6243c2c3f20a66dcebb4eb87768de69eabac2631
15 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
gsxdsm
|
9f24a517cf |
FN-8956: track resolved review findings
Add durable, scoped resolution states for workflow review findings. - Persist reviewer-applied and superseded finding receipts without making them actionable. - Scope supersession claims to a named prior workflow result, preserving duplicate IDs in other review lanes. - Render informational resolution badges and reject resolved items from revision requests. Files changed: .changeset/fn-8956-review-finding-resolution.md | 7 + docs/dashboard-guide.md | 2 +- docs/workflow-steps.md | 8 +- .../src/__tests__/review-severity-gate.test.ts | 25 ++++ .../src/__tests__/workflow-step-results.test.ts | 45 +++++- packages/core/src/index.gate.ts | 6 + packages/core/src/index.ts | 6 + packages/core/src/types.ts | 2 + packages/core/src/types/task/task-review.ts | 4 + packages/core/src/types/workflow/workflow-steps.ts | 15 +- .../src/workflows/builtin-code-review-group.ts | 2 +- .../src/workflows/builtin-plan-review-group.ts | 2 +- .../core/src/workflows/review-severity-gate.ts | 37 ++++- .../core/src/workflows/workflow-step-results.ts | 54 ++++++- packages/dashboard/app/api/agents/run-audit.ts | 1 + .../dashboard/app/components/TaskReviewTab.css | 22 +++ .../dashboard/app/components/TaskReviewTab.tsx | 36 +++-- .../components/__tests__/TaskReviewTab.test.tsx | 46 ++++++ .../dashboard/src/__tests__/routes-tasks.test.ts | 48 ++++++ .../src/routes/register-task-workflow-routes.ts | 14 +- .../__tests__/review-finding-supersession.test.ts | 163 +++++++++++++++++++++ .../__tests__/review-findings-injection.test.ts | 22 +++ .../workflow-step-verdict-parsing.test.ts | 16 +- .../engine/src/executor/execute-workflow-graph.ts | 129 ++++++++-------- .../engine/src/executor/execute-workflow-step.ts | 25 +++- .../engine/src/executor/run-graph-custom-node.ts | 7 + .../executor/workflow-step-failure-injection.ts | 8 +- .../engine/src/executor/workflow-step-verdict.ts | 17 ++- .../src/workflows/workflow-graph-executor.ts | 15 ++ packages/i18n/locales/en/app.json | 4 +- packages/i18n/locales/es/app.json | 4 +- packages/i18n/locales/fr/app.json | 4 +- packages/i18n/locales/ko/app.json | 4 +- packages/i18n/locales/pt-BR/app.json | 4 +- packages/i18n/locales/zh-CN/app.json | 4 +- packages/i18n/locales/zh-TW/app.json | 4 +- 36 files changed, 703 insertions(+), 109 deletions(-) Fusion-Task-Id: FN-8956 Fusion-Task-Lineage: 80568280-85aa-4a49-a60a-99b75f88f486 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
06ea444339 |
fix: uncap workflow principals and auto-resume stranded continuations
Two independent wedges kept cards silently stuck on the board. 1. Workflow principals were capped. `WorkflowAgentCapacity.acquire` enforced `settings.maxConcurrent` as a project session budget plus an optional per-agent `maxWorkflowSessions`, and `routeWorkflowPrincipal`'s availability test applied the same per-agent ceiling. The workflow roles stand in for STAGES, not workers, and there is typically one agent per role - so the cap serialized the entire board behind a single Workflow Executor regardless of maxConcurrent/maxWorktrees. Admission now always succeeds; the lease survives as bookkeeping (it is what activeSessions counts and what the renewal timer keeps warm). `maxProjectSessions` is removed from the input rather than defaulted, so it cannot be reintroduced without deleting the contract, and the agent-capacity re-route loops in triage and graph admission are deleted with the refusal they existed to work around. 2. Continuations that stop in `running` or `held` were never re-polled. The scheduler's due-poll takes only `runnable`/`retrying`; a row claimed through a path that leaves `leaseExpiresAt` NULL keeps `state: "running"` forever after its process dies, and `acquireWorkflowWorkItemLease` can only re-take a `held` row whose blockedReason matches workflow-principal-%. Observed live: seven cards `running` behind leases from a process that exited ~9h earlier, two `held` with a NULL blockedReason for 46h, none emitting a single run-audit row while stranded. A further 33 active-state rows belonged to archived+soft-deleted tasks (the FK cascade only fires on hard delete). New sweep `reconcileStrandedWorkflowContinuations` (startup + periodic) re-queues both stranded shapes and retires dead tasks' rows, gated by the canonical liveness triple, a 10-minute grace matching the capacity lease duration, and a compare-and-set on the scanned state so a real claim wins. The decision is the pure `evaluateStrandedContinuationReclaim`, shared with its tests so coverage cannot drift from behavior - the drift that let the FN-8923 sweep ship covering one ninth of this problem. Verified: pnpm lint, engine typecheck, pnpm test:gate (606 tests), verify:fast, and the new suite under mutation (removing either guard fails 3 cases). The two pre-existing failures in self-healing-orphaned-pending-step-results.test.ts reproduce identically at HEAD without these changes. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
gsxdsm
|
963dba6f80 |
feat: gate review verdicts on finding severity and preserve remediation sessions
Review remediation loops were the dominant cost of task wall-clock: over 14 days,
tasks with >=5 post-review fix rounds were 22% of tasks but consumed 78% of all
task active time, and 311 of 331 recorded findings were spec-internal-consistency
complaints that changed no delivered behavior.
