root/fusion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
11,005 Commits 1 Branch 0 Tags
70330bcffbf8179a715021434e8e070e0bd2b892
Commit Graph

3007 Commits

Author SHA1 Message Date
gsxdsm
df8ad460af FN-7772: add per-lane thinking level for workflow model lanes 
Adds a per-workflow-lane thinking-level setting so execution, planning, and
review model lanes can each specify their own reasoning-effort/thinking
level, threaded through engine phase precedence so lane-specific settings
override the workflow default.

- Add workflow lane thinking-level settings to builtin workflow settings and
  settings schema, with new types in core.
- Thread lane thinking-level precedence through model-resolution and engine
  phase execution (executor, step-session-executor, triage,
  agent-session-helpers).
- Surface per-lane thinking-level controls in the dashboard
  WorkflowSettingsPanel and ProjectModelsSection.
- Add/adjust tests for workflow settings, agent-session-helpers, and the
  dashboard settings panels.
- Update settings-reference.md and workflow-steps.md docs.
- Add changeset for the new feature (minor).

Files changed:
 .changeset/fn-7772-workflow-lane-thinking.md       |  7 ++++
 docs/settings-reference.md                         | 10 ++---
 docs/workflow-steps.md                             |  4 +-
 .../core/src/__tests__/workflow-settings.test.ts   | 41 ++++++++++++++++++++
 packages/core/src/builtin-workflow-settings.ts     | 27 ++++++++++++-
 packages/core/src/index.ts                         |  4 +-
 packages/core/src/model-resolution.ts              | 45 +++++++++++++++++++++-
 packages/core/src/settings-schema.ts               |  3 ++
 packages/core/src/types.ts                         |  6 +++
 .../app/components/WorkflowSettingsPanel.tsx       | 35 ++++++++++++++---
 .../__tests__/SettingsModal.models-auth.test.tsx   |  7 +++-
 .../__tests__/WorkflowSettingsPanel.test.tsx       | 31 +++++++++++++++
 .../settings/sections/ProjectModelsSection.tsx     | 39 ++++++++++++++++---
 .../src/__tests__/agent-session-helpers.test.ts    | 13 ++++---
 .../engine/src/__tests__/executor-test-helpers.ts  |  1 +
 packages/engine/src/agent-session-helpers.ts       | 19 +++++----
 packages/engine/src/executor.ts                    |  4 +-
 packages/engine/src/step-session-executor.ts       |  2 +-
 packages/engine/src/triage.ts                      |  8 +++-
 19 files changed, 264 insertions(+), 42 deletions(-)

Fusion-Task-Id: FN-7772

Fusion-Task-Lineage: 70aba3a9-66c2-4bb0-aff9-acabc7b98818

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-10 02:21:01 -07:00
gsxdsm
235ff4c65e FN-7771: add per-node thinking level for workflow model bindings 
Adds a per-node thinking-level override (config.thinkingLevel) for workflow IR model bindings so individual workflow nodes can set reasoning effort independently of the global default.

- Extend workflow-ir types/schema and workflow-steps-to-ir conversion to carry config.thinkingLevel per node
- Wire thinkingLevel through executor and step-session-executor so the engine applies the per-node override during model calls
- Add a thinking-level control to WorkflowNodeEditor for authoring per-node overrides in the dashboard
- Add/extend tests covering IR round-trip, steps-to-ir conversion, executor model binding, and the WorkflowNodeEditor UI
- Document the new setting in docs/workflow-steps.md
- Add changeset for @runfusion/fusion (minor)

Files changed:
 .changeset/fn-7771-workflow-node-thinking.md       |  7 +++
 docs/workflow-steps.md                             | 10 ++-
 packages/core/src/__tests__/workflow-ir.test.ts    | 42 +++++++++++++
 .../src/__tests__/workflow-steps-to-ir.test.ts     | 15 +++++
 packages/core/src/store.ts                         |  1 +
 packages/core/src/types.ts                         |  9 +++
 packages/core/src/workflow-ir.ts                   | 21 +++++++
 packages/core/src/workflow-steps-to-ir.ts          |  5 ++
 .../app/components/WorkflowNodeEditor.tsx          | 42 ++++++++++++-
 .../__tests__/WorkflowNodeEditor.test.tsx          | 73 ++++++++++++++++++++++
 .../engine/src/__tests__/executor-test-helpers.ts  |  5 ++
 .../__tests__/executor-workflow-step-model.test.ts | 31 +++++++++
 .../src/__tests__/workflow-step-review.test.ts     | 53 ++++++++++++++++
 packages/engine/src/executor.ts                    | 61 ++++++++++++++++--
 packages/engine/src/step-session-executor.ts       | 12 +++-
 packages/engine/src/workflow-node-handlers.ts      | 29 ++++++++-
 16 files changed, 404 insertions(+), 12 deletions(-)

Fusion-Task-Id: FN-7771

Fusion-Task-Lineage: 5dbe3efb-773d-47db-9412-b740eb1d7745

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-10 01:49:15 -07:00
gsxdsm
5f14a58d3b FN-7770: add per-lane thinking-level overrides for project & global model settings 
Adds an optional thinking-effort/reasoning override per model lane in Settings (project and global), resolved with precedence task > lane > global default, and reconciles this work with the already-landed FN-7768 inline thinking-level control on CustomModelDropdown (kept the shared shouldShowThinking/thinkingBadgeLabel implementation to avoid duplicating the selector/badge UI).

- Add lane thinking-level settings schema fields and runtime precedence (task > lane > global default) in @fusion/core
- Wire per-lane thinking selectors into GlobalModelsSection and ProjectModelsSection via CustomModelDropdown's existing showThinkingLevel/thinkingLevel/onThinkingLevelChange/defaultThinkingLevel props
- Resolve merger thinking level from the default lane rather than the title-summarizer lane in engine session helpers/executor/merger/triage
- Update settings-reference docs and add a minor changeset for the new lane thinking overrides
- Add/expand test coverage: settings-parity, store-settings, settings-sections, agent-session-helpers
- Add new i18n key models.options.defaultWithLevel across locales

Files changed:
 .changeset/fn-7770-lane-thinking.md                |   7 ++
 docs/settings-reference.md                         |   8 ++
 .../core/src/__tests__/settings-parity.test.ts     |  17 ++++
 packages/core/src/__tests__/store-settings.test.ts |  42 +++++++++
 packages/core/src/settings-schema.ts               |  14 +++
 packages/core/src/types.ts                         |  16 ++++
 .../app/__tests__/settings-sections.test.tsx       | 100 ++++++++++++++++++---
 .../app/components/CustomModelDropdown.css         |   1 +
 .../dashboard/app/components/SettingsModal.tsx     |  37 ++++++++
 .../settings/sections/GlobalModelsSection.tsx      |   9 +-
 .../settings/sections/ProjectModelsSection.tsx     |  12 ++-
 .../app/components/settings/sections/context.ts    |   2 +
 .../src/__tests__/agent-session-helpers.test.ts    |  36 ++++++++
 packages/engine/src/agent-session-helpers.ts       |  60 +++++++++++++
 packages/engine/src/executor.ts                    |  14 +--
 packages/engine/src/merger-ai.ts                   |  12 ++-
 packages/engine/src/merger.ts                      |  12 +--
 packages/engine/src/pr-response-run-ops.ts         |   4 +-
 packages/engine/src/step-session-executor.ts       |   3 +-
 packages/engine/src/triage.ts                      |   5 +-
 packages/i18n/locales/en/app.json                  |   3 +-
 packages/i18n/locales/es/app.json                  |   3 +-
 packages/i18n/locales/fr/app.json                  |   3 +-
 packages/i18n/locales/ko/app.json                  |   3 +-
 packages/i18n/locales/zh-CN/app.json               |   3 +-
 packages/i18n/locales/zh-TW/app.json               |   3 +-
 packages/i18n/src/resources.d.ts                   |   3 +
 27 files changed, 390 insertions(+), 42 deletions(-)

Fusion-Task-Id: FN-7770
Fusion-Task-Lineage: 3418c621-ac99-4cd4-a435-9348da03972f
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-10 01:15:40 -07:00
gsxdsm
587bdfd394 FN-7764: add cross-type artifact create/list/view test coverage 
Extend artifact test coverage to pin creation, listing, and viewing across every artifact type and payload variant on both the agent/dashboard-chat tool surface and the dashboard artifacts route.

- Add a route-level integration test covering list/serve for all artifact types (document, image, video, audio, other) across inline content, uri reference, and binary data payloads, including task-scoped filtering, registry-level (task-less) artifacts, and 404 behavior for uri-only artifacts requested via /media.
- Add an engine-level real-TaskStore test exercising fn_artifact_register/list/view (agent tools) and the dashboard-chat artifact tool for every artifact type and content/uri/dataBase64 variant, asserting list and view output correctness.
- Factor out shared PNG_IMAGE_BYTES fixture and per-type MIME/binary fixtures to keep new assertions concise.

Files changed:
 .../__tests__/artifacts-route-integration.test.ts  | 150 ++++++++++++++++++++-
 .../src/__tests__/agent-artifact-tools.test.ts     | 142 ++++++++++++++++++-
 2 files changed, 287 insertions(+), 5 deletions(-)

Fusion-Task-Id: FN-7764

Fusion-Task-Lineage: 187b3f0f-d1b4-42fe-9658-1ee67870b524

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 23:48:45 -07:00
gsxdsm
18841d76a0 FN-7761: fix Grok CLI auth to use logged-in CLI instead of requiring API key 
Packaged fn serve/daemon/dashboard hosts previously failed with a misleading missing-API-key error for grok-cli agents even though the operator was already logged in via the Grok CLI. This fixes routing so those hosts eagerly ensure the bundled Grok Runtime plugin is installed/loaded before session creation, and no longer silently falls back to the key-requiring direct endpoint when no key is visible.

- Eagerly ensure the bundled fusion-plugin-grok-runtime in serve, daemon, and dashboard commands before loadAllPlugins() so runtime id "grok" is available on fresh installs without manual plugin-settings setup.
- agent-session-helpers.ts: deriveGrokRuntimeHintForNoVisibleKey now throws an actionable error (naming both remediations: install/enable the Grok CLI runtime plugin, or set GROK_API_KEY) instead of silently falling through to the key-requiring pi/openai-completions path when the runtime can't be loaded.
- Update docs/grok-cli-contract.md to document the FN-7761 packaged-host wiring and new no-silent-fallback behavior.
- Add regression tests for the packaged bootstrap behavior and bundled-plugin install path.
- Add changeset for @runfusion/fusion (patch, category: fix).

