root/fusion
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
9,173 Commits 1 Branch 0 Tags
b6ac5f2e51bd362bfe45884d02193fa72d59e721
Commit Graph

2630 Commits

Author SHA1 Message Date
gsxdsm
b6ac5f2e51 FN-6608: bound engine verification runs 
Add durable engine-level guardrails for verification command timeouts.

- Add project-level verificationCommandTimeoutMs settings plumbing and docs.
- Enforce configured verification budgets and hard caps in executor and merger verification paths.
- Detect marathon verification commands, soft-cap them by default, and require allowFullSuite for explicit full-suite runs.
- Cover timeout defaults, marathon detection, and guidance updates with engine/core tests.

Files changed:
 .changeset/fn-6608-verification-bound.md           |   5 +
 docs/settings-reference.md                         |   1 +
 docs/testing.md                                    |   2 +
 .../src/__tests__/settings-consistency.test.ts     |   5 +
 packages/core/src/agent-prompts.ts                 |   6 +-
 packages/core/src/settings-schema.ts               |   7 +-
 packages/core/src/types.ts                         |   6 +
 .../engine/src/__tests__/executor-core.test.ts     |   3 +
 .../src/__tests__/run-verification-command.test.ts | 176 ++++++++++++++++++++-
 packages/engine/src/executor.ts                    |  11 +-
 packages/engine/src/merger.ts                      |   9 +-
 packages/engine/src/run-verification-tool.ts       | 142 +++++++++++++++--
 packages/engine/src/verification-utils.ts          |  13 +-
 13 files changed, 360 insertions(+), 26 deletions(-)

Fusion-Task-Id: FN-6608
Fusion-Task-Lineage: c593a96d-eb8b-492c-82c7-8943c239f588
 2026-06-18 01:27:09 -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
98ccf8a293 FN-6625: classify completion finalization aborts 
Prevent completed no-commit executions that already advanced to review from being re-parked as pause-abort failures.

- Add completion-finalize pause-abort provenance and exclude it from genuine pause handling after review handoff.
- Mark paused-after-completion finalization paths with the new provenance before handing tasks to review.
- Cover the finalize-to-review abort recovery path with executor regression tests and document the lifecycle exception.
- Add a patch changeset for the published Fusion package.

Files changed:
 .changeset/fn-6625-finalize-to-review-abort.md     |   5 +
 docs/architecture.md                               |   2 +-
 .../engine/src/__tests__/executor-recovery.test.ts | 158 ++++++++++++++++++++-
 packages/engine/src/executor.ts                    |  26 +++-
 4 files changed, 185 insertions(+), 6 deletions(-)

Fusion-Task-Id: FN-6625

Fusion-Task-Lineage: 728f6fe5-4c27-4597-b17e-e16ff97b9277
 2026-06-18 00:01:32 -07:00
gsxdsm
0453a65bf1 FN-6613: inject skills into agent session lanes 
Ensure every agent-acting session lane requests available agent and plugin skills.\n\n- Add skill selection context to planning, mission interview, workflow design, memory insight, and cron automation sessions.\n- Thread plugin runners through dashboard session creation, retry, reconnect, and route registration paths.\n- Cover skill injection behavior with dashboard and cron runner regression tests.\n- Document which agent session lanes request skills and which utility-only lanes remain exempt.\n- Add a minor changeset for the published CLI package.\n\nFiles changed:\n .changeset/fn-6613-session-skill-lanes.md          |   5 +\n docs/agents.md                                     |   1 +\n .../src/__tests__/mission-interview.test.ts        |  55 ++++++\n .../src/__tests__/planning-skill-selection.test.ts | 130 +++++++++++++\n .../src/__tests__/session-error-recovery.test.ts   |   6 +\n .../session-persistence-roundtrip.test.ts          |   6 +\n .../src/__tests__/session-reconnect.test.ts        |   6 +\n .../src/__tests__/session-resume-history.test.ts   |   6 +\n packages/dashboard/src/mission-interview.ts        |  23 ++-\n packages/dashboard/src/mission-routes.ts           |   4 +-\n packages/dashboard/src/planning.ts                 |  32 +++-\n .../register-settings-memory-worktrunk.test.ts     | 203 ++++++++++++++++++++-\n .../routes/__tests__/workflow-design-route.test.ts |  56 +++++-\n .../src/routes/register-integrated-routers.ts      |   2 +-\n .../src/routes/register-planning-subtask-routes.ts |   5 +\n .../src/routes/register-settings-memory-routes.ts  |  33 +++-\n .../src/routes/register-workflow-routes.ts         |  16 +-\n packages/dashboard/src/test/mockCoreEngine.ts      |   9 +\n packages/engine/src/__tests__/cron-runner.test.ts  |  17 ++\n packages/engine/src/cron-runner.ts                 |   7 +\n 20 files changed, 599 insertions(+), 23 deletions(-)

Fusion-Task-Id: FN-6613

Fusion-Task-Lineage: 985fa9fb-0381-4abf-930f-b547a475c4ed
 2026-06-17 21:12:53 -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
7f4f611367 FN-6611: clarify engineer backlog auto-claim routing 
Clarifies why engineer agents see but do not auto-claim backlog tasks without opt-in.

- Surface actionable project and per-agent opt-in guidance in no-task heartbeat prompts.
- Include eligible backlog candidates in the blocked engineer guidance so routing remains visible.
- Cover disabled engineer auto-claim scenarios with prompt assertions.
- Update agent and settings docs with the visible configuration paths.