Two causes compounded. Plan/Code Review remediation was unbounded by default, and
the review policy ordered a full re-derivation of the artifact after every edit
("distrust the edit ... fresh holistic pass"), so each round surfaced a fresh crop
of previously-acceptable observations as new blockers.
Make the already-persisted WorkflowReviewFinding.severity load-bearing instead of
decorative: a REVISE only blocks when it carries a finding at or above the review
kind's threshold (plan: P0+P1, code: P0). Non-blocking findings are still parsed,
persisted, and handed to the implementer as advisory notes in PROMPT.md. Fails
closed — a REVISE with no findings, or with any unclassified finding, still blocks,
so prose-only and custom reviewers keep full blocking power. The gate only ever
relaxes a verdict, never promotes one.
Reviewer prompts now request the structured findings schema (Plan Review emitted
none before), define severity by consequence as P0/P1/P2, omit nits entirely rather
than filing them as low-severity findings, and use an incremental re-review contract.
Remediation renders findings grouped by priority and sanctions an explicit decline
with rationale, so a disputed finding has a terminal state.
Also preserve the implementation session across a review bounce: sendTaskBackForFix
no longer nulls sessionFile when preserving resume state, and the executor's finally
no longer clears it on a review handoff. Remediation rounds continue the conversation
instead of re-reading the repo and re-deriving the change they just wrote. The resume
prompt now directs a PROMPT.md re-read, without which a resumed agent would never see
the new findings.
New per-workflow settings planReviewBlockingSeverity / codeReviewBlockingSeverity;
set either to "any" to restore the previous behavior.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
gsxdsm
|
51437558ac |
fix(workflow): give a stranded planning hold a retry owner, and stop status erasure
FN-8923 sat silent in Todo for 7+ hours with zero run-audit rows. Its plan node held on principal routing, triage correctly recorded `needs-replan`, and then dependency auto-unblock nulled that status when its blocker completed. From that moment the card was invisible to both lanes: triage saw a fully-written spec with no replan flag and skipped it, while the executor's `isUnplannedForExecution` refused to dispatch because no capacity-boundary continuation existed. Not stuck in a retry loop -- unowned. - Dependency auto-unblock clears only the `queued` marker it owns, at all four sites (scheduler.ts plus three in self-healing.ts). `status` is a shared lifecycle channel and `needs-replan` is the only signal that re-admits a hold-column card whose PROMPT.md is already a real spec. - New self-healing sweep `reconcilePrincipalHeldPlanningContinuations` re-queues planning for a card whose sole active continuation is a principal-routing hold. A planning hold otherwise has no retry owner at all. Gated on the planning lane, effective auto-merge, an owned (null) status, and the shared planning lifecycle lock, so it cannot clobber a triage claim or launder a `failed` / `stuck-killed` / `queued` card into a replan. - Workflow node-instance-id materialization is idempotent across foreach, loop, and optional-group containers. It re-wrapped its own output on every dispatch, so FN-8869 grew a ~1.8 KB `run_id` of ~30 repeated segments on a hot indexed column and every retry read as a distinct run. - An unresolvable node instance or absent IR now fails closed instead of being treated as an edited-away override -- the previous shape would have discarded a real reviewer fence and handed a named review to the pool. - Mirror the routing exports into the gate-safe core barrel; the reduced barrel resolved them to `undefined`, a latent trap for any suite reaching the router. Findings from a multi-reviewer pass; 9 of 11 confirmed by an independent validator. Each fix carries a regression asserting the invariant across its surfaces, not the single reported case -- the optional-group accretion test was verified to fail without the fix. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
