A rate-limited reviewer filled a task's Chat tab with 14 identical
"Reviewer using model: ..." markers and no review text, hammering an
already-limited provider.
Root cause: the reviewer was the only AI lane that never classified
provider errors, so a 429 became an UNAVAILABLE verdict. With no
validator fallback configured the fallback ladder re-ran the SAME model
instantly, and fn_review_step answered with "code review remains
blocking; retry once" — bounding the loop with prompt text rather than
code. The tool's catch-all also swallowed the error into tool output, so
withRateLimitRetry, UsageLimitPauser and RetryStormError never fired.
- reviewer: throw ReviewerProviderError for usage-limit/transient errors
instead of laundering them into UNAVAILABLE, and never spend the
fallback budget (which bounds bad reviews) on an outage.
- reviewer: absorb flaky-network blips in-lane via withRetry with
jittered backoff; rate limits still escalate immediately.
- executor: re-raise the fatal after the prompt via
throwDeferredReviewerFatal — pi-agent-core converts tool throws into
tool_error results, so a tool cannot throw out of session.prompt().
- executor: give code review a real MAX_CODE_REVIEW_UNAVAILABLE_RETRIES
counter, mirroring the plan/spec limiter.
- reviewer: dedupe the model marker on text, so same-model retries stay
silent while a genuine model switch still emits.
Also fixes the run-on rendering: AgentLogType gains `status` for complete
engine messages. `text` means "streamed delta" and is re-glued with
join(""), which is why N standalone markers rendered as one string. The
split is at the type, not a separator — a separator would reintroduce the
FN-5787/5789/5803 streamed-spacing regression.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Renames the task-detail Activity Current segment to Live and makes expansion available across Activity views.
- relabel Activity Current as Live while preserving the legacy internal current segment routing
- move the Activity expand/collapse control to the shared Activity toolbar for Live, Feed, and Raw Logs
- update expanded Activity layout, docs, tests, and release notes for the shared behavior
Files changed:
.changeset/fn-7325-activity-live-expand.md | 7 ++
docs/dashboard-guide.md | 8 +-
packages/dashboard/app/components/TaskChatTab.tsx | 6 +-
.../dashboard/app/components/TaskDetailModal.css | 53 ++++++++++-
.../dashboard/app/components/TaskDetailModal.tsx | 103 ++++++++++++---------
.../app/components/__tests__/TaskChatTab.test.tsx | 12 +--
.../TaskDetailModal.attachments-and-tabs.test.tsx | 90 ++++++++++++++++--
.../__tests__/TaskDetailModal.rendering.test.tsx | 2 +-
.../components/__tests__/TaskDetailModal.test.tsx | 8 +-
9 files changed, 213 insertions(+), 76 deletions(-)
Fusion-Task-Id: FN-7325
Fusion-Task-Lineage: 1aee503b-ace8-4238-a9f9-3e536a43c1f8
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
The idle session hint banner is suppressed (empty) per user request — idle chats stay sendable but no longer show the banner. Done/active hints remain. Test updated to assert the banner is absent.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Prevent task chat from showing idle guidance while planner sessions are actively working.
- Treat triage/planning task states as active steering sessions when they are not queued, paused, or blocked.\n- Keep queued, awaiting, failed, and paused states on idle guidance even in active columns.\n- Cover inline and expanded planning chat surfaces across empty, populated, and loading transcripts.\n- Update the dashboard guide to document planning and live session bridge steering behavior.\n\nFiles changed:\n docs/dashboard-guide.md | 2 +-\n packages/dashboard/app/components/TaskChatTab.tsx | 24 +++++++---\n .../app/components/__tests__/TaskChatTab.test.tsx | 51 +++++++++++++++++++---\n 3 files changed, 66 insertions(+), 11 deletions(-)
Fusion-Task-Id: FN-6866
Fusion-Task-Lineage: 48c57515-40fa-40c1-ae3b-fec0690bba75
- TaskChatTab: add FNXC:TaskDetailChat prefix/date to the ephemeral
active-session comment, matching the file's comment convention.
- useModalManager: clear stale planning/subtask resume-session id (and
initial plan) when opening a fresh planning/subtask flow, so the modal
no longer reopens into a prior session.
- boardWorkflowsCache: validate cached workflow item shape (id/name/
columns) and taskWorkflowIds value types so a malformed cache entry
can't pass and later crash Board on render.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Reliability (P3): emit an `Auto-recovered:`-prefixed log on the
benign-todo stale-failure clear path so NotificationService
proactively cancels the pending failure timer (recoveredStatus path)
instead of relying only on the fire-time re-check, which is
race-contingent when failureNotificationDelayMs is near 0. Scoped to
the actual-clear path so the common no-failure re-queue isn't
mislabeled as a recovery.