Files changed:
 docs/agents.md                                        |  2 +-
 docs/settings-reference.md                            |  2 +-
 .../engine/src/__tests__/heartbeat-executor.test.ts   | 11 +++++++++--
 packages/engine/src/agent-heartbeat.ts                | 19 ++++++++++++++++---
 4 files changed, 27 insertions(+), 7 deletions(-)

Fusion-Task-Id: FN-6611

Fusion-Task-Lineage: ffcafc50-1664-4807-826c-cccf68d31012
 2026-06-17 19:11:31 -07:00
gsxdsm
48da420414 FN-6593: delete unresolved flaky test quarantines 
Delete unresolved quarantined flaky tests under the deletion ratchet while preserving newer active quarantines.

- Remove four flaky test files that were not rescued before the ratchet follow-up.
- Drop their matching Vitest excludes and quarantine ledger entries.
- Preserve later sync, work-bridge, and core quarantine records from main.

Files changed:
 .../src/__tests__/github-tracking-hook.test.ts     | 592 ---------------------
 packages/dashboard/vitest.config.ts                |   8 +-
 .../src/__tests__/cli-agent-executor.test.ts       | 404 --------------
 packages/engine/vitest.config.ts                   |   5 +-
 .../src/__tests__/orchestrator-flow.test.ts        | 156 ------
 .../src/__tests__/skill-wiring.test.ts             | 101 ----
 .../vitest.config.ts                               |   6 +-
 scripts/lib/test-quarantine.json                   |  20 -
 8 files changed, 13 insertions(+), 1279 deletions(-)

Fusion-Task-Id: FN-6593

Fusion-Task-Lineage: 1165ba24-894a-4cc9-b678-50ae1625ba6b
 2026-06-17 17:37:08 -07:00
gsxdsm
01b80db603 FN-6589: add structured ask-question chat tool 
Add a native chat-agent tool for presenting structured questions to dashboard users.

- Register `fn_ask_question` for dashboard chat sessions with prompt guidance to wait for user replies.
- Reuse the existing structured question card parser by recognizing the new tool name.
- Validate ask-question parameters in engine tooling and cover chat/parser behavior with tests.
- Document the dashboard chat question flow and add a patch changeset.

Files changed:
 .changeset/fn-6589-chat-ask-question.md            |  5 ++
 docs/dashboard-guide.md                            |  3 +-
 .../utils/__tests__/parseQuestionToolCall.test.ts  | 19 +++++
 .../dashboard/app/utils/parseQuestionToolCall.ts   |  3 +-
 .../dashboard/src/__tests__/chat-manager.test.ts   | 10 ++-
 packages/dashboard/src/chat.ts                     | 10 ++-
 .../src/__tests__/agent-tools-ask-question.test.ts | 51 ++++++++++++
 packages/engine/src/agent-tools.ts                 | 94 ++++++++++++++++++++++
 packages/engine/src/index.ts                       |  2 +
 9 files changed, 190 insertions(+), 7 deletions(-)

Fusion-Task-Id: FN-6589
Fusion-Task-Lineage: 3f416010-ed2f-40b3-a899-7a9f4a6ed265
 2026-06-17 16:53:29 -07:00
gsxdsm
e48df026c6 FN-6594: classify Codex transcript desync as non-continuable 
Recognize Codex transcript replay desync failures so completed tasks can recover instead of wedging.

- Add Codex transcript-desync matching to non-continuable session error detection.
- Cover canonical and symmetric missing function-call-output messages while excluding auth, quota, and ordinary bad-input errors.
- Add self-healing coverage for post-done wedges with Codex envelope and log evidence.

Files changed:
 .../post-done-continuation-no-wedge.test.ts        | 72 ++++++++++++++++++++++
 .../src/__tests__/transient-error-detector.test.ts | 24 +++++++-
 packages/engine/src/transient-error-detector.ts    |  7 ++-
 3 files changed, 101 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-6594

Fusion-Task-Lineage: 517f39c8-9bbb-47d2-a4a4-495eaf8c3fca
 2026-06-17 15:11:55 -07:00
gsxdsm
403bd9d716 FN-6582: enforce workflow gate artifact verdicts 
Enforce custom workflow terminal gates for required artifacts and malformed pre-merge verdicts.

- Add runtime validation that declared workflow artifacts exist before reporting workflow success.
- Treat malformed pre-merge gate output as a blocking failure instead of a skipped success.
- Cover required-artifact and malformed-verdict gate behavior with focused engine tests.
- Document the required-artifact gate and add a patch changeset for the published CLI package.

Files changed:
 .changeset/fn-6582-workflow-gates.md               |   5 +
 docs/workflow-steps.md                             |   5 +-
 .../workflow-malformed-verdict-gate.test.ts        | 114 +++++++++++++++++++
 .../workflow-required-artifact-gate.test.ts        | 123 +++++++++++++++++++++
 packages/engine/src/executor.ts                    |  63 +++++++----
 packages/engine/src/workflow-task-runtime.ts       |  41 ++++++-
 6 files changed, 326 insertions(+), 25 deletions(-)

Fusion-Task-Id: FN-6582

Fusion-Task-Lineage: 6f59fc33-dd35-4e28-bf6b-85b709c77453
 2026-06-17 14:52:56 -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
593ebac85c FN-6573: guard task-list formatter resolution 
Make fn_task_list surfaces tolerate stale core runtimes without crashing.