Files changed:
 .changeset/fn-7761-grok-cli-packaged-routing.md    |  7 +++++
 docs/grok-cli-contract.md                          | 19 +++++++++----
 .../__tests__/grok-runtime-bootstrap.test.ts       | 31 ++++++++++++++++++++++
 packages/cli/src/commands/daemon.ts                | 17 +++++++++++-
 packages/cli/src/commands/dashboard.ts             | 20 +++++++++++++-
 packages/cli/src/commands/serve.ts                 | 19 +++++++++++--
 .../__tests__/bundled-plugin-install.test.ts       | 17 ++++++++++++
 .../src/__tests__/grok-runtime-routing.test.ts     | 17 ++++++------
 packages/engine/src/agent-session-helpers.ts       | 15 +++++++++--
 9 files changed, 142 insertions(+), 20 deletions(-)

Fusion-Task-Id: FN-7761
Fusion-Task-Lineage: 3be5f054-965c-4e8a-ad91-6e61d4dc4a42
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 23:43:15 -07:00
gsxdsm
2be6040b02 FN-7758: route Grok CLI fallback models through the CLI runtime when no API key is visible 
Fix Grok CLI 'missing API key' false-positive by extending the no-visible-key routing invariant to configured fallback models, not just the default provider.
- deriveGrokRuntimeHintForNoVisibleKey now also triggers when the fallback provider is grok-cli
- new applyGrokCliNoKeyRuntimeOptions promotes a grok-cli fallback model into the primary session (stripping the provider-qualified model prefix) instead of leaving it as an unused fallback
- docs/grok-cli-contract.md updated to describe the fallback-routing contract
- added regression tests in grok-runtime-routing.test.ts, chat-manager.test.ts, and chat-manager-room-hybrid.test.ts
- added changeset fn-7758-grok-cli-no-key-routing.md (patch)

Files changed:
 .changeset/fn-7758-grok-cli-no-key-routing.md      |   7 ++
 docs/grok-cli-contract.md                          |  29 +++--
 .../src/__tests__/chat-manager-room-hybrid.test.ts |  36 +++++++
 .../dashboard/src/__tests__/chat-manager.test.ts   |  41 +++++++
 packages/dashboard/src/chat.ts                     |  16 ++-
 .../src/__tests__/grok-runtime-routing.test.ts     | 118 +++++++++++++++++++++
 packages/engine/src/agent-session-helpers.ts       |  36 ++++++-
 7 files changed, 266 insertions(+), 17 deletions(-)

Fusion-Task-Id: FN-7758

Fusion-Task-Lineage: 6b564b21-50ab-4c3e-b0d7-7fded2091d90

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 22:19:22 -07:00
gsxdsm
f7c6f560c0 FN-7753: route grok-cli execution through the grok CLI when no Fusion-visible GROK_API_KEY resolves 
Route grok-cli model selections through the grok CLI runtime when no Fusion-visible GROK_API_KEY is available.

- Add read-only isGrokApiKeyFusionVisible() in packages/core/src/grok-provider.ts, refactored to share user-settings-file reading with hydrateGrokApiKeyFromUserSettings without mutating process.env or logging key material.
- In packages/engine/src/agent-session-helpers.ts, auto-derive the existing "grok" runtimeHint when defaultProvider is grok-cli, no key is Fusion-visible, and the grok plugin runtime is registered; explicit runtime hints and mock/test-mode routing remain unchanged, and the provider-qualified model prefix is stripped before handoff.
- Normalize provider-qualified model ids (grok-cli/<id>, grok/<id>) in the grok-runtime plugin's runtime-adapter and CLI stream spawn so the concrete model reaches `grok --model`, with the historical grok/default fallback preserved for the no-model path.
- Update docs (grok-cli-contract.md, settings-reference.md, plugin README) and add/extend tests covering the new fallback behavior, model normalization, and CLI streaming.
- Add changeset fn-7753-grok-cli-no-key-fallback.md (patch, fix).

Files changed:
 .changeset/fn-7753-grok-cli-no-key-fallback.md     |   7 ++
 docs/grok-cli-contract.md                          |  83 ++++++++++------
 docs/settings-reference.md                         |   6 +-
 .../__tests__/grok-provider-user-settings.test.ts  |  46 +++++++++
 packages/core/src/grok-provider.ts                 |  39 +++++++-
 packages/core/src/index.gate.ts                    |   1 +
 packages/core/src/index.ts                         |   1 +
 .../src/__tests__/grok-runtime-routing.test.ts     | 107 +++++++++++++++++++--
 packages/engine/src/agent-session-helpers.ts       |  52 +++++++++-
 plugins/fusion-plugin-grok-runtime/README.md       |  46 +++++----
 .../src/__tests__/cli-stream.test.ts               |  70 ++++++++++++++
 .../src/__tests__/runtime-adapter.test.ts          |  28 ++++++
 .../fusion-plugin-grok-runtime/src/cli-stream.ts   |   6 ++
 .../src/runtime-adapter.ts                         |  24 ++++-
 14 files changed, 443 insertions(+), 73 deletions(-)

Fusion-Task-Id: FN-7753

Fusion-Task-Lineage: 30ef7265-1ba9-47fd-8c4e-87b02f6a1d78

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 21:36:14 -07:00
gsxdsm
d2c2a4cab1 FN-7754: seed OpenAI GPT-5.6 Codex models into pi createFnAgent registry 
Wires the GPT-5.6 codenamed OpenAI Codex models (gpt-5.6-luna/sol/terra) into the engine pi model-registry seeding surface, mirroring the dashboard's /api/models supplemental merge so the models are no longer missing from pi.

- Call mergeSupplementalOpenAiCodexModels() in createFnAgent (packages/engine/src/pi.ts) alongside the existing Anthropic supplemental merge
- Add regression tests covering synthesis of missing GPT-5.6 rows and dedupe against pinned catalog entries
- Update docs/settings-reference.md to describe the additive surfacing on both /api/models and the engine/pi registry-seeding path
- Add a patch changeset for @runfusion/fusion

Files changed:
 .changeset/fn-7754-openai-gpt-5-6-pi-surface.md    |  7 +++
 docs/settings-reference.md                         |  2 +-
 .../src/__tests__/pi-create-fn-agent.test.ts       | 63 ++++++++++++++++++++++
 packages/engine/src/pi.ts                          |  6 +++
 4 files changed, 77 insertions(+), 1 deletion(-)

Fusion-Task-Id: FN-7754

Fusion-Task-Lineage: b61b6812-c94b-46d8-b187-445ccdd6e4e9

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 21:30:34 -07:00
gsxdsm
eb377ba831 FN-7750: gate shared-branch-group auto-merge exemption on live groups 
Fixes autoMerge=false being bypassed for engine-created branch-group member tasks whose branch group had already dissolved/finalized.

- Add isLiveSharedBranchGroupMemberIntegration(task, group) in @fusion/core, requiring the branch group's status be "open" before the shared-branch-member exemption bypasses the global/task autoMerge:false hold.
- Export the new helper from packages/core/src/index.ts and index.gate.ts.
- Thread the live-group check through packages/engine/src/project-engine.ts (allowInReviewMergeProcessing, enqueueEligibleInReviewTasks, merge-confirmed fast-path branch routing, and merge handoff paths).
- Add TaskExecutor.isLiveSharedBranchGroupMember helper in packages/engine/src/executor.ts and use it in retryable pre-merge remediation, no-op finalize, benign pause-abort classification, and merge-processing gates.
- Keep self-healing.ts's solo no-op finalize predicate on the pure branchContext-shape check (isSharedBranchGroupMemberIntegration) intentionally, so stale shared-group members stay excluded from solo finalize regardless of group liveness.
- Add regression tests covering the executor and project-engine auto-merge-hold behavior for stale/dissolved branch groups.
- Add a patch changeset documenting the fix.

Files changed:
 .../fn-7750-automerge-hold-stale-branch-group.md   |  7 ++
 packages/core/src/__tests__/task-merge.test.ts     | 42 +++++++++--
 packages/core/src/index.gate.ts                    |  1 +
 packages/core/src/index.ts                         |  1 +
 packages/core/src/task-merge.ts                    | 13 +++-
 ...cutor-live-branch-group-auto-merge-hold.test.ts | 85 ++++++++++++++++++++++
 .../engine/src/__tests__/project-engine.test.ts    | 37 +++++++++-
 packages/engine/src/executor.ts                    | 22 ++++--
 packages/engine/src/project-engine.ts              | 32 +++++---
 packages/engine/src/self-healing.ts                |  1 +
 10 files changed, 214 insertions(+), 27 deletions(-)

Fusion-Task-Id: FN-7750

Fusion-Task-Lineage: d61f8847-0b09-49b5-b66a-00018c8738bb

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:08 -07:00
gsxdsm
786a274ae6 FN-7749: fix benign pause/resume abort marking manual merge holds as failed 
Fixes tasks in auto-merge-off manual merge hold getting incorrectly marked failed by a benign pause/resume abort, which blocked Merge & Close.

- Add isBenignManualMergeHoldPauseAbort classifier in executor.ts: recognizes a hard-cancel pause-abort at a merge-region node while auto-merge is off (or processing is disallowed) as benign, and preserves the in-review row instead of failing/re-enqueueing it.
- Clear stale pause-abort status/error and suppress the failure notification when this benign manual-hold case is detected, per FN-5147's no-backward-move/no-reenqueue contract.
- Extend self-healing.ts recovery to handle this manual-hold case alongside existing paused-abort recovery paths.
- Add/extend tests in merge-node-paused-abort-retryable.test.ts and self-healing-paused-abort-recovery.test.ts covering the new benign classification.
- Document the fix in docs/architecture.md.
- Add changeset (patch) describing the user-facing fix.

Files changed:
 .changeset/fn-7749-manual-merge-hold-false-failure.md                                   |  7 +++
 docs/architecture.md                                                                    |  4 +-
 packages/engine/src/__tests__/reliability-interactions/merge-node-paused-abort-retryable.test.ts | 50 +++++++++++++++++----
 packages/engine/src/__tests__/self-healing-paused-abort-recovery.test.ts                | 49 ++++++++++++++++++++-
 packages/engine/src/executor.ts                                                         | 51 +++++++++++++++++++++-
 packages/engine/src/self-healing.ts                                                     | 23 ++++++++--
 6 files changed, 168 insertions(+), 16 deletions(-)

Fusion-Task-Id: FN-7749
Fusion-Task-Lineage: 6d90adc3-6cd9-463d-b9d0-7a5c3069c1a5
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:08 -07:00
gsxdsm
0e90578122 FN-7737: Add file_scope agent permission category with default allow disposition 
Introduces a new file_scope sensitive-action category to the agent permission policy model so file-scope-related FN tools are classified and gated distinctly from other categories, defaulting to allowed under the grant-all preset.

