only on the legacy scheduler/EphemeralWorkerManager path — whose
onTaskStart spawn refusal is a fire-and-forget callback that runs after
execution begins — so unassigned tasks reaching execute() off a non-scheduler
path still ran. Unassigned tasks are now re-queued for permanent-agent
assignment; permanent-agent-bound tasks still run. Adds regression coverage
across all three entry points.
Also includes the ephemeralAgentsCanCreateTasks project setting (default on)
gating fn_task_create for ephemeral callers in both the pi extension and the
executor task-worker tool.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A pre-merge-remediation/plan-replan node (e.g. code-review-remediation) is a
fire-and-forget async scheduler with no failure out-edge. When its schedule call
can't re-arm (missing rehydrated failureContext after restart,
remediation-not-scheduled, or an exhausted rework budget), the failure bubbled
out as the terminal graph outcome and handleGraphFailure stamped status:"failed"
— surfacing a spurious "Task Failed" even while the previously-scheduled
fix/reviewer session was still live.
Guard the terminal sink: skip the failed park when the failed node is a
remediation node AND a live agent session surface is still registered for the
task. Scoped via isRemediationGraphNode (IR workflowAction + built-in node-id
fallback) and hasLiveTaskSessionSurface; genuine execute/merge failures and
remediation failures with no live session still park failed unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolves the pnpm-lock.yaml conflict. Main's #1865 (review-checkout routing)
auto-merged cleanly with the completion-summary backstop in executor.ts.
Main independently pinned pi-claude-cli's pi-ai/pi-coding-agent to ^0.80.3
(e15489259) but kept the top-level `getModels` import, which 0.80.3 removed —
this branch's migration to `getBuiltinModels` from `/providers/all` is retained
as the working fix. Lockfile regenerated against the merged package.json.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two distinct v0.52.0 regressions reported in issue #1863.
1. Triage loop (engine): the best-effort completion-summary graph node is
wired into every built-in workflow with a success-only edge. A thrown
handler exception or a failed summary projection write bypassed the
advisory `!blocking -> success` coercion, terminated the graph at
'completion-summary', and routeGraphFailureToExecutionResume bounced the
in-review task back to todo forever (token usage 0, execution NOT STARTED).
The graph executor now degrades a completion-summary node failure to
success (ensureWorkflowCompletionSummary still backfills task.summary), with
a routeGraphFailureToExecutionResume backstop. Shared isCompletionSummaryNode
predicate exported from @fusion/core.
2. i18n object-key crashes (dashboard): three views called t() with keys that
resolve to nested objects (taskDetail.executionMode, routing.source,
nodes.dockerHost), so i18next returned "returned an object instead of
string" and crashed the render. Added leaf label keys across all locales and
switched the callers.
Tests: engine non-fatal completion-summary regression (fails without the fix),
dashboard invariant guard scanning t("literal") callers against real en/app.json,
and a Stats-panel reproduction against the real bundle.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
