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>
Replace the fixed generic "Would you like to go deeper?" theme buckets with AI-proposed, plan-specific topics, falling back to the existing regex-derived themes when the AI supplies none.
- Add optional PlanningSummary.deepeningThemes (id/label/description) to the completion payload contract in @fusion/core.
- Instruct the planning AI prompt to propose 2-5 concrete, plan-aligned deepening themes tied to the plan's actual title/description/deliverables.
- Add normalizeDeepeningThemes to validate/sanitize untrusted AI-supplied theme data (dedupe, cap at 6, trim, drop malformed entries) and omit the field entirely when nothing valid remains.
- Update buildDeepeningCheckpointOptions to prefer AI-supplied deepeningThemes over the generic CHECKPOINT_THEME_CANDIDATES regex fallback, keeping the reserved 'Proceed to final plan' option first and deterministic in both branches.
- Update docs/dashboard-guide.md to describe the new plan-specific deepening behavior and its generic fallback.
- Add unit test coverage for the new normalization and checkpoint-option-building logic.
- Add a minor changeset for @runfusion/fusion.
Files changed:
.changeset/fn-7616-planning-deepening-themes.md | 7 +
docs/dashboard-guide.md | 3 +-
packages/core/src/types.ts | 11 ++
.../planning-interview-formatters.test.ts | 176 +++++++++++++++++++++
.../src/__tests__/routes-planning.test.ts | 61 +++++++
packages/dashboard/src/planning.ts | 86 +++++++++-
6 files changed, 341 insertions(+), 3 deletions(-)
Fusion-Task-Id: FN-7616
Fusion-Task-Lineage: f6c1d0d7-f0ca-45c9-85cd-d57958ad94c7
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Moving a card out of a non-legacy workflow column — e.g. Coding (Ideas)
"ideas" → "todo" — was rejected with "Invalid transition: 'ideas' → 'todo'.
Valid targets: none".
Workflow columns graduated to always-on but moveTaskInternal's compat-flag
legacy branch (the default path, since no experimental flag is emitted)
validated every move against the legacy VALID_TRANSITIONS table, which is
keyed only by the built-in column ids. Default-workflow moves survived by
coincidence (its ids ARE the legacy ids); a task in a custom column had no
key so every move was rejected.
The legacy branch now resolves a non-legacy source column's targets from the
task's own workflow adjacency (resolveAllowedColumns), while keeping the
legacy bare-Error contract intact for legacy columns (transition-parity /
characterization suites unchanged). Adds a regression test covering the
ideas -> todo -> in-progress -> in-review chain and non-adjacent rejection.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reorders task-definition prompt templates so the Before -> After Transformation section appears before other sections, making the expected change visible first.
- Move the Before -> After Transformation section ahead of other sections in agent-prompts.ts task-definition templates
- Update docs/task-management.md to reflect the new section order
- Add/extend tests in agent-prompts.test.ts and triage.test.ts covering the new ordering
- Add changeset fn-7593-before-after-top.md documenting the change
Files changed:
.changeset/fn-7593-before-after-top.md | 7 +++++++
docs/task-management.md | 2 +-
packages/core/src/__tests__/agent-prompts.test.ts | 20 ++++++++++++++++++++
packages/core/src/agent-prompts.ts | 20 +++++++++++++-------
packages/engine/src/__tests__/triage.test.ts | 17 +++++++++++++++++
5 files changed, 58 insertions(+), 8 deletions(-)
Fusion-Task-Id: FN-7593
Fusion-Task-Lineage: d0d5eb4d-2fe0-456c-b061-5c078b78911b
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds a discoverable built-in Brainstorming workflow composing the ask-user + exit-gate reach-out loop ahead of the standard coding plan/execute/review/merge spine, plus a WorkflowNodeEditor fix so clearing the ask-user question textarea deletes the config key instead of persisting an empty string.