- Add file_scope to AGENT_PERMISSION_POLICY_ACTION_CATEGORIES in @fusion/core types
- Classify FILE_SCOPE_FN_TOOLS in both agent-action-gate and permanent-agent-gating with a uniform preset disposition (no review_gate_bypass-style override)
- Update AgentDetailView and AgentPermissionPolicyEditor to surface the new category in the dashboard UI
- Add/extend unit tests across core, engine, and dashboard packages covering the new category's resolution, gating, and UI rendering
- Update docs/agents.md and docs/settings-reference.md to document the new permission category
- Regenerate i18n locale strings (en/es/fr/ko/zh-CN/zh-TW) and resources.d.ts for the new category labels
- Add changeset for @runfusion/fusion (minor) describing the new File Scope permission category

Files changed:
 .../fn-7737-file-scope-permission-category.md      |   7 +
 docs/agents.md                                     |  10 +-
 docs/settings-reference.md                         |   8 +-
 .../agent-permission-policy-resolution.test.ts     |  13 +
 .../src/__tests__/agent-permission-policy.test.ts  |  45 +++
 packages/core/src/types.ts                         |   7 +
 .../dashboard/app/components/AgentDetailView.tsx   |   2 +
 .../app/components/AgentPermissionPolicyEditor.tsx |   8 +
 .../__tests__/AgentPermissionPolicyEditor.test.tsx |  37 +++
 .../engine/src/__tests__/agent-action-gate.test.ts |  46 +++
 .../src/__tests__/gating-classifications.test.ts   |  67 +++++
 .../src/__tests__/permanent-agent-gating.test.ts   |  41 +++
 packages/engine/src/agent-action-gate.ts           |   7 +
 packages/engine/src/gating-classifications.ts      |   6 +
 packages/engine/src/permanent-agent-gating.ts      |   6 +
 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/zh-CN/app.json               |   4 +
 packages/i18n/locales/zh-TW/app.json               |   4 +
 packages/i18n/src/resources.d.ts                   | 310 +++++++++++++++------
 22 files changed, 550 insertions(+), 94 deletions(-)

Fusion-Task-Id: FN-7737

Fusion-Task-Lineage: 7b161fb3-7dd9-4860-aa4d-0cb35f38ea5b

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:07 -07:00
gsxdsm
1fa4a69dde FN-7747: derive dashboard authStorage fallback from engine.getAuthStorage() 
Fixes desktop provider API keys not persisting when a host wires an engine into createServer() but forgets to pass its own authStorage, which previously caused register-auth-routes.ts to throw "Authentication is not configured".

- Add ProjectEngine.getAuthStorage() exposing the OAuth subsystem's raw createFusionAuthStorage() instance
- In createServer(), derive options.authStorage from engine.getAuthStorage() when not explicitly provided (mirrors existing engine-derivation pattern for onMerge/automationStore/etc.); explicit authStorage still overrides
- Add regression tests covering the fallback-derivation and explicit-override behavior
- Add changeset (patch) documenting the fix for @runfusion/fusion

Files changed:
 .changeset/fn-7747-derive-authstorage-from-engine.md |   7 ++
 packages/dashboard/src/__tests__/server.test.ts      | 119 +++++++++++++++++++++
 packages/dashboard/src/server.ts                     |  28 ++++-
 packages/engine/src/project-engine.ts                |  25 +++++
 4 files changed, 178 insertions(+), 1 deletion(-)

Fusion-Task-Id: FN-7747

Fusion-Task-Lineage: f8e72b15-d084-4e8d-89db-47453d57b41b

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:07 -07:00
gsxdsm
2ff8e2e13e FN-7743: detect and recover stalled in-progress executor tasks in overseer 
Fix the planner overseer's executor-stage stall detection so hung in-progress tasks get unstuck instead of being reported as progressing forever.

- Add configurable stuck-detection: the executor-stage overseer observation now emits signal: "stuck" once an in-progress task has been inactive past a new plannerOverseerExecutorStuckAfterMs threshold, feeding the existing decidePlannerRecovery -> bounded inject_guidance recovery path.
- Register the new plannerOverseerExecutorStuckAfterMs setting in builtin-workflow-settings.ts and export it via core index.ts/index.gate.ts.
- Preserve human-control withholds (user-paused / approval-blocked / autoMerge-off) taking precedence over stuck detection.
- Add/extend tests covering planner-overseer, planner-recovery-controller, planner-recovery, and builtin-workflow-settings-triage.
- Document the new setting in docs/architecture.md and docs/settings-reference.md.
- Add changeset fn-7743-overseer-executor-stall.md (patch).

Files changed:
 .changeset/fn-7743-overseer-executor-stall.md      |   7 +
 docs/architecture.md                               |  31 +++++
 docs/settings-reference.md                         |   3 +-
 .../builtin-workflow-settings-triage.test.ts       |  22 ++++
 .../core/src/__tests__/planner-recovery.test.ts    |  12 ++
 packages/core/src/builtin-workflow-settings.ts     |  26 ++++
 packages/core/src/index.gate.ts                    |   1 +
 packages/core/src/index.ts                         |   1 +
 .../engine/src/__tests__/planner-overseer.test.ts  | 146 +++++++++++++++++++++
 .../__tests__/planner-recovery-controller.test.ts  |  52 +++++++-
 packages/engine/src/planner-overseer.ts            |  88 ++++++++++++-
 packages/engine/src/project-engine.ts              |  11 +-
 12 files changed, 391 insertions(+), 9 deletions(-)

Fusion-Task-Id: FN-7743

Fusion-Task-Lineage: 791852a2-5b77-48de-955a-1b3916616dfa

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:07 -07:00
gsxdsm
bab42b40dd FN-7736: prevent recovery/oversight from resuming approval-blocked tasks 
Introduces a canonical awaiting-approval pause reason and predicate so recovery and oversight paths treat approval-blocked tasks as terminal-until-approved instead of eligible for early rebound.

- Add isTaskBlockedOnApproval predicate and canonical "awaiting-approval" pause reason in @fusion/core (store.ts, task-merge.ts, index.ts/index.gate.ts)
- Exclude approval-blocked tasks from paused-scope-decay rebound in self-healing.ts
- Keep the planner overseer withholding oversight for approval-blocked tasks (overseer-human-control-policy.ts)
- Executor and agent-heartbeat now recognize the approval-blocked state and avoid resuming it
- Add regression tests across store-persistence, task-merge, overseer-human-control-policy, paused-scope-decay, and self-healing-paused-abort-recovery
- Update docs/architecture.md with the new approval-hold invariant
- Add changeset fn-7736-approval-hold.md (patch)

Files changed:
 .changeset/fn-7736-approval-hold.md                |  7 +++
 docs/architecture.md                               | 64 ++++++++++++++++++++--
 .../core/src/__tests__/store-persistence.test.ts   | 18 ++++++
 packages/core/src/__tests__/task-merge.test.ts     | 34 ++++++++++++
 packages/core/src/index.gate.ts                    |  2 +
 packages/core/src/index.ts                         |  2 +
 packages/core/src/store.ts                         | 18 +++++-
 packages/core/src/task-merge.ts                    | 34 ++++++++++++
 .../executor-approval-gate-suspend.test.ts         |  5 +-
 .../src/__tests__/heartbeat-executor.test.ts       |  5 +-
 .../overseer-human-control-policy.test.ts          | 44 +++++++++++++++
 .../paused-scope-decay.test.ts                     | 44 +++++++++++++++
 .../self-healing-paused-abort-recovery.test.ts     | 21 +++++++
 packages/engine/src/agent-heartbeat.ts             |  8 ++-
 packages/engine/src/executor.ts                    | 13 ++++-
 .../engine/src/overseer-human-control-policy.ts    | 45 +++++++++++----
 packages/engine/src/self-healing.ts                | 12 +++-
 17 files changed, 351 insertions(+), 25 deletions(-)

Fusion-Task-Id: FN-7736

Fusion-Task-Lineage: 67e05b7f-f621-4f9b-bc01-721ff05d715b

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:06 -07:00
gsxdsm
e4a59f7269 fix: remove over-firing triage release-authorization gate 
The triage release-authorization gate (FN-6481/FN-6469) false-flagged any
spec that merely mentioned release tooling (scripts/release.mjs, pnpm release)
and, because non-user sources made the in-band authorization marker inert,
stranded ordinary tasks in awaiting-approval with no exit.

- Delete triage-release-authorization.ts + its test and the finalizeApprovedTask
  parking block; release-class specs now flow through triage normally.
- Remove the dashboard approve/reject-plan API guards and UI gating so tasks
  still carrying the legacy awaitingApprovalReason="release-authorization" hold
  render as ordinary manual plan-approval holds and can be resolved.
- Keep the awaitingApprovalReason field + activity label for backward-compat.
- Replace the engine gate with agent instruction (AGENTS.md -> Releasing):
  agents must never run a release from inside a Fusion task.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-09 19:58:06 -07:00
gsxdsm
927741a8cf FN-7727: persist failed workflow step history across self-healing retries 
Preserves prior failed pre-merge review attempts instead of overwriting them when self-healing re-runs a failed workflow step.

- Add optional bounded `priorAttempts?: WorkflowStepResult[]` field to `WorkflowStepResult` (capped at `MAX_WORKFLOW_STEP_PRIOR_ATTEMPTS`)
- Add shared pure `upsertWorkflowStepResult(existing, incoming, opts?)` helper in `@fusion/core` (packages/core/src/workflow-step-results.ts)
- Route the executor graph adapter's `recordWorkflowStepResult` and triage's `recordPlanReviewWorkflowResult` through the new helper so a self-healing recovery re-run snapshots the prior failed/advisory_failure attempt into `priorAttempts` instead of dropping it
- Selection logic (self-healing, merge-blocker, progress/timing) is unchanged and still reads only the current entry
- Surface prior failed attempts in the TaskDetailModal Summary tab's Workflow results list as a collapsed "previous failed attempts" disclosure
- Add core/engine/dashboard tests covering the upsert helper, self-healing recovery snapshotting, and the UI disclosure
- Document the behavior in docs/workflow-steps.md
- Add changeset for @runfusion/fusion (patch)

Files changed:
 .changeset/fn-7727-persist-failed-step-history.md  |   7 ++
 docs/workflow-steps.md                             |  15 +++
 .../src/__tests__/workflow-step-results.test.ts    | 138 +++++++++++++++++++++
 packages/core/src/index.gate.ts                    |   4 +
 packages/core/src/index.ts                         |   4 +
 packages/core/src/types.ts                         |  19 +++
 packages/core/src/workflow-step-results.ts         |  99 +++++++++++++++
 .../dashboard/app/components/TaskDetailModal.css   |  55 ++++++++
 .../dashboard/app/components/TaskSummaryTab.tsx    |  42 ++++++-
 .../TaskSummaryTab.prior-attempts.test.tsx         |  89 +++++++++++++
 .../clear-terminal-workflow-step-failures.test.ts  |  27 ++++
 packages/engine/src/__tests__/self-healing.test.ts |  50 ++++++++
 ...flow-step-results-self-healing-recovery.test.ts | 115 +++++++++++++++++
 packages/engine/src/executor.ts                    |  29 +++--
 packages/engine/src/triage.ts                      |  14 ++-
 15 files changed, 688 insertions(+), 19 deletions(-)

Fusion-Task-Id: FN-7727
Fusion-Task-Lineage: 7316fb18-bc92-426d-91f4-b1a4ad41c9b1
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:05 -07:00
gsxdsm
d44dbaab15 FN-7728: add review_gate_bypass RBAC category for fn_task_bypass_review 
Introduces a dedicated review_gate_bypass permission-policy category so operators can govern who may bypass a failed pre-merge review gate independently of ordinary task-mutation permissions.

