Importing a catalog ("company") agent assigns role "custom", which the
scheduler never auto-assigns mission/queue work to. Combined with a
model/provider that rejects the "developer" system role, this surfaced as
an invisible, repeating failure loop (GitHub #1261).
- pi.ts: treat an unsupported message-role rejection as a model-selection
error so a configured fallback model is tried once (single-swap guarded)
before the task is marked failed.
- mission-autopilot.ts: block a mission feature immediately on an
operator-actionable failure instead of burning the retry budget
re-running the same cryptic error.
- mission-routes.ts: preflight mission start — when ephemeral agents are
disabled and no eligible executor exists, fail fast with an actionable
message instead of queueing tasks forever.
- agent import route + AgentImportModal: warn when only custom-role agents
are imported and no executor exists.
- agent-assignment.ts: extract shared listEligibleExecutorAgents helper.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Main independently landed the same pausedReason persistence fix (column in
the task INSERT/upsert, TaskRow type, rowToTask mapping) with the column
ordered between paused and userPaused; adopt main's ordering and drop this
branch's duplicate entries so the values array stays aligned. Union the
dashboard package.json deps (main's compound-engineering plugin alongside
this branch's sorted pi-coding-agent/cli-printing-press/cursor-runtime).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Both sides bootstrapped CONCEPTS.md — kept main's broader structure (Missions,
Merge lifecycle, CE sessions) and folded the branch-group vocabulary into its
Merge-lifecycle cluster (enriched Shared branch group + Self-healing sweep;
added Branch assignment mode, Landed, Group promotion). Union-merged core
index/store imports; took main's AGENTS.md discoverability wording. Also adds
execFile to the two child_process test mocks that only stubbed exec (the
coordinator's argv-based git calls now require it).
Agent-native parity: users can list workflows and select one for a task in
the dashboard, so agents should be able to as well. Adds two task-session
tools — fn_workflow_list (read: built-ins + user definitions) and
fn_workflow_select (assign a workflow to a task, defaulting to the current
one) — wired into the executor's customTools and exported from the engine
index. Covered by unit tests against mock stores.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Users can now watch everything the agent does while a CE stage works, steer
it mid-stage, and read the whole conversation as a proper chat surface.
Live output:
- New host capability: CreateInteractiveAiSessionOptions.onProgress — the
engine adapter streams thinking/text deltas + tool start/end markers from
the pi agent hooks (any plugin can use this).
- Orchestrator buffers per-session live activity (merged deltas, discrete
tool lines, capped), emits throttled progress events over SSE, and
GET /sessions/:id attaches it as liveActivity for the polling fallback.
- Routes detach turn execution: start/answer/resume return immediately
(status active) and clients converge via push/poll — the turn is watchable
instead of hidden inside a blocking POST.
- Turn timeout is now INACTIVITY-based: an actively-working long turn is
never killed; a quiet one interrupts with its working trace preserved.
- On settle the trace persists into history as a condensed record.
Steering:
- Stage protocol: responses may be a direct answer, {value, comment}
(answer + guidance), or {feedback} (guidance without answering); the
system prompt instructs agents to treat steering as first-class input.
- CeFlow: guidance textarea alongside selectable questions — attach to the
clicked answer, or "Send guidance" on its own.
Q&A UI:
- Transcript no longer hides control records: past questions/answers render
as chat bubbles (option ids → labels), steering turns marked, working
traces as collapsible "Agent work" blocks, completion marker.
- Live working pane (pulse + streaming thinking/tool lines) while a turn runs.
Tests: 130 plugin tests green (14 new: live buffer/flush ordering, inactivity
watchdog survives active work, detached convergence, steering payload shapes,
transcript rendering, live pane). Engine seam tests green; plugin/core/
engine/dashboard tsc clean. Core full suite OOMs locally (known orchestrator-
shell issue) — covered by CI shards.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Review residuals #3/#4/#6/#10: per-group in-process promotion lock (concurrent
route+auto promotion could double-create PRs), finalized-but-PR-less groups can
be repaired by re-promotion without re-merging, auto-promotion failures emit
merge:branch-group-promotion-failed instead of silent swallow, exported
reconcileBranchGroupPr for out-of-band merged reconciliation, and the merger
sync block drops its (store as any) casts (TaskStore already carries the
methods).