- Resolve formatTaskListText from the runtime @fusion/core namespace with a typeof guard.
- Add bounded inline fallback formatting for CLI, dashboard planning-board, and engine triage task-list tools.
- Cover missing formatter exports with regression tests and add a published package changeset.

Files changed:
 .changeset/fn-6573-task-list-format-resolve-fix.md |  5 +++
 packages/cli/src/__tests__/extension.test.ts       | 25 +++++++++------
 packages/cli/src/extension.ts                      | 36 ++++++++++++++++++++--
 .../src/__tests__/planning-board-tools.test.ts     | 27 +++++++++++++++-
 packages/dashboard/src/planning-board-tools.ts     | 36 ++++++++++++++++++++--
 packages/engine/src/__tests__/triage.test.ts       | 25 +++++++++++++++
 packages/engine/src/triage.ts                      | 36 ++++++++++++++++++++--
 7 files changed, 174 insertions(+), 16 deletions(-)

Fusion-Task-Id: FN-6573

Fusion-Task-Lineage: 64577f09-5ca5-426e-a453-a91e6c2c3aee
 2026-06-17 14:52:55 -07:00
gsxdsm
8037ef15a3 Merge main into feature/factory-view: reconcile lazy-view inventory to 23 
Resolves conflicts in the lazy-loaded heavy-views inventory. main independently
grew the curated list to 22 (adding AppModals lazy modals); this branch added the
Command Center view. Combined count is 23 — updated the AGENTS.md prose/inventory
and the lazy-loaded-views-docs test contract (count + length assertions) to 23,
keeping main's richer "App-level and AppModals" wording.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-17 11:46:31 -07:00
gsxdsm
a84a8e1793 FN-6570: guard task list formatting fallback 
Prevent fn_task_list surfaces from crashing when the runtime core namespace lacks the clamp export.

- Add a shared defensive task-list formatter with a bounded fallback clamp.
- Route CLI, dashboard planning-board, and engine triage fn_task_list output through the formatter.
- Cover missing, throwing, and non-string clamp behavior in core and CLI tests.
- Document the resilient task-list formatting behavior and add a patch changeset.

Files changed:
 .changeset/fn-6570-task-list-resolve-fix.md        |  5 ++
 docs/cli-reference.md                              |  2 +-
 packages/cli/src/__tests__/extension.test.ts       | 57 +++++++++++++++++++++-
 packages/cli/src/extension.ts                      |  8 ++-
 .../core/src/__tests__/task-list-format.test.ts    | 49 ++++++++++++++++++-
 packages/core/src/index.ts                         |  2 +-
 packages/core/src/task-list-format.ts              | 35 +++++++++++++
 packages/dashboard/src/planning-board-tools.ts     |  8 ++-
 packages/engine/src/triage.ts                      |  8 ++-
 9 files changed, 164 insertions(+), 10 deletions(-)

Fusion-Task-Id: FN-6570

Fusion-Task-Lineage: 455f38a8-5e4f-4643-a3ce-088ef0c92b01
 2026-06-17 06:14:10 -07:00
gsxdsm
e2a3a37b26 FN-6569: make auto-merge retry cap configurable 
Adds a project setting that controls how many auto-merge conflict retries run before recovery paths give up.

- Add maxAutoMergeRetries to project settings defaults, schema, types, and dashboard controls.
- Resolve the retry cap in engine merge handling, self-healing recovery, stall detection, and blocker fanout logic.
- Cover custom retry caps with core, dashboard, and engine regression tests.

Files changed:
 .changeset/fn-6569-max-auto-merge-retries.md       |  5 ++
 docs/architecture.md                               |  2 +-
 docs/settings-reference.md                         |  1 +
 .../core/src/__tests__/settings-defaults.test.ts   | 12 ++++
 packages/core/src/in-review-stall.ts               | 16 ++++-
 packages/core/src/index.ts                         |  1 +
 packages/core/src/settings-schema.ts               |  6 ++
 packages/core/src/task-priority.ts                 |  4 +-
 packages/core/src/types.ts                         |  8 +++
 .../dashboard/app/components/SettingsModal.tsx     |  8 +++
 .../components/settings/sections/MergeSection.tsx  | 26 +++++++
 .../app/hooks/__tests__/useBlockerFanout.test.ts   |  5 +-
 packages/dashboard/app/hooks/useBlockerFanout.ts   |  3 +-
 .../auto-merge-retry-cap-settings.test.ts          | 79 ++++++++++++++++++++++
 packages/engine/src/project-engine.ts              | 77 +++++++++++++--------
 packages/engine/src/self-healing.ts                | 30 +++++---
 16 files changed, 236 insertions(+), 47 deletions(-)

Fusion-Task-Id: FN-6569
Fusion-Task-Lineage: 42242d6a-68bc-41f1-b2d9-af2e6f168eed
 2026-06-17 04:51:31 -07:00
gsxdsm
6ced5d73de FN-6568: route merge-seam graph aborts to retry 
Classify merge-seam abort provenance so non-paused merge graph failures retry instead of parking as pauses.

- Track paused-abort provenance separately from the legacy pause-abort bit.
- Route merge and requestMerge graph failures through bounded auto-merge retry when they are not genuine pauses.
- Preserve user/global pause parking behavior with regression coverage and document the lifecycle invariant.