- Add packages/core/src/builtin-brainstorming-workflow-ir.ts registering builtin:brainstorming (non-default, default-enabled): ask-user -> refine prompt -> exit-gate-on-approval ahead of the unmodified Coding plan/execute/review/merge spine
- Wire the new builtin into packages/core/src/builtin-workflows.ts and extend the builtin-workflows parity test suite
- Add builtin-brainstorming-workflow-ir.test.ts covering the new workflow's IR shape and validation
- Fix WorkflowNodeEditor.tsx ask-user question textarea onChange to delete the config.question key when cleared to empty (validateAskUserAndExitGateNodes rejects present-but-empty question; only an absent key falls back to the engine default)
- Update docs/workflow-steps.md to document builtin:brainstorming as a selectable built-in composition
- Add .changeset/fn-7584-brainstorming-builtin.md (minor, feature)
Files changed:
.changeset/fn-7584-brainstorming-builtin.md | 7 ++
docs/workflow-steps.md | 2 +-
.../builtin-brainstorming-workflow-ir.test.ts | 79 ++++++++++++++++
.../core/src/__tests__/builtin-workflows.test.ts | 66 +++++++++++++
.../core/src/builtin-brainstorming-workflow-ir.ts | 103 +++++++++++++++++++++
packages/core/src/builtin-workflows.ts | 46 +++++++++
.../app/components/WorkflowNodeEditor.tsx | 18 +++-
7 files changed, 319 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-7584
Fusion-Task-Lineage: 2c0258c2-9a35-403a-8688-ee49393a7231
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
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>
decidePlannerRecovery fell through to inject_guidance for any non-failed
executor/workflow-gate signal, including the healthy `progressing` signal.
Under autonomous oversight this dispatched steering into the live agent of
every healthy task — flipping the card badge to "recovering", burning a
bounded-attempt slot, and consuming AI usage for no reason.
- Only problem signals (`stuck`/`blocked`, plus the existing `failed` path)
now trigger autonomous steering; healthy (`progressing`/`complete`) and
human-wait (`awaiting-human`) signals return `none`.
- PlannerRecoveryController.tick clears stale attempt/last-action records for
a (taskId, stage) once its signal is healthy, so a recovered task drops
from "recovering" back to "watching" and a later problem gets a fresh budget.
- PlannerOverseerMonitor dedupes the activity-feed heartbeat: an unchanged
(stage, signal, reason) observation logs once per change, not every tick.
Invariant tests added across all signals for both fall-through stages.
Fusion-Task-Id: FN-7577
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Manual plan approval now skips re-asking for approval when a re-specification produces an identical plan to one already approved.
- Add nullable Task.approvedPlanFingerprint field with DB migration 139 to track the approved PROMPT.md fingerprint
- Skip re-parking at awaiting-approval when replan/plan-review-retry/self-healing rebound yields the same plan fingerprint as before
- Require fresh approval when the plan content changes or when a plan is rejected
- Leave Release Authorization, Workflow Plan Review, and auto-approve-all behavior unchanged
- Add/extend tests across core (db, plan-approval, store-persistence), engine (triage), and dashboard (routes-github) to cover fingerprint comparison and idempotent re-approval
- Update docs (settings-reference.md, workflow-steps.md) to describe the idempotent approval behavior
- Add changeset for @runfusion/fusion (patch)
Files changed:
.changeset/fn-7569-plan-approval-idempotent.md | 7 +
docs/settings-reference.md | 2 +-
docs/workflow-steps.md | 2 +
packages/core/src/__tests__/db.test.ts | 54 +++++++
packages/core/src/__tests__/plan-approval.test.ts | 31 +++-
.../core/src/__tests__/store-persistence.test.ts | 39 +++++
packages/core/src/db.ts | 22 ++-
packages/core/src/index.ts | 2 +-
packages/core/src/plan-approval.ts | 23 +++
packages/core/src/store.ts | 20 ++-
packages/core/src/types.ts | 13 ++
.../dashboard/src/__tests__/routes-github.test.ts | 69 +++++++-
.../src/routes/register-task-workflow-routes.ts | 37 ++++-
packages/engine/src/__tests__/triage.test.ts | 178 ++++++++++++++++++++-
packages/engine/src/triage.ts | 58 +++++--
15 files changed, 527 insertions(+), 30 deletions(-)
Fusion-Task-Id: FN-7569
Fusion-Task-Lineage: 7d3855ae-6f45-4571-90db-cf1ae3b541dd
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Replace the raw kebab-case planner-overseer badge state and bare tooltip with a human-readable label and an explanatory tooltip built from the existing runtime snapshot.
