Aligns web fetch tool test coverage across multiple test suites and updates the agents documentation, with a patch changeset for `@runfusion/fusion`.
Fusion-Task-Id: FN-3758
The merge delivers two major features: mesh auth snapshot synchronization across nodes (FN-3707 steps 2/4/5, including core types, central-core plumbing, peer-exchange updates, and settings/node sync route helpers) and a bundled roadmap plugin with chat UX improvements (FN-3162, FN-3756, FN-3771, FN
Fusion-Task-Id: FN-3707
Merges major roadmap plugin extraction (FN-3160/3161/3162), hardening the merger with autostash orphan cleanup and TOCTOU defenses (FN-3755/3756), adding shared state snapshots for mesh sync (FN-3451), shipping polling task notifications for the even realities plugin (FN-3743), defaulting non-epheme
Fusion-Task-Id: FN-3756
- Add canonical working-directory resolution with node mapping support in core and engine paths
- Update runtime/multi-project documentation and include published-package changesets for the merged work
- Migrate roadmap dashboard surface to the bundled plugin registry flow and adjust lazy-view integration/tests
- Default non-ephemeral agents to active state and extend related agent/route/executor test coverage
Fusion-Task-Id: FN-3508
Merges reviewState hardening (FN-3280 steps 2-3: hardened persistence, API fixes, and PR feedback sync), stepIndex reconciliation for task updates (FN-3757), roadmap route context extraction into the fusion-plugin-roadmap plugin (FN-3160), and shared state snapshots for mesh sync with autostash hard
Fusion-Task-Id: FN-3280
Fixes a step-index normalization bug in the task executor where update map lookups were inconsistent with the zero-indexed keys used by verdicts and checkpoints, causing reconciliation failures on review/update step pairing.
Fusion-Task-Id: FN-3757
When `git stash apply` exits non-zero without producing conflict markers
(typical causes: untracked-overwrite, path missing at HEAD, index-conflict
that git refuses to mark), the previous code logged the bare exception
message and abandoned the stash. Operators couldn't distinguish failure
shapes without grepping runtime logs, and the dev's uncommitted work was
left to manual recovery even when an automated path would have worked.
Three additions on top of the conflict-marker path that already exists:
1. Capture stderr from the failing `git stash apply` (execAsync attaches
stderr/stdout to the rejection) and surface it in the task feed and
any subsequent failure messages, so the operator sees `error: untracked
working tree files would be overwritten by merge:` directly instead of
hunting it in mergerLog.
2. Layer 1 fallback: extract the patch via `git stash show -p --binary`
and try `git apply --3way`. This is more permissive than `stash apply`
for several common shapes (notably untracked overwrites — `--3way`
produces conflict markers we can route to the existing AI resolver
where stash apply just refuses).
3. Layer 2 fallback: if `--3way` also hard-fails and smartConflictResolution
is enabled, spawn `runAiAgentForAutostashHardFail` with the patch text +
git stderr. The agent reconstructs the developer's edits on top of HEAD
by editing files directly, then the orchestrator scans for residual
conflict markers before declaring success and dropping the stash.
The existing conflict-marker path remains unchanged — only the previously-
abandoned hard-fail branch gains recovery. Stash is dropped on success at
every layer; on every failure path the stash is preserved for manual
recovery and the failure cause is surfaced to the task feed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
dropAutostashBySha resolved SHA→stash@{N} then ran git stash drop ${ref}
non-atomically. Any other process (interactive shell, parallel merger,
fix-agent) pushing a stash between resolve and drop shifted the index, so
we silently dropped the wrong entry while leaving ours behind. The task
log then claimed "Restored pre-merge autostash X cleanly" even though the
stash was still in the list — observed on FN-3558 (e81e922) and others.
