Commit Graph

25 Commits

Author SHA1 Message Date
gsxdsm
a63cf1c911 FN-6750: harden task chat steering coverage
Verify task chat timestamps and immediate steering delivery across UI, route, and executor surfaces.

- Assert inline and expanded TaskChatTab timestamp parity for agent output and user steering comments.
- Cover steering route wake payloads so assigned agents receive the newest steering comment id immediately.
- Harden executor real-time steering tests for seen-before-inject ordering, queued prompt delivery, duplicate suppression, and empty-comment no-ops.

Files changed:
 .../app/components/__tests__/TaskChatTab.test.tsx  |  79 +++++++++++-
 .../src/__tests__/routes-tasks-ops.test.ts         | 136 +++++++++++++++++++++
 .../src/__tests__/executor-step-session.test.ts    | 116 ++++++++++++++++--
 3 files changed, 316 insertions(+), 15 deletions(-)

Fusion-Task-Id: FN-6750

Fusion-Task-Lineage: 48e1d57d-fd37-4d45-9b98-766c4a2f704d
2026-06-19 22:24:18 -07:00
gsxdsm
d0be3e462d FN-6610: harden engine test isolation recovery
Harden shared test isolation seams so engine tests survive mid-run cleanup.

- Recreate owned worker roots, HOME directories, and cwd before child-process launches.
- Add regression coverage for tmpdir redirect, HOME, cwd, SQLite, and git config recovery.
- Revalidate worktree database scratch directories before direct SQLite opens and document the rescue pattern.

Files changed:
 docs/testing.md                                    |  2 +
 packages/core/src/__test-utils__/vitest-setup.ts   | 92 ++++++++++++++++++----
 .../__tests__/vitest-setup-tmp-redirect.test.ts    | 33 ++++++++
 .../src/__tests__/executor-step-session.test.ts    |  6 +-
 .../src/__tests__/worktree-db-hydrate.test.ts      | 22 +++++-
 5 files changed, 135 insertions(+), 20 deletions(-)

Fusion-Task-Id: FN-6610

Fusion-Task-Lineage: 18233ee2-1dfe-4b0d-bd12-e4f5b7f9cc29
2026-06-18 01:20:03 -07:00
gsxdsm
4315cd01c6 FN-6598: suppress stuck detection during verification
Treat bounded verification subprocesses as healthy activity so progressing tasks avoid false stuck-loop recovery.

- Bracket fn_run_verification commands with stuck-detector start/end signals.
- Suppress loop and no-progress churn while verification is active, with timeout-bounded cleanup.
- Add regression coverage for verification heartbeats, compact-and-resume recovery, and no-progress churn behavior.
- Document verification suppression in reliability guidance.

Files changed:
 docs/architecture.md                               |   5 +-
 docs/testing.md                                    |   1 +
 .../src/__tests__/executor-step-session.test.ts    |  10 +-
 .../non-progress-churn.test.ts                     |  55 +++++++++
 .../src/__tests__/run-verification-command.test.ts |  45 ++++++-
 .../src/__tests__/stuck-task-detector.test.ts      | 136 +++++++++++++++++++++
 packages/engine/src/executor.ts                    |   2 +
 packages/engine/src/run-verification-tool.ts       |  33 +++--
 packages/engine/src/stuck-task-detector.ts         |  69 +++++++++++
 9 files changed, 341 insertions(+), 15 deletions(-)

Fusion-Task-Id: FN-6598

Fusion-Task-Lineage: 5449b413-c500-46aa-b46d-cf94c2d88710
2026-06-18 00:39:01 -07:00
gsxdsm
a013bc0309 FN-6607: align step tools with zero-based prompt steps
Align executor step tools and review bookkeeping with the 0-based Step N labels agents see in PROMPT.md.