- Add packages/dashboard/app/components/plannerOverseerBadge.ts: pure, type-only helper exposing plannerOverseerStateLabel() and plannerOverseerBadgeTooltip(), composing the tooltip from reason/watchedStage/signal/pendingConfirmation with graceful fallbacks
- Re-export PlannerOverseerState and PlannerOverseerRuntimeSnapshot as type-only from packages/core/src/types.ts so the dashboard's @fusion/core vite alias can resolve them
- Update TaskCard.tsx to render the new label/tooltip instead of the raw state string
- Add unit tests for the new badge helper and extend TaskCard tests for the updated label/tooltip behavior
- Add a patch changeset documenting the operator-facing fix
Files changed:
.changeset/fn-7563-overseer-badge-explanation.md | 7 ++
packages/core/src/types.ts | 7 ++
packages/dashboard/app/components/TaskCard.tsx | 7 +-
.../app/components/__tests__/TaskCard.test.tsx | 72 ++++++++++++++
.../__tests__/plannerOverseerBadge.test.ts | 103 ++++++++++++++++++++
.../app/components/plannerOverseerBadge.ts | 104 +++++++++++++++++++++
6 files changed, 296 insertions(+), 4 deletions(-)
Fusion-Task-Id: FN-7563
Fusion-Task-Lineage: 64ed011b-5486-4272-abd1-a6123c60785f
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Disambiguate release-authorization approval holds from manual plan-approval holds so auto-approve no longer appears broken.
- Add `Task.awaitingApprovalReason` (`"release-authorization" | null`) to distinguish the release-authorization gate from the independent manual plan-approval gate, both of which set `status: "awaiting-approval"`.
- Stamp `awaitingApprovalReason: "release-authorization"` when the release gate blocks a task, and explicitly clear it (`null`) when the manual plan-approval gate parks the task, so a stale reason never survives a replan.
- Add DB migration/persistence support for the new column in `db.ts`/`store.ts`/`types.ts`.
- TaskCard/TaskDetailModal now render a distinct status for release-authorization holds and suppress the generic manual Approve/Reject affordance for them.
- Add i18n string and docs updates (`settings-reference.md`, `workflow-steps.md`) plus a changeset.
- Extend regression tests in db, triage, TaskCard, and TaskDetailModal to cover the new reason field and disambiguated UI.
Files changed:
$(git diff --cached --stat)
Fusion-Task-Id: FN-7559
Fusion-Task-Lineage: 0b37cbf0-40a4-4165-8088-482ed365ba19
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds an AI-undo fallback to the revert route: when a git-based revert conflicts or is unsupported, an ordinary board task is created to perform the undo via AI instead of a forced/failed git write.
- POST /tasks/:id/revert now accepts an optional `{ mode?: "git" | "ai" | "auto" }` body (default "auto"); unknown values reject with 400.
- "git" preserves the FN-7523 git-only contract unchanged; "ai" always creates the AI-undo task; "auto" tries git first and falls back to AI only on a conflicting or unsupported (e.g. workspace) result — needsHuman (autoMerge:false) never triggers the fallback.
- New engine helpers in task-revert.ts: `createAiUndoTask`, `buildAiUndoTaskDescription`, `REVERT_OF_METADATA_KEY`, plus `AiUndoTaskResult`/`CreateAiUndoTaskDeps` types, exported from packages/engine/src/index.ts.
- The AI-undo task is created via the normal triage-column `store.createTask` path with no dependency on the source task, referencing the source task's mission, id, and landed files, and instructing an undo commit using the `revert(FN-xxxx): ...` convention.
- New core `TaskStore.findOpenRevertTaskForSource` backs an idempotency guard: a repeated call while an AI-undo task is still open returns the same `createdTaskId` with `alreadyOpen: true` instead of creating a duplicate.
