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
Adds executor runtime environment support to the plugin system, enabling plugins to contribute environment variables that get injected into executor commands. The implementation includes new plugin types (`ExecutorRuntimeEnvPlugin`), aggregation in the plugin runner, thread-through into executor com
Fusion-Task-Id: FN-3767
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 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
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
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-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 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
- Capture prompt/completion/total token usage from step-scoped sessions in the step session executor
- Persist per-step token usage in executor run context so stats survive across task execution
- Record single-session token usage totals alongside run context stats logging for consistent aggregation
- Expand executor and step-session executor tests to validate token usage persistence and fixture behavior
TUI quit ('q'/Ctrl+C) bypassed signal handlers via process.exit(0), and
neither shutdown path closed the HTTP server, so server.close()'s
stopAllDevServers() listener never ran. In-flight agent bash commands
(spawned detached for their own pgroup) were also never aborted, so
their subprocess trees — including vitest workers — survived as orphans.
Route the TUI quit through SIGINT so the registered shutdown handler
runs, await stopAllDevServers() in both shutdown paths, and abort
in-flight bash on every active agent session at the start of the
runtime drain so killProcessTree reaches every grandchild.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Update Fusion skill docs, prompts, and capability references to use public fn_* tool names consistently
- Align engine system prompts and tool schemas for messaging/task actions with fn_send_message, fn_read_messages, fn_task_* naming
- Refresh related tests across CLI, engine, dashboard, and core to match normalized tool naming and behavior
- Add a patch changeset for @runfusion/fusion describing the skill-tool namespace normalization
- Add shared executor model pair resolution in task executor and step-session executor to apply lane hierarchy consistently
- Prefer project defaultProviderOverride/defaultModelIdOverride before global defaults when execution lanes are unset
- Update hot-swap model resolution to use the same precedence logic as runtime session creation
- Add regression tests for runtime, hot-swap, and step-session precedence/fallback behavior
- Add a changeset for @runfusion/fusion describing the executor model precedence fix
Atomic worktree creation: on `git worktree add` failure, remove the
partial directory so retries see a clean slate (executor.ts,
step-session-executor.ts). Add `reapOrphanWorktrees()` sweep on engine
startup to delete `.worktrees/*` dirs that have no `.git` file and are
not registered with git. Force readonly workflow steps to run pre-merge
so review personas reuse the coding worktree instead of allocating a
fresh post-merge one. Inject a Frontend UX Criteria checklist into
TRIAGE_SYSTEM_PROMPT when a task touches dashboard UI, so the first
coding pass can meet UX reviewer expectations.
Motivated by FN-2185 post-mortem: an incomplete `.worktrees/pale-raven`
dir blocked retries, and three Step 6 revision cycles over cosmetic UX
issues consumed ~13 hours.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- 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
- Detect context-window-limit errors from AI sessions and automatically compact
the session conversation history before retrying (one attempt per session)
- Centralize auto-compaction in promptWithFallback (pi.ts) so executor, merger,
and step-session-executor all benefit from the same mechanism
- Remove scattered context-limit error handling from executor.ts, merger.ts, and
step-session-executor.ts in favor of the centralized approach
- Add comprehensive tests for auto-compaction retry behavior in pi.test.ts
- Remove unused compactSessionContext import from step-session-executor.ts
- Add memory note documenting the centralized auto-compaction design
- Add SkillSelectionResolver and SkillSelectionContext for deterministic skill sets
- Implement skill-resolver.ts with request/filter/resolve workflow
- Add session-skill-context.ts helper for unified skill selection across all session types
- Wire skill override into createKbAgent via AgentOptions
- Apply skill selection to triage, executor, reviewer, merger, and heartbeat sessions
- Add comprehensive tests for skill-resolver and session-skill-context
- Export skill resolver types and functions from engine index
- Add skill selection resolver pattern to memory documentation
- Replace blocking execSync calls with async execAsync in executor.ts for user-configured commands
- Convert self-healing.ts worktree status checks to async to avoid blocking the event loop
- Update step-session-executor.ts to use async worktree operations
- Refactor worktree-pool.ts for fully async worktree creation, cleanup, and listing
- Convert pi.ts agent session handling to async execution
- Update all corresponding tests with async/await patterns
- Add changeset for @gsxdsm/fusion patch release
- Add context-overflow detection and recovery in step-session executor with same parity as single-session
- Implement step resumption from overflow checkpoints with accumulated context replay
- Add overflow state tracking and recovery logging for diagnostics
- Harden single-session executor overflow recovery with improved state management
- Update appendAgentLog parameter signatures across executors
- Add comprehensive tests for context overflow scenarios in both execution modes
- Add memory entry documenting the unified context-limit recovery approach
In step-session mode each step is registered with StuckTaskDetector
under a compound key (e.g. "FN-1452-step-1") rather than the bare
task ID. When stuck detection fired, event.taskId was that compound
key, breaking three things simultaneously:
1. beforeRequeue("FN-1452-step-1") → store.getTask() threw (no such
task) → stuckKillCount never incremented on the real task.
2. markStuckAborted("FN-1452-step-1") → activeStepExecutors.get()
returned undefined (keyed by "FN-1452") → terminateAllSessions()
never called, other step sessions kept running.
3. stuckAborted.set("FN-1452-step-1") → executor checks
stuckAborted.has("FN-1452") → miss → stuckRequeue never set
→ task never moved to todo.
Fix: add a canonicalTaskId field to TrackedTask (defaults to the
tracking key for single-session mode where they are identical).
StepSessionExecutor now passes taskDetail.id as the third arg to
trackTask(). killAndRetry() uses entry.canonicalTaskId for all
external callbacks so they always resolve to the real task ID.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Wire AgentLogger into heartbeat runs, including tool/text callbacks and stdout excerpts on run records
- Persist heartbeat context taskId snapshots earlier and ensure logger flushes on success and failure paths
- Pass TaskStore into StepSessionExecutor and flush per-attempt agent logs in finally cleanup
- Expand heartbeat and step-session tests to verify log persistence and flush behavior, and add a patch changeset for @gsxdsm/fusion