- Add review_gate_bypass as a new sensitive-action category in packages/core/src/types.ts, distinct from task_agent_mutation, with fn_task_bypass_review as its sole example tool
- Default review_gate_bypass to require-approval even under the unrestricted preset (stricter than the preset's uniform disposition) in packages/core/src/agent-permission-policy.ts, while approval-required/locked-down already cover it uniformly
- Classify fn_task_bypass_review into the new category via a shared REVIEW_GATE_BYPASS_FN_TOOLS set in packages/engine/src/gating-classifications.ts, consumed identically by both evaluateAgentActionGate and the permanent-agent gate to prevent path drift
- Render the new category as its own row in the dashboard's project-default and per-agent AgentPermissionPolicyEditor, surfaced in AgentDetailView
- Update docs/settings-reference.md and add unit tests across core/engine/dashboard covering the new category, its stricter default, and gate-classification alignment
- Add changeset (@runfusion/fusion: minor) documenting the new operator-facing permission category

Files changed:
 .changeset/fn-7728-review-gate-bypass-rbac.md      |  7 +++
 docs/settings-reference.md                         |  8 +--
 .../src/__tests__/agent-permission-policy.test.ts  | 54 ++++++++++++++++++-
 packages/core/src/agent-permission-policy.ts       | 12 ++++-
 packages/core/src/types.ts                         |  8 +++
 .../dashboard/app/components/AgentDetailView.tsx   |  2 +
 .../app/components/AgentPermissionPolicyEditor.tsx |  8 +++
 .../__tests__/AgentPermissionPolicyEditor.test.tsx |  5 ++
 .../engine/src/__tests__/agent-action-gate.test.ts | 45 ++++++++++++++++
 .../src/__tests__/gating-classifications.test.ts   | 63 ++++++++++++++++++++++
 .../src/__tests__/permanent-agent-gating.test.ts   | 41 ++++++++++++++
 packages/engine/src/agent-action-gate.ts           |  7 +++
 packages/engine/src/gating-classifications.ts      |  8 ++-
 packages/engine/src/permanent-agent-gating.ts      |  6 +++
 14 files changed, 266 insertions(+), 8 deletions(-)

Fusion-Task-Id: FN-7728

Fusion-Task-Lineage: 100c8563-2897-4d53-9546-5c2faa6ab7d8

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:05 -07:00
gsxdsm
e5c3ffbb39 FN-7725: wire Grok CLI runtime adapter routing end-to-end with tests and docs 
Formalizes and tests the existing agent Runtime-mode picker path as the decided Grok CLI routing wiring.

- Add FNXC decision note at the extractRuntimeHint seam documenting the Grok CLI routing chain (agent-session-helpers.ts)
- Add routing test verifying runtimeHint="grok" resolves through resolveRuntime/resolvePluginRuntime to GrokRuntimeAdapter (grok-runtime-routing.test.ts)
- Update docs/grok-cli-contract.md with the wiring decision and documented limitations
- Update plugins/fusion-plugin-grok-runtime/README.md with routing guidance
- Add changeset for the new opt-in Grok CLI streaming runtime routing feature

Files changed:
 .changeset/fn-7725-grok-cli-routing.md             |   7 +
 docs/grok-cli-contract.md                          | 106 ++++++--
 .../src/__tests__/grok-runtime-routing.test.ts     | 275 +++++++++++++++++++++
 packages/engine/src/agent-session-helpers.ts       |  12 +
 plugins/fusion-plugin-grok-runtime/README.md       |  38 ++-
 5 files changed, 414 insertions(+), 24 deletions(-)

Fusion-Task-Id: FN-7725

Fusion-Task-Lineage: f5210793-59d0-4a0c-8152-4c5ef61ca737

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:04 -07:00
gsxdsm
626e00288c FN-7720: add operator review-lane bypass for stranded pre-merge review failures 
Add a policy-gated review-lane bypass primitive so operators can unstick cards stranded by a failed pre-merge review step (e.g. the no-feedback review-engine defect), without exposing it to agent-driven lanes.

- Add `store.bypassFailedPreMergeReviewStep(id, { reason, actor })` in @fusion/core plus `getLatestFailedPreMergeReviewStep` in task-merge.ts, and new `bypassedBy`/`bypassedAt`/`bypassReason`/`bypassedFromStatus`/`bypassedFromVerdict` fields on `WorkflowStepResult`
- Add operator-only `fn_task_bypass_review` CLI/pi-extension tool; explicitly withheld from executor/reviewer/triage agent tool lists
- Add `POST /tasks/:id/bypass-review` dashboard API route and wire it through `register-task-workflow-routes.ts` and legacy API compatibility layer
- Add dashboard UI affordance (context menu action + task detail modal + right-dock controller wiring) to trigger the bypass with a reason
- Add i18n strings for the bypass action/labels across en/es/fr/ko/zh-CN/zh-TW locales
- Update `gating-classifications.ts` to recognize the bypassed state
- Add unit tests: `store-bypass-review.test.ts`, `task-merge-bypass.test.ts`, extension test coverage, and `useTasks` hook test coverage
- Update docs (`docs/workflow-steps.md`, `docs/dashboard-guide.md`, AGENTS.md, fusion skill references) to describe the new bypass tool/route
- Add changeset `.changeset/fn-7720-review-lane-bypass-primitive.md` (minor)

Files changed:
$(git diff --cached --stat)

Fusion-Task-Id: FN-7720

Fusion-Task-Lineage: 590b020a-ae02-4b51-8189-df8f54bf3044

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:04 -07:00
gsxdsm
e657d3b965 FN-7723: add cross-process agent state change notification bus 
Adds opt-in cross-process change detection to AgentStore so the engine reacts to CLI-driven agent stop/start mutations promptly instead of waiting for the periodic audit sweep.

- AgentStore gains fs.watch-based (with poll fallback) cross-process notification, modeled on TaskStore's existing mechanism
- Re-emits existing agent:updated/agent:stateChanged events in the engine process when another process (the fn CLI) mutates an agent row
- HeartbeatTriggerScheduler listeners now fire immediately instead of waiting up to 60s for the auditTimerRegistrations sweep; the sweep remains as durable backstop
- in-process-runtime.ts wires up the new notification bus
- Adds unit tests for agent-store cross-process notifications and heartbeat-scheduler reaction behavior
- Updates docs/agents.md and docs/architecture.md
- Adds changeset (patch) for @runfusion/fusion

Files changed:
 .changeset/fn-7723-cross-process-agent-notify.md   |   7 +
 docs/agents.md                                     |   1 +
 docs/architecture.md                               |   1 +
 packages/core/src/__tests__/agent-store.test.ts    | 177 +++++++++++++++++
 packages/core/src/agent-store.ts                   | 210 ++++++++++++++++++++-
 .../src/__tests__/heartbeat-scheduler.test.ts      | 162 ++++++++++++++++
 packages/engine/src/runtimes/in-process-runtime.ts |  30 +++
 7 files changed, 587 insertions(+), 1 deletion(-)

Fusion-Task-Id: FN-7723
Fusion-Task-Lineage: d3a7fa05-b40d-4388-8e98-140f9d8861c9
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:04 -07:00
gsxdsm
a24b0fac1a FN-7721: cap heartbeat worktree-acquisition retries and record exhaustion failures 
Bounds durable-agent heartbeat worktree acquisition to a fixed retry count instead of requeuing to todo indefinitely across heartbeat cycles.

- Add MAX_HEARTBEAT_WORKTREE_ACQUISITION_RETRIES (3) in agent-heartbeat.ts, reusing Task.recoveryRetryCount as a cross-heartbeat counter (no schema migration)
- On cap exhaustion, terminally mark the task status:"failed" with an explanatory error, log the entry, and reopen to todo with preserveStatus so the failed status isn't wiped by reopen-to-todo semantics
- Add onTaskAcquisitionExhausted callback wired in in-process-runtime.ts to CentralCore.recordTaskCompletion(taskId, false) so exhausted acquisitions count toward totalTasksFailed
- Add regression tests in agent-heartbeat-worktree.test.ts and in-process-runtime.test.ts covering the retry cap and completion recording
- Add changeset (patch) and a docs/solutions/logic-errors writeup documenting the investigation and other worktree-collision sub-gaps found not to reproduce on HEAD

Files changed:
 .changeset/fn-7721-worktree-heartbeat-retry-cap.md |  7 ++
 docs/solutions/logic-errors/heartbeat-worktree-acquisition-unbounded-requeue.md | 84 ++++++++++++++++++++++
 packages/engine/src/__tests__/agent-heartbeat-worktree.test.ts | 58 +++++++++++++++
 packages/engine/src/__tests__/in-process-runtime.test.ts | 11 +++
 packages/engine/src/agent-heartbeat.ts | 72 ++++++++++++++++++-
 packages/engine/src/runtimes/in-process-runtime.ts | 12 ++++
 6 files changed, 242 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-7721

Fusion-Task-Lineage: caad671c-f360-4c1c-8aaa-5b48fca5a55b

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:04 -07:00
gsxdsm
cda9532c3b FN-7718: fix zombie heartbeat timers surviving agent stop/start 
Ensures stopping and restarting an agent durably clears its heartbeat timer instead of relying on the later FN-7645 watchdog repair.

- HeartbeatTriggerScheduler.auditTimerRegistrations now unregisters lingering timers for non-eligible (stopped/paused/disabled) agents
- syncTimerForAgent force-re-arms a stale present timer on a start transition so no orphaned timer entry lingers
- Added 308 lines of new heartbeat-scheduler regression tests covering the stop/start zombie-timer scenarios
- Added changeset (patch) documenting the fix
- Updated docs/agents.md and docs/architecture.md to describe the new invariant

Files changed:
 .changeset/fn-7718-zombie-timer-invalidate.md      |   7 +
 docs/agents.md                                     |   2 +
 docs/architecture.md                               |   1 +
 .../src/__tests__/heartbeat-scheduler.test.ts      | 308 +++++++++++++++++++++
 packages/engine/src/agent-heartbeat.ts             |  49 +++-
 5 files changed, 364 insertions(+), 3 deletions(-)

Fusion-Task-Id: FN-7718

Fusion-Task-Lineage: fc834ccd-495e-4294-805d-325b4cb536a2

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:04 -07:00
gsxdsm
a4931a4731 FN-7719: derive implicit planning fallback model when no fallback configured 
Triage planning-model retries no longer dead-end on "no fallback configured" when a provider primary-model call fails (e.g. a 404 wrapped in a 429 for nvidia/moonshotai/kimi-k2.6).

- Add resolveImplicitPlanningFallbackModel() to agent-session-helpers.ts: derives a fallback from the resolved project/global default (execution) model when neither planningFallback*/global fallback* is set, guarding against self-swap and skipping in test mode.
- Wire the implicit fallback into TriageProcessor.specifyTask() in triage.ts so a retryable primary planner-model failure swaps once via the derived fallback instead of failing triage outright.
- Add unit test coverage in agent-session-helpers.test.ts and triage.test.ts for the new implicit-fallback resolution and its triage integration.
- Document the new implicit-fallback behavior in docs/settings-reference.md.
- Add a patch changeset for @runfusion/fusion describing the fix.