gsxdsm
|
7611ce7baa |
FN-8841: route Plan Review no-op verdicts to terminal close
Allow validated duplicate and no-op Plan Review verdicts to complete work without implementation dispatch. - Add terminal no-op routes to built-in coding workflows and validate reviewer evidence. - Persist close verdicts, safely hold failed terminalizations, and guard pause races. - Document the verdict contract and cover route, validation, and completion behavior. - Add a patch changeset for the published Fusion package. Files changed: .changeset/fn-8841-plan-review-no-op.md | 7 + docs/workflow-steps.md | 14 + .../core/src/__tests__/builtin-workflows.test.ts | 24 ++ packages/core/src/types/task/task-review.ts | 7 +- packages/core/src/types/workflow/workflow-steps.ts | 2 +- .../src/workflows/builtin-coding-workflow-ir.ts | 3 + .../src/workflows/builtin-plan-review-group.ts | 3 +- .../builtin-stepwise-coding-workflow-ir.ts | 3 + packages/core/src/workflows/builtin-workflows.ts | 5 + .../engine/src/__tests__/plan-review-no-op.test.ts | 289 +++++++++++++++++++ .../workflow-step-verdict-parsing.test.ts | 18 ++ packages/engine/src/executor.ts | 318 +++++++++++++++++---- .../src/workflows/workflow-graph-executor.ts | 103 ++++++- .../src/workflows/workflow-graph-task-runner.ts | 6 + 14 files changed, 741 insertions(+), 61 deletions(-) Fusion-Task-Id: FN-8841 Fusion-Task-Lineage: bde2e001-9cd0-496e-8367-36540c9ac31d Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
0cce560e4a |
fix: stop three bookkeeping faults from terminalizing or mis-scoping a run
Found by a subsystem audit of FN-8764's work-item and role-routing design, prompted by three production deadlocks already fixed in it. 1. executor.ts — closing out the continuation could skip handleGraphFailure. The two transitions that close a run's continuation sat outside the interpreter try/catch with no handler, unlike their siblings in the same function. The row is usually ALREADY terminal by then: the run's first fence write retires the continuation it resumed on, which is what makes the handover atomic. So `succeeded -> failed` hit the store's terminal guard and threw, escaping executeWorkflowGraph and skipping handleGraphFailure — a failed run's card was left sitting in its wip column, unparked, with no error recorded. Closing the continuation is bookkeeping and must never pre-empt the lifecycle action. 2. executor.ts — capacity attemptId dropped its run-id fallback. `resolvedRunId` is optional by construction (a definition load failure leaves it undefined) and this interpolated it raw, producing the literal attempt id `undefined:<nodeInstance>` shared by every task in the project that hit that failure. The lease is keyed on (projectId, attemptId) and returns "acquired" for a pre-existing row regardless of agent, so colliding tasks bypass both the project and per-agent caps and one task's release deletes another's live lease. The two durable writes on either side already used the fallback. 3. workflow-task-runtime.ts — failWorkItem dropped a promise bare. The write is deliberately fire-and-forget, but an unhandled rejection (most likely the terminal guard when a peer already closed the row) crossed into process-level unhandled-rejection territory while the caller had already returned "failed" as if it were persisted. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
gsxdsm
|
560256bb73 |
fix: resume the graph at a top-level node, not a foreach template node
A principal fence written for a node inside a foreach template stores the
TEMPLATE node id (step-execute) with the materialized instance in
nodeInstanceId (steps#0:step-execute). The template node lives under the
foreach's config.template and is never in ir.nodes, so handing it to the
interpreter as a start node resolved to nothing and threw WorkflowIrError.