- Treat fn_task_update and fn_review_step step parameters as 0-indexed values, including validation, logs, checkpoints, and review verdict maps.
- Update executor/reviewer/step-runner guidance and generated tool docs to describe Step 0 semantics consistently.
- Adjust affected executor and reliability tests and add coverage proving Step 0 progress, review, and revise handling work without off-by-one shifts.
- Add a patch changeset for the published Fusion CLI package.

Files changed:
 .changeset/fn-6607-step-numbering.md               |   5 +
 .../cli/skill/fusion/references/engine-tools.md    |   4 +-
 .../engine/src/__tests__/executor-pause.test.ts    |   2 +-
 .../executor-review-step-indexing.test.ts          |  18 +-
 .../src/__tests__/executor-review-verdicts.test.ts |  18 +-
 .../executor-step-numbering-zero-based.test.ts     | 196 +++++++++++++++++++++
 .../src/__tests__/executor-step-session.test.ts    |  24 ++-
 ...executor-task-done-revise-verdict-guard.test.ts |   4 +-
 .../executor-pending-review-skip-retry.test.ts     |   8 +-
 .../task-done-refusal-x-invariant.test.ts          |   2 +-
 packages/engine/src/__tests__/step-runner.test.ts  |   4 +-
 packages/engine/src/executor.ts                    |  57 +++---
 packages/engine/src/reviewer.ts                    |   3 +
 packages/engine/src/step-runner.ts                 |   6 +-
 14 files changed, 284 insertions(+), 67 deletions(-)

Fusion-Task-Id: FN-6607

Fusion-Task-Lineage: 1b1fb1d8-07ca-4a33-84f5-1dab83388c01
2026-06-17 19:52:20 -07:00
gsxdsm
0cc557121c FN-6590: inject task-detail chat into active step sessions
Ensure task-detail comments are delivered to live executor threads and preserved for the next step prompt when no step session is active.

- Forward steering comments through legacy, step-session, and workflow-step executor targets with delivery status logging.
- Keep step-session task details updated and include pending steering comments in full and reduced step prompts.
- Track delivered steering comment IDs so comments are injected or queued exactly once across active and subsequent step sessions.
- Update step-session executor tests for live steering, queued prompt fallback, and reduced prompt behavior.

Files changed:
 .../src/__tests__/executor-step-session.test.ts    | 467 ++++++---------------
 .../src/__tests__/step-session-executor.test.ts    |  63 ++-
 packages/engine/src/executor.ts                    |  34 +-
 packages/engine/src/step-session-executor.ts       |  69 ++-
 4 files changed, 283 insertions(+), 350 deletions(-)

Fusion-Task-Id: FN-6590

Fusion-Task-Lineage: 18fffd41-7632-4f29-8721-daaf3c239a74
2026-06-17 14:52:56 -07:00
gsxdsm
be2773b412 FN-6423: fix scheduler capacity accounting
Correct scheduler dispatch diagnostics so capacity decisions use consistent non-negative slot counts.

- Clamp excess semaphore releases at zero and warn once when a slot is returned without an active holder.
- Recompute dispatch capacity at each queue decision, including tasks started earlier in the same scheduler tick.
- Update scheduler and semaphore tests for true binding gates, non-negative diagnostics, and workflow-step env stability.
- Add a patch changeset for the scheduler capacity fix.

Files changed:
 .changeset/fn-6423-scheduler-capacity.md           |   5 +
 packages/engine/src/__tests__/concurrency.test.ts  |  32 ++++++
 .../src/__tests__/executor-step-session.test.ts    |  10 +-
 packages/engine/src/__tests__/scheduler.test.ts    | 122 ++++++++++++++++++++-
 packages/engine/src/concurrency.ts                 |  29 ++++-
 packages/engine/src/scheduler.ts                   | 117 ++++++++++----------
 6 files changed, 248 insertions(+), 67 deletions(-)

Fusion-Task-Id: FN-6423

Fusion-Task-Lineage: a6b2e668-a822-46e9-9cd8-ac267fbde804
2026-06-13 21:23:39 -07:00
gsxdsm
7b839069b5 FN-6420: run dependency sync in AI merge worktrees
Run configured or inferred dependency installs before AI merge verification uses the clean-room worktree.