- Updated docs/task-management.md's revert section to document the git path + AI-undo fallback contract.
- Added a minor changeset for the @runfusion/fusion release notes.
- Added/extended tests: packages/engine/src/__tests__/task-revert-ai-undo.test.ts (new) and packages/dashboard/src/__tests__/task-revert-route.test.ts (extended) covering mode validation, auto-fallback-on-conflict, forced "ai" mode, and the duplicate-open-task guard.
Files changed:
.changeset/fn-7524-ai-undo-revert.md | 7 +
docs/task-management.md | 13 +-
packages/core/src/store.ts | 31 +++++
packages/dashboard/src/__tests__/task-revert-route.test.ts | 143 ++++++++++++++++++++-
packages/dashboard/src/routes/register-task-workflow-routes.ts | 75 +++++++++--
packages/engine/src/__tests__/task-revert-ai-undo.test.ts | 114 ++++++++++++++++
packages/engine/src/index.ts | 5 +
packages/engine/src/task-revert.ts | 117 ++++++++++++++++-
8 files changed, 487 insertions(+), 18 deletions(-)
Fusion-Task-Id: FN-7524
Fusion-Task-Lineage: 64dfedcf-c286-4c46-8cf8-51ec5e668bf7
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Changes the project-wide plan approval default from deferring to per-workflow settings to auto-approving all task plans, so new/unset projects skip the manual awaiting-approval gate by default.
- Change DEFAULT_PROJECT_SETTINGS.planApprovalMode default from "workflow" to "auto-approve-all" in settings-schema.ts, with FNXC comments documenting the requirement change
- Update ProjectSettings.planApprovalMode JSDoc in types.ts to reflect the new default
- Update useAppSettings hook's initial state and hydration fallback to default to "auto-approve-all" while still honoring an explicit stored "workflow" value
- Update MergeSection UI: move the "(default)" label from the "Use workflow setting" option to "Auto-approve all tasks", keeping the select's fallback value in sync
- Update settings-reference.md docs and i18n locale/resource strings to match the new default label
- Update existing tests (MergeSection legacy auto-merge cleanup, settings default descriptions, useAppSettings) to assert the new default, and add coverage for the updated hydration/fallback behavior
- Add changeset fn-7557-plan-auto-approve-default.md documenting the behavior change
Files changed:
.changeset/fn-7557-plan-auto-approve-default.md | 7 +++++
docs/settings-reference.md | 2 +-
packages/core/src/settings-schema.ts | 6 +++-
packages/core/src/types.ts | 3 ++
.../dashboard/app/components/SettingsModal.tsx | 3 +-
.../components/settings/sections/MergeSection.tsx | 9 ++++--
.../MergeSection.legacy-automerge-cleanup.test.tsx | 4 +--
.../settings-default-descriptions.test.tsx | 3 +-
.../app/hooks/__tests__/useAppSettings.test.ts | 35 +++++++++++++++++++---
packages/dashboard/app/hooks/useAppSettings.ts | 12 ++++++--
packages/i18n/locales/en/app.json | 4 +--
packages/i18n/src/resources.d.ts | 2 +-
12 files changed, 71 insertions(+), 19 deletions(-)
Fusion-Task-Id: FN-7557
Fusion-Task-Lineage: 7dcfe339-6088-4ebc-8387-eb81258a693d
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Fix agent-created artifacts not showing live in the dashboard because a second TaskStore instance (e.g. engine writing while dashboard polls) never detected or re-emitted artifact:registered for rows it did not insert itself.