Loads a task's selected workflow, runs the graph with injected legacy seams
(execute/review/merge) and a custom-node runner, and maps the terminal outcome
to completed/failed/fell-back. Any interpreter-level error falls back so the
caller can run the legacy pipeline — a task is never stranded. Covered with
fake seams: lifecycle ordering, failure routing, gate blocking, fallback
reasons, diagnostics isolation. Includes the interpreter-cutover plan doc.
Push the single group PR's body (member checklist, x/N landed) on each member
landing via an injected SyncGroupPrFn — new updatePr/closePr GitHubClient
helpers (gh CLI + API parity); refreshPrInBackground is task-scoped/wrong
direction and intentionally not reused. Sync failures are non-fatal+retryable;
out-of-band closed/merged PRs reconcile prState instead of erroring. New
POST /branch-groups/:id/abandon closes the PR best-effort and marks the group
abandoned. Also fixes the U5-introduced stub-context regression in the U4
dashboard bridge test (missing options).
Group promotion in PR mode previously flipped prState to 'open' without ever
calling GitHub — prNumber/prUrl were never populated. Add an injected
CreateGroupPrFn (mirrors the processPullRequestMerge seam, no engine→dashboard
import): coordinator creates-or-reuses exactly one PR per group, persists
prNumber/prUrl/prState, and leaves state untouched on GitHub failure so
re-promotion retries. Idempotent via persisted prNumber +
getBranchGroupByBranchName. Wired at all three CLI engine-construction sites
(daemon/dashboard/serve).
Closes the U2/U5 skill-discovery carry-forward so the plugin's interactive ce-*
sessions actually load the stage's bundled skill in a live agent (not just in
scripted-fake tests).
Root cause: createFnAgent built its DefaultResourceLoader without forwarding any
skill-discovery path, and the interactive seam options couldn't carry one. The
loader's skillsOverride only *filters* skills already discovered from cwd's
standard roots, so the plugin-local .fusion-ce-skills/<id>/SKILL.md was never
discoverable.
Fix (end-to-end):
- AgentOptions.additionalSkillPaths forwarded into DefaultResourceLoader
- CreateInteractiveAiSessionOptions gains requestedSkillNames + additionalSkillPaths
- the interactive engine adapter forwards them to createFnAgent (skills +
additionalSkillPaths)
- the orchestrator runs the session with cwd on the real project root and hands
it [stage.skillId] + the install root
Proven: a real DefaultResourceLoader with additionalSkillPaths discovers ce-plan
and filters out ce-work; the orchestrator passes the right id/path/cwd. Plugin 96,
engine 136, core 99 tests green.
Expose createInteractiveAiSession on route/loader PluginContext alongside the
one-shot createAiSession. The prompt->parse->retry->pause->resume loop is
reimplemented in an engine seam modeled on planning.ts (no engine await-input
primitive exists). Reuses PlanningQuestion/PlanningResponse; stays generic with
no plugin-specific concepts. Injected on route contexts only; tool/runtime
contexts omit it (parity with createAiSession).
Add the Phase 2 workflow-graph interpreter scaffold and builtin coding IR wiring while keeping execution behavior unchanged by default.
- add BUILTIN_CODING_WORKFLOW_IR and builder in @fusion/core with coverage tests
- export new coding workflow IR APIs from core index
- add WorkflowGraphExecutor scaffold in @fusion/engine plus parity-focused test coverage
- document the flagged-off interpreter scaffold, parity gate, and v1 IR gap reconciliation in workflow docs
- include a changeset for published @runfusion/fusion
Files changed:
.../fn-5766-workflow-graph-executor-scaffold.md | 11 +++
docs/workflow-steps.md | 27 +++++++
.../__tests__/builtin-coding-workflow-ir.test.ts | 34 +++++++++
packages/core/src/builtin-coding-workflow-ir.ts | 60 ++++++++++++++++
packages/core/src/index.ts | 4 ++
.../workflow-graph-executor-parity.test.ts | 32 +++++++++
packages/engine/src/index.ts | 7 ++
packages/engine/src/workflow-graph-executor.ts | 82 ++++++++++++++++++++++
8 files changed, 257 insertions(+)
Fusion-Task-Id: FN-5766
Fusion-Task-Lineage: 4bbef713-a415-4d42-a20b-9ae4f3235419
After advanceIntegrationBranchRef ff-updates refs/heads/<integrationBranch>,
the merger now enumerates other worktrees on that branch and reconciles
each one's index + working tree to the new tip via syncWorktreeToHead.