- Project-standards (P3): add the required yyyy-MM-dd-hh:mm stamp to the
new FNXC comments (AGENTS.md FNXC_LOG convention).
- Maintainability (P3): extract the scheduler "queued" waiting marker to
a named SCHEDULER_WAITING_STATUS constant.
- Testing: pin the guard's skip on a clean todo row, assert the
Auto-recovered log fires on the stale-failure path, and add a
paused+unassigned in-progress idle case (paused early-return wins over
the ephemeral active-session path).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Mirror the in-progress fix for in-review: a reviewer/merger runs
ephemerally with no assignedAgentId/checkedOutBy, so an in-review task
in an active review/merge status (reviewing, merging, merging-fix,
fixing) now reads as a live session without an assignment. A null-status
in-review row is awaiting human review, not actively worked, so it stays
assignment-gated and idle.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
isActiveAgentSession required a persistent assignedAgentId/checkedOutBy,
but the scheduler only sets those when ephemeralAgentsEnabled === false
(scheduler.ts:1857). The default is ephemeralAgentsEnabled: true
(settings-schema.ts:351), so an actively-executing in-progress task
never has either field and always read as idle, showing the
"No agent is working on this task right now" hint while an agent was
running. sessionLive only covers live CLI sessions, not ephemeral runs.
Treat assignment as sufficient-but-not-necessary: a non-blocked,
non-"queued" in-progress task is a live agent session on its own.
"queued" (the waiting marker) stays assignment-gated and in-review is
unchanged, so existing FN-6314 idle/active behavior is preserved.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Make task-detail chat disclose when sent guidance will not receive an immediate agent reply.
- Add an idle session hint for non-done tasks without an active steerable agent while keeping the composer sendable.
- Style the idle hint with warning color and expose a stable test id for regression coverage.
- Expand TaskChatTab tests across inline, expanded, empty, populated, paused, and non-live session states.
- Document the idle saved-guidance behavior in the dashboard guide.
Files changed:
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.css | 5 ++
packages/dashboard/app/components/TaskChatTab.tsx | 13 ++-
.../app/components/__tests__/TaskChatTab.test.tsx | 95 +++++++++++++++++++---
4 files changed, 99 insertions(+), 16 deletions(-)
Fusion-Task-Id: FN-6751
Fusion-Task-Lineage: 21f0764d-23db-49ca-b737-3b6a8be7a918
Keep the task chat expand action visible as an icon-only overlay inside the chat view.
- Move the expand/collapse button out of the scrolling transcript and onto the task chat container.
- Style the control as a centered icon-only button with stable overlay positioning.
- Extend TaskChatTab coverage for empty, loading, populated, expanded, and scrolled transcript states.
Files changed:
packages/dashboard/app/components/TaskChatTab.css | 10 +++-
packages/dashboard/app/components/TaskChatTab.tsx | 26 +++++-----
.../app/components/__tests__/TaskChatTab.test.tsx | 58 +++++++++++++++++-----
3 files changed, 68 insertions(+), 26 deletions(-)
Fusion-Task-Id: FN-6425
Fusion-Task-Lineage: 6526eb4a-4be9-472b-9595-c7fcea6971b1
Enable the task-detail Chat composer to submit messages with standard Enter behavior.
- Submit non-empty task chat drafts on plain Enter while preserving Shift+Enter newline entry and IME composition safety.
- Keep Cmd/Ctrl+Enter as a supported send path through the same handler.
- Document the composer keyboard shortcuts and add dashboard tests for steering, refinement, newline, shortcut, and composition behavior.
- Add a patch changeset for the published Fusion package.
Files changed:
.changeset/tiny-tasks-chat-enter.md | 5 +
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.tsx | 13 ++-
.../app/components/__tests__/TaskChatTab.test.tsx | 120 +++++++++++++++++++++
4 files changed, 136 insertions(+), 4 deletions(-)
Fusion-Task-Id: FN-6415
Fusion-Task-Lineage: 7d200bf6-5130-4fb8-b59c-66bccffe4265
Moves the task chat expand control into the transcript as an overlay while preserving accessible labels and state coverage.
- Render the expand/collapse button inside the transcript container instead of a separate toolbar.
- Add tokenized overlay positioning and mobile sizing styles for the transcript expand control.
- Extend TaskChatTab tests across loading, empty, populated, and CSS states to prevent toolbar regressions.