Files changed:
 .../fn-6568-merge-seam-abort-classification.md     |   5 +
 docs/architecture.md                               |   1 +
 .../engine/src/__tests__/executor-recovery.test.ts | 131 ++++++++++++++++++++-
 packages/engine/src/executor.ts                    | 122 +++++++++++++------
 4 files changed, 221 insertions(+), 38 deletions(-)

Fusion-Task-Id: FN-6568

Fusion-Task-Lineage: 5d9ee4f8-0336-4fb9-aa95-beb65e6c1ed9
 2026-06-17 04:16:10 -07:00
gsxdsm
21c4d3e5ca FN-6495: load chat session skills 
Enable dashboard chat sessions to request the same agent and plugin skills used by execution lanes.

- Pass enabled plugin-contributed skills through the dashboard chat plugin runner contract.
- Add skill selection for bound-agent chat, model-only QuickChat, and room responder sessions.
- Cover regular chat, QuickChat, no-metadata fallback, legacy runner, and room responder skill requests.
- Document dashboard chat skill behavior and add a minor changeset for the published CLI package.

Files changed:
 .changeset/fn-6495-chat-skill-selection.md         |   5 +
 docs/agents.md                                     |   1 +
 .../dashboard/src/__tests__/chat-manager.test.ts   | 125 +++++++++++++++++++++
 .../dashboard/src/__tests__/chat.rooms.test.ts     |  45 ++++++++
 packages/dashboard/src/chat.ts                     |  35 ++++++
 packages/dashboard/src/server.ts                   |   5 +
 packages/engine/src/index.ts                       |   6 +
 7 files changed, 222 insertions(+)

Fusion-Task-Id: FN-6495

Fusion-Task-Lineage: 0b8998e2-848c-4c79-b93a-16c0b3c3d8a3
 2026-06-16 19:40:56 -07:00
gsxdsm
0db81349bb FN-6492: clamp task list text output 
Bound fn_task_list responses now stay as plain text across board-tool surfaces.\n\n- Add a shared task-list text clamp with an explicit truncation marker.\n- Route CLI, dashboard planning-board, and engine triage task-list output through the shared formatter.\n- Cover bounded and column-filtered output with core and CLI regression tests.\n- Record the patch changeset and quarantine the observed engine CLI executor flake.\n\nFiles changed:\n .changeset/fn-6492-task-list-text-bound.md         |  5 ++\n packages/cli/src/__tests__/extension.test.ts       | 79 +++++++++++++++++++++-\n packages/cli/src/extension.ts                      |  7 +-\n .../core/src/__tests__/task-list-format.test.ts    | 75 ++++++++++++++++++++\n packages/core/src/index.ts                         |  1 +\n packages/core/src/task-list-format.ts              | 45 ++++++++++++\n packages/dashboard/src/planning-board-tools.ts     |  8 ++-\n packages/engine/src/triage.ts                      |  7 +-\n packages/engine/vitest.config.ts                   |  5 ++\n scripts/lib/test-quarantine.json                   |  5 ++\n 10 files changed, 232 insertions(+), 5 deletions(-)

Fusion-Task-Id: FN-6492

Fusion-Task-Lineage: 8b347efb-bc17-4bbe-937c-4f07c63df318
 2026-06-16 19:31:33 -07:00
gsxdsm
0093678ee6 FN-6481: require release triage authorization 
Block release-class tasks from automatic triage dispatch unless they come from a user-authored source with explicit authorization.

- Add release intent classification and authorization-marker enforcement before final triage transitions.
- Record activity/log details when release tasks are parked awaiting manual approval.
- Surface the new release-authorization activity in dashboard activity views.
- Cover release gating behavior with engine tests and document the architecture pattern.
- Add a changeset for the published CLI package.

Files changed:
 .changeset/fn-6481-release-triage-authorization.md |   5 +
 .../release-triage-requires-user-authorization.md  |  33 +++++
 packages/core/src/types.ts                         |   2 +
 packages/core/vitest.config.ts                     |   4 +
 packages/dashboard/app/components/ActivityFeed.tsx |   5 +
 .../dashboard/app/components/ActivityLogModal.tsx  |   6 +
 .../__tests__/triage-release-authorization.test.ts | 158 +++++++++++++++++++++
 .../engine/src/triage-release-authorization.ts     | 100 +++++++++++++
 packages/engine/src/triage.ts                      |  51 +++++++
 scripts/lib/test-quarantine.json                   |   8 +-
 10 files changed, 371 insertions(+), 1 deletion(-)

Fusion-Task-Id: FN-6481
Fusion-Task-Lineage: 0bddb77a-87e5-4fa5-b31a-e773bdae7a29
 2026-06-16 15:08:24 -07:00
gsxdsm
cb91d3fc06 FN-6482: preserve awaiting graph failure states 
Preserve resumable workflow graph waits instead of parking them as execute failures.