Verify the ref still resolves to our SHA via git rev-parse before dropping;
on mismatch, re-resolve and retry up to 5x. Return success/failure so the
caller can record honest status to the task feed instead of unconditionally
logging "cleanly".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merges a significant refactor of agent action gating into a unified `gating-classifications.ts` module shared across permanent agents and executor gating logic, plus new glasses quick-capture support with dedicated routes and parser, and a fix restoring step progress visibility during task execution
Fusion-Task-Id: FN-3742
The merge introduces the new `fusion-plugin-even-cards` workspace plugin providing board card endpoints and API key authentication, while also unifying agent action gating classifications across permanent agents with configurable display limits. The GitHub integration receives review state refresh i
Fusion-Task-Id: FN-3754
Merges two new plugin packages — `fusion-plugin-even-cards` (board/card endpoints with API key auth) and `fusion-plugin-even-realities-glasses` (notifier, quick-capture, settings, transport, Fusion API client, and agent actions) — plus a substantial engine refactor that unifies agent action gating c
Fusion-Task-Id: FN-3751
Implements a new Fusion plugin package (`fusion-plugin-even-realities-glasses`) providing settings schema, a Fusion HTTP API client, cards, quick capture actions, a notifier, and transport stub — plus plugin routes and lifecycle hooks wired into the pi extension. The branch concludes with a small fi
Fusion-Task-Id: FN-3738
This merge adds a direct-mode review tab to the task detail modal (FN-3278), improves mobile mailbox keyboard handling and fixes request hangs during wake dispatch (FN-3750/FN-3751), and reclassifies coordination tools with lock exemptions in the agent gating system (FN-3724), alongside GitHub route
Fusion-Task-Id: FN-3724
Merges reloadable exempt-tools action-gate reload endpoint into the engine alongside a new heartbeat readonly-tools gating mechanism, plus a service worker first-install blank page fix. The engine gains a reload endpoint for action gates, permanent-agent gating exports, and comprehensive test covera
Fusion-Task-Id: FN-3734
Adds a reload endpoint for action-gate exempt tools, exposing `POST /api/system/reload-exempt-tools` on the dashboard to hot-reload the engine's mutable EXEMPT_TOOLS registry without a restart. The endpoint is wired through `agent-action-gate.ts` with test coverage for reloadable behavior.
Fusion-Task-Id: FN-3731
Tasks were getting stuck in In Review with "verification fix succeeded but no
merge commit could be created" even though the merge commit was already on
main. Verification failures on attempt 1 were being swallowed by the smart-
conflict-resolution retry path, triggering attempt 2 with a stale baseline,
and the in-merge-fix finalizer would then fail its phantom-merge check.
- Propagate VerificationError out of executeMergeAttempt so the in-merge fix
runs once on attempt 1 with the correct preAttemptHeadSha baseline.
- In commitOrAmendMergeWithFixes, recognize "task already on HEAD" via the
Fusion-Task-Id trailer (line-anchored match) and treat the no-progress
finalize as success instead of tripping the guard.
- Add real-git regression test plus update merger.test.ts call counts to
reflect the (now correctly absent) attempt-2 AI agent.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add shared agent role policy helpers for implementation task detection and executor-role enforcement
- Provide a standardized role-mismatch error formatter for delegation and assignment paths
- Update test isolation leak detection to ignore ephemeral fusion-test-home-root temp directories while preserving baseline checks
Fusion-Task-Id: FN-3716
- Store plugin installation metadata in central DB while preserving per-project enable/disable state
- Update plugin CLI and dashboard Plugin Manager copy/behavior to distinguish global install from project enablement
- Expand plugin store and loader test coverage, including legacy migration and scoped install assertions
- Update runtime plugin e2e tests to use isolated central DB directories and document the new semantics
- Add a changeset for @runfusion/fusion describing the plugin scope behavior change
Fusion-Task-Id: FN-3182
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
This merge lands three major features and a significant dashboard enhancement. FN-3276 adds a full Review tab to the task detail modal with multi-step lifecycle: review metadata persistence in the task store, new task workflow routes for refresh and same-task revision, and the review tab UI surface
Fusion-Task-Id: FN-3276
Adds validation to block task dispatch when no project-node mapping exists (FN-3507), including a read helper in CentralCore and a new `node-dispatch-validation` module integrated into the scheduler and in-process runtime, with test coverage across routing and validation scenarios.