Not a git pull — origin may still be at the previous tip without
pushAfterMerge, so pull --ff-only is a no-op and a naive stash/pull/pop
ends with the worktree restored to the old state. Instead the new
worktree-ref-sync helper:
1. Diffs the worktree against the previous tip to isolate real edits
from the stale-index "phantom diff" against the new HEAD.
2. Snaps clean worktrees forward via reset --hard HEAD.
3. In stash-and-ff mode with real edits, captures them as a binary patch
against the previous tip, snaps to HEAD, then git apply --3way to
restore. Untracked files are saved + restored separately. Patch
conflicts surface as synced-with-pop-conflict with the patch left on
disk for manual recovery.
Per-worktree outcome emitted as merge:auto-sync (new GitMutationType).
Per-step pull:fast-forward / stash:push / stash:pop / stash:pop-conflict
that pass through the auditor are tagged metadata.autoSync=true.
Isolated in its own try-catch so an auto-sync failure can't fail the
already-landed merge. Default behavior is mergeAdvanceAutoSync="stash-and-ff";
"off" preserves the legacy surprise behavior.
Backstopped by merger-auto-sync.slow.test.ts: clean-sync snaps both index
and files forward, ff-only with real edits is a no-op, stash-and-ff
preserves untracked locals across the snap, task worktrees on fusion/fn-*
are skipped, empty branch map emits nothing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Standalone implementation of the stash → ff → pop pipeline used by the
upcoming mergeAdvanceAutoSync merger hook. Returns a discriminated union
(clean-pull | stash-pull-pop | stash-pop-conflict | skipped-dirty |
skipped-not-on-branch | failed) and emits structured audit events via an
optional callback. The dashboard's user-triggered Pull keeps using the
existing /api/git/pull integration path; smartPull stays free of AI
conflict resolution so the merger's post-advance auto-sync is safe to run
inline without escalating to a model call.
Backstopped by smart-pull.slow.test.ts (engine-slow lane): clean-pull,
stash-pull-pop, ff-only skip, off-branch skip, audit-emitter exception
tolerance.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Implements a pull-based merge workflow by wiring the merger pull helpers from the engine, extending the git pull and stash routes, and aligning the `MergeAdvanceNotice` and `StashConflictModal` components to gate dismissal on stash drop. The `run-audit` module is updated with pull mutation documenta
Fusion-Task-Id: FN-5419
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Fusion-Task-Id: FN-5419
Removes the branch-recovery CLI surface, orphan-rescue engine primitives, and their associated tests (over 1,500 lines deleted), while restoring a minimal prune-only orphan branch sweep with proper git audit mutation types. Documentation across `cli-reference.md`, `task-management.md`, and `AGENTS.m
Fusion-Task-Id: FN-5329
Implements external integration validation (FN-5321) with a manifest validator scaffold, worktrunk manifest wiring, and an evidence gap detector that runs during spec validation and triage; the reviewer also gates on external integration readiness. Includes tests for manifest, evidence gap, and tria
Fusion-Task-Id: FN-5321
Implements the `mergeIntegrationWorktree` setting (FN-5279) that allows tasks to reuse their own worktree as the integration root instead of spawning a separate one. Steps 1–2 added the settings schema, types, and SettingsModal surface with documentation; Step 3 wired an integration-root resolver th
Fusion-Task-Id: FN-5279
Implements canonical worktrunk binary naming and manifest handling (FN-5320), adding a worktrunk installer that canonicalizes the executable name and manifest data, with documentation updates for architecture and settings, plus test alignments across routes, audit, and worktree acquisition fixtures.
Fusion-Task-Id: FN-5320
Adds a per-machine singleton lock that engages in
ProjectEngineManager.createAndStart() before any engine subsystems
spin up. Two fn dashboard processes can no longer run engines for the
same project on the same host — previously they would share .fusion/
state and corrupt worktrees / task rows for in-process projects.
The guard combines two independent checks:
- A proper-lockfile file at <project>/.fusion/engine.lock with
stale-lock recovery (auto-released on process death).
- A loopback listener on a hashed per-project address — UDS on
POSIX, named pipe on Windows. Stale UDS files are probed and
unlinked before a retry bind.
Failures raise EngineAlreadyRunningError. Both guards are released
from stopAll() and pauseProject(); a release on engine.start()
failure lets retries re-acquire cleanly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