- Add shared dependency-sync helpers with install marker caching for inferred lockfile installs.
- Run dependency sync during AI clean-room merges and audit/log the command, skip reason, and duration.
- Reuse the helper from merger paths while documenting the new behavior and covering install success/failure cases.

Files changed:
 .changeset/fn-6420-ai-merge-dependency-sync.md     |   5 +
 docs/architecture.md                               |   2 +-
 docs/settings-reference.md                         |   2 +-
 .../src/__tests__/executor-step-session.test.ts    |   5 +-
 .../merger-ai-dependency-install.slow.test.ts      | 269 +++++++++++++++++++++
 packages/engine/src/merge-dependency-sync.ts       | 144 +++++++++++
 packages/engine/src/merger-ai.ts                   |  31 +++
 packages/engine/src/merger.ts                      | 120 +++------
 packages/engine/src/run-audit.ts                   |   1 +
 9 files changed, 484 insertions(+), 95 deletions(-)

Fusion-Task-Id: FN-6420

Fusion-Task-Lineage: 49353cb6-4953-4670-b620-a90331f048dc
2026-06-13 21:09:12 -07:00
gsxdsm
e0ec3d1fbd FN-6368: route task chat steering to active sessions
Ensure task chat messages reach the live execution surface instead of waiting for a future session.

- Track seen steering comments for legacy, step-session, and workflow-step execution paths.
- Forward new task chat steering to active step sessions and workflow step sessions, including parallel step handles.
- Remove misleading inactive-session composer copy and cover the steering paths with regression tests.
- Add a patch changeset for the published Fusion package.

Files changed:
 .changeset/fn-6368-steering-running-session.md     |   5 +
 packages/dashboard/app/components/TaskChatTab.tsx  |  12 +-
 .../app/components/__tests__/TaskChatTab.test.tsx  |  18 +-
 .../src/__tests__/executor-step-session.test.ts    | 108 ++++++++++++
 .../engine/src/__tests__/executor-test-helpers.ts  |   3 +
 .../src/__tests__/step-session-executor.test.ts    |  40 +++++
 packages/engine/src/executor.ts                    | 186 ++++++++++++++-------
 packages/engine/src/step-session-executor.ts       |  16 ++
 8 files changed, 312 insertions(+), 76 deletions(-)

Fusion-Task-Id: FN-6368

Fusion-Task-Lineage: 610a6185-b136-4fea-a4bd-ea78ab5aab47
2026-06-13 09:41:20 -07:00
gsxdsm
aa8bd3dc92 fix(FN-6043): recover stuck task processing
Fusion-Task-Id: FN-6043
2026-06-08 18:14:48 -07:00
gsxdsm
c0b6f212c9 fix(FN-5994): address verification review feedback
Harden command normalization edge cases and abort loop compaction on timeout before falling through to stuck-task requeue.

Fusion-Task-Id: FN-5994
2026-06-08 10:23:01 -07:00
gsxdsm
0c8674c37c fix(FN-5994): prevent verification hangs
Normalize package file-filter verification to direct Vitest execution, kill timed-out process groups, and bound loop-recovery compaction so stuck tasks cannot spin indefinitely.

