Code review (8 reviewers) fixes:
- P1: embedded board task-detail now passes onRequestClose so delete/merge/retry dismiss the panel (no ghost task).
- P1: RightDock + TerminalModal drag handlers add pointercancel + unmount teardown (no leaked document listeners / rAF / stuck userSelect); remove dead onOpenChange prop.
- Planning slot DOM-poll interval now caps (self-cancels on mobile); heartbeat slider persist debounced + mounted-guarded.
- Cleanup: remove dead ViewHeader-migration CSS (Skills/Insights), extract shared GithubIcon, move Activity Log embedded CSS to ActivityLogModal.css, FNXC date-format fixes, AGENTS lazy-view note.
- Update stale RightDock roster tests + LeftSidebarNav 'Compound Eng' test to current behavior.
Live UI tweaks:
- Default load lands on board, never the Command Center Dashboard.
- View Board/View Agents moved to the Command Center Overview tab (under the live-activity strip).
- Heartbeat card full-width with spaced, wrapping controls.
- Dev Server panel scrolls in the dock; ChatView right-pane title takes the full line.
- Files pop-out renders deterministic left-right two-pane.
- Mailbox list pane narrower + narrow by default; Add Goal button height matches the Compound stage button; Memory Working-Memory tab no longer overlaps; Skills view fills full width.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Compound Engineering plugin view now renders the dashboard's shared ViewHeader (Sparkles icon + title) so it matches the other main-content views. Expose ViewHeader via the dashboard exports map; resolve it in the plugin via an ambient interop declaration (no host runtime dependency). Tests updated (plugin suite green).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
dist-freshness.test.ts reads the plugin's compiled dist/settings.js and
dist/session/orchestrator.js to guard against stale dist (FN-6596), but the
plugin had no pretest build and was missing from ensure-test-artifacts.mjs.
On a fresh CI checkout dist/ does not exist, so the guard threw "dist/ is
missing" — failing the non-blocking Full Suite on every main commit.
Register the plugin's required artifacts in ensure-test-artifacts.mjs and add
a `pretest` hook that builds them, matching the dependency-graph / hermes /
openclaw plugins. Verified locally: with dist/ absent, `pnpm --filter
@fusion-plugin-examples/compound-engineering test` now builds dist via the
pretest and all 192 plugin tests pass (incl. the two dist-freshness cases).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Restore the compound-engineering broad lane tests after the timeout could not be reproduced on the stabilized shared test infrastructure.
- Re-enable the compound-engineering sync and work-bridge tests by clearing their Vitest quarantine excludes.
- Remove the stale quarantine ledger entries now that the broad package lane stayed stable under verification.
Files changed:
plugins/fusion-plugin-compound-engineering/vitest.config.ts | 10 ++++------
scripts/lib/test-quarantine.json | 13 +------------
2 files changed, 5 insertions(+), 18 deletions(-)
Fusion-Task-Id: FN-6606
Fusion-Task-Lineage: f357c626-c181-44a7-a463-c53644566ca1
Normalize spawned Vitest processes to NODE_ENV=test so React/jsdom lanes do not inherit release-shell production mode. Split the compound-engineering plugin Vitest projects so Node-only setup and teardown only run in Node lanes, and quarantine the remaining broad-lane CE timeout flakes under the deletion ratchet.
Quarantine compound-engineering timeout flakes from the broad test workflow.
- Add the compound-engineering orchestrator and skill-wiring tests to the quarantine ledger.
- Exclude the quarantined tests from the compound-engineering node Vitest project without changing timeouts or retries.
- Document the quarantine requirement next to the Vitest excludes.
Files changed:
.../fusion-plugin-compound-engineering/vitest.config.ts | 15 ++++++++++++++-
scripts/lib/test-quarantine.json | 10 ++++++++++
2 files changed, 24 insertions(+), 1 deletion(-)
Fusion-Task-Id: FN-6587
Fusion-Task-Lineage: 5aeb0202-8330-4a93-bdab-675c81b9cb54
The non-blocking Full Suite tier on main was red on shards 2 and 4:
- roadmap-store schema assertion lagged core's SCHEMA_VERSION bump to 117
(landed in FN-6277), so it still expected 116.