- Classify awaiting user input and CLI approval node values before terminal graph failure handling.\n- Read foreach container context values for step-execute instances.\n- Cover awaiting graph exits and genuine step-execute-unwired failures in executor recovery tests.\n\nFiles changed:\n .../engine/src/__tests__/executor-recovery.test.ts | 87 ++++++++++++++++++++++\n packages/engine/src/executor.ts                    | 34 +++++++++\n 2 files changed, 121 insertions(+)

Fusion-Task-Id: FN-6482

Fusion-Task-Lineage: 2443d4cd-1307-470a-b456-2f3b44b9cc83
 2026-06-16 15:08:24 -07:00
gsxdsm
61f389ed3c Address PR review feedback (#1683) 
- monitor-trait: atomic incident-level claim (conditional UPDATE) so concurrent
  regression ingests can't open duplicate fix tasks; loser absorbs (+ tests)
- register-git-github: attach/detach KnowledgeIndexRefreshService per project
  store so task:moved→done refreshes the index for non-primary projects
- agent-logger: make usage-event emission genuinely fail-soft (try/catch +
  absorb async rejection) so a throwing emitUsageEvent can't break tool logging
  (+ sync-throw and rejected-promise tests)
- db: add composite (kind, ts) index on usage_events backing Command Center
  tool analytics; folded into migration 118 (unreleased) — no SCHEMA_VERSION bump
- db.test: assert the six v120 deployments/incidents indexes survive migration
- lazy-loaded-views-docs.test: fix stale "20-view" → "21-view" description
- add FNXC_LOG change-log annotations across the touched package files per AGENTS.md

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-16 05:56:11 -07:00
gsxdsm
e617ce65d9 feat(pr): U18 — surface + gate auto-resolution of PR review comments 
Adds autoResolveReviewComments project setting (default on) gating the existing
Review-response loop, a single-sourced summarizePrThreadActivity counter, and
fixed/acted thread counts in the dashboard PR summary. Resolution stays
independent of the auto-merge gate (disabled merge still resolves threads).
 2026-06-15 19:44:17 -07:00
gsxdsm
ab9fdc4136 feat(telemetry): U1 — queryable usage_events table + emitUsageEvent capture 
Schema migration 117→118 adds usage_events; events captured via a dedicated
emitUsageEvent seam wired through AgentLogger tool hooks + executor session
context (model/provider/nodeId), not by widening log signatures. meta is
size-capped and carries only non-sensitive descriptors.
 2026-06-15 19:20:38 -07:00
gsxdsm
799e590e3e Merge pull request #1580 from Runfusion/feature/workflow-owned-merge-s07-completion-handoff-merge-work 
refactor(workflow): S07 completion handoff creates merge work
 2026-06-16 04:30:22 +08:00
gsxdsm
1b5b8708a6 Merge pull request #1579 from Runfusion/feature/workflow-owned-merge-s06-git-merge-capabilities 
refactor(workflow): S06 git and merge capability extraction
 2026-06-16 04:28:26 +08:00
gsxdsm
5696d4497f fix(review): address PR #1681 feedback (acp.active accuracy + FNXC comments) 
- Greptile P2: `acp.active` now reflects the ACTUAL dispatch determinant
  (FUSION_CLAUDE_ACP, which includes the operator force-override), not the
  experimental flag alone — so the status isn't misleading when forced on/off.
- CodeRabbit/Greptile P2: add FNXC:ClaudeAcp comments to the new code blocks
  per the AGENTS.md greppable-comment convention.

Already fixed in the prior commit (daa37d08c): the P1 "sticky env" / latch
(applyClaudeAcpEnable now recomputes each call + FUSION_CLAUDE_ACP_FORCE
override) and the enable->disable-on-same-env regression test.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-15 12:34:44 -07:00
gsxdsm
daa37d08c5 feat(acp): surface bridge auth failure in the UI with fallback / fix-auth (R17) 
When the bridged `claude` can't authenticate (detached daemon / no keychain),
the turn returns "Not logged in" instead of a real answer. Rather than silently
relay that, detect it and let the user choose.

- Driver: detect a "Not logged in"-only turn and write a cross-process signal
  (fusion-acp-bridge-auth.json); a real response clears it (acp-driver test).
- Dashboard status: GET /providers/claude-cli/status reports
  acp.authFailed + authReason from the signal.
- UI: the Claude CLI provider card shows an auth-failure banner with
  "Use claude -p" (sets experimentalFeatures.claudeCliAcp=false) and
  "I fixed auth — re-test", plus a fix hint (run `claude` to log in).
- Enable resolution now recomputes each call with an operator force-override
  (FUSION_CLAUDE_ACP_FORCE), so the "Use -p" fallback takes effect on the next
  turn — no restart. claude-acp-enable tests updated.

pi-claude-cli + engine tests green; dashboard typecheck clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-15 12:32:00 -07:00
gsxdsm
45184aef7e feat(acp): enable Route A via experimental flag (claudeCliAcp), default ON 
Replace the manual FUSION_CLAUDE_ACP env enable with an experimental feature
switch. `experimentalFeatures.claudeCliAcp` is ON by default (off only when
explicitly set false); the engine translates it into the FUSION_CLAUDE_ACP
dispatch the pi-claude-cli provider reads, at registerExtensionProviders time.

- Still fail-closed: with no bridge path published (acp-runtime plugin absent),
  the provider falls back to `claude -p`.
- Explicit FUSION_CLAUDE_ACP env always wins (operator / test override).
- New testable helper claude-acp-enable.ts (6/6 tests); flag documented in the
  core experimentalFeatures doc.

So with the acp-runtime plugin installed, Claude CLI now routes through the ACP
bridge by default; set experimentalFeatures.claudeCliAcp=false to force `-p`.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-15 12:14:20 -07:00
gsxdsm
079844e1c1 feat(acp): forward MCP servers on session/new (U10) + record U9 GO / R17 
Route A unblock + the first Route A code increment.

