- 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>
- Add a reusable .btn-secondary style (including light-theme hover/focus states) for reflections tab actions
- Initialize ReflectionStore in reflection API routes before reading or writing reflections
- Create AgentStore and ReflectionStore during in-process runtime startup and wire AgentReflectionService into TaskExecutor
- Reuse the initialized AgentStore for HeartbeatMonitor and trigger scheduler setup with non-fatal guards
- Apply a default 30s heartbeat interval when scheduler config is missing or invalid
- Dynamically register and update heartbeat triggers from AgentStore create/update events
- Register all non-disabled agents at startup and guard listener cleanup when stopping runtime
- Treat non-periodic agents as healthy in dashboard health checks to avoid stale-time false alarms
- Expand engine and dashboard tests and add a patch changeset for @gsxdsm/fusion
Why: tests were leaking ~700 per-temp-dir collection registrations
into the user's global ~/.config/qmd/index.yml because searchWithQmd
and the agent-memory qmd path called execFile("qmd", ...) with the
real binary, bypassing shouldSkipBackgroundQmdRefresh() which only
guarded the schedule* wrappers.
Guard both direct-execFile paths under the same skip flag and fall
back to file-based agent memory search when skipping.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add Memory section controls for enabling auto-summarize with threshold and cron schedule inputs
- Wire ProjectEngine to sync auto-summarize automation on startup and when related settings change
- Reuse a single startup settings snapshot when syncing insight extraction and auto-summarize automations
- Add SettingsModal and ProjectEngine tests covering auto-summarize UI persistence and automation re-sync behavior
- Add agent memory support to instruction resolution and introduce/export buildAgentChatPrompt for identity-aware prompt assembly with optional project memory
- Wire ChatManager to AgentStore so chat sessions can enrich system prompts per agent and include recent conversation context in prompt payloads
- Update server chat wiring to provide an AgentStore for prompt enrichment and keep graceful fallback behavior when agent context is unavailable
- Enrich HeartbeatMonitor system prompts with resolved agent instructions/ratings while preserving base-prompt fallback paths
- Expand dashboard and engine tests to cover prompt enrichment, fallback behavior, conversation context assembly, and AgentStore route mocks