Files changed:
packages/dashboard/app/components/TaskChatTab.css | 34 +++++++++---------
packages/dashboard/app/components/TaskChatTab.tsx | 22 ++++++------
.../app/components/__tests__/TaskChatTab.test.tsx | 42 ++++++++++++++++++++--
3 files changed, 67 insertions(+), 31 deletions(-)
Fusion-Task-Id: FN-6405
Fusion-Task-Lineage: 344d3ad0-bd57-4df2-86dc-deb8cddb76bc
Add a full-modal expansion affordance for task-detail chat conversations.
- Add an expand/collapse toolbar button to the task chat tab with accessible labels and icon states.
- Let the task detail modal switch into a chat-expanded layout and reset that state when leaving chat or entering edit mode.
- Cover the chat toggle and layout behavior with dashboard component tests and document the control.
Files changed:
docs/dashboard-guide.md | 1 +
packages/dashboard/app/components/TaskChatTab.css | 22 +++++
packages/dashboard/app/components/TaskChatTab.tsx | 21 ++++-
.../dashboard/app/components/TaskDetailModal.css | 42 +++++++++
.../dashboard/app/components/TaskDetailModal.tsx | 13 ++-
.../app/components/__tests__/TaskChatTab.test.tsx | 37 ++++++++
.../TaskDetailModal.attachments-and-tabs.test.tsx | 100 +++++++++++++++++++++
7 files changed, 233 insertions(+), 3 deletions(-)
Fusion-Task-Id: FN-6370
Fusion-Task-Lineage: 787300bb-b928-45cf-a5c1-7fed5f375111
Refine the task-detail chat composer so the send action stays narrow and inline with the input.
- Replace the composer placeholder with the steering-focused copy.
- Convert the send button to an accessible icon-only control with loading state labels.
- Keep the send control inline at mobile breakpoints and cover the behavior in tests and docs.
Files changed:
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.css | 14 +++++++----
packages/dashboard/app/components/TaskChatTab.tsx | 11 ++++++---
.../app/components/__tests__/TaskChatTab.test.tsx | 27 ++++++++++++++++++++--
4 files changed, 44 insertions(+), 10 deletions(-)
Fusion-Task-Id: FN-6369
Fusion-Task-Lineage: b7e0717f-4cba-4380-a08a-e01fc12985e3
Adds an in-transcript control for returning to the newest task chat output after reviewing older messages.
- Track whether the task chat transcript is near the bottom and preserve live-follow behavior.
- Render an accessible sticky Latest button when populated transcripts are scrolled up, including mobile styling.
- Cover empty/loading, desktop, mobile, and click-to-jump behavior in TaskChatTab tests.
- Document the Latest jump affordance in the dashboard guide.
Files changed:
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.css | 40 +++++++++++
packages/dashboard/app/components/TaskChatTab.tsx | 40 ++++++++++-
.../app/components/__tests__/TaskChatTab.test.tsx | 82 ++++++++++++++++++++++
4 files changed, 162 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-6359
Fusion-Task-Lineage: 9b4a3533-2969-4f0d-a4de-6ba895662726
Task-detail Chat now accepts guidance even when no steerable session is active and queues it for the next run.
- Keep the task chat composer enabled whenever there is draft text and no send is in flight.
- Replace the blocking no-session hint with active-session versus queued-for-next-session copy.
- Extend TaskChatTab coverage across idle, paused, inactive CLI, and send-in-flight states.
- Quarantine the unrelated flaky dashboard settings route test observed during broad verification.
Files changed:
packages/dashboard/app/components/TaskChatTab.tsx | 21 ++--
.../app/components/__tests__/TaskChatTab.test.tsx | 135 +++++++++++++++++----
packages/dashboard/vitest.config.ts | 5 +-
scripts/lib/test-quarantine.json | 5 +
4 files changed, 133 insertions(+), 33 deletions(-)
Fusion-Task-Id: FN-6354
Fusion-Task-Lineage: b0f0d033-bb4d-4eaa-a15d-f06b82643ade
Display user steering comments alongside agent output and wake immediate-response agents when new messages are sent.
- Render persisted and optimistic user messages in the task chat transcript with mobile styling.
- Propagate updated task detail data after sends and roll back optimistic messages on failures.
- Cover steering route validation, immediate heartbeat wakeups, chat rendering, and workflow alias round-trips.
- Add a patch changeset for the published CLI package.