- U9 verdict recorded (plan OQ1 + docs/acp-contract.md): in an authenticated
  interactive session the pinned claude-code-cli-acp 0.1.1 bridge forwards
  session/new mcpServers to Claude, Claude invokes the forwarded Fusion tool,
  and the call traverses the ACP permission gate (session/request_permission).
  Both security-critical answers resolve positively — overturns the headless
  NOT-GO chain (FN-6466/6467/6473/6476), whose only blocker was running
  detached from the login keychain session.
- R17 (daemon auth) recorded and closed for the supported setup: creds are
  macOS Keychain-only; the user's login-session fn daemon has keychain access
  (the existing claude -p provider authenticates there), so the bridge does too.
- U10: thread an optional mcpServers list through the ACP runtime contract.
  newAcpSession now forwards it (was hardcoded []); AgentRuntimeOptions (engine
  + plugin-local copy) gains the field; defaults to [] to preserve Route B's
  read-only ask posture. Tool calls still route through the U5 permission floor.

Plugin typechecks clean; provider-session tests 12/12 (incl. 2 new forwarding
tests). U11-U13 (provider transport swap, picker/auth, workflow verify) remain.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-15 05:56:47 -07:00
gsxdsm
bc6dfd386e FN-6478: surface paused workflow graph failures 
Surface stranded paused workflow exits as actionable executor failures.

- Treat paused or aborted graph exits as benign only while the live task remains in-progress.
- Preserve terminal/review lifecycle state while recording operator-actionable failure evidence for advanced columns.
- Cover user-paused, pause-aborted, existing-failure, in-progress, in-review, todo, and done column recovery paths.
- Document the workflow lifecycle invariant and add a patch changeset.

Files changed:
 .changeset/fn-6478-paused-workflow-executions.md   |   5 +
 docs/architecture.md                               |   1 +
 .../engine/src/__tests__/executor-recovery.test.ts | 283 +++++++++++++++++++++
 packages/engine/src/executor.ts                    |  30 ++-
 4 files changed, 315 insertions(+), 4 deletions(-)

Fusion-Task-Id: FN-6478

Fusion-Task-Lineage: 219d8612-6604-4dbc-9a3a-a1c7837419c1
 2026-06-15 02:30:41 -07:00
gsxdsm
a9815fb1ff FN-6457: add ACP ask runner and bundled Claude bridge setup 
Route ACP-backed planning and validation through a read-only ask-once runner with a pinned Claude bridge foundation.

- Add askAcpOnce for single-turn ACP sessions with timeout handling, JSON recovery, clean stop validation, and disposal.
- Refactor validation seams to use ACP runtime prompts and require structured pass verdicts.
- Resolve the Claude ACP bridge from the plugin bundle and add setup checks for identity, environment, probing, and auth readiness.
- Document the ACP Route B plan and update tests for validator, session, runtime, and plugin setup behavior.

Files changed:
 CONCEPTS.md                                        |   6 +
 docs/acp-contract.md                               |  36 ++
 .../2026-06-14-001-feat-claude-acp-runtime-plan.md | 465 +++++++++++++++++++++
 .../engine/src/__tests__/cli-agent-ask.test.ts     | 104 +++++
 .../src/__tests__/cli-agent-validator.test.ts      | 137 +++---
 .../src/__tests__/interactive-ai-session.test.ts   |  96 +++--
 packages/engine/src/agent-runtime.ts               |   6 +-
 packages/engine/src/cli-agent-ask.ts               | 120 ++++++
 packages/engine/src/cli-agent-validator.ts         |  65 ++-
 .../cli-agent/__tests__/one-shot-session.test.ts   |  16 +-
 packages/engine/src/cli-agent/one-shot-session.ts  |  17 +-
 packages/engine/src/index.ts                       |   8 +-
 packages/engine/src/interactive-ai-session.ts      |  33 +-
 plugins/fusion-plugin-acp-runtime/AGENTS.md        |  14 +
 plugins/fusion-plugin-acp-runtime/CHANGELOG.md     |   6 +
 plugins/fusion-plugin-acp-runtime/README.md        |  13 +-
 plugins/fusion-plugin-acp-runtime/package.json     |   3 +-
 .../src/__tests__/index.test.ts                    |  51 ++-
 .../src/__tests__/process-manager.test.ts          |  32 +-
 .../src/__tests__/runtime-adapter.test.ts          |   4 +-
 .../src/__tests__/setup.test.ts                    |  71 ++++
 plugins/fusion-plugin-acp-runtime/src/cli-spawn.ts |  95 ++++-
 plugins/fusion-plugin-acp-runtime/src/index.ts     |  16 +-
 .../src/process-manager.ts                         |  26 +-
 .../src/runtime-adapter.ts                         |  11 +-
 plugins/fusion-plugin-acp-runtime/src/setup.ts     | 104 +++++
 plugins/fusion-plugin-acp-runtime/src/types.ts     |   6 +-
 pnpm-lock.yaml                                     | 139 ++++--
 28 files changed, 1502 insertions(+), 198 deletions(-)

Fusion-Task-Id: FN-6457
Fusion-Task-Lineage: a3364ed7-cb28-4a2b-b898-6ccd0d95fb92
 2026-06-15 02:30:41 -07:00
gsxdsm
fee0178b4f FN-6461: block incomplete no-commits no-op finalization 
Add a shared no-op finalize guard so no-commits tasks with mostly incomplete steps return to todo instead of silently completing.