- Track a per-instance lastArtifactRowId cursor seeded from the max artifacts rowid at watch() startup
- In checkForChanges(), pick up artifact rows with rowid > cursor written by other instances and re-emit artifact:registered, advancing the cursor
- Advance the cursor on local inserts (insertArtifactRow) so this instance never double-emits its own writes
- Call db.bumpLastModified() in registerArtifact() so other instances' pollers actually look at the artifacts table
- Add regression tests covering cross-instance artifact registration in core store and dashboard artifacts route integration
- Add changeset and doc note for the cross-instance live-refresh fix
Files changed:
.changeset/fn-7544-artifact-cross-instance-live-refresh.md | 7 ++
docs/storage.md | 1 +
packages/core/src/__tests__/artifacts.test.ts | 85 +++++++++++++++
packages/core/src/store.ts | 63 ++++++++++-
packages/dashboard/src/routes/__tests__/artifacts-route-integration.test.ts | 120 ++++++++++++++++++++-
5 files changed, 274 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-7544
Fusion-Task-Lineage: 76570505-082e-4f9a-8b06-29591c06c435
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds a canonical emission layer over recordPlannerIntervention so overseer decision points (observation, steering, recovery attempt, retry, confirmation, escalation) emit consistent overseer:intervention run-audit events without inlining action/outcome logic at each call-site.
- Add packages/core/src/planner-overseer-events.ts with emitOverseerObservation, emitOverseerSteering, emitOverseerRecoveryAttempt, emitOverseerRetry, emitOverseerConfirmation, and emitOverseerEscalation, each fixing its category's intervention action/default outcome and delegating to recordPlannerIntervention.
- Export the new emitters and OverseerEventInput type from packages/core/src/index.ts.
- Add unit tests covering each emitter's action/outcome mapping and metadata pass-through.
- Add a minor changeset documenting the new run-audit emission facade for planner-overseer events.
- Update docs/architecture.md's Run Audit API section to describe the FN-7520 emission facade and its relationship to FN-7519's overseer:intervention mutation type.
Files changed:
.changeset/fn-7520-planner-overseer-events.md | 7 +
docs/architecture.md | 2 +-
packages/core/src/__tests__/planner-overseer-events.test.ts | 236 +++++++++++++++++++++
packages/core/src/index.ts | 9 +
packages/core/src/planner-overseer-events.ts | 128 +++++++++++
5 files changed, 381 insertions(+), 1 deletion(-)
Fusion-Task-Id: FN-7520
Fusion-Task-Lineage: 85e0d761-e4f3-437e-abe2-031e6cf89c1c
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Introduces a persisted planner-overseer intervention timeline surfaced in the task-detail Planner Oversight cluster, recording stage, reason, action taken, outcome, attempt count/limit, and source links for each intervention.
- Add core `PlannerInterventionEntry` type plus `recordPlannerIntervention`/`getPlannerInterventionTimeline` helpers that persist entries via the run-audit store under the `overseer:intervention` mutation
- Add `PlannerInterventionTimeline` dashboard component rendering the timeline (stage/reason/action/outcome/attempts/links) with associated styles
- Wire the new API route/legacy handler and TaskDetailModal integration to expose and render the timeline
- Add unit tests for the core helpers and the new UI component
- Add changeset for the new minor feature and update architecture/dashboard-guide docs
Files changed:
$(cat /tmp/diffstat_7519.txt)
Fusion-Task-Id: FN-7519
Fusion-Task-Lineage: 3c4fcda3-9eb2-46d3-b142-b0c7d6334cd0
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Branch-group completion no longer silently drops archived-but-unlanded members, which previously let genuinely-incomplete groups be flagged complete and promoted.
- listTasksByBranchGroup now scans with includeArchived:true so archived members stay counted in the group's total instead of dropping out silently
- ArchivedTaskEntry gains a persisted mergeDetails snapshot so an archived member that had already landed is still distinguished from one that never landed
- store.ts archival paths (task->archive projection) now carry mergeDetails through so isBranchGroupMemberLanded keeps working post-archival
- Added regression coverage in branch-group-store.test.ts and group-merge-coordinator.test.ts for archived-landed and archived-unlanded gating
- Added changeset documenting the fix as a patch-level bug fix
Files changed:
.changeset/fn-7534-branch-group-archived-member.md | 7 +
docs/dashboard-guide.md | 2 +
packages/core/src/__tests__/branch-group-store.test.ts | 77 +++++++++++
packages/core/src/store.ts | 30 ++++-
packages/core/src/types.ts | 11 ++
packages/engine/src/__tests__/group-merge-coordinator.test.ts | 148 ++++++++++++++++++++-
6 files changed, 273 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-7534
Fusion-Task-Lineage: 510af857-ce08-49a0-a2a1-41b3ad473804
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
## The bug
`GET /api/command-center/tokens` documents and accepts `groupBy=task`,
but the `task` dimension was never actually wired through the
aggregator. Four enumeration sites all stopped at `model | provider |
node | agent`:
- `TokenGroupBy` (core `token-analytics.ts`) did not include `"task"`.
