aedee4b8231bf050c3240a00ab6645ede5d87ee9
19 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
gsxdsm
|
fca8dd9841 |
FN-9137: Define approval request ordering semantics
Clarify and verify deterministic newest-first approval request listing across storage paths. - Document created-at descending order with request-ID descending tie resolution. - Align dedupe ordering commentary across async and legacy SQL stores. - Add PostgreSQL coverage for ties, pagination, filters, project binding, and audit isolation. Files changed: .../approval-request-list-ordering.pg.test.ts | 184 +++++++++++++++++++++ packages/core/src/agents/approval-request-store.ts | 11 ++ .../async-stores/async-approval-request-store.ts | 9 +- 3 files changed, 202 insertions(+), 2 deletions(-) Fusion-Task-Id: FN-9137 Fusion-Task-Lineage: b87867aa-fdf3-49bf-a037-7d74163a093d Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
d9fcabfaef |
FN-9112: default Memory Keeper heartbeats to disabled
Default built-in Memory Keeper agents to opt-in heartbeat scheduling while retaining operator choices. - Provision new Memory Keeper agents with heartbeat disabled and hourly scheduling preconfigured. - Preserve explicit heartbeat settings during startup convergence and avoid no-op rewrites. - Add provisioning coverage, operator documentation, and a release changeset. Files changed: .../fn-9112-memory-keeper-heartbeat-default-off.md | 7 +++ docs/agents.md | 2 +- .../__tests__/memory-agent-provisioning.test.ts | 59 +++++++++++++++++++--- packages/core/src/agents/agent-store.ts | 34 ++++++++++--- 4 files changed, 86 insertions(+), 16 deletions(-) Fusion-Task-Id: FN-9112 Fusion-Task-Lineage: 49edc6d9-3d9b-412f-91a5-c26f4a26a662 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
b7604a94bf |
FN-9041: remove agent state-change activity logs
Remove durable agent state-change events and hide retained state-change rows from activity displays. - Stop AgentStore update and reconciliation paths from writing state-change activity events. - Filter historical state-change events in activity stores and panels while retaining live roster notifications. - Document the retained activity contract, add coverage, and include a patch changeset. Files changed: .changeset/fn-9041-removal.md | 7 ++++ docs/agent-activity-contract.md | 4 ++ docs/architecture.md | 2 +- docs/dashboard-guide.md | 2 +- .../src/__tests__/agent-activity-writers.test.ts | 23 ++++++----- packages/core/src/agents/agent-store.ts | 28 +++++-------- .../app/components/agentsOrgChartActivity.ts | 12 ++++++ .../command-center/AgentActivityPanel.tsx | 25 +++++++---- .../__tests__/AgentActivityPanel.test.tsx | 48 ++++++++++++++++++++++ .../app/hooks/__tests__/agentActivityStore.test.ts | 39 +++++++++++++++++- packages/dashboard/app/hooks/agentActivityStore.ts | 3 +- 11 files changed, 153 insertions(+), 40 deletions(-) Fusion-Task-Id: FN-9041 Fusion-Task-Lineage: 532724b1-5945-4904-b5cd-2c27909805de Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
52facd1461 |
FN-9000: scope runtime records to their projects
Scope runtime data access to the owning project while preserving explicit unbound compatibility. - Thread optional project identifiers through project-table reads and mutations. - Isolate chat, approvals, artifacts, secrets, audit, branch groups, plugin analytics, and verification cache records. - Add PostgreSQL coverage and a patch changeset documenting multi-project isolation. Files changed: .../fn-9000-project-ownership-runtime-scope.md | 7 + docs/storage.md | 3 +- .../project-ownership-runtime-scope.pg.test.ts | 155 +++++++++++++++++++++ packages/core/src/agents/approval-request-store.ts | 20 ++- .../async-stores/async-approval-request-store.ts | 30 ++-- packages/core/src/async-stores/async-chat-store.ts | 105 +++++++++++--- .../core/src/async-stores/async-secrets-store.ts | 58 +++++--- packages/core/src/chat/chat-store.ts | 22 +-- .../src/plugins/plugin-activation-analytics.ts | 12 +- packages/core/src/secrets/secrets-store.ts | 12 +- packages/core/src/store.ts | 6 +- .../src/task-store/async/async-archive-lineage.ts | 16 ++- packages/core/src/task-store/async/async-audit.ts | 18 ++- .../src/task-store/async/async-branch-groups.ts | 50 ++++--- .../task-store/async/async-comments-attachments.ts | 35 +++-- .../core/src/task-store/branch-and-pr-entities.ts | 15 +- packages/core/src/task-store/branch-group-ops.ts | 2 +- packages/core/src/task-store/task-artifacts-ops.ts | 2 +- packages/core/src/task-store/task-id-integrity.ts | 2 +- packages/core/src/task-store/task-mutation-ops.ts | 14 +- .../core/src/task-store/workflow-definitions.ts | 7 + packages/dashboard/src/server.ts | 2 +- 22 files changed, 472 insertions(+), 121 deletions(-) Fusion-Task-Id: FN-9000 Fusion-Task-Lineage: 9842e9e9-ec50-4459-8534-dfdaa2cdf35e Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
3b1c7881a8 |
FN-8988: partition agent ratings by project
Isolate PostgreSQL agent ratings within each project while preserving compatibility behavior. - Add migration 0055 to enforce the (project_id, id) rating identity key and repair drifted composite keys. - Scope rating CRUD operations to bound projects and document the storage contract. - Cover cross-project rating isolation and drifted-key migration repair. Files changed: .changeset/fn-8988-agent-ratings-project-partition.md | 7 ++ docs/storage.md | 1 + packages/core/src/__tests__/postgres/agent-ratings-project-isolation.pg.test.ts | 105 +++++++++++++++++++++ packages/core/src/__tests__/postgres/schema-applier.test.ts | 66 ++++++++++++- packages/core/src/agents/agent-store.ts | 18 +++- packages/core/src/async-stores/async-agent-store.ts | 11 ++- packages/core/src/postgres/migrations/0055_fn_8988_agent_ratings_project_partition.sql | 74 +++++++++++++++ packages/core/src/postgres/schema-applier.ts | 12 ++- packages/core/src/postgres/schema/project.ts | 5 + 9 files changed, 293 insertions(+), 6 deletions(-) Fusion-Task-Id: FN-8988 Fusion-Task-Lineage: 5d3e5e60-1589-4641-8695-1786f1c15c5d Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
637854ad36 |
FN-8932: add durable memory consolidation agent
Add a provisioned memory agent that consolidates durable recall material through idempotent heartbeat ticks. - Provision and configure the durable memory agent with an enabled workflow setting. - Add consolidation adapters, material collection, recall graph references, and run-audit metadata. - Expose the setting in the dashboard and document the memory-agent behavior. - Cover provisioning, heartbeat, consolidation, audit, and recall graph behavior with tests. Files changed: .changeset/fn-8932-memory-agent.md | 7 ++ AGENTS.md | 1 + docs/agents.md | 10 ++ docs/settings-reference.md | 1 + docs/storage.md | 2 +- .../memoryConsolidationEnabled-default.test.ts | 22 ++++ .../memory-recall-graph-cross-reference.pg.test.ts | 115 +++++++++++++++++++++ .../__tests__/memory-agent-provisioning.test.ts | 31 ++++++ packages/core/src/agents/agent-store.ts | 85 +++++++++++++++ packages/core/src/agents/memory-agent-defaults.ts | 30 ++++++ packages/core/src/index.gate.ts | 2 + packages/core/src/index.ts | 9 ++ packages/core/src/memory/recall/index.ts | 1 + packages/core/src/memory/recall/recall-dedup.ts | 3 + packages/core/src/memory/recall/recall-store.ts | 35 ++++++- .../src/workflows/builtin-workflow-settings.ts | 14 +++ .../src/workflows/workflow-settings-resolver.ts | 12 ++- .../__tests__/WorkflowSettingsPanel.test.tsx | 8 ++ .../__tests__/workflow-setting-display.test.ts | 6 ++ .../app/components/workflow-setting-display.ts | 5 + .../memory-consolidation-heartbeat-hook.test.ts | 92 +++++++++++++++++ .../__tests__/memory-consolidation-ports.test.ts | 34 ++++++ ...memory-consolidation-run-audit-metadata.test.ts | 19 ++++ .../__tests__/memory-consolidation-tick.test.ts | 62 +++++++++++ packages/engine/src/agent-heartbeat.ts | 55 ++++++++++ packages/engine/src/index.ts | 1 + packages/engine/src/memory/index.ts | 3 + .../src/memory/memory-consolidation-adapters.ts | 29 ++++++ .../src/memory/memory-consolidation-material.ts | 22 ++++ packages/engine/src/memory/memory-consolidation.ts | 41 ++++++++ packages/engine/src/util/run-audit.ts | 10 ++ 31 files changed, 764 insertions(+), 3 deletions(-) Fusion-Task-Id: FN-8932 Fusion-Task-Lineage: b4fdec50-1f42-4120-af17-0b6f3a94586e Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