- Add core step-evidence evaluation for no-commits no-op finalization.
- Apply the guard across AI empty merge, early empty-own-diff, legacy no-op classifier, direct no-op, and self-healing finalize lanes.
- Emit run-audit/log evidence and preserve progress when demoting blocked tasks.
- Cover guard behavior with core, merger, AI merge, real-git, and self-healing tests.
- Document the finalize integrity invariant and add a patch changeset.

Files changed:
 .changeset/fn-6461-no-commits-finalize-guard.md    |   5 +
 docs/architecture.md                               |   2 +
 .../__tests__/no-commits-finalize-guard.test.ts    |  58 +++++++
 packages/core/src/index.ts                         |   2 +
 packages/core/src/no-commits-finalize-guard.ts     |  42 +++++
 packages/engine/src/__tests__/merger-ai.test.ts    |  59 +++++++
 .../merger-finalize-unproven.real-git.test.ts      | 176 +++++++++++++++++++++
 packages/engine/src/__tests__/self-healing.test.ts | 125 +++++++++++++++
 packages/engine/src/merger-ai.ts                   |  45 ++++++
 packages/engine/src/merger.ts                      | 130 +++++++++++++++
 packages/engine/src/run-audit.ts                   |   6 +
 packages/engine/src/self-healing.ts                |  41 ++++-
 12 files changed, 689 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-6461
Fusion-Task-Lineage: 36647768-42da-414a-9304-d8e0ed61b99c
 2026-06-15 02:29:08 -07:00
gsxdsm
dc4c2b2204 FN-6453: clean up AI-merge worktrees after setup failures 
Ensure AI-merge clean-room directories are cleaned up even when setup fails before worktree registration.

- Move clean-room directory creation inside the cleanup guard so terminal setup failures can remove it.
- Skip cleanup only when no merge root was ever created, while still unregistering any registered paths.
- Add regression coverage for active-session registration failure after mkdtemp and before git worktree add.

Files changed:
 .../ai-merge-worktree-cleanup.test.ts              | 31 ++++++++++++++++++++++
 packages/engine/src/merger-ai.ts                   | 21 ++++++++++-----
 2 files changed, 45 insertions(+), 7 deletions(-)

Fusion-Task-Id: FN-6453

Fusion-Task-Lineage: 364b329b-c3e7-4902-8ca8-673360b0d9ac
 2026-06-15 02:29:08 -07:00
gsxdsm
1815b87022 Merge pull request #1678 from plarson/fix/mission-stale-feature-repair 
fix(engine): retriage stale mission feature links
 2026-06-15 16:51:41 +08:00
gsxdsm
f80b301af2 chore(release): v0.43.1 
Version bump via changesets.
 2026-06-14 22:43:49 -07:00
Phil Larson
283f689d8a fix(engine): retriage stale mission feature links 2026-06-14 19:26:55 -07:00
gsxdsm
4f7b3ac78f FN-6439: clear stale near-duplicate flags 
Clear near-duplicate decisions when their canonical task is no longer active.

- Add a shared canonical activity helper for near-duplicate detection.
- Clear stale persisted near-duplicate metadata when canonical tasks are done, archived, or deleted.
- Prevent triage and dashboard surfaces from presenting duplicate decisions for inactive canonicals.
- Cover stale-flag cleanup and hidden dashboard affordances with regression tests.

Files changed:
 docs/task-management.md                            |   4 +-
 .../near-duplicate-stale-flag-clear.test.ts        | 105 +++++++++++++++++++++
 packages/core/src/__tests__/near-duplicate.test.ts |  19 +++-
 packages/core/src/index.ts                         |   2 +
 packages/core/src/near-duplicate-canonical.ts      |  25 +++++
 packages/core/src/near-duplicate.ts                |   3 +
 packages/core/src/store.ts                         | 102 +++++++++++++++++++-
 packages/dashboard/app/App.tsx                     |   7 +-
 packages/dashboard/app/components/Column.tsx       |  10 ++
 packages/dashboard/app/components/TaskCard.tsx     |  12 ++-
 .../dashboard/app/components/TaskDetailModal.tsx   |  12 ++-
 packages/dashboard/app/components/WorktreeGroup.tsx     |  30 +++++-
 .../app/components/__tests__/TaskCard.test.tsx     |  28 ++++++
 .../__tests__/TaskDetailModal.rendering.test.tsx   |  26 +++++
 .../near-duplicate-intake.test.ts                  |  24 +++++
 packages/engine/src/triage.ts                      |  10 ++
 16 files changed, 411 insertions(+), 8 deletions(-)

Fusion-Task-Id: FN-6439

Fusion-Task-Lineage: e57b80e8-36aa-4b96-ad13-53b5a431477d
 2026-06-14 15:29:35 -07:00
gsxdsm
93b2288d37 FN-6433: rescue non-CLI quarantined tests 
Rescue and ratchet non-CLI quarantine state across engine, core, and dashboard suites.

- Empty the core, dashboard, and engine quarantine exclude arrays after proving rescued suites run under package load.
- Replace broad AI-merge active-session registry cleanup with path-scoped unregistering in engine tests.
- Delete the duplicate soft-delete blocker residue suite and clear the quarantine ledger.
- Document the non-CLI quarantine sweep pattern for future rescues.

