Removes the broad-scope detection feature end-to-end: the TaskCard chip and TaskDetailModal advisory banner are gone from the dashboard, the triage heuristic that flagged tasks as broad-scope has been deleted from the engine along with its associated run-audit events, and documentation references ha
Fusion-Task-Id: FN-5405
Implements external integration validation (FN-5321) with a manifest validator scaffold, worktrunk manifest wiring, and an evidence gap detector that runs during spec validation and triage; the reviewer also gates on external integration readiness. Includes tests for manifest, evidence gap, and tria
Fusion-Task-Id: FN-5321
Adds an explicit duplicate-marker guard (FN-5220) spanning core helper, dashboard API endpoint, triage short-circuit, and self-healing sweep to detect and handle duplicate task creation attempts; includes comprehensive test coverage across unit, API, and integration layers plus documentation.
Fusion-Task-Id: FN-5220
Adds a reconcile script to recover leaked soft-deleted tasks, threads delete audit context through all callers, and records soft-delete audit events with archive column tracking across core/engine/cli/dashboard, with reliability backstop tests covering caller alignment.
Fusion-Task-Id: FN-5175
Implements in-flight abort for soft-deleted tasks across all three execution lanes: executor, merger, and triage now check for `deletedAt` before proceeding and emit `task:soft-delete-in-flight-abort` audits rather than continuing work on a deleted task. The 829-line addition is dominated by integra
Fusion-Task-Id: FN-5264
Fusion-Task-Lineage: 4ee8e63b-abf0-43e2-9130-39a05434d8f9
The doc was rewritten to cover "every task-creation path" (with an
explicit enumeration of surfaces) instead of the older "task creation
flows (including ...)" wording, and uses "best-effort and non-blocking"
instead of "Creation is best-effort and non-blocking". Update the
documentation contract test to match the current phrasing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Fusion-Task-Id: FN-5208
- Add diagnostics.md and FN-4886/FN-5048 entries to docs/README.md index
- Fix test-project.test.ts spy target (updateSettings → init) to match fixture flow
- Remove unused DEFAULT_PROJECT_SETTINGS import and skip empty settings patch
- Add explanatory comments to empty catch blocks in secrets-env-writer
- Refine near-duplicate timestamp guard in triage for cleaner NaN handling
Adds a `lineage-unlink` flag to triage parent deletes (FN-5131), enabling the split-into-subtasks path to break parent-child lineage on deletion. The primary addition is a comprehensive new test covering that split scenario, with minor adjustments to two existing lineage-related test files.
Fusion-Task-Id: FN-5131
Fusion-Task-Lineage: cb720e8f-8c49-42e4-873a-9949f3ba3427
Adds task priority support to the task creation flow, spanning the engine runtime (`agent-tools.ts`, `triage.ts`), the CLI extension interface (`extension.ts`), and corresponding documentation and tests. The changeset bumps `@runfusion/fusion` as a minor version.
Fusion-Task-Id: FN-4074
Fusion-Task-Lineage: 726c0ae6-90fb-4c13-ace1-215a2becb2a9
Adds a global `thinkingLogEnabled` setting that gates AI thinking log persistence across the engine (executor, reviewer, merger, triage, step-session) and exposes the control in the dashboard Settings modal, with tests verifying settings parity and modal behavior.
Fusion-Task-Id: FN-4062
Hardened empty `rawResponse` handling in the memory insights module by adding defensive checks to prevent errors when the response is empty, accompanied by tests to cover those edge cases (FN-4041 Step 1).
Fusion-Task-Id: FN-4041
The merge fixes triage planning model session key recovery in the engine, enabling the triage agent to properly use default model keys when resuming planning sessions. Tests were added to `triage.test.ts` to assert the correct behavior.
Fusion-Task-Id: FN-3931
The merge introduces the universal web fetch tool across reviewer/merger/triage agents (FN-3803, 4 commits) with docs and regression test, extracts the roadmap as a plugin scaffold in `plugins/fusion-plugin-reports` (FN-3166, FN-3165) while removing dashboard roadmap backend and associated tests, ad
Fusion-Task-Id: FN-3803
The merge introduces a research tool surface gating mechanism: shared availability helpers in core and engine, applied to the executor and triage agent so research prompts and tool exposure are gated behind experimental-feature flags, with tests covering the new logic.
