Fixes two classes of task failures found while investigating stuck in-review
tasks FN-2165 (worktree base ref missing) and FN-2152 (stray .tmp-fn-2152
gitlink accidentally committed via merger amend).
FN-2165 — stale baseBranch:
- resolveWorktreeStartPoint now returns null instead of throwing
NonRetryableWorktreeError when the stored baseBranch is gone. Caller clears
task.baseBranch and falls back to branching from the default base (HEAD) so
the task self-heals instead of failing permanently.
- New TaskStore.clearStaleBaseBranchReferences() nulls baseBranch on any
dependent task when its upstream branch is deleted. Wired into
cleanupBranchForTask (archive/delete), merger branch cleanup, self-healing
orphan-branch sweep, executor dep-abort and conflict-cleanup paths, and
stale-branch recovery.
Nested worktrees:
- assertWorktreePathNotNested guard in tryCreateWorktree refuses to create a
worktree inside another registered worktree (previously produced pathological
paths like .worktrees/green-finch/.worktrees/amber-panda when rootDir pointed
at a worktree instead of the main repo).
Context-overflow recovery (FN-2182 class):
- Reduced-prompt retry budget raised from 1 → 3 within the same session.
- Adds a fresh-session requeue path when same-session retries still overflow:
task moves back to todo with worktree retained, bounded by
computeRecoveryDecision / MAX_RECOVERY_RETRIES. Prevents late-step context
exhaustion from becoming terminal.
Gitlink prevention (FN-2152 class):
- .gitignore now excludes .tmp-fn-* and .tmp-kb-* so stray worktrees at the
repo root cannot be captured by git add -A.
- Merger amend flow now scans staged entries for 160000 gitlinks and unstages
them with a loud warning; the project uses no submodules, so any such entry
is a bug (this is how f8f90f26 landed in HEAD as .tmp-fn-2152).
Tests: new coverage for baseBranch fallback, nested-worktree guard, and
clearStaleBaseBranchReferences. Full engine + core + dashboard + cli suites
pass (15349 tests).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Root cause: during a triage split the AI could set a child task's
`dependencies` to the parent id. The parent is hard-deleted after the split,
and the scheduler's dep check treats a missing id as unmet — permanently
blocking the dependent. This stranded FN-2164 behind the deleted FN-2163.
- core/store.deleteTask: refuse to delete when any live task still has the id
in its `dependencies` array. Throws TaskHasDependentsError listing dependents
so callers can rewrite or recover. Covers the triage-split path and any
future caller.
- engine/triage task_create: validate each proposed dependency before creating
a child — reject the parent id, reject unknown task ids, allow siblings
created earlier in the same split or pre-existing tasks.
- engine/triage split cleanup: wrap the parent deleteTask in try/catch that
keeps the parent alive (safer than stranding dependents) and logs the reason.
- engine/triage prompts: both the mandatory-split and proactive-split prompts
now explicitly state that subtask deps must never reference the parent.
- dashboard/routes /subtasks/create-tasks: reject parent-id deps, drop unknown
deps with an audit log entry, surface parentTaskCloseError + droppedDependencies
in the response instead of silently swallowing them.
- engine/executor: on execute entry, detect the drift state (in-progress task
with no worktree) and emit a loud log + task log entry; the existing
fresh-worktree path then recovers. Prevents silent "operating without a
worktree" behavior that we saw on FN-2152.
Tests:
core: 2907/2907 pass (+5 new, incl. deleteTask guard regression)
engine: 2554/2554 pass (+17 new, incl. task_create dep validation)
dashboard: 9064/9064 pass (+2 new for /subtasks/create-tasks).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Root cause: during a triage split the AI could set a child task's
`dependencies` to the parent id. The parent is hard-deleted after the split,
and the scheduler's dep check treats a missing id as unmet — permanently
blocking the dependent. This stranded FN-2164 behind the deleted FN-2163.
- core/store.deleteTask: refuse to delete when any live task still has the id
in its `dependencies` array. Throws TaskHasDependentsError listing dependents
so callers can rewrite or recover. Covers the triage-split path and any
future caller.
- engine/triage task_create: validate each proposed dependency before creating
a child — reject the parent id, reject unknown task ids, allow siblings
created earlier in the same split or pre-existing tasks.
- engine/triage split cleanup: wrap the parent deleteTask in try/catch that
keeps the parent alive (safer than stranding dependents) and logs the reason.