- useCeSessions "cancel surfaces a transport error" failed deterministically:
a session with an in-flight status keeps the poll fallback running, and a
successful background list refresh called setError(undefined), wiping the
cancel error before it could be observed. Background refreshes (poll + push)
now leave action errors intact; only user-initiated/initial refreshes clear.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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>
In a Fusion workflow step (FUSION_WORKFLOW_STEP set), the skills now:
- emit a ===FUSION_AWAIT_INPUT=== block instead of calling AskUserQuestion
into the void (Fusion pauses the task + surfaces it on the card; U6/U7),
and take the assumptions path when FUSION_HEADLESS is set;
- dispatch sub-agents via fn_spawn_agent with systemPromptOverride read
from FUSION_CE_AGENTS_DIR/<persona>.md (U2/U3), falling back to inline
single-agent work when the dir/def is absent.
This is the keystone that makes the U1/U2/U3 plumbing actually used.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Vendor the 43 ce-* persona definitions (from compound-engineering 3.9.4),
add installBundledCeAgents() mirroring the skill installer (pinned,
plugin-local, idempotent, never a global ~/.claude/agents), install them
in onLoad, and expose the install dir to executor/step sessions via an
executorRuntimeEnv hook (FUSION_CE_AGENTS_DIR).
Together with U2's systemPromptOverride this gives the lightweight
subagent path: a CE skill reads a persona def from FUSION_CE_AGENTS_DIR
and passes its body to fn_spawn_agent. Installer test added (19 plugin
tests green).
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>
Use per-invocation Vitest worker roots to keep compound-engineering tests from timing out on stale temp fixtures.
- Allocate a fresh FUSION_TEST_WORKER_ROOT during Vitest global setup and remove it during teardown.
- Preserve per-worker fallback root creation when global setup is not available.
- Clean compound-engineering harness project roots on close and cover the setup invariants with regression tests.
Files changed:
packages/core/src/__test-utils__/vitest-setup.ts | 20 +++++++---
.../core/src/__test-utils__/vitest-teardown.ts | 38 +++++++++++--------
.../src/__tests__/_harness.ts | 7 +++-
.../src/__tests__/setup-invariant.test.ts | 43 ++++++++++++++++++++++
4 files changed, 85 insertions(+), 23 deletions(-)
Fusion-Task-Id: FN-6282
Fusion-Task-Lineage: 8b842dd0-4f51-44de-b2db-8e8bfa97239c
Expose the dashboard file viewer to plugin views and wire Compound Engineering artifacts to it.
- add an openFile callback to the dashboard plugin view context and pass through the app host implementation
- switch Compound Engineering artifact Open actions to the built-in file viewer with matching styling and coverage
- document the new plugin context capability and add a published changeset for the CLI package
Files changed:
.changeset/ce-docs-built-in-viewer.md | 5 +++
docs/PLUGIN_AUTHORING.md | 2 +-
packages/dashboard/app/App.tsx | 1 +
packages/dashboard/app/plugins/types.ts | 2 ++
.../src/dashboard-interop.d.ts | 1 +
.../src/dashboard/CompoundEngineeringView.css | 16 +++++++++
.../src/dashboard/CompoundEngineeringView.tsx | 24 +++++++-------
.../__tests__/CompoundEngineeringView.test.tsx | 38 ++++++++++++++++++++++
8 files changed, 76 insertions(+), 13 deletions(-)
Fusion-Task-Id: FN-6119
Fusion-Task-Lineage: 8feb461c-b1d2-4059-9aa1-ffc756d15196
Keep the Compound Engineering interview transcript full-width and pinned to the latest messages when appropriate.
