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
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 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
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>
FN-2910 surfaced concurrent reviewer + merger activity on the same task.
Root cause: asymmetric in-flight guards let an unpause-resume kick off a
fresh executor session while a recovery path was already running, and the
auto-merge handoff fired before the executor's finally block finished
cleanup. This sweeps the surrounding lifecycle paths for similar races and
tightens the reviewer pause gate against TOCTOU through runtime setup.
- Symmetric in-flight tracking across `executing`, `recoveringCompleted`,
and `resumingUnpaused`; `recoverCompletedTask` bails when any are set.
- Atomic claim of the recovery slot in the completed-task watchdog before
any awaited work.
- Workflow-rerun bounce returns "bounced" | "skipped-pending" so the
watchdog can no longer log a false-success retry when the original
bounce is still mid-flight.
- Self-healing's completed-task scan re-checks executing IDs inside the
loop instead of trusting a pre-await snapshot.
- 300ms grace period before auto-merge enqueue, giving the executor's
finally block (session disposal, child cleanup) time to drain and
eliminating the residual log-overlap symptom from FN-2910. Test uses
fake timers, no real sleep added.
- New AgentSemaphore.runNested for synchronously nested helper agents
(reviewers): bumps activeCount for honest observability while bypassing
the wait queue, preserving forward-progress fairness for the parent at
low maxConcurrent. Both createReviewStepTool and triage's
createReviewSpecTool now use it.
- New beforeSpawnSession hook on AgentRuntimeOptions/AgentOptions fired
inside createFnAgent immediately before createAgentSession, past every
awaited setup step. Reviewer wires a pause re-check that throws a
sentinel error converted to UNAVAILABLE, closing the TOCTOU window
where pause flipped during runtime resolution or resource loading.
All 2887 engine tests pass; engine + core + cli + dashboard + plugin-sdk
+ pi-claude-cli + desktop typecheck clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Reviewer subprocesses were