- engine/triage prompts: both the mandatory-split and proactive-split prompts
now explicitly state that subtask deps must never reference the parent.
- dashboard/routes /subtasks/create-tasks: reject parent-id deps, drop unknown
deps with an audit log entry, surface parentTaskCloseError + droppedDependencies
in the response instead of silently swallowing them.
- engine/executor: on execute entry, detect the drift state (in-progress task
with no worktree) and emit a loud log + task log entry; the existing
fresh-worktree path then recovers. Prevents silent "operating without a
worktree" behavior that we saw on FN-2152.
Tests:
core: 2907/2907 pass (+5 new, incl. deleteTask guard regression)
engine: 2554/2554 pass (+17 new, incl. task_create dep validation)
dashboard: 9064/9064 pass (+2 new for /subtasks/create-tasks).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Rename core loader, dashboard server chat/planning routes, and frontend agent IDs/storage keys from kb-agent to fn-agent naming
- Update dashboard hooks and components (agent list, chat view, quick chat) to use the new fn agent key prefixes consistently
- Refresh engine, dashboard, core, and CLI tests/mocks to remove remaining kb-agent route and temp prefix references
- Update storage/gap-analysis docs to reflect fn agent key names and add a @gsxdsm/fusion patch changeset for the rename
- Rename engine export and call sites to use createFnAgent consistently across runtime flows
- Update core lazy engine loader and dashboard agent-generation/planning/chat paths to reference createFnAgent
- Refresh affected unit and integration tests, including renaming pi-create-kb-agent.test.ts to pi-create-fn-agent.test.ts
- Update AGENTS.md documentation references to match the new createFnAgent name
- Add project settings for pushAfterMerge and pushRemote with defaults and typed merge result fields for push status/errors
- Implement post-merge remote sync in the merger with pull --rebase, auto/AI conflict resolution, and one non-fast-forward retry before push
- Expose push-after-merge controls in Settings modal with conditional Push Remote input and coverage for desktop/mobile save flows
- Document the new settings in the settings reference and stabilize CLI cross-build help test timeout
- Add mock-only rationale comments and tighten assignment watcher typing in heartbeat tests
- Replace SQLite-backed MessageStore setup in heartbeat message-flow coverage with an in-memory fake store
- Swap assignment watcher AgentStore setup to an EventEmitter-based mock with explicit heartbeat and budget stubs
- Refactor run-audit integration tests to use an in-memory TaskStore fake for recording and filtering audit events
- Update executor, reviewer, core prompt templates, and path-boundary messaging to reference the .fusion/memory/ directory instead of a single MEMORY.md file
- Broaden worktree boundary checks in pi path validation to allow .fusion/memory/ directory access from task worktrees
- Align memory backend metadata and dashboard backend labels to display file backend storage as .fusion/memory/
- Refresh core/engine tests to assert the new directory-based memory wording and boundary behavior
- Add heartbeatIntervalMultiplier to shared settings schema/types with settings parity coverage
- Apply heartbeat multiplier in engine scheduling logic while preserving explicit per-agent interval behavior
- Add Settings modal and Agents view controls for heartbeat multiplier and per-agent interval overrides, including new styling
- Expand dashboard and engine test coverage for multiplier/heartbeat controls and document the new setting
- Replace direct console.warn calls in agent-instructions with createLogger("agent-instructions") warnings
- Keep existing truncation and path-validation safeguards while standardizing diagnostic output format
- Add focused diagnostics tests that verify single warning emission for truncation and invalid instructionsPath scenarios
- Add coverage for missing instructions files and project memory read failures to ensure graceful fallback behavior
- Replace previously silent catch blocks in auto-merge and settings-listener flows with runtimeLog.warn messages
- Add warning logs for startup and periodic auto-merge sweeps plus poll interval fallback when settings reads fail
- Add regression tests that force each swallowed-error path and assert structured warnings are emitted
- Cover global/engine unpause resumeOrphaned failures and stuck-detector checkNow failures in project-engine tests
- Promote HEARTBEAT_NO_TASK_SYSTEM_PROMPT as the primary no-task heartbeat constant while keeping a backward-compatible alias.
- Refine no-task heartbeat guidance for lightweight ambient coordination and explicit tool usage.
- Select the no-task prompt for heartbeat runs without task context before appending instruction/rating overlays.
- Update heartbeat regression tests to assert the renamed no-task prompt constant and prompt/tool expectations.