Files changed:
.changeset/fn-6345-task-chat-user-messages.md | 5 +
packages/dashboard/app/components/TaskChatTab.css | 32 ++++
packages/dashboard/app/components/TaskChatTab.tsx | 170 ++++++++++++++++-----
.../dashboard/app/components/TaskDetailModal.tsx | 8 +-
.../app/components/__tests__/TaskChatTab.test.tsx | 150 +++++++++++++++++-
.../app/components/__tests__/board-mobile.test.tsx | 2 +-
.../__tests__/workflow-flow-mapping.test.ts | 4 +-
.../app/components/workflow-flow-mapping.ts | 4 +-
.../src/__tests__/routes-tasks-ops.test.ts | 86 +++++++++++
9 files changed, 414 insertions(+), 47 deletions(-)
Fusion-Task-Id: FN-6345
Fusion-Task-Lineage: 0355cc67-bd23-4e90-9034-bbaae277cfd6
Task detail chat now renders adjacent text log chunks as continuous bubbles.
- Combine consecutive non-tool, non-thinking chat entries within each agent role group before rendering.
- Preserve tool and thinking segment boundaries while simplifying segment keys for grouped text.
- Add dashboard tests for single, consecutive, and cross-role text bubble behavior.
- Document the text chunk grouping behavior in the dashboard guide.
Files changed:
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.tsx | 28 ++++++++-----
.../app/components/__tests__/TaskChatTab.test.tsx | 48 ++++++++++++++++++++++
3 files changed, 66 insertions(+), 12 deletions(-)
Fusion-Task-Id: FN-6344
Fusion-Task-Lineage: e88f0383-7d91-4272-8c9b-532a382074d4
Allow the chat composer to recognize live CLI sessions as steerable agent sessions.
- Pass live CLI session state from the task detail modal into the chat tab.\n- Keep paused and user-paused tasks blocked even when a CLI session exists.\n- Cover live, ended, and missing CLI session states in chat composer tests.\n\nFiles changed:\n packages/dashboard/app/components/TaskChatTab.tsx | 18 +++--\n .../dashboard/app/components/TaskDetailModal.tsx | 22 ++++--\n .../app/components/__tests__/TaskChatTab.test.tsx | 92 ++++++++++++++++++++--\n 3 files changed, 111 insertions(+), 21 deletions(-)
Fusion-Task-Id: FN-6338
Fusion-Task-Lineage: 7229c059-e094-4be3-bfba-b15d8c5069f9
Reliably settles task-detail chat transcripts to the latest output after load and reactivation.
- Add a bounded animation-frame settle loop that re-pins populated transcripts while late layout growth occurs.
- Cancel pending settle frames on cleanup to avoid stale scroll writes after unmount or rerender.
- Cover async transcript height growth and settle-loop cleanup in TaskChatTab tests.
- Add a patch changeset for the published CLI package.
Files changed:
.changeset/fn-6337-chat-scroll-settle.md | 5 +
packages/dashboard/app/components/TaskChatTab.tsx | 52 +++++++++-
.../app/components/__tests__/TaskChatTab.test.tsx | 108 +++++++++++++++++++++
3 files changed, 163 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-6337
Fusion-Task-Lineage: d31de363-7ee6-4098-ac43-991dc33192e4
Refine task chat transcripts so collapsed tool groups summarize real invocations and expand into paired call/result details.
- Count tool calls by invocation instead of raw tool log rows.
- Show deduped tool names, overflow counts, and error badges in collapsed summaries.
- Pair tool calls with their result or error details when expanded.
- Cover the grouped summary behavior with dashboard tests and documentation.
Files changed:
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.css | 36 +++++--
packages/dashboard/app/components/TaskChatTab.tsx | 116 +++++++++++++++++----
.../app/components/__tests__/TaskChatTab.test.tsx | 105 ++++++++++++++++---
4 files changed, 213 insertions(+), 46 deletions(-)
Fusion-Task-Id: FN-6332
Fusion-Task-Lineage: 7c14b76c-dcaa-4227-8393-cb24f99b765d
Task Chat can now steer active assigned sessions while tasks are being reviewed or merged.
- Permit composer steering for in-review reviewing, merging, merging-fix, and fixing statuses when an agent is assigned or checked out.
- Keep paused, user-paused, unassigned, todo, and done tasks disabled with clearer active-session messaging.
- Cover in-review steering and disabled-session states in TaskChatTab tests and update dashboard documentation.
Files changed:
docs/dashboard-guide.md | 2 +-
packages/dashboard/app/components/TaskChatTab.tsx | 13 +++--
.../app/components/__tests__/TaskChatTab.test.tsx | 61 ++++++++++++++++++++--
3 files changed, 67 insertions(+), 9 deletions(-)
Fusion-Task-Id: FN-6314
Fusion-Task-Lineage: 42c0f4f7-58f5-4e0c-837f-9f4b7c497fa3