41bb94ba77 |
FN-8957: isolate PostgreSQL agents by project
Keep durable PostgreSQL agent records and analytics isolated to their bound project. - Scope agent reads, mutations, satellite records, ratings, reassignment links, and analytics task data by project. - Add a project-local agent-ratings migration and schema coverage. - Exercise duplicate agent IDs, ratings, and token analytics across shared PostgreSQL projects. Files changed: .changeset/fn-8957-agent-project-isolation.md | 7 + docs/multi-project.md | 9 + .../postgres/agent-project-isolation.pg.test.ts | 207 +++++++++++++++++++++ .../src/__tests__/postgres/schema-applier.test.ts | 13 +- packages/core/src/agents/agent-store.ts | 52 +++--- .../core/src/async-stores/async-agent-store.ts | 118 ++++++++++-- packages/core/src/board/team-analytics.ts | 20 +- ...0054_fn_8957_agent_rating_project_isolation.sql | 32 ++++ packages/core/src/postgres/schema-applier.ts | 13 +- packages/core/src/postgres/schema/project.ts | 6 +- packages/core/src/task-store/task-artifacts-ops.ts | 19 +- 11 files changed, 443 insertions(+), 53 deletions(-) Fusion-Task-Id: FN-8957 Fusion-Task-Lineage: 02cb3f13-e5d1-4cea-8afb-72bcd9fae890 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
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
|
37d32357e9 |
fix(workflow): keep assigned tasks executing instead of holding on a dead principal
Workflow principal routing conflated two different questions: whether an agent CAN run a node, and whether it can run it RIGHT NOW. Both produced a hold, and a named principal never falls through to the role pool — so an agent that could never satisfy the node wedged the task permanently. FN-8869, FN-8928, and FN-8845 were each explicitly assigned to a permanent engineer-role agent (which the assignment policy allows). Their `step-execute` nodes took that owner as `task-assignee` authority, found no `executor` tag, and held closed. Each card re-dispatched and re-held every ~15 minutes for hours while two idle `Workflow Executor` pool agents were never consulted. The only thing still touching them was the owner's hourly heartbeat, which logged "progressing, no blockers" and exited: heartbeat observation had replaced execution. - Structural incapability (wrong role, agent deleted, authority edited away) is no longer authority for the node. Routing continues to the column binding and then the role pool. - A resumed continuation whose fence proves stale discards it and re-routes, instead of re-asserting a dead principal on every dispatch. - Availability is unchanged and still fail-closed: a role-capable principal that is paused, disabled, or at session capacity holds, and is never silently replaced by a pool member. - An explicitly assigned engineer-role agent is now valid task-assignee authority for an executor node, so the assigned agent executes its own task continuously under graph dispatch. The role pool stays strict, since automatic backlog pickup by engineers is a separate opt-in. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
gsxdsm
|
51a5e1c275 |
fix(agents): separate heartbeat runtime from workflow routability
runtimeConfig.enabled answered two different questions. Every consumer in the
engine reads it as "run this agent's own durable heartbeat loop" — heartbeat
scheduling, error recovery, self-healing, in-process runtime — except the
workflow router, which also read it as "may own a workflow stage".
That conflation caused both failures:
- Built-in owners ship with the heartbeat off, which is CORRECT (they are
invoked by the workflow engine and must not run autonomous loops or auto-claim
work). That silently made every built-in role unroutable and deadlocked the
board.
- Enabling the heartbeat to restore routing then gave four agents autonomous
loops and auto-claiming nobody asked for.