Fusion-Task-Id: FN-3507
Wired permanent-agent approval context into runtime paths for FN-3561, updating the agents documentation and adding test coverage for the heartbeat executor to validate the runtime behavior.
Fusion-Task-Id: FN-3561
The merge lands three major features: a permanent-agent gating system (FN-3560, 6 steps) that classifies and enforces tool access policies for permanent agents in the PI extension, with full test coverage and updated agent docs; an OpenClaw MCP bridge (FN-3717) adding MCP config, schema server, and
Fusion-Task-Id: FN-3560
Merges FN-3620, completing the Hermes chat mailbox integration with wired message tools, locked sender/recipient contract tests, and mailbox behavior documentation, plus a small CSS polish adding `focus-visible` styles and token radius to the render toggle. A changeset for FN-3710 (cluster task ID o
Fusion-Task-Id: FN-3620
Merged branch lands two features: FN-3718 wires workspace memory into the agent instruction pipeline — adding a reader helper, injecting workspace memory into agent instructions and identity snapshots, and documenting the resolution order — and FN-3716 adds planning mode priority controls for task r
Fusion-Task-Id: FN-3718
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
Merged seven commits that introduce a runtime action gate for task execution (FN-3547) — adding action classification, git-based heuristics for branch/remote gating, and per-step session enforcement — with tests covering the gate logic, heartbeat integration, and PI agent creation. Also landed FN-37
Fusion-Task-Id: FN-3547
Merges FN-3428's branch-field contract and merge target override/default behavior tests across core, dashboard, and engine, plus a companion fix that sweeps subsumed autostash orphans and surfaces outcomes on the task feed. Adds project-node path mapping persistence APIs and schema (FN-3503), new ag
Fusion-Task-Id: FN-3428
Autostash entries from prior runs piled up indefinitely (50+ on a single
working tree) because every silent restore failure (apply hard-fails on
untracked-overwrite, transient git error, etc.) leaves a permanent stash
and the warn-only behavior trains developers to ignore the warnings.
- Add `sweepAutostashOrphans`, called at merge entry: classifies each
orphan by diffing its stashed paths against HEAD. If every path is
byte-identical to HEAD the dev's work has already landed, so drop the
stash automatically. Live orphans (real lost work) get loud warnings
on both the engine log and the task feed.
- Surface every restore terminal outcome (`restored`, `failed`,
`conflict-needs-manual` from each path) via `store.logEntry` so devs
can see in `fn task show` what happened to their stash without
grepping engine logs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Added agent permission policy model with persistence in core, and wired web-builtin tool opt-in enabling planning and synthesis web tools in the dashboard with corresponding docs and a changeset. Also added an inline fast-mode toggle wired into peer executor state, retry logic for cluster task-ID ov
Fusion-Task-Id: FN-3713
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
Merges peer exchange shared state wiring (FN-3464) into the engine with updated tests, adds immediate wake controls for agent inbox and message API (FN-3087), and restores the narrow logs/system mouse auto-toggle policy with CLI documentation (FN-3708). Dependency graph plugin receives test and high
Fusion-Task-Id: FN-3464
The merge delivers four major bodies of work. The dominant theme is FN-3588, which adds an "immediate wake" override to the message inbox API, exposes it in the MailboxModal UI, and updates `agent-heartbeat.ts` and `executor.ts` to honor the override alongside timer/signal triggers. FN-3705 gates re
Fusion-Task-Id: FN-3588
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
This merge delivers five major feature clusters: a fully rebuilt dependency graph plugin with draggable nodes, position persistence, modular architecture, highlighting and selection states, toolbar navigation, and keyboard controls; a new roadmap plugin with domain store, ordering logic, and compreh
Fusion-Task-Id: FN-3581
Merges FN-3396's full Cursor CLI provider integration (Steps 1–4): defines a CLI-backed provider contract, adds the `fusion-plugin-cursor-runtime` plugin package with process management and runtime probes, wires dashboard auth flows and UI (ProviderCard, onboarding modal, settings), and bundles the
Fusion-Task-Id: FN-3396
Documents `lastError` recovery semantics in the agents reference, clarifying how the system handles and recovers from error states.