Fusion-Task-Id: FN-5994
2026-06-08 09:44:00 -07:00
gsxdsm
3d03505a62 feat(engine): U2 — runTaskStep/resetStepToBaseline substrate seams with blast-radius guard (RETHINK extraction)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-04 11:50:45 -07:00
Phil Larson
6b57e7cbf6 fix(engine): resume execution after review revise 2026-05-29 12:57:53 -07:00
Phil Larson
b5f2f91e87 fix(FN-057): park pending review without failed status 2026-05-29 06:54:45 -07:00
gsxdsm
cec191eac3 FN-5638: migrate pi-ai and pi-coding-agent packages to @earendil-works scope
Fusion-Task-Id: FN-5638

Fusion-Task-Lineage: 6e99c156-5f6c-42e6-bd26-618e08ffd05f
2026-05-28 21:23:48 -07:00
Fusion (runfusion.ai)
a2a643844d feat(FN-5436): skip step retries when review is pending
Added executor logic to skip retries when a review is pending for a task, introducing a `pendingReviewBlockHelper` in the task-done path and updating the retry-gate to consult it; two new reliability-interaction test suites cover the feature behavior and composition with existing retry/backstop laye

Fusion-Task-Id: FN-5436
2026-05-21 10:58:28 -07:00
Fusion (runfusion.ai)
23dae4b495 test(FN-5168): complete Step 6 — verification gates green
Fusion-Task-Id: FN-5168
Fusion-Task-Lineage: 0c865d3e-0886-4e51-a7ff-cb4c713dcc54
2026-05-19 16:15:25 -07:00
Fusion (runfusion.ai)
656744fb95 test(FN-5039): stabilize workflow scope tests under attribution filtering
Fusion-Task-Id: FN-5039
Fusion-Task-Lineage: 324b7259-e08f-4051-b89c-b94836b73d5d
2026-05-18 08:07:06 -07:00
gsxdsm
78b1842ddb feat(FN-4396): merge fusion/fn-4396 2026-05-14 08:24:01 -07:00
Fusion
a8e05b5757 feat(FN-4368): complete Step 3 — advisory workflow failures never block
Fusion-Task-Id: FN-4368
Fusion-Task-Lineage: ac9b12e6-2101-4b51-89a0-6422fd7850ed
2026-05-14 07:21:45 -07:00
Fusion
95d742abb3 feat(FN-4468): add workflow step gateMode advisory gating
Adds an "advisory" `gateMode` option for workflow steps: steps in advisory mode log findings but no longer block merge completion, while steps that must block can still be configured as blocking. The change covers the workflow step types and schema, executor gating logic, dashboard UI in WorkflowSte

Fusion-Task-Id: FN-4468
2026-05-14 05:35:12 -07:00
Fusion
7002427c90 feat(FN-4070): add workflow revision forking for task retries
Implements workflow revision forking with a new per-project setting, allowing follow-up tasks to inherit a fork of the calling task's workflow rather than the original revision. The feature adds classification logic, fork execution, and the settings UI, with docs and tests covering the full flow.

Fusion-Task-Id: FN-4070
2026-05-12 07:47:10 -07:00
Fusion
e441398208 feat(FN-3906): add frontend scope helpers for workflow step auto-skip
Adds frontend-UX auto-skip behavior for workflow steps in the executor, with tests covering the flow and documentation of the recovery logic. A changeset is included for this patch release.

Fusion-Task-Id: FN-3906

Fusion-Task-Lineage: 3c50b82b-dd03-4ba3-8d77-5aaabb8734da
2026-05-11 11:21:21 -07:00
Fusion
234c2a5945 feat(FN-3968): add tests for task env inheritance and isolation in spawn/ch
Adds test coverage for task environment propagation through the spawn flow, covering child agents inheriting task env, workflow step task env, and spawn hook env isolation cases in `pi-create-fn-agent.test.ts`, with minor additions to `executor-step-session.test.ts` and `executor-pause.test.ts`.

Fusion-Task-Id: FN-3968
2026-05-10 23:36:10 -07:00
Fusion
f240683fc8 feat(FN-3720): split executor.test.ts into eight focused suites and add she
The merge splits the large monolithic `executor.test.ts` into seven focused test suites covering core logic, pause behavior, prompt handling, recovery, review verdicts, step sessions, and worktree operations, and adds shell context hook plumbing across the dashboard, desktop, and mobile packages to

Fusion-Task-Id: FN-3720
2026-05-07 23:21:05 -07:00