- expand the Compound Engineering view and transcript containers so the interview flow can fill the available panel width and height
- auto-scroll the transcript on first load and while new messages arrive if the viewer is still following the bottom
- preserve user scroll position when they scroll away from the bottom and cover the transcript follow behavior with tests
Files changed:
plugins/fusion-plugin-compound-engineering/src/dashboard/CeFlow.tsx | 53 ++++++++-
plugins/fusion-plugin-compound-engineering/src/dashboard/CompoundEngineeringView.css | 28 ++++-
plugins/fusion-plugin-compound-engineering/src/dashboard/__tests__/CeFlow.test.tsx | 132 ++++++++++++++++++++-
3 files changed, 207 insertions(+), 6 deletions(-)
Fusion-Task-Id: FN-6120
Fusion-Task-Lineage: 1f7152f3-5af0-4db3-a767-96bca06b93c3
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>
The store/orchestrator were already multi-session (independent rows + live
handles per session); this surfaces it end to end:
- Sessions panel in the dashboard view: lists every session with stage,
status badge ("needs your input" for awaiting_input), and last activity;
stays visible while a flow is open so switching is one click. Closing a
flow returns to the overview without stopping the session.
- useCeSession.open(): adopt an existing session (pins its projectId for
answer/resume/poll); useCeSessions list hook with push-event refresh and
poll fallback while any session is mid-turn.
- DELETE /sessions/:id + orchestrator.discard(): dispose the live handle
before deleting the row (pipeline-link rows kept for task provenance);
Discard affordance on settled sessions.
- Tests: cross-session independence through one orchestrator, store delete,
route list/delete, hook open/list/remove/push/poll, view panel
open/switch/discard. 116 tests green; plugin + dashboard tsc clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A new workspace-acyclicity invariant on main (run via the PR merge) flagged
compound-engineering -> @fusion/dashboard -> compound-engineering: the plugin is
listed in @fusion/dashboard's deps (for view loading) AND declared @fusion/dashboard
as a runtime dependency, which the cycle check (deps+devDeps) and the
'bundled plugins must not depend on host packages' check both reject.
The plugin's only @fusion/dashboard use is the type-only PluginDashboardViewContext
import. Drop the @fusion/dashboard dependency and resolve that type via an ambient
dashboard-interop.d.ts + tsconfig paths mapping (the fusion-plugin-dependency-graph
interop pattern). Breaks the cycle; the host passes the real context at runtime.
safeParse() previously only caught JSON syntax errors, so a semantically-wrong
but valid column ('null', '{}', a string) would rehydrate a non-array
conversationHistory that later crashed appendHistory's spread (and a bogus
currentQuestion). safeParse now takes a shape validator and falls back to []/null
on invalid shapes too. + regression test covering 'null'/'{}'.
- session-store: rowToSession parses JSON columns via a safeParse helper, so a
corrupted currentQuestion/conversationHistory column degrades to null/[] instead
of throwing and crashing reads of an otherwise-valid row (+regression test)
- session-routes: validate the ?status= list filter against CE_SESSION_STATUSES
(asCeSessionStatus) instead of casting an arbitrary query string with 'as never'
- _harness: makeScriptedSession throws on an empty script rather than yielding
undefined, surfacing test mistakes loudly
- useCeSession tests: use fake timers (advanceTimersByTimeAsync) instead of real
setTimeout waits for deterministic poll-interval assertions
Skipped: 3 doc nits in src/skills/ce-*/references/** — those are pinned upstream
ce-* skill copies (KTD5 vendored snapshot), not this repo's content.
Replaces polling-only with a true server-push seam (any plugin benefits):
- core: createRouteContext accepts an emitEvent override (default still logs)
- dashboard: emitPluginCustomSseEvent forwards a plugin's ctx.emitEvent calls to
connected /api/events clients as a project-scoped 'plugin:custom' event; the
plugin route context's emitEvent is wired to it
- dashboard: PluginDashboardViewContext gains subscribePluginEvents so views
consume push via a host capability (no raw EventSource, no deep app import)
- CE view subscribes its session to push and refetches on each event; polling
stays as the fallback when push isn't wired or an event is missed
Also: skill-reachability test installs into a temp dir (no repo-dir writes).
Tests: dashboard sse +2 (plugin:custom relay + project scoping), plugin 99.
The session's owning store (and its live in-process handle) is selected per
request by projectId. start() sent projectId but answer/resume/getSession did
not, so any project-scoped session broke on the first answer (a different store
resolved → session not found / no live handle). The client now captures the
start projectId and reuses it on every subsequent call. Closes the multi-project
session-identity residual.