Files changed:
 .changeset/fn-7719-triage-planning-implicit-fallback.md           |   7 +
 docs/settings-reference.md                                       |   2 +
 packages/engine/src/__tests__/agent-session-helpers.test.ts       |  75 +++++++
 packages/engine/src/__tests__/triage.test.ts                      | 237 +++++++++++++++++++++
 packages/engine/src/agent-session-helpers.ts                      |  41 ++++
 packages/engine/src/triage.ts                                     |  31 ++-
 6 files changed, 389 insertions(+), 4 deletions(-)

Fusion-Task-Id: FN-7719

Fusion-Task-Lineage: 69e797e1-5bac-47f3-8dce-505b9d64d83c

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:04 -07:00
gsxdsm
c8fcbec94f FN-7717: release active-session locks when a task is archived 
Archiving a task from triage/planning/todo (not just in-progress) previously left leaked active-session-registry entries, so a successor task could hit ActiveSessionPathHeldByForeignTaskError and get blocked from Plan Review.

- Add an explicit `to === "archived"` branch in the task-move handler that awaits abort of in-flight task work and sweeps any leftover activeSessionRegistry paths for the task, checked before the narrower `from === "in-progress"` branch so direct in-progress→archived transitions are covered too.
- Deliberately exclude `to === "done"` / `to === "in-review"` from this sweep since those columns legitimately hold ai-merge / workspace-repo-land merge leases that must survive the transition.
- Add regression test coverage for archive releasing active sessions across originating columns.
- Add changeset and architecture doc note.

Files changed:
 .../fn-7717-archive-active-session-release.md      |   7 +
 docs/architecture.md                               |   1 +
 ...xecutor-archive-releases-active-session.test.ts | 167 +++++++++++++++++++++
 packages/engine/src/executor.ts                    |  35 +++++
 4 files changed, 210 insertions(+)

Fusion-Task-Id: FN-7717

Fusion-Task-Lineage: 7cff6821-7bb3-4b75-b502-a26467ca7f51

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:03 -07:00
gsxdsm
7dc271027f FN-7711: add built-in Grok CLI provider to fix pi model registry lookup 
Registers a built-in grok-cli provider so Grok CLI model executions no longer hard-fail with "not found in the pi model registry".

- Add packages/core/src/grok-provider.ts: built-in grok-cli provider config (xAI OpenAI-compatible endpoint https://api.x.ai/v1, api openai-completions, apiKey $GROK_API_KEY), mirroring the existing Z.ai provider
- Register the provider in packages/engine/src/pi.ts (registerExtensionProviders) and packages/engine/src/provider-registration.ts (seedDashboardProviders)
- Wire the provider into CLI entrypoints: packages/cli/src/commands/daemon.ts, dashboard.ts, serve.ts
- Export grok-provider from packages/core/src/index.ts and packages/core/src/index.gate.ts
- Add unit tests: packages/core/src/__tests__/grok-provider.test.ts, and extend packages/engine/src/__tests__/pi-create-fn-agent.test.ts and provider-registration.test.ts
- Document the new provider in docs/settings-reference.md
- Add changeset .changeset/fn-7711-grok-cli-model-registry.md (patch, category: fix)

Note: Grok CLI binary remains discovery/probe only; GrokRuntimeAdapter streaming is a stub (tracked follow-up).

Files changed:
 .changeset/fn-7711-grok-cli-model-registry.md      |   7 +
 docs/settings-reference.md                         |   2 +
 packages/cli/src/commands/daemon.ts                |   4 +
 packages/cli/src/commands/dashboard.ts             |   4 +
 packages/cli/src/commands/serve.ts                 |   4 +
 packages/core/src/__tests__/grok-provider.test.ts  | 130 ++++++++++++
 packages/core/src/grok-provider.ts                 | 224 +++++++++++++++++++++
 packages/core/src/index.gate.ts                    |   7 +
 packages/core/src/index.ts                         |   7 +
 .../src/__tests__/pi-create-fn-agent.test.ts       |  78 ++++++-
 .../src/__tests__/provider-registration.test.ts    |   4 +-
 packages/engine/src/pi.ts                          |   4 +
 packages/engine/src/provider-registration.ts       |   4 +
 13 files changed, 476 insertions(+), 3 deletions(-)

Fusion-Task-Id: FN-7711

Fusion-Task-Lineage: ae90b54f-206e-46fd-8365-b0a4488ceb84

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-09 19:58:03 -07:00
gsxdsm
f10c39fa0b feat: add fn_task_file_scope_add tool so agents can widen their File Scope 
Agents that must edit files beyond a task's declared ## File Scope had no
way to keep the scope in sync, so those edits were stranded at merge (the
squash merge is scoped to ## File Scope, and cross-task overlap blocking +
the merge file-scope invariant both read it).

New executor tool fn_task_file_scope_add validates repo-relative
paths/globs with isValidFileScopeEntry, de-dupes against existing scope,
appends them to the ## File Scope section of PROMPT.md, and persists via
store.updateTask({ prompt }) (same validation + task.json/PROMPT.md sync as
fn_task_prompt_write). Registered in the main coding-agent tool list; the
base executor prompt now instructs the agent to call it when editing beyond
the declared scope. Merge-time peer-claim refusal is unchanged and remains
the cross-task backstop.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-08 23:40:52 -07:00
gsxdsm
7f2e34f5b3 test(FN-7690): reconcile anthropic-compatible apiType assertions + de-slow retry test 
FN-7690 changed resolveApiType() to return the registered pi-ai key
"anthropic-messages" for anthropic-compatible providers (the bare
"anthropic" key is never registered and throws at stream time), but left
behind a stale JSDoc and a stale test expectation:

- custom-provider-registry.ts: update the FN-7689 buildCustomProviderModels
  comment that still described the anthropic/anthropic-messages drift as
  unresolved.
- provider-registration.test.ts: assert config.api === "anthropic-messages"
  (was still asserting the pre-fix "anthropic").

Also de-slow a retry-exhaustion test: the describe uses fake timers with
shouldAdvanceTime, so awaiting a 3-retry backoff (1s+5s+15s) burned ~21s of
real wall time. Drive the backoff with advanceTimersByTimeAsync instead
(Standing Rule: prefer fake timers over real time waits).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-08 23:40:52 -07:00
gsxdsm
409de31e57 fix: stop false Anthropic OAuth expiry notifications when token is valid 
The OAuth expiry monitor and validity logger iterated the un-aliased
getOAuthProviders() id `anthropic` and evaluated get("anthropic"), which
can resolve to a stale legacy/supplemental row (e.g. ~/.pi/agent/auth.json)
even when the fresh, actually-used token lives under `anthropic-subscription`.
That fired a false "Anthropic OAuth expired" notification while the real
subscription token had refreshed successfully.

Both surfaces now resolve the freshest of the two aliased ids via a shared
resolveEffectiveOAuthCredential helper (mirroring the refresh scheduler's
getRefreshCandidateIds alias handling), so a live subscription token
suppresses the false alert. Notification throttle/cadence unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-08 23:39:35 -07:00
gsxdsm
053e34b370 FN-7693: add real-store integration test for image artifact register/list/view pipeline 
Adds an end-to-end integration test proving the artifact pipeline works against a real TaskStore, not just a mocked one.

- New test file exercises createArtifactRegisterTool/createArtifactListTool/createArtifactViewTool bound to a real TaskStore (inMemoryDb, real filesystem writes) instead of a mocked store
- Pins the register -> list -> view invariant for a real base64 PNG image artifact, verifying disk persistence, SQLite row fields (type, mimeType, sizeBytes, uri, taskId), and the list/view text surfaces
- Pins the invalid-base64-payload rejection path (non-image bytes for an image-typed artifact) to confirm no artifact row is persisted
- Pins the empty-state list text for a task with no registered artifacts

Files changed:
 packages/engine/src/__tests__/agent-artifact-tools-real-store-integration.test.ts | 131 +++++++++++++++++++++
 1 file changed, 131 insertions(+)

Fusion-Task-Id: FN-7693

Fusion-Task-Lineage: fd3493aa-6fb2-4e18-a735-c4a9d87c9c6c

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 23:39:33 -07:00
gsxdsm
c74c5f6d67 perf(test): fast-forward fake timers in step-session terminal-activity test (was 22.6s real-time wait) 
The 'publishes failed terminal workflow step activity' test awaited executeAll()
directly while the executor retried a failing step 3x with sleep() delays. Under
useFakeTimers({ shouldAdvanceTime: true }) those sleeps consumed REAL wall-clock
time (~22.6s locally, ballooning under CI load and busting the shard-2 watchdog).
Fast-forward the retry sleeps via vi.advanceTimersByTimeAsync like sibling retry
tests; the loop now completes in milliseconds.
 2026-07-08 22:37:29 -07:00
gsxdsm
0bfe7e811b test(engine): opt into FN-7658 auto-archive in verification-followup-dedup additive test 2026-07-08 15:17:46 -07:00
gsxdsm
67cc02750c FN-7692: fix misleading merger confirmation copy under active auto-merge 
Correct the planner-oversight confirmation messaging so it no longer claims a hard block when the active auto-merge policy will actually advance the merge/pull-request stage unattended.

- decidePlannerRecovery accepts an additive, messaging-only `autoMergeWillProceed` flag and picks accurate reason wording (advisory vs. genuine human-approval block vs. neutral/unknown) for merger/pull-request await_confirmation decisions
- PlannerRecoveryController.tick threads `allowsAutoMergeProcessing(task, settings)` into decidePlannerRecovery as `autoMergeWillProceed`
- project-engine's requestConfirmation steering comment prefix changed from "confirmation required" to neutral "merge checkpoint" so it doesn't contradict the now-accurate reason text
- added regression tests in planner-recovery.test.ts and planner-overseer-intervention-wiring.test.ts
- added changeset and doc note

Files changed:
 .changeset/fn-7692-merger-confirmation-copy.md     |  7 +++
 docs/architecture.md                               | 10 +++-
 packages/core/src/__tests__/planner-recovery.test.ts    | 66 ++++++++++++++++++++++
 packages/core/src/planner-recovery.ts              | 36 +++++++++++-
 packages/engine/src/__tests__/planner-overseer-intervention-wiring.test.ts | 37 ++++++++++++
 packages/engine/src/planner-recovery-controller.ts | 14 ++++-
 packages/engine/src/project-engine.ts               | 11 +++-
 7 files changed, 176 insertions(+), 5 deletions(-)

Fusion-Task-Id: FN-7692

Fusion-Task-Lineage: 187684b8-1d24-425d-85d4-627587469908

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 15:09:26 -07:00
gsxdsm
7cb76669db fix: resolve 3 staff-engineer review findings from #1957 (init_error mislabel, unbounded off-screen polling, duplicate toasts) (#1960) 
## Summary

A Staff Engineer pre-landing review (Greptile/CodeRabbit) on #1957
(merged) flagged four structural issues. This PR fixes the three that
were confirmed still present on `main`; the fourth (an unregistered-rule
`eslint-disable-next-line react-hooks/exhaustive-deps` comment) was
already fixed in #1957's second commit before merge and needed no
further change.