Files changed:
 docs/testing.md                                    |   2 +
 packages/core/vitest.config.ts                     |  10 +-
 packages/dashboard/vitest.config.ts                |  12 +-
 .../merger-ai-cleanup-active-session.test.ts       |  20 +++-
 .../engine/src/__tests__/merger-ai-cleanup.test.ts |   5 +-
 .../soft-delete-blocker-residue.test.ts            | 128 ---------------------
 packages/engine/vitest.config.ts                   |  12 +-
 scripts/lib/test-quarantine.json                   |  65 +----------
 8 files changed, 40 insertions(+), 214 deletions(-)

Fusion-Task-Id: FN-6433

Fusion-Task-Lineage: 18c37475-e6e1-4358-9350-eca65cf53b68
 2026-06-14 15:29:35 -07:00
Phil Larson
93fd220aaf fix: guard stuck-loop park logging 
Handle logEntry failures after in-place parking without falling back to executor requeue and tighten the reliability assertion for STUCK_LOOP_EXHAUSTED.
 2026-06-14 11:19:11 -07:00
Phil Larson
10ee5954d5 fix: guard stuck-loop in-place park patch failure 2026-06-14 11:09:17 -07:00
Phil Larson
f1ac8d5f6b fix: address stuck-loop parking review comments 2026-06-14 10:59:21 -07:00
Phil Larson
19eca3d74b fix(engine): park incomplete stuck-loop exhaustion 
Preserve incomplete task progress after stuck-kill budget exhaustion while marking the task failed and paused for manual intervention instead of making it scheduler-runnable again.
 2026-06-14 10:42:36 -07:00
gsxdsm
4482425d4b chore(release): v0.43.0 
Version bump via changesets.
 2026-06-14 00:43:13 -07:00
gsxdsm
aa71ace101 fix(auth): refresh expired Claude OAuth tokens 
Refresh stored Claude OAuth credentials before reporting dashboard auth status or resolving model auth so users do not need to repeatedly re-login after access-token expiry.

Coalesce concurrent refresh attempts, prevent stale refreshes from overwriting newer logins, and route CLI dashboard/serve/daemon/onboard auth wiring through the shared refresh-capable storage.
 2026-06-13 23:20:06 -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
b1ba87e599 FN-6414: preserve built-in Z.ai models after extensions 
Keep GLM-5.2 visible when user Z.ai extensions replace the provider registration.

- Add shared helpers to clone and register the built-in Z.ai provider safely.
- Re-merge missing built-in Z.ai models after extension provider registration in daemon, serve, dashboard, and pi flows.
- Cover provider replacement behavior in core and dashboard model route tests, and document the extension-preserving behavior.

Files changed:
 .changeset/FN-6414-glm-5-2-visible.md              |  5 ++
 docs/settings-reference.md                         |  2 +-
 packages/cli/src/commands/daemon.ts                | 12 +--
 packages/cli/src/commands/dashboard.ts             | 12 +--
 packages/cli/src/commands/serve.ts                 | 12 +--
 packages/core/src/__tests__/zai-provider.test.ts   | 33 +++++++-
 packages/core/src/index.ts                         |  7 +-
 packages/core/src/zai-provider.ts                  | 93 +++++++++++++++++++++
 ...register-model-routes-zai-real-registry.test.ts | 97 ++++++++++++++++++++++
 packages/engine/src/pi.ts                          | 12 +--
 10 files changed, 250 insertions(+), 35 deletions(-)

Fusion-Task-Id: FN-6414

Fusion-Task-Lineage: f0990da2-968d-4782-8c00-fbc350d6954f
 2026-06-13 21:17:20 -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
821a8fb936 Merge pull request #1672 from Runfusion/feature/ce-workflow-integration 
feat: make the compound-engineering workflow run the CE way end-to-end
 2026-06-13 16:36:57 -07:00
gsxdsm
9149121bb6 FN-6401: add built-in Z.ai GLM-5.2 support 
Add Z.ai's built-in provider registration so GLM-5.2 is selectable across Fusion model settings.

- Define and export a shared Z.ai provider registration with existing GLM models plus GLM-5.2.
- Register the built-in provider for CLI server and engine pi model registries.
- Cover provider availability and CLI auth-provider wrapping with focused tests.
- Document Z.ai model selection and add a minor changeset.

Files changed:
 .changeset/FN-6401-glm-5-2.md                      |   5 +
 docs/settings-reference.md                         |   2 +
 packages/cli/src/commands/__tests__/daemon.test.ts |  11 ++
 .../cli/src/commands/__tests__/dashboard.test.ts   |  13 +++
 packages/cli/src/commands/__tests__/serve.test.ts  |  11 ++
 packages/cli/src/commands/daemon.ts                |   8 ++
 packages/cli/src/commands/dashboard.ts             |   8 ++
 packages/cli/src/commands/serve.ts                 |   8 ++
 packages/core/src/__tests__/zai-provider.test.ts   |  48 ++++++++
 packages/core/src/index.ts                         |   2 +
 packages/core/src/zai-provider.ts                  | 125 +++++++++++++++++++++
 .../src/__tests__/pi-create-fn-agent.test.ts       |   5 +-
 packages/engine/src/pi.ts                          |  20 +++-
 13 files changed, 264 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-6401

Fusion-Task-Lineage: e1f7a90d-0614-4d9f-826f-015605a08baa
 2026-06-13 16:30:29 -07:00