- Return the created task ID directly from runTaskPlan and propagate it through fn_task_plan
- Remove hardcoded FN-### log parsing so CLI extension supports structured IDs like PROJ-042
- Add heartbeat fallback parsing from task_create text output when details.taskId is absent
- Expand engine and CLI tests to cover structured task IDs and updated task-plan return behavior
- Add structured warning logs in silent catch paths for IPC worker shutdown, plugin unregistration cleanup, child runtime metrics polling, and merger build rollback reset
- Improve merger rollback warning context to make build-verification reset and retry failures easier to diagnose
- Add regression tests covering each new warning path to ensure errors are surfaced without changing existing control flow
- Add StepSessionExecutor test coverage for cherry-pick abort logging when conflict cleanup fails
- Update HEARTBEAT_NO_TASK_SYSTEM_PROMPT copy to emphasize inbox, memory, delegation, and heartbeat_done usage
- Expand heartbeat monitor tests to assert no-task prompt/tool alignment and preserve task-scoped prompt behavior
- Harden first-run and App view tests by using a safe cwd fallback and more robust async UI waits
- Add best-effort dashboard performance reporting hooks in App and useProjects via a new reportDashboardPerf API helper
- Remove legacy .fusion/memory.md fallback references and normalize prompts/docs to .fusion/memory/MEMORY.md
- Stop legacy mirror writes and fallback reads in core memory backend and project memory flows
- Update engine worktree boundary checks and tests for canonical memory file handling
- Align dashboard memory/settings surfaces and route tests with canonical memory behavior
- Add model-favorites persistence test coverage for mission interview and new agent dialogs
- Add structured warning logs for plugin-runner fallback paths instead of silent catches
- Add warning telemetry in agent-tools for agent-memory directory, QMD search, and index refresh failures
- Log cron-runner session disposal failures and update agent-logger persistence warnings to use logger output
- Expand engine tests to cover warning behavior across plugin-runner, agent-tools, cron-runner, and agent-logger
- Update core and engine prompt text to reference .fusion/memory/ with MEMORY.md and daily-note guidance
- Allow worktree tool boundary access to .fusion/memory/ files while preserving legacy .fusion/memory.md compatibility
- Revise memory compaction/insight extraction messaging and related type/docs comments to use canonical memory paths
- Refresh dashboard and test expectations across core/engine/dashboard/docs for the new memory path wording
- Add HEARTBEAT_NO_TASK_SYSTEM_PROMPT for no-task heartbeat sessions with only non-task-scoped tooling guidance
- Switch heartbeat session setup to choose the no-task base prompt when executing without task context
- Keep agent instruction and memory enrichment on top of the selected base prompt for both task and no-task runs
- Extend heartbeat tests to verify no-task prompts exclude task-scoped tool references and are passed into createKbAgent
- Log final-path git reset --merge cleanup failures in aiMergeTask with task-scoped warning details
- Preserve the original "all 3 attempts exhausted" merge error even when cleanup reset fails
- Add merger retry tests covering successful final cleanup and failed final cleanup logging behavior
- Add a patch changeset for @gsxdsm/fusion documenting the improved merger diagnostics
- Convert seed-sample-nodes into a test-only helper and remove direct execution against the real central database
- Replace private-looking host examples with RFC 5737 test-net addresses in node connection docs and ConnectNodeModal expectations
- Add Vitest aliases for @fusion/core and @fusion/engine to stabilize cross-package test imports
- Load AgentReflectionService via local engine source path in in-process runtime to avoid alias resolution failures
- Add defensive cleanup for in-memory task tracking when tasks move state or agents pause
- Improve stuck-detection and self-healing flow to reduce leaked state and missed recovery paths
- Add logging around previously swallowed errors and tighten executor cleanup behavior
- Expand restart and self-healing reliability tests to cover regression scenarios
- Recompute slice status when adding a feature so stale "complete" slices cascade back to milestone and mission statuses
- Require checkMissionCompletion to verify every feature is done before marking a mission complete
- Add mission-wide status-chain recomputation when stale complete slices or milestones are detected during reconciliation
- Expand core and engine tests to cover addFeature downgrades, stale complete states, and feature-level completion checks
Adds a SelfHealingManager scan that finds tasks parked in in-review with
a failed pre-merge workflow step and no active session, and sends them
back through the existing sendTaskBackForFix flow (PROMPT.md injection,
step reset, todo → in-progress). Bounded by a new maxPostReviewFixes
setting (default 1) and a per-task postReviewFixCount so a persistently-
failing verifier cannot ping-pong a task indefinitely.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