1. **`resolvePluginRuntime()` mislabeled "found but failed to init" as
`not_found`.** When a `runtimeHint` plugin registration is found but
`pluginContext`/`createRuntimeContext(...)` comes back falsy, the
resolver returned `reason: "not_found"` — indistinguishable from "never
registered" — defeating the point of a distinct `FallbackReason`. Now
returns `reason: "init_error"`. Updated the existing test that wrongly
asserted `"not_found"` for this path, and added a new test asserting all
three reachable `FallbackReason` values (`not_found`, `init_error`,
`factory_error`) are pairwise distinct.

2. **`ActiveAgentsPanel.tsx`/`AgentsView.tsx` hardcoded
`isInViewport={true}`.** Every agent card (live-agent header, board
card, list card) polled the runtime-fallback endpoint every 30s forever,
even scrolled off-screen — unlike `TaskCard.tsx`'s correct
`IntersectionObserver`-gated pattern. Both files now thread a real
`IntersectionObserver`-backed viewport signal into
`RuntimeFallbackBadge`. Added regression tests proving polling stops
once a badge instance's `isInViewport` transitions to `false` and
resumes once it goes back to `true` (desktop + a mobile-breakpoint
variant), plus verified via `tsc --noEmit` for `@fusion/dashboard`.

3. **Toast dedupe was per-hook-instance, not shared.**
`useRuntimeFallbackStatus`'s `lastToastedEventIdRef` was a local
`useRef`, so the same task rendered simultaneously in two card surfaces
(e.g. `ActiveAgentsPanel` + `AgentsView`) fired two separate toasts for
one fallback event. Dedupe now lives in module-level shared state (a
bounded `Map` keyed by `taskId:eventId`, FIFO-evicted past 500 entries)
so a fallback event toasts exactly once across every
simultaneously-mounted badge instance for the same task. Added a
cross-instance regression test mounting two badges for the same
`taskId`/`eventId` and asserting exactly one toast fires.

## Test evidence

- `pnpm --filter @fusion/engine exec vitest run
src/__tests__/runtime-resolution.test.ts --reporter=dot` — 25/25 pass
- `pnpm --filter @fusion/dashboard exec vitest run
app/components/__tests__/RuntimeFallbackBadge.test.tsx --reporter=dot` —
11/11 pass
- `pnpm --filter @fusion/dashboard run typecheck` — clean
- `pnpm --filter @fusion/engine run typecheck` — clean

## Scope

Isolated 6-file diff on top of current `main`
(`packages/engine/src/runtime-resolution.ts`,
`packages/engine/src/__tests__/runtime-resolution.test.ts`,
`packages/dashboard/app/hooks/useRuntimeFallbackStatus.ts`,
`packages/dashboard/app/components/ActiveAgentsPanel.tsx`,
`packages/dashboard/app/components/AgentsView.tsx`,
`packages/dashboard/app/components/__tests__/RuntimeFallbackBadge.test.tsx`).
No behavior outside the three findings above was touched.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **New Features**
- The desktop dashboard now supports plugin-backed runtime features,
improving how plugin-enabled workflows are loaded and run.
- Agent cards now pause background fallback polling when they’re
off-screen, helping the dashboard feel smoother and more responsive.

- **Bug Fixes**
- Improved runtime fallback handling so missing runtimes and
initialization failures are reported more accurately.
- Toast notifications are now better deduplicated, reducing repeated
alerts when multiple views show the same fallback state.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
 2026-07-08 15:07:56 -07:00
gsxdsm
461a4a2711 FN-7689: add opt-in Anthropic-style prompt caching for custom providers 
Custom providers previously never enabled prompt-cache control, so agent turns re-billed the full context every request even on cache-capable backends.

- Add `CustomProvider.anthropicPromptCaching` opt-in flag in @fusion/core types
- Set pi-ai `compat.cacheControlFormat="anthropic"` on opted-in models in both registration paths: custom-provider-registry `toProviderConfig` and pi.ts `createFnAgent`
- Expose the new toggle in the dashboard CustomProvidersSection UI (with supporting CSS) and thread it through the legacy API + custom-provider routes
- Update docs (dashboard-guide, settings-reference) to document the new setting
- Add engine test coverage for the caching flag across provider registration and pi-create-fn-agent paths
- Add changeset for the fix

Files changed:
 .changeset/fn-7689-custom-provider-prompt-caching.md          |   7 +
 docs/dashboard-guide.md                                       |   1 +
 docs/settings-reference.md                                    |   2 +-
 packages/core/src/types.ts                                    |  15 ++
 packages/dashboard/app/api/legacy.ts                          |  12 ++
 packages/dashboard/app/components/CustomProvidersSection.css  |  24 +++
 packages/dashboard/app/components/CustomProvidersSection.tsx  |  58 +++++-
 packages/dashboard/src/routes/register-custom-provider-routes.ts |  16 ++
 packages/engine/src/__tests__/pi-create-fn-agent.test.ts      |  71 +++++++
 packages/engine/src/__tests__/provider-registration.test.ts   | 204 ++++++++++++++++++++-
 packages/engine/src/custom-provider-registry.ts               |  71 +++++--
 packages/engine/src/pi.ts                                     |  27 ++-
 12 files changed, 473 insertions(+), 35 deletions(-)

Fusion-Task-Id: FN-7689

Fusion-Task-Lineage: b4f88f32-50da-4651-a546-432a95a1ab1c

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 13:09:10 -07:00
gsxdsm
64d4bb753a FN-7690: fix custom-provider anthropic-compatible apiType resolution 
Reconciles a naming drift where resolveApiType() mapped anthropic-compatible custom providers to an unregistered pi-ai api key, causing streaming failures.

- resolveApiType() now maps anthropic-compatible to "anthropic-messages" (was "anthropic"), matching pi.ts's resolveCustomProviderApiType and the built-in Anthropic provider config
- Added FNXC:CustomProviders comment documenting why anthropic-messages is the only key pi-ai's ModelRegistry actually registers
- Added/updated regression tests in custom-provider-registry.test.ts and provider-registration.test.ts
- Added changeset (patch) documenting the fix

Files changed:
 .changeset/fn-7690-apitype-resolver-reconcile.md    |  7 +++++++
 packages/cli/src/commands/__tests__/custom-provider-registry.test.ts | 21 ++++++++++++++++++---
 packages/engine/src/__tests__/provider-registration.test.ts | 20 ++++++++++++++++++++
 packages/engine/src/custom-provider-registry.ts     | 15 ++++++++++++++-
 4 files changed, 59 insertions(+), 4 deletions(-)

Fusion-Task-Id: FN-7690

Fusion-Task-Lineage: 461c340f-bc29-44a2-b8ec-19f0b03224d7

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 13:06:37 -07:00
ddonaldson130
c3c726cff4 fix(FUX-039): return init_error for found-but-uninitialized plugin runtime 
Co-authored-by: Fusion <noreply@runfusion.ai>
 2026-07-08 12:29:14 -04:00
gsxdsm
a8c018f7d4 fix: prevent false "OAuth token expired" push on startup 
Start OAuthRefreshScheduler before the refresh-blind OAuthExpiryMonitor so a
stale-but-refreshable access token is renewed before the monitor's first
awaited check() reads `expires`. Previously the monitor fired a false
"OAuth token expired" ntfy push on startup, moments before the refresher
silently renewed the token. Ordering locked by an invocationCallOrder
assertion in project-engine.test.ts.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-08 09:14:14 -07:00
gsxdsm
8ee8f15dc6 FN-7675: add agent runtime self-awareness to system prompts 
Agents were composing plans (e.g. reboot/wait-and-retry loops) that assumed they could keep acting even after the Fusion platform itself shut down, since prompts never told them they run inside Fusion. This adds a shared, docs-grounded self-awareness preamble prepended to chat, heartbeat, and executor base prompts so agents know their own runtime constraints.

- Added FUSION_RUNTIME_SELF_AWARENESS shared preamble in packages/core/src/agent-prompts.ts, exported via packages/core/src/index.ts
- Prepended the preamble to the chat system prompt (packages/dashboard/src/chat.ts)
- Prepended the preamble to the heartbeat session prompt (packages/engine/src/agent-heartbeat.ts)
- Prepended the preamble to the executor base prompt (packages/engine/src/executor.ts)
- Updated docs/agents.md and CONCEPTS.md to document the new self-awareness/capability-grounding behavior
- Added regression tests across core, dashboard, and engine covering the new prompt content
- Added changeset for @runfusion/fusion (minor, fix category)

Files changed:
 .changeset/fn-7675-agent-runtime-self-awareness.md |  7 ++++
 CONCEPTS.md                                        |  4 +-
 docs/agents.md                                     | 17 ++++++++
 packages/core/src/__tests__/agent-prompts.test.ts  | 41 ++++++++++++++++++++
 packages/core/src/agent-prompts.ts                 | 32 ++++++++++++++-
 packages/core/src/index.ts                         |  1 +
 packages/dashboard/src/__tests__/chat-system-prompt.test.ts | 17 ++++++++
 packages/dashboard/src/chat.ts                     |  6 ++-
 packages/engine/src/__tests__/executor-prompt.test.ts       | 45 ++++++++++++++++++++++
 packages/engine/src/__tests__/heartbeat-session-prompt.test.ts | 35 +++++++++++++++++
 packages/engine/src/agent-heartbeat.ts             | 10 +++--
 packages/engine/src/executor.ts                    |  7 +++-
 12 files changed, 213 insertions(+), 9 deletions(-)

Fusion-Task-Id: FN-7675

Fusion-Task-Lineage: 126d04a6-2c68-4347-9789-591b274277bf

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 08:16:30 -07:00
gsxdsm
be94f630ea Surface runtime-resolution fallback in dashboard; thread real FallbackReason (#1957) 
Closes/relates to Runfusion/Fusion#1956.

## Summary

Surfaces silent runtime-resolution fallback in the dashboard, and
threads the real `FallbackReason` ("not_found" vs "factory_error")
through instead of hardcoding `"not_found"` for every fallback.

## Changes

- `packages/engine/src/runtime-resolution.ts`: `resolvePluginRuntime()`
now returns a tagged miss result (`{ ok: false, reason }`)
distinguishing "not found" from "factory/instantiation error" instead of
collapsing both to `null`. `resolveRuntime()` threads the real reason
through to `logRuntimeFallback(...)` and returns it via
`ResolvedRuntime.fallbackReason`.
- `packages/engine/src/agent-session-helpers.ts`:
`createResolvedAgentSession()` includes `fallbackReason` in the
`session:runtime-resolved` audit event metadata when present.
- `packages/dashboard/src/routes/register-task-workflow-routes.ts`: new
`GET /api/tasks/:id/runtime-fallback` endpoint, returning the most
recent `session:runtime-resolved` event normalized for UI consumption
(`wasConfigured`, `runtimeHint`, `reason`, `showFallbackBadge`).
- `packages/dashboard/app/hooks/useRuntimeFallbackStatus.ts` (new):
polls the endpoint, dedupes toast firing per audit-event-id.
- `packages/dashboard/app/components/RuntimeFallbackBadge.tsx` (new):
renders the badge + fires the toast; wired into `TaskCard.tsx`,
`ActiveAgentsPanel.tsx`, and `AgentsView.tsx` (board and list variants).