- `groupKeyFor()` had no `case "task"`.
- `VALID_GROUP_BY` (dashboard route) rejected the value, so
`resolveGroupBy()` returned `undefined`.
- `groupAttributes()` (core `otel-metrics.ts`) emitted no attribute for
it.
Net effect: a caller asking for a per-task rollup silently fell back to
**ungrouped grand totals** — the per-task breakdown returned zero
groups, even though every task carries `tokenUsage*` and the data was
right there.
## The fix
Thread `"task"` through all four sites (5 functional lines + doc/test):
- Add `"task"` to the `TokenGroupBy` union — this makes the two `switch`
statements **compiler-exhaustive**, so `tsc` forces the two new cases
(no silent gaps).
- `groupKeyFor`: task rows group by their task id; chat rows have no
task and return `null`, mirroring the existing `node` case.
- `groupAttributes`: emit `task.id` for OTLP export, matching `node.id`
/ `agent.id`.
- `VALID_GROUP_BY`: accept `"task"`.
No schema or migration change — the task id is already on the row.
## Verification
- `pnpm --filter @fusion/core typecheck` and `@fusion/dashboard
typecheck` — clean.
- Extended the existing `groups by provider, node, agent` core test with
a `groupBy: "task"` assertion (two tasks → two groups keyed by task id,
100 / 200 tokens). Full suites green: **core 25/25**, **dashboard
325/325**.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added task-based token analytics grouping, alongside existing grouping
options.
* Analytics views and metrics now include task-level breakdowns when
available.
* **Bug Fixes**
* Improved grouping behavior so task totals are reported correctly in
analytics results.
* **Documentation**
* Updated supported analytics options to reflect task grouping in
endpoint and metric descriptions.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## What
Adds a new built-in workflow **Coding (Ideas)** — a capture-first
variant of the default coding pipeline that puts a manual **Ideas (no
AI)** intake in front of a merged **Todo** (planner + capacity) column.
The board becomes five stages, each staffed by a distinct role:
```
Ideas (no AI) → Todo (planner) → In-progress (coder) → In-review (reviewer) → Done
```
## Why
The current board parks un-worked cards in a passive **Todo** column
where no agent is active. Operators asked for a way to (1) capture ideas
without the engine auto-planning them, and (2) collapse the triage/todo
split so every visible column has an agent working it — planning now
happens *in* Todo. A "Ready" badge distinguishes planned cards waiting
for a capacity slot from freshly promoted unplanned ones.
## How it works
1. **Create** a task against Coding (Ideas) → it lands in **Ideas**
(`autoTriage:false` intake). The triage service ignores it — no AI runs.
2. **Start** (button on the card, or drag) moves it to **Todo**. The
triage poll discovers the unplanned card (bootstrap-stub PROMPT.md) and
plans it in place.
3. While planning the card shows **Planning**; once the spec is written
it shows **Ready** and waits for an in-progress slot under the normal
capacity hold.
4. From Todo onward the graph is identical to the default Coding
workflow (stepwise execution → optional code review → merge).
## Engine changes
| Surface | Change |
|---|---|
| `createTask` (`store.ts`) | Lands cards in the workflow's intake
column (`resolvedEntryColumn`) instead of hardcoding `"triage"`. Default
workflow is byte-identical (intake resolves to `"triage"`).