Fusion-Task-Id: FN-3630
Implements distributed mesh task creation by adding replicated create primitives to the core store, wiring new API routes (`register-mesh-routes.ts`) that replicate task creation across clustered nodes while preserving remote-targeting metadata, and updating the dashboard's task creation flow accord
Fusion-Task-Id: FN-3450
When ChatView remounted (e.g. tab switch with keyboard still up), the
hook started with keyboardOpen=false and corrected itself only after
the effect ran. That single stale-state render briefly unhid the
executor status bar, which appeared as a blank pane covering half the
input box before the next state update settled it.
useState initializers now call getKeyboardMetrics() lazily on first
render so the very first paint already reflects the live keyboard
state.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merges the evaluator follow-up suggestion system (FN-3392, Steps 1–5), which adds a normalized contract, provenance tracking, and lifecycle documentation for AI-generated follow-up tasks, alongside chat UI improvements including unread indicators in header and mobile nav, corrected message routing,
Fusion-Task-Id: FN-3392
Merger receives substantial hardening: autostash race-rescue with de-duplication, advisory observer for destructive operations, and subject-line preference for step headlines. The TUI gains a narrow log-split mode on System panel with proper back-navigation to the main pane. Chat header and mobile n
Fusion-Task-Id: FN-3606
P0 — parsePorcelainZ rename/copy handling
Git's -z porcelain emits `R <new>\0<old>\0` for renames (and
C for copies). The naive split-and-slice treated <old> as an
independent dirty path, which made runObservedDestructiveSyncOp
warn about phantom "cleared paths" whenever a rename was in
flight. Now we detect R/C status and skip the trailing entry.
P1 — race-rescue loop unstages between attempts
`git stash create` snapshots the index without clearing it, so
iteration 2's `git add -A` would re-stage atop iteration 1's
leftovers. Tree differences inside the loop then reflected stale
staging rather than genuine new writes. Added a `git reset` at
the top of each iteration so every attempt starts from a clean
index baseline.
P1 — writeActiveMergerStatus is now atomic
Switched from in-place writeFileSync to temp-file + renameSync.
POSIX guarantees rename atomicity on the same filesystem, so a
reader can no longer catch the file mid-flush and return a
false-negative "no merger active" advisory.
P2 — Step regex em-dash clarity
`[—\-:]` is functionally fine but obscures intent; switched to
`(?:—|-|:)` so the em-dash branch is obvious. Added a test case
for the em-dash separator.
New tests:
- parse-porcelain-z.test.ts (8 cases including renames + copies)
- em-dash case added to derive-subject-summary.test.ts
247/247 merger-suite tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The race-rescue loop was firing on every merger run because
`git add -A && git stash create` does not clean the working tree —
files stay dirty post-stash, so a subsequent `snapshotDirtyFiles` saw
the SAME paths the primary stash had just captured and stashed them
again, producing identical-tree race-rescue duplicates (visible in
git stash list as `fusion-merger-autostash:FN-XXXX:race-rescue-0`
sitting next to its identical `fusion-merger-autostash:FN-XXXX:`).
Fix: list the path set captured by the primary stash via
`git stash show --name-only`, and only rescue paths in the current
dirty snapshot that are NOT in that set — those are genuine
late-dirty writes from concurrent dev edits or interleaved ops.
Also drop any rescue whose tree-SHA exactly equals the primary,
as a defensive belt-and-braces.
Existing duplicate race-rescue stashes are harmless (identical
content to their primaries) and can be dropped manually.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