## Test plan

- `pnpm --filter @fusion/engine exec vitest run
src/__tests__/runtime-resolution.test.ts` — 24/24 pass (21 pre-existing
+ 3 new, none weakened)
- `pnpm --filter @fusion/dashboard exec vitest run
src/routes/__tests__/register-task-workflow-routes.runtime-fallback.test.ts`
— 5/5 pass
(empty/configured-ok/fallback-with-hint/fallback-blank-hint/stale-superseded
states)
- `pnpm --filter @fusion/dashboard exec vitest run
app/components/__tests__/RuntimeFallbackBadge.test.tsx` — 8/8 pass (all
data states + mobile breakpoint + toast-fires-once)
- `pnpm --filter @fusion/dashboard run typecheck` and `pnpm --filter
@fusion/engine run typecheck` — both clean


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Added runtime-fallback warning badges across task and agent views
(including board and “working on” sections) with automatic toast
notifications.
* Introduced a new backend API to surface the latest runtime-fallback
state for a task.
* Added runtime-fallback status polling and UI messaging to reflect the
most recent state.

* **Bug Fixes**
* Prevented repeated toasts by deduplicating notifications across
polling updates.
* Improved fallback reporting so the UI reflects the latest
runtime-resolved audit event.
* Enhanced diagnostics by distinguishing fallback reasons (e.g., missing
runtime vs factory failure) for clearer user guidance.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
 2026-07-08 07:24:51 -07:00
gsxdsm
aa534c19af FN-7672: recover durable agents stuck in error state despite active manager 
Root-causes 4 correlated CTO-report agent failures where durable non-ephemeral agents got stuck in `error` state indefinitely because the heartbeat scheduler stops ticking error-state agents entirely, and self-healing's recovery sweep previously only considered them when their manager row was missing.

- SelfHealingManager: scope the `managerMissing` gate to the "running" orphan-detection path only, so "error"-state durable agents with a present/active manager now fall through to the existing transient/operator-actionable/active-execution/cooldown/retry-budget recovery guards instead of being skipped outright
- Add FNXC:AgentHeartbeat comment documenting the FN-7672 incident and rationale for the scoping change
- Extend self-healing.test.ts with coverage for manager-present durable agents in error state
- Add changeset (patch) describing the fix for release notes
- Update docs/agents.md accordingly

Files changed:
 .changeset/fn-7672-durable-agent-recovery.md       |   7 ++
 docs/agents.md                                     |   2 +
 packages/engine/src/__tests__/self-healing.test.ts | 129 ++++++++++++++++++++-
 packages/engine/src/self-healing.ts                |  24 +++-
 4 files changed, 160 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-7672

Fusion-Task-Lineage: 6676dc9e-66e7-4f70-804a-cccf77e8d337

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 05:38:01 -07:00
gsxdsm
f7d9509294 FN-7658: gate same-agent duplicate auto-archiving behind opt-in setting 
Duplicate tasks created by the same agent are no longer auto-archived by default; they are flagged for review instead, controlled by a new opt-in project setting.

- Add project setting `autoArchiveDuplicateTasksEnabled` (default false) gating the FN-4892 same-agent duplicate intake path
- Add `flagSameAgentDuplicate` path and `nearDuplicateOf` metadata used when auto-archive is disabled; tombstone-resurrection blocking is unchanged
- Wire the setting through core settings schema/types/store, dashboard SchedulingSection UI, and i18n strings
- Update docs (settings-reference.md, task-management.md) to describe the new default-off behavior
- Add a changeset for the @runfusion/fusion minor release
- Extend duplicate-intake, tombstone-window, store-parent-task-dedup, and reliability-interaction tests to cover both flag states

Files changed:
$(cat /tmp/fn7658_stat.txt)

Fusion-Task-Id: FN-7658

Fusion-Task-Lineage: 7d0d1074-1020-48a8-b96f-186154c2c408

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-08 00:23:32 -07:00
Fusion
0bed997af8 feat: surface runtime-resolution fallback in dashboard, thread real FallbackReason 
Fixes silent runtime fallback visibility (dashboard never read wasConfigured
or session:runtime-resolved) and threads the real FallbackReason
(not_found vs factory_error) through resolveRuntime()/logRuntimeFallback
instead of hardcoding "not_found" for every fallback.

- packages/engine/src/runtime-resolution.ts: resolvePluginRuntime() now
  returns a tagged miss result distinguishing not_found from factory_error;
  resolveRuntime() threads the real reason through and returns it as
  ResolvedRuntime.fallbackReason
- packages/engine/src/agent-session-helpers.ts: includes fallbackReason in
  the session:runtime-resolved audit event metadata
- packages/dashboard/src/routes/register-task-workflow-routes.ts: new
  GET /api/tasks/:id/runtime-fallback endpoint
- packages/dashboard/app/hooks/useRuntimeFallbackStatus.ts +
  packages/dashboard/app/components/RuntimeFallbackBadge.tsx: new polling
  hook + badge/toast component wired into TaskCard, ActiveAgentsPanel, and
  AgentsView

Ref: Fusion task FUX-022, investigations/FUX-017-hermes-runtime-fallback.md
recommendation #1
 2026-07-08 03:09:29 -04:00
gsxdsm
bec8987ce9 FN-7648: gate hold-release on trait-based unplanned-card check, not literal todo column 
Blocks planning/intake column cards from entering processing columns regardless of literal column id, so renamed custom intake/planning columns are covered by the same guard as the legacy todo column.

- Add isUnplannedForExecution() in hold-release.ts: true when task.status==="planning", or when the card sits in the legacy todo column or a column carrying the intake trait AND its PROMPT.md still equals the bootstrap stub.
- Route issueRelease() (used by the sweep, promoteHeldTask, and releaseHeldTaskByEvent) through this guard before releasing into any countsTowardWip processing column.
- Update scheduler.ts's reserveSlot guard to use the same trait-based predicate instead of a hardcoded "todo" column id check.
- Add regression tests in hold-release.test.ts and scheduler-workflow-cutover.test.ts covering renamed intake/planning columns.
- Document the invariant in docs/architecture.md and docs/workflow-steps.md.
- Add changeset (patch) describing the fix.

Files changed:
 .changeset/fn-7648-unplanned-intake-cards-never-execute.md |   7 +
 docs/architecture.md                               |   2 +
 docs/workflow-steps.md                             |   2 +
 packages/engine/src/__tests__/hold-release.test.ts | 238 +++++++++++++++++++++
 packages/engine/src/__tests__/scheduler-workflow-cutover.test.ts |  60 +++++-
 packages/engine/src/hold-release.ts                |  60 ++++++
 packages/engine/src/scheduler.ts                   |  26 +--
 7 files changed, 378 insertions(+), 17 deletions(-)

Fusion-Task-Id: FN-7648

Fusion-Task-Lineage: a4b54d30-f86d-4eb9-9cf2-6ac55b6dbe58

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-07 22:06:21 -07:00
gsxdsm
009ce26fd0 FN-7646: prevent OAuth credential clobbering across concurrent Fusion processes 
Fix API keys/OAuth credentials in ~/.fusion/agent/auth.json being clobbered when the desktop app and CLI-served web app run concurrently on one machine.

- Reload primary auth storage from disk (primary.reload()) before persisting a refreshed OAuth credential, so a concurrent process's newer login/refresh for the same provider isn't overwritten by this process's stale in-flight refresh.
- Re-check credential identity against the freshly reloaded disk state before writing the refreshed token back.
- Add cross-process regression coverage exercising concurrent auth.json read-modify-write scenarios.
- Add changeset documenting the fix and its dependency on the pi-coding-agent locked per-provider merge (>=0.80.x).

Files changed:
 .changeset/fn-7646-auth-storage-coordination.md    |   7 +
 .../src/__tests__/auth-storage-concurrency.test.ts | 234 +++++++++++++++++++++
 packages/engine/src/auth-storage.ts                |  27 +++
 3 files changed, 268 insertions(+)

Fusion-Task-Id: FN-7646

Fusion-Task-Lineage: de39f08d-2d9f-46ff-b293-c603e3268ecf

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-07 22:06:21 -07:00
gsxdsm
4e8c621e9c FN-7641: fix cards stranded after out-of-band/workspace merges by allowing proven-merge rehome 
Fixes a state-machine bug family where cards got stranded after out-of-band or workspace merges landed: store.moveTask now allows a proven-merge recoveryRehome to cross legacy columns (e.g. todo→done), and nodeId='end' finalize no longer silently no-ops — it finalizes on durable merge proof or returns an explicit error, consistently across the dashboard route, the CLI task-update tool, and store.updateTask.

- packages/core/src/store.ts: allow proven-merge recoveryRehome moves across legacy columns (e.g. todo→done) instead of rejecting them
- packages/core/src/node-override-guard.ts: nodeId='end' finalize now checks for durable merge proof and returns an explicit error instead of silently no-op'ing
- packages/dashboard/src/routes/register-task-workflow-routes.ts: dashboard workflow route surfaces the new explicit finalize error/behavior
- packages/cli/src/extension.ts: CLI task-update tool surfaces the same explicit finalize error/behavior
- docs/task-management.md: documented the updated finalize/rehome behavior
- Added regression tests across core (node-override-guard, store-movement, task-node-override), dashboard (register-task-workflow-routes.nodeid-finalize), engine (merger-merge-lifecycle), and CLI (extension) covering the stranded-card invariant
- Added changeset for @runfusion/fusion (patch)

Files changed:
 .changeset/fn-7641-stranded-cards-after-merge.md   |  7 ++
 docs/task-management.md                            |  2 +
 packages/cli/src/__tests__/extension.test.ts       | 59 ++++++++++++++
 packages/cli/src/extension.ts                      | 10 +++
 .../core/src/__tests__/node-override-guard.test.ts | 93 +++++++++++++++++++++
 packages/core/src/__tests__/store-movement.test.ts | 94 ++++++++++++++++++++++
 .../core/src/__tests__/task-node-override.test.ts  | 73 +++++++++++++++++
 packages/core/src/node-override-guard.ts           | 69 +++++++++++++++-
 packages/core/src/store.ts                         | 69 +++++++++++++++-
 ...er-task-workflow-routes.nodeid-finalize.test.ts | 90 +++++++++++++++++++++
 .../src/routes/register-task-workflow-routes.ts    | 10 +++
 .../src/__tests__/merger-merge-lifecycle.test.ts   | 58 +++++++++++++
 12 files changed, 631 insertions(+), 3 deletions(-)

Fusion-Task-Id: FN-7641

Fusion-Task-Lineage: 48ea7851-ee68-48f1-92f9-302d0da5acff

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-07 22:06:20 -07:00
gsxdsm
923bba7082 FN-7645: force re-arm zombie heartbeat timers detected as stale during audit 
Fixes the heartbeat timer audit so it repairs not just missing timer registrations but also 'zombie' ones — timer entries that remain present in memory after their underlying interval silently stopped firing. Long-interval (~1h) agents were most affected since a single lost tick compounded into hours of staleness before self-healing noticed.