executeWorkflowGraph's catch turned that into a terminal graph failure, so a
healthy card was parked on every dispatch:
[workflow-graph] FN-8825 could not resolve workflow — parking task instead of
legacy fallback: interpreter-error: Workflow IR missing start node
Latent since FN-8764 introduced these fences, and reachable only once a
step-execute fence could become the task's sole active continuation — which the
atomic-handover change in
|
||
|
gsxdsm
|
ef8828f145 |
fix: unblock workflow execution stalled by silent role-routing deadlocks
Every task sat in progress with no session, no log, and no error after the FN-8764 role-agent rollout. Two independent deadlocks, both invisible: 1. The in-process runtime built its AgentStore but never passed it into TaskExecutorOptions, so the executor's fail-closed role-routing gate refused every classified node (execute/step-execute/review/merge). 2. A resumed run keeps the continuation work item it woke on active until the interpreter returns, so the next node's principal-fence upsert violated idx_workflow_work_items_one_active_task_continuation — a different index than its ON CONFLICT target — and raised. The run re-suspended on every dispatch; only an operator bouncing the card to the hold column cleared it. Both refusals were swallowed as recoverable "principal holds" that write no log, audit row, or task error, which is why a fully deadlocked board looked idle. - Wire agentStore into the executor; assert the shared instance at every runtime seam in the PG composition test. - Supersede an active work item for a node the run has already left, then retry the fence write once; never touch a claim on the node currently executing. - Record task:workflow-run-suspended and task:workflow-continuation-superseded; log principal holds, routing-unavailable faults, and fence-write errors. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
gsxdsm
|
eaadd153b1 |
FN-8764: route workflow stages through durable role agents
Route workflow stages through task-scoped durable role agents. - Persist normalized multi-role agents and workflow principal fences with migrations. - Route planning, execution, review, and merge workflow nodes through authorized permanent principals with capacity leasing and recovery. - Retire ephemeral workflow-stage workers and expose role-aware agent configuration, workflow editing, and documentation. - Preserve lifecycle-column ratchet coverage by centralizing workflow-role classification rather than adding test exemptions. Files changed: .changeset/fn-8764-workflow-role-agents.md | 7 + CONCEPTS.md | 3 + docs/agents.md | 6 + docs/architecture.md | 6 + docs/cli-reference.md | 2 + docs/dashboard-guide.md | 4 + docs/settings-reference.md | 6 +- docs/storage.md | 2 + docs/workflow-steps.md | 6 + .../src/__tests__/extension-agent-update.test.ts | 11 +- packages/cli/src/__tests__/extension.test.ts | 18 +- packages/cli/src/extension.ts | 41 +- .../core/src/__tests__/agent-permissions.test.ts | 12 + .../core/src/__tests__/agent-role-policy.test.ts | 7 + packages/core/src/__tests__/agent-roles.test.ts | 21 + .../legacy-column-collection-gating-ledger.test.ts | 19 +- .../src/__tests__/postgres/schema-applier.test.ts | 16 +- .../core/src/__tests__/settings-parity.test.ts | 9 +- .../workflow-agent-node-classification.test.ts | 25 + .../src/__tests__/workflow-work-item-cas.test.ts | 38 ++ packages/core/src/agents/agent-permissions.ts | 11 +- packages/core/src/agents/agent-role-policy.ts | 39 +- packages/core/src/agents/agent-store.ts | 190 ++++++- .../core/src/async-stores/async-agent-store.ts | 6 + packages/core/src/config/settings-schema.ts | 5 +- packages/core/src/index.gate.ts | 2 +- packages/core/src/index.ts | 7 +- .../0045_fn_8764_multi_role_workflow_agents.sql | 20 + .../0046_fn_8764_workflow_principal_fence.sql | 49 ++ packages/core/src/postgres/schema-applier.ts | 22 +- packages/core/src/postgres/schema/project.ts | 21 + packages/core/src/store.ts | 2 +- .../task-store/async/async-workflow-workitems.ts | 49 +- packages/core/src/task-store/row-types.ts | 4 + packages/core/src/task-store/settings-helpers.ts | 16 +- packages/core/src/task-store/settings-ops-2.ts | 13 +- packages/core/src/task-store/settings-ops.ts | 16 +- packages/core/src/task-store/task-row-mappers.ts | 4 + .../src/task-store/workflow-task-create-ops.ts | 6 +- .../src/task-store/workflow-workitems-ops-2.ts | 25 +- packages/core/src/types.ts | 2 + packages/core/src/types/agents/agents.ts | 45 +- packages/core/src/types/merge/merge-queue.ts | 17 + packages/core/src/types/settings/settings-scope.ts | 9 +- packages/core/src/workflows/workflow-ir-types.ts | 58 +++ packages/core/src/workflows/workflow-ir.ts | 19 + .../dashboard/app/components/AgentDetailView.css | 14 + .../dashboard/app/components/AgentDetailView.tsx | 34 +- .../dashboard/app/components/NewAgentDialog.tsx | 28 +- .../app/components/WorkflowNodeEditor.tsx | 19 + .../__tests__/AgentDetailView.core.test.tsx | 4 +- .../app/components/__tests__/AgentsView.test.tsx | 2 +- .../__tests__/SettingsModal.general.test.tsx | 86 --- .../__tests__/SettingsModal.test-harness.tsx | 1 - .../components/agent-presets/agentCreatePayload.ts | 9 +- .../app/components/settings/section-keys.ts | 1 - .../settings/sections/GeneralSection.tsx | 8 - .../settings-default-descriptions.test.tsx | 1 - .../app/components/workflow-flow-mapping.ts | 7 + packages/dashboard/src/mission-routes.ts | 26 +- .../src/routes/__tests__/agent-core-routes.test.ts | 23 +- .../src/routes/register-agent-core-routes.ts | 42 +- ...gister-agent-import-export-generation-routes.ts | 21 - .../engine/src/__tests__/agent-action-gate.test.ts | 33 ++ .../engine/src/__tests__/agent-assignment.test.ts | 370 ------------- .../src/__tests__/ephemeral-worker-manager.test.ts | 575 --------------------- ...ecutor-ephemeral-disabled-dispatch-gate.test.ts | 223 -------- .../__tests__/executor-fast-mode-workflows.test.ts | 58 +++ .../engine/src/__tests__/log-severity-manifest.ts | 1 - .../__tests__/log-severity-spam-contract.test.ts | 3 - .../resolved-read-with-literal-filter.test.ts | 4 - .../__tests__/scheduler-ephemeral-toggle.test.ts | 175 ------- .../__tests__/scheduler-workflow-cutover.test.ts | 19 - .../src/__tests__/workflow-agent-capacity.test.ts | 47 ++ .../src/__tests__/workflow-agent-routing.test.ts | 137 +++++ .../src/__tests__/workflow-graph-foreach.test.ts | 15 + .../__tests__/workflow-graph-task-runner.test.ts | 73 +++ .../src/__tests__/workflow-task-runtime.test.ts | 95 ++++ .../src/__tests__/workflow-work-scheduler.test.ts | 20 + packages/engine/src/agents/agent-action-gate.ts | 64 +++ packages/engine/src/agents/agent-assignment.ts | 135 ----- packages/engine/src/agents/agent-reflection.ts | 1 + .../engine/src/agents/ephemeral-worker-manager.ts | 429 --------------- .../engine/src/agents/workflow-agent-capacity.ts | 113 ++++ .../engine/src/agents/workflow-agent-router.ts | 185 +++++++ packages/engine/src/execution/reviewer.ts | 26 +- packages/engine/src/executor.ts | 501 +++++++++++++++--- packages/engine/src/index.ts | 1 - packages/engine/src/merger.ts | 20 +- packages/engine/src/pi.ts | 11 + packages/engine/src/runtimes/in-process-runtime.ts | 37 -- packages/engine/src/scheduler.ts | 114 +--- packages/engine/src/triage.ts | 196 ++++++- .../src/workflows/workflow-graph-executor.ts | 109 +++- .../engine/src/workflows/workflow-graph-loop.ts | 13 +- .../src/workflows/workflow-graph-task-runner.ts | 12 + .../engine/src/workflows/workflow-task-runtime.ts | 125 ++++- .../src/workflows/workflow-work-scheduler.ts | 8 +- 98 files changed, 2722 insertions(+), 2468 deletions(-) Fusion-Task-Id: FN-8764 Fusion-Task-Lineage: 5527fccb-342d-46f6-8108-bbf89142efec Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
4f4aef7173 |
FN-8811: preserve explicit shared-member review holds