Separate the flag:
- runtimeConfig.enabled governs the heartbeat runtime ONLY
- isWorkflowPrincipalEligible answers routability, and treats the four built-in
role owners as routable structurally — there is no fallback if a role cannot
route, so "unroutable" is not a state an operator can meaningfully select
- provision built-ins { enabled: false, autoClaimRelevantTasks: false }
- paused/errored still outranks the exemption, so it can never resurrect a
broken principal
Removes the earlier write-seam coercion that forced enabled:true — the invariant
is now structural rather than fought for on every write.
Also re-applies the principal-hold backoff ladder (15s -> 5m, checked before
graph entry) into executor/execute-workflow-graph.ts. PR #3317's executor peel
rewrote executor.ts from a pre-change base and dropped it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
gsxdsm
|
e573178e31 |
fix(agents): never let a built-in workflow role agent be unroutable
The board stopped moving. Work items churned held -> running -> held at ~3.5/sec across every task, pinning a core and writing ~19k workflowWorkItem audit rows/hour while nothing executed. Hold reason: workflow-principal-role-pool-exhausted:executor. provisionBuiltinWorkflowRoleAgents seeded the four permanent owners (triage, executor, reviewer, merger) with runtimeConfig.enabled=false, while the router's available() treats enabled===false as unavailable. The only permanent principals for every built-in role were unroutable BY CONSTRUCTION — shipped that way, so any instance without operator-created role agents deadlocks at its first workflow node. Nothing self-recovers: a pool only changes by operator action. Routability of these four is an invariant, not a setting. Unlike an operator's agent, disabling one does not opt an agent out — it removes the only thing that can run that stage, and there is no fallback. - seed built-ins enabled; converge existing rows on provisioning - enforceBuiltinWorkflowRoleRoutability coerces enabled back at the durable writeAgent seam, so no REST/UI/plugin/restore path can reintroduce the deadlock. Other runtimeConfig keys are preserved; operator-owned agents keep their off switch - share the static routability predicate (isWorkflowPrincipalEligible) between provisioning and the router so the two cannot drift apart again Also fix the spin itself: a principal hold had no cooldown, so the scheduler re-dispatched instantly and the run re-entered only to re-fence and re-park. It now records a backoff ladder (15s -> 5m) checked before graph entry, and logs once per distinct reason instead of every pass — the same self-recovering shape as holdForSessionContention. The hold never increments `attempt`, so no existing guard could ever fire. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
gsxdsm
|
6bd178bdcf |
FN-8864: add durable agent activity stream
Add a persisted, project-scoped agent activity feed with query and live delivery surfaces. - Store sequenced, attributed activity events with privacy-safe metadata and retention. - Emit activity across agents, workflow execution, reviews, approvals, merges, and recovery. - Provide paginated API history and resilient SSE tailing with coverage and documentation. - Renumber the activity migration to 0049 after reconciling main’s 0048 GitHub check-state migration. Files changed: .changeset/fn-8864-agent-activity-events.md | 7 + docs/architecture.md | 8 + docs/diagnostics.md | 4 + docs/storage.md | 1 + .../__tests__/agent-activity-attribution.test.ts | 21 + .../agent-activity-metadata-hygiene.test.ts | 60 +++ .../src/__tests__/agent-activity-writers.test.ts | 94 +++++ .../postgres/agent-activity-events.pg.test.ts | 57 +++ .../src/__tests__/postgres/schema-applier.test.ts | 34 +- packages/core/src/agents/agent-store.ts | 24 ++ packages/core/src/agents/approval-request-store.ts | 15 +- packages/core/src/index.ts | 4 + .../0049_fn_8864_agent_activity_events.sql | 24 ++ packages/core/src/postgres/schema-applier.ts | 15 +- packages/core/src/postgres/schema/project.ts | 19 +- packages/core/src/store.ts | 17 + .../core/src/task-store/agent-activity-outbox.ts | 75 ++++ .../src/task-store/async/async-agent-activity.ts | 71 ++++ packages/core/src/types.ts | 2 + packages/core/src/types/agents/agents.ts | 79 ++++ packages/dashboard/app/api.ts | 54 +++ .../src/__tests__/agent-activity-route.test.ts | 68 ++++ .../src/__tests__/sse-agent-activity.test.ts | 315 +++++++++++++++ packages/dashboard/src/routes/README.md | 2 +- .../src/routes/register-setup-activity-routes.ts | 19 +- packages/dashboard/src/sse.ts | 139 ++++++- .../src/__tests__/agent-activity-writers.test.ts | 442 +++++++++++++++++++++ packages/engine/src/executor.ts | 110 ++++- packages/engine/src/merger.ts | 15 +- packages/engine/src/self-healing.ts | 35 +- 30 files changed, 1809 insertions(+), 21 deletions(-) Fusion-Task-Id: FN-8864 Fusion-Task-Lineage: 4938f35b-a0bc-4eb3-905c-178fed859cc6 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
75796ebe6f |
FN-8850: capture task completion recommendations
Capture bounded, task-ready executor follow-ups at accepted completion. - Guide executor prompts to submit recommendations or an explicit empty list at completion. - Enforce default and disabled recommendation caps in completion handling. - Document recommendation behavior and cover prompt and validation contracts. Files changed: .../fn-8850-populate-task-recommendations.md | 7 +++ docs/dashboard-guide.md | 2 +- packages/core/src/agents/agent-prompts.ts | 16 ++++-- .../__tests__/ephemeral-task-create-gate.test.ts | 3 +- .../engine/src/__tests__/executor-prompt.test.ts | 67 ++++++++++++++++++++++ .../executor-task-recommendations.test.ts | 39 ++++++++++++- packages/engine/src/executor.ts | 44 ++++++++++++-- 7 files changed, 162 insertions(+), 16 deletions(-) Fusion-Task-Id: FN-8850 Fusion-Task-Lineage: 55a99d05-33fa-464c-869c-18a9cf7e495a Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
70a830d1ad |
FN-8830: backfill built-in workflow agent identities
Provision complete workflow-agent identities while preserving operator-owned configuration. - Seed instructions, souls, and managed setup mirrors for canonical workflow owners. - Repair sparse default owners and demote duplicate provenance without losing agent data. - Cover provisioning recovery and identity preservation with PostgreSQL and engine tests. Files changed: .changeset/fn-8830-workflow-agent-identities.md | 7 + docs/agents.md | 10 + ...nt-store-builtin-role-provisioning-pool.test.ts | 41 ++++ .../postgres/agent-instructions.pg.test.ts | 233 +++++++++++++++++++++ packages/core/src/agents/agent-store.ts | 167 ++++++++++++--- .../src/agents/workflow-role-agent-defaults.ts | 57 +++++ packages/core/src/index.ts | 6 + .../src/__tests__/agent-instructions.test.ts | 32 ++- 8 files changed, 526 insertions(+), 27 deletions(-) Fusion-Task-Id: FN-8830 Fusion-Task-Lineage: bdf75989-3282-4833-a8b6-8c2997af8363 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai> |
||
|
gsxdsm
|
1f9b0e644a |
fix(FN-8764): run built-in role provisioning on the locking transaction
provisionBuiltinWorkflowRoleAgents took a project-scoped pg_advisory_xact_lock
inside transactionImmediate, then ran provision() against the pool. The lock
holder therefore needed a SECOND pooled connection to finish while concurrent
callers occupied the remaining slots blocking on that same advisory lock. With
DEFAULT_POOL_MAX=3 this self-deadlocked: the holder could never complete, the
waiters could never take the lock, and every subsequent query -- that is, every
DB-backed API route -- queued forever behind an exhausted pool. Observed as a
dashboard that booted ("Ready in 6.5s") and then answered no /api request while
the event loop sat idle in kevent; pg_stat_activity showed one session idle in
transaction holding the lock and two active sessions waiting on it.
Thread an optional QueryHandle through listAgents, findAgentByName, createAgent,
and writeAgent so provisioning runs on tx and the lock and its work share one
connection.
Regression test bounds the pool to a single connection, which makes any second
checkout unsatisfiable and fails deterministically rather than racing. Verified
by reverting the one-line fix: the suite hangs past 300s instead of passing in
under 4s.
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
|
1d1a7fedab |
fix(FN-8785): ignore completed duplicate history
Fusion-Task-Id: FN-8785 |
||
|
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
|
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** |