- HeartbeatTriggerScheduler audit now computes staleness (elapsed vs repair-stale threshold) up front for every timer-eligible agent, not only for agents missing a timer entry
- Present-but-stale timer entries are now treated as non-advancing and force cleared/re-registered via registerAgent() (which already clears any existing timer before re-arming)
- Fresh (non-stale) present timers are left alone so healthy short-interval agents are never force-re-armed or double-ticked
- Repair reason/log messages now distinguish zombie-timer-rearmed repairs from missing-registration repairs, and the summary log reports counts for each
- Added heartbeat-scheduler tests covering the zombie-timer repair path
- Added changeset and a docs/architecture.md note

Files changed:
 .changeset/fn-7645-heartbeat-rearm.md              |   7 +
 docs/architecture.md                               |   1 +
 .../src/__tests__/heartbeat-scheduler.test.ts      | 223 +++++++++++++++++++++
 packages/engine/src/agent-heartbeat.ts             |  42 +++-
 4 files changed, 266 insertions(+), 7 deletions(-)

Fusion-Task-Id: FN-7645

Fusion-Task-Lineage: 652bc2eb-a660-4306-9f85-d2d5f9ca7e38

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-07 22:06:18 -07:00
gsxdsm
f1db31374a FN-7642: emit diagnostic output for dispatch/infra failures in optional-group and CE gate nodes 
Fixes the code-review/plan-review/CE gate workflow node failing with a blank "(no feedback captured)" message when a dispatch or infra exception (not a reviewer verdict) causes the step to fail.

- WorkflowGraphExecutor now synthesizes a non-blank WorkflowStepResult.output when an enabled optional-group (code-review, plan-review, browser-verification) or CE source:"node" skill-gate template node fails via dispatch/infra exception
- Diagnostic output is derived from the node:<id>:error context-patch key, falling back to the failure value, then a stable sentinel
- status, verdict extraction, edge routing, and self-healing's latestFailedPreMergeStep selection are unchanged
- Added regression test coverage: workflow-graph-optional-group-no-feedback.test.ts
- Added changeset (patch) documenting the fix for Runfusion/Fusion#1946

Files changed:
 .changeset/fn-7642-code-review-no-feedback-diagnostic.md          |   7 +
 packages/engine/src/__tests__/workflow-graph-optional-group-no-feedback.test.ts | 246 +++++++++++++++++++++
 packages/engine/src/workflow-graph-executor.ts                    | 104 ++++++++-
 3 files changed, 355 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-7642

Fusion-Task-Lineage: 1329e907-652f-4230-a945-5a9d7040ae69

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-07 22:06:18 -07:00
gsxdsm
fe5a595984 FN-7622: unify desktop and CLI provider seeding to fix truncated provider list 
The Electron desktop app's in-process dashboard server skipped the CLI's provider seeding sequence, so /api/providers and /api/models returned a truncated catalog (missing built-in API-key providers and user customProviders[]) compared to the identical config on the web build.

- Move provider-auth.ts and custom-provider-registry.ts from @fusion/cli into @fusion/engine as the single shared implementation
- Add engine/src/provider-registration.ts exposing seedDashboardProviders(), mirroring the CLI's exact startup order (built-in Zai provider registration -> wrapAuthStorageWithApiKeyProviders -> model merge/refresh -> registerCustomProviders -> settings:updated resubscription)
- Update desktop/src/local-runtime.ts and local-server.ts to call the shared seedDashboardProviders() helper instead of constructing a raw authStorage/modelRegistry
- Convert packages/cli/src/commands/provider-auth.ts and custom-provider-registry.ts into re-export shims preserving unchanged observable behavior
- Add engine/src/__tests__/provider-registration.test.ts and expand desktop local-runtime/local-server tests to cover the shared seeding path
- Add changeset for @runfusion/fusion (patch)

Files changed:
 .changeset/fn-7622-desktop-provider-parity.md      |   7 +
 .../cli/src/commands/custom-provider-registry.ts   | 122 +----
 packages/cli/src/commands/provider-auth.ts         | 517 +--------------------
 .../desktop/src/__tests__/local-runtime.test.ts    |  93 ++++
 .../desktop/src/__tests__/local-server.test.ts     |  62 ++-
 packages/desktop/src/local-runtime.ts              |  33 +-
 packages/desktop/src/local-server.ts               |  21 +-
 .../src/__tests__/provider-registration.test.ts    | 192 ++++++++
 packages/engine/src/custom-provider-registry.ts    | 117 +++++
 packages/engine/src/index.ts                       |  18 +
 packages/engine/src/provider-auth.ts               | 513 ++++++++++++++++++++
 packages/engine/src/provider-registration.ts       | 105 +++++
 12 files changed, 1172 insertions(+), 628 deletions(-)

Fusion-Task-Id: FN-7622
Fusion-Task-Lineage: fb6fbbf3-745e-4623-b7af-11471e13f138
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
 2026-07-07 22:04:51 -07:00
gsxdsm
1add12d703 fix: resolve full-suite CI failures across engine + dashboard (shards 1-4) (#1947) 
## Summary

Fixes the failing **full-suite** CI run on `main` ([run
28874651861](https://github.com/Runfusion/Fusion/actions/runs/28874651861))
— all 4 test shards were red. ~32 test files failing across engine +
dashboard (src + app), rooted in ~13 distinct causes from recent main
commits. All resolved; the merge gate and full engine/dashboard suites
are green locally.

## Root causes & fixes

### Engine (shards 1 & 2)
- **`appendAgentLog` 6th timing arg (FN-7503, `2797803c0`)** —
`agent-logger.ts` now passes an optional
`{durationMs,timeToFirstTokenMs}` 6th arg; many
executor/heartbeat/merger tests asserted the old 5-arg form. Added a
shared timing-tolerant helper `agent-log-assertions.ts` (asserts
`taskId/text/type`, tolerant of the timing object) and applied it across
affected files — so future timing fields won't re-break every executor
test.
- **`reconcileSupersededGeneratedFixFeatures` (mission)** —
`mission-execution-loop.ts` calls a method the test's missionStore mock
lacked; added a no-op stub (the real `MissionStore` already implements
it).
- **`ModelFallbackExhaustedError` / `proseSignalsClearApproval` /
`extractJsonObjectCandidates` missing from `vi.mock`** — converted stale
hand-written mocks (`../pi.js`, `../reviewer.js` in
`executor-test-helpers.ts`) to `importOriginal`-spread so real exports
carry through.
- **Workspace product fixes (2):**
- `merger-ai.ts` — `landWorkspaceTask` now recovers the integration-tip
sha as `landedSha` when the A1 trailer-fallback proved a sub-repo landed
but its sha was never persisted, so `finalizeWorkspaceTask` can build
merge proof (was stranding partial-land retries in-review).
- `worktree-acquisition.ts` — `acquireWorkspaceRepoWorktree` strips the
shared project `integrationBranch/baseBranch` overrides before
forwarding to `acquireTaskWorktree` (FN-7360's `freshStartPoint` was
resolving an absent shared branch).
- **FN-7360 extra `git symbolic-ref` exec** — updated worktree
exec-count assertions for the new `resolveIntegrationBranch` call.
- **Planner-overseer / stepwise-workflow / workflow-graph /
workflow-prompt / executor-step-session / liveness-gate / checkout /
ce-workflow / triage-split** — test-alignments for intentional behavior
changes (FN-7229 retry-cap, FN-7265 review-node removal, FN-7335
pause-abort logging, FN-7577 recovery-budget, FN-7577 overseer denial
loop, specifyTask single promptWithFallback call, FN-4944
already-on-main noop log, FN-7486 ownership short-circuit).

### Dashboard API (shard 3)
- **`store.on('task:moved')` (FN-7337)** — `createServer` now registers
the listener; backed the 4 affected MockStores with EventEmitter (shared
root cause across chat-routes.rooms, register-git-github,
routes-run-cited-goals, routes-sandbox-audit).
- **`routes-agent-import`** — core mock converted to
`importOriginal`-spread (was missing FN-7444 planning-deepening
constants).
- **`session-resume-history`** — engine mock missing
`resolveMcpServersForStore`.
- **`task-create-workflow-route`** — `builtin:legacy-coding`
defaultSteps now include `plan-review` (FN-7224/7226).
- **GitLab parity** — added the missing `[GitLab Parity Inventory]`
cross-link in `docs/signals-connectors.md`.

### Dashboard app (shard 4)
- Test-alignments for intentional product changes: FN-7057 (workflow
selection preservation), FN-7340 (footer concurrency geometry), FN-7156
(Missions overview default), FN-7342/FN-6825 (board scroll + workflow
switcher), FN-7352 (openDetailTask 3rd arg), FN-7261 (backdrop dismiss
default-off), FN-7234 (non-authoritative fetch failures), plus a missing
`fetchWorkflowOptionalSteps` mock.

### MCP coverage
- `mcp-surface-coverage` forwarding needle updated for FN-7446's
`resolvePlanningMcpServers` helper.

## Approach notes
- Each fix is the **minimal** change at the correct source (test-update
where a recent commit intentionally changed behavior; product-fix for
the 2 real regressions). No assertion was loosened/deleted to force a
pass; no timeout appeasement.
- Coordination: work was partitioned by package across parallel
subagents (engine / dashboard-src / dashboard-app) with Main as the sole
git committer (path-scoped commits) after an early shared-index reset
wiped in-progress edits — process was tightened mid-flight.

## Verification
- **Full engine suite**: green (9231 passed; the lone local-only
`custom-providers-openai-completions` import error is stale local
`pi-ai@0.79.9` vs the lockfile's `0.80.3` — CI's fresh install resolves
`/compat`; it passed in the original CI run).
- **Dashboard API** (`dashboard-api-quality-backfill`): 242 files / 3185
tests / 0 failures.
- **Dashboard app** (`dashboard-app-quality-backfill`): all targeted
files green (37 + 95 tests).
- **Merge gate** (`pnpm test:gate`): engine-core 326 + ci-shape 63, plus
nohup/4040/appeasement/changeset-format checks — all pass.
- 2 changesets added for the published-`@runfusion/fusion` behavior
fixes (workspace landedSha, sub-repo worktree branch-strip).

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Bug Fixes**
* Improved reliability for partial workspace land retries by recovering
the exact proven landed commit so durable merge proofs can complete.
* Fixed per-sub-repo worktree creation by removing invalid branch
override settings, preventing worktree-add failures.
* Dashboard stability updates: preserve mobile board scroll during
stabilization/restore, correct task filtering when workflows are
missing, ensure the Chat tab appears for done tasks, and refine
modal-dismiss and responsive popover behavior.
* **Documentation**
* Expanded the GitLab connector section with GitLab parity context and a
GitLab Parity Inventory reference.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
 2026-07-07 22:04:17 -07:00
gsxdsm
203c734340 fix(engine): require exact trailer line, not substring, for proven landed commit (Greptile P1) 
findProvenLandedCommit now keeps --grep as a prefilter but verifies each
candidate carries an actual 'Fusion-Task-Id: <taskId>' trailer line via
git show -s --format=%B, so a later commit that merely mentions the trailer
text in its body cannot be selected. Regression covers a body-mention
intervening commit.
 2026-07-07 10:25:11 -07:00