Keep shared branch-group integration moving unless an operator explicitly holds the task. - Track auto-merge provenance and distinguish explicit user holds from inherited mission policy. - Preserve manual holds across workflow recovery, merge coordination, API updates, and dashboard status. - Add regression coverage, document the behavior, and quarantine the observed flaky test. Files changed: .changeset/fn-8811-shared-member-review-hold.md | 7 ++ docs/architecture.md | 4 +- docs/dashboard-guide.md | 1 + .../mission-store.sync-auto-merge.test.ts | 7 +- .../__tests__/postgres/mission-store.pg.test.ts | 1 + .../__tests__/postgres/store-movement.pg.test.ts | 20 ++++ packages/core/src/__tests__/task-merge.test.ts | 14 +++ .../core/src/async-stores/async-mission-store.ts | 6 +- packages/core/src/index.gate.ts | 1 + packages/core/src/index.ts | 1 + packages/core/src/merge/task-merge.ts | 20 +++- packages/core/src/missions/mission-store.ts | 6 +- packages/core/src/task-store/serialization.ts | 2 +- packages/core/src/task-store/task-creation.ts | 8 +- packages/core/src/types/task/task-core.ts | 12 ++- .../components/__tests__/TaskDetailModal.test.tsx | 63 ++++++++++++ .../dashboard/src/__tests__/routes-tasks.test.ts | 47 +++++++++ .../src/routes/register-task-workflow-routes.ts | 15 ++- ...cutor-live-branch-group-auto-merge-hold.test.ts | 87 +++++++++++++++++ .../src/__tests__/group-merge-coordinator.test.ts | 99 ++++++++++++++++++- .../engine/src/__tests__/project-engine.test.ts | 57 ++++++++++- .../self-healing-paused-abort-recovery.test.ts | 52 +++++++++- packages/engine/src/__tests__/self-healing.test.ts | 106 +++++++++++++++++++++ .../workflow-graph-executor-handlers.test.ts | 23 +++++ packages/engine/src/executor.ts | 37 ++++++- packages/engine/src/project-engine.ts | 25 +++-- packages/engine/src/self-healing.ts | 71 ++++++++++++-- .../src/workflow-node-runners/merge-runner.ts | 24 ++++- .../src/workflows/workflow-graph-executor.ts | 4 + .../src/workflows/workflow-graph-task-runner.ts | 6 ++ .../engine/src/workflows/workflow-node-handlers.ts | 5 +- packages/engine/vitest.config.ts | 11 ++- scripts/lib/test-quarantine.json | 5 + 33 files changed, 789 insertions(+), 58 deletions(-) Fusion-Task-Id: FN-8811 Fusion-Task-Lineage: 5c1609bf-3132-4988-a254-fedec6c0e33d Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
ec10411c4c |
FN-8795: persist structured workflow review findings
Persist normalized actionable findings from review workflow nodes. - Normalize bounded finding IDs, text, locations, and severities in workflow results. - Surface individual findings for Review-tab selection and same-task revision. - Preserve findings through workflow retries and document the advisory contract. Files changed: .changeset/fn-8795-structured-review-findings.md | 7 +++ docs/dashboard-guide.md | 2 +- docs/workflow-steps.md | 4 +- .../src/__tests__/workflow-step-results.test.ts | 32 +++++++++++++- packages/core/src/index.gate.ts | 4 ++ packages/core/src/index.ts | 6 ++- packages/core/src/types.ts | 4 ++ packages/core/src/types/task/task-review.ts | 5 +++ packages/core/src/types/workflow/workflow-steps.ts | 20 +++++++++ .../core/src/workflows/workflow-step-results.ts | 50 +++++++++++++++++++++- .../dashboard/app/components/TaskReviewTab.tsx | 12 +++++- .../src/routes/register-task-workflow-routes.ts | 26 ++++++++++- .../workflow-malformed-verdict-gate.test.ts | 12 ++++++ packages/engine/src/executor.ts | 46 +++++++++++++++++--- .../src/workflows/workflow-graph-executor.ts | 11 +++++ 15 files changed, 227 insertions(+), 14 deletions(-) Fusion-Task-Id: FN-8795 Fusion-Task-Lineage: 09003b01-3f9a-4387-b6a7-f29066ce52f6 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
e75c788db2 |
FN-8794: add workflow review-kind markers
Classify workflow review nodes so review feedback can target their persisted results. - validate and type explicit plan/code review-kind markers in workflow IR - expose review-kind selection in the workflow editor and document the authoring contract - persist markers through task workflow routes and graph execution with regression coverage Files changed: .changeset/fn-8794-review-kind.md | 7 + docs/dashboard-guide.md | 4 + docs/workflow-steps.md | 10 + .../__tests__/workflow-ir-optional-group.test.ts | 17 ++ packages/core/src/__tests__/workflow-ir.test.ts | 83 +++++++++ packages/core/src/index.gate.ts | 2 +- packages/core/src/index.ts | 2 +- packages/core/src/types.ts | 2 + packages/core/src/types/workflow/workflow-steps.ts | 8 + .../src/workflows/builtin-code-review-group.ts | 1 + .../src/workflows/builtin-plan-review-group.ts | 1 + packages/core/src/workflows/workflow-ir-types.ts | 5 + packages/core/src/workflows/workflow-ir.ts | 24 +++ .../app/components/WorkflowNodeEditor.tsx | 17 ++ .../__tests__/WorkflowNodeEditor.test.tsx | 206 +++++++++++++++++++++ .../dashboard/src/__tests__/routes-tasks.test.ts | 166 ++++++++++++++++- .../src/routes/register-task-workflow-routes.ts | 82 ++++++-- .../workflow-graph-optional-group.test.ts | 177 +++++++++++++++++- .../src/workflows/workflow-graph-executor.ts | 20 +- 19 files changed, 801 insertions(+), 33 deletions(-) Fusion-Task-Id: FN-8794 Fusion-Task-Lineage: a7752469-59bc-406f-82e8-6ffde6c392ef Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
9939897aab |
fix: prevent stale planning approvals and review churn (#3327)
## Summary Planning can no longer approve or execute against evidence from a superseded dependency episode. Dependency mutations, approval decisions, recovery, and execution admission now share serialized lifecycle rules, so stale planner work cannot restore an invalid approval or release an unplanned task. Review also converges instead of discovering one blocker per round. Planning performs a repository-grounded completeness pass up front; Plan Review batches all independently discoverable blockers and carries an episode-scoped decision ledger across revisions; code review traces changed invariants through production consumers and tests. Repeated feedback still advances the safety budget, while provider failures and superseded episodes stay outside the remediation ledger. The dashboard now exposes manual approval only for the intended exhausted-review state, and refusal/recovery audit events make rejected lifecycle transitions diagnosable without leaking prompt content. ## Validation - `pnpm verify:fast` — scoped typechecks/builds, CLI build, and boot smoke passed. - Focused Core and Engine regression suites — 511 tests passed. - `pnpm lint`, strict changeset validation, Core/Engine typechecks, and package builds passed. Fixes #3325. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Improved Plan Review approvals, rejections, and replan-cap handling across task workflows. * Added cumulative feedback and attempt tracking across repeated planning reviews. * Added safer recovery for stalled planning handoffs and interrupted approval updates. * **Bug Fixes** * Prevented stale approvals and unplanned execution after dependency changes. * Improved concurrent approval handling, retryability, and refusal-record deduplication. * Refined dashboard approval indicators and responsive approval views. * **Quality Improvements** * Strengthened planning and code-review completeness checks and blocking-finding coverage. * Preserved review history while clearly marking outdated approvals. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
gsxdsm
|
9dc7b94c17 |
fix(FN-8768): resume manually approved plans
Persist exhausted Plan Review approval as audited terminal evidence and wake scheduler and deferred continuations immediately. Fusion-Task-Id: FN-8768 |
||
|
gsxdsm
|
cb57093d03 |
refactor: domain folder layout (types, API, core, engine) (#2398)
## Summary Wave 17 organizes Fusion into **domain folders** (stacks on #2397). ### Layout - **core/types/** — board, task, agents, settings, merge, workflow, mesh, … - **core/src/** — agents, ai, async-stores, workflows, tasks, config, db, … - **dashboard/app/api/** — client, tasks, agents, git, missions, planning, … - **engine/src/** — agents, auth, execution, merge, missions, overseer, worktree, … Root keepers retained for large entrypoints (`store.ts`, `executor.ts`, `merger.ts`, …). Public barrels (`@fusion/core`, `@fusion/engine`, `app/api.ts` → legacy) stay stable. ## Test plan - [x] `@fusion/core` typecheck - [x] `@fusion/engine` typecheck (pre-existing playwright-core noise only) - [ ] CI merge gate **Stack:** #2394 → #2397 → **this PR** |