Bootstrap-prompt check generalized to all pre-planning columns. |
| Triage poll (`triage.ts`) | Also discovers unplanned `todo` tasks
(bootstrap-stub prompt); `finalizeApprovedTask` skips the redundant
triage→todo move for in-place planning; planning-concurrency counter
covers both columns. |
| Scheduler (`scheduler.ts`) | Skips `todo` tasks with
`status:"planning"` or a bootstrap-stub prompt so unplanned cards are
never dispatched. |
| TaskCard (`TaskCard.tsx`) | **Start** button on ideas cards; **Ready**
badge on planned todo tasks. |
| Board (`board-workflows.ts`) | `ideas` column label. |
All engine changes are **gated** — they only affect workflows whose
intake is not `"triage"`, so the default Coding workflow and every
existing built-in are byte-identical in behavior.
## Tests
- `builtin-coding-ideas-workflow-ir.test.ts` *(new)* — column set,
intake trait (`autoTriage:false`), merged todo traits, node re-homing
(start→ideas, planning→todo), optional-group defaults, round-trip.
- `store-create-intake-column.test.ts` *(new)* — createTask lands in
`ideas` for explicit + default selection, `triage` for the default
workflow, writes a bootstrap prompt.
- Updated `builtin-workflows.test.ts` catalog-order assertion for the
new entry.
## Verification
- Typecheck: core ✓ engine ✓ dashboard ✓
- Lint ✓ · Changeset format ✓ (`minor`)
- Merge gate (`test:gate`): 321 engine-core + 63 CI-shape ✓
- Regression suites: triage (39), concurrency (165),
movement/migration/hooks (259), builtin workflows (65), store-create
(54) — all green
- `verify:fast`: workspace build + CLI build + boot smoke (`fn --help` +
real `/api/health`) ✓
## Changeset
`.changeset/fn-coding-ideas-workflow.md` — `@runfusion/fusion: minor`
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added a new “Coding (Ideas)” builtin workflow with an Ideas intake
stage and merged planning flow.
* Updated task cards to support a **Start** action and show a **Ready**
badge for qualifying planning-stage tasks.
* **Bug Fixes**
* Tasks created for the Ideas workflow now persist into the correct
entry column and get the right prompt bootstrapping.
* Scheduler and triage avoid promoting/releasing unplanned todo tasks
that still contain the bootstrap prompt stub, and stale planning is
cleaned up across the merged intake flow.
* **Tests**
* Added coverage for the new builtin workflow IR and create-task intake
wiring.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## The bug
Per-task token usage (and the cost figures derived from it) is
**silently dropped the moment a task is archived**. A task that burned
millions of tokens shows `0` — or nothing — everywhere once it leaves
the live board.
Root cause is a field whitelist plus a missing type field:
- `TaskStore.taskToArchiveEntry()` (`packages/core/src/store.ts`)
constructs the archived record from an **explicit property whitelist**.
It copies `modelId` / `modelProvider` / `planningModelId` / … but never
`task.tokenUsage`.
- `ArchivedTaskEntry` (`packages/core/src/types.ts`) has no `tokenUsage`
field, so even a stray copy would be dropped by the type.
At archival time the task is DB-hydrated and still carries `tokenUsage`,
and the live `tasks` row (with its `tokenUsage*` columns) is then
deleted — so the whitelist is the only place the data survives or dies.
Result: `archive.db` (`archived_tasks.taskJson`) never contains token
stats. Any tool that reports token/cost usage can only ever see the
small live working set, never the hundreds of finished tasks.
## The fix
Thread `tokenUsage` through the archive round-trip (5 lines, all
pass-through of the already-typed `TaskTokenUsage`):
- `ArchivedTaskEntry` gains an optional `tokenUsage?: TaskTokenUsage`
field.
- `taskToArchiveEntry()` copies `tokenUsage: task.tokenUsage` (write
path).
- `archiveEntryToTask()` and `unarchiveTask()` copy `tokenUsage:
entry.tokenUsage` (both restore paths), so restored tasks keep their
history too.
Because the archived entry is serialized into `taskJson`, no DB
migration/column is needed — the counts land in the existing JSON blob
and read back via `json_extract(taskJson, '$.tokenUsage.totalTokens')`
(and the `inputTokens` / `outputTokens` / `cachedTokens` /
`cacheWriteTokens` breakdown).
## Verification
Applied the equivalent change to the bundled `dist/bin.js` on a live
install and archived a 9.9M-token task into an isolated copy of the
store. The full breakdown survived into `archive.db`:
```
inputTokens=119 outputTokens=26100 cachedTokens=9637483 cacheWriteTokens=233674
totalTokens=9897376 modelId=claude-sonnet-4-6 (+ per-model split intact)
```
Without the change the same archival leaves `tokenUsage` absent from the
entry.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Archived tasks now keep token usage details when saved and restored,
so task history remains accurate across archive flows.
* Restored archived tasks now display the same usage accounting they had
before being archived.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
- Gate bootstrap prompt to entry column/triage only, not every non-execution
column, so direct createTask({column:'todo'}) keeps generateSpecifiedPrompt.
- Guard the workflow-column hold-release dispatch path (reserveSlot) against
planning-status and bootstrap-stub todo tasks, matching the legacy filter.
- Extend clearStaleSpecifyingStatuses startup sweep to the todo column so a
restarted in-place planning task does not hold a maxTriageConcurrent slot.
- Gate the Start button on the intake column flag instead of the literal
'ideas' id, so any manual-intake workflow gets the affordance.
- Add regression test: direct todo create must not get a bootstrap stub.
The command-center token endpoint accepts groupBy=task, but the
dimension was never wired through: TokenGroupBy did not include "task",
groupKeyFor had no task case, VALID_GROUP_BY rejected it, and
groupAttributes emitted no attribute. As a result groupBy=task silently
fell back to ungrouped totals — the per-task rollup returned zero groups
even though tasks.tokenUsage* is populated per task.
Thread "task" through all four enumeration sites (the union type makes
the two switches compiler-exhaustive). Task rows group by task id; chat
rows have no task and return null, mirroring the existing node case.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
taskToArchiveEntry() builds the archived record from an explicit field
whitelist that omits task.tokenUsage, and ArchivedTaskEntry has no
tokenUsage field — so a task's input/output/cache token (and derived cost)
accounting is silently dropped the moment it is swept out of the live
tasks table into archive.db. Every archived task loses its token stats.
Add tokenUsage to the ArchivedTaskEntry type and thread it through both the
archive write path (taskToArchiveEntry) and the two restore paths
(archiveEntryToTask, unarchiveTask) so the counts round-trip intact.
Require generated task specs to summarize the requested before-to-after transformation near the top.
- Add a Before → After Transformation section to standard and fast planning prompt templates.\n- Document the new task definition section and cover it with prompt regression tests.\n- Add a patch changeset for the published Fusion package.\n\nFiles changed:\n .changeset/fn-7499-before-after-transformation.md | 7 +++++++\n docs/task-management.md | 1 +\n packages/core/src/__tests__/agent-prompts.test.ts | 17 +++++++++++++++\n packages/core/src/agent-prompts.ts | 25 +++++++++++++++++++----\n packages/engine/src/__tests__/triage.test.ts | 20 ++++++++++++++++++\n 5 files changed, 66 insertions(+), 4 deletions(-)
Fusion-Task-Id: FN-7499
Fusion-Task-Lineage: d049b5d6-a4bc-40dd-831d-04a11f9dc2cf
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Add builtin:coding-ideas, a capture-first variant of the default coding
pipeline. New cards land in a manual Ideas intake (autoTriage:false) and are
not auto-planned until an operator promotes them into the merged Todo
planner+capacity column, where the triage service plans them in place.
Engine foundation:
- createTask lands cards in the workflow intake column (resolvedEntryColumn)
instead of hardcoding triage; default workflow is byte-identical.
- Triage poll discovers unplanned todo tasks (bootstrap-stub prompt) and
plans them in place; finalizeApprovedTask skips the redundant move.
- Scheduler skips todo tasks that are planning or still carry a bootstrap
prompt, so unplanned cards are never dispatched.
Dashboard:
- Start button on ideas cards (ideas -> todo move triggers planning).
- Ready badge on planned todo tasks waiting for an in-progress slot.
- ideas column label in board-workflows.
Tests: workflow IR round-trip/column/node-placement, createTask intake wiring,
and updated builtin catalog order assertion.