Fusion-Task-Id: FN-3706
Implements assigned-agent triage inheritance (FN-3703), allowing triage logic to be delegated to the assigned agent rather than always routing through the original owner, with test coverage and documentation. Also adds immediate wake controls for agent inbox and message API (FN-3087), wires shared s
Fusion-Task-Id: FN-3703
This merge introduces two major themes. First, research tools in both the engine and CLI are now gated behind an experimental flag, using a shared helper from core — the research tools are documented as experimental and the dashboard settings reference is updated. Second, the testing suite receives
Fusion-Task-Id: FN-3705
TriageProcessor.stop() previously only halted the polling loop, so
in-flight specify sessions and their reviewer subagents kept streaming
past shutdown. Extracted the existing global-pause teardown into
abortAndDisposeActiveSessions() and call it from stop() too.
aiMergeTask creates three sessions during a merge — autostash resolver,
in-merge verification fix agent, and pull-rebase conflict resolver — but
only the autostash one was registered via onSession. The other two are
now registered (with onSession threaded through pushToRemoteAfterMerge
into the rebase resolver chain), so ProjectEngine.stop() actually
disposes whichever merger session is running when shutdown lands.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merged four commits implementing comment-driven retriage: triage rules now respond to specific comment patterns (Step 1) and surface needs-replan feedback inputs in the UI (Step 2), with documentation for the new behavior and a bug fix restoring workspace typecheck defaults. Changes span the core ta
Fusion-Task-Id: FN-3502
`TriageProcessor.finalizeApprovedTask` (added in FN-3056) called
`store.updateTask({title})` while the task was still in column='triage',
which triggered a pre-existing regen path in `TaskStore.updateTask` that
overwrote the agent's just-written specification with the bootstrap stub
(`# {id}: {title}\n\n{description}\n`). Tasks shipped to `todo` (and
through to `done`) with empty 70–200 byte specs while the executor only
saw the original one-line user description. The same regen path also
silently dropped `## Review Level` / `## Frontend UX Criteria` and any
section outside a fixed whitelist whenever a non-triage task's title or
description was edited.
Replaces the regen with wrapper-shape-exact stub detection (compare to
the bytes `createTask` would have written for the pre-update title and
description) plus surgical edits for real specs: title changes splice
only the leading `# ...` heading, description changes rewrite only the
body of `## Mission`, and every other section is preserved verbatim.
`finalizeApprovedTask` now applies the prompt-declared title after
`moveTask("todo")` as defense in depth. New regression tests cover real
specs surviving title sync, long bootstrap stubs, stubs whose body
contains `##` markdown or `**Created:**` text, and the end-to-end
triage finalize sequence on a real `TaskStore`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merges FN-3008 to add a "fallback-used" notification system: the engine now emits events when AI model fallbacks are triggered, dispatches notifications via ntfy/webhook providers, surfaces a session banner in the dashboard, and exposes a settings toggle to enable or disable these alerts.
Fusion-Task-Id: FN-3008
This merge ships several feature and infrastructure improvements across the codebase. Task title validation is strengthened in triage with stricter rejection of malformed titles and preference for prompt-declared titles (FN-3056), while task creation now preserves priority settings (FN-3210). The Mi
Fusion-Task-Id: FN-3056
Merged FN-3076 introducing an auto completion-doc mode that automates task completion documentation. The feature adds a new setting to the settings schema and types, surfaces it in the dashboard Settings UI, provides triage-stage guidance to suggest completion documentation, and is documented in the
Fusion-Task-Id: FN-3076
This release (v0.15.0) brings significant plugin system enhancements including a new dependency graph plugin with dashboard view, plugin skills in session selection, and extended plugin UI slot metadata. Database improvements add SQLite WAL tuning, integrity checks, and batch writes for agent logs.
Fusion-Task-Id: FN-3117
This merge adds droid CLI path reconciliation as a new pi extension, wires agent task auto-summarization for the agent tools layer, makes the UsageIndicator component resizable with improved styling, and updates related tests and documentation. The core changes include a new `reconcile-droid-cli-pat
Fusion-Task-Id: FN-3060
engine: reviewer subagents previously kept running after the parent task
was moved out of in-progress, paused, or globally paused — they spawn
their own AgentSession outside `activeSessions`/`activeStepExecutors`,
so the existing kill paths never reached them. Track them in a per-task
`activeSubagentSessions` map (mirrored in TriageProcessor) and dispose
on the same triggers as the main session. ReviewOptions gains
`onSessionCreated` / `onSessionEnded` callbacks the executor and triage
processor wire to register/unregister.
droid-cli: probe timeouts (`validateCliPresence`, `validateCliAuth`,
`runDroidProbe`) raised from 5s to 45s — observed cold-start is ~20s,
so 5s reported the binary as missing even when present. Provider gains
a `FIRST_LINE_TIMEOUT_MS` (60s) cold-start guard so a hung droid binary
is reported with an actionable error instead of being indistinguishable
from a slow-thinking turn. Fix the await race in `streamViaCli`: when
SIGKILL destroys stdout mid-buffer, `rl` may never emit "close", so the
promise also resolves on `proc.close` and forces `rl.close()` — prevents
the engine's "executor did not unwind within 60s — hung subprocess".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This merge brings multiple substantial features: new research extension tools wired through the AI engine (with full test coverage and documentation), legacy routines agentId backward compatibility with migration paths, migration of experimental remote settings to the global scope, Nerd Font glyph a
Fusion-Task-Id: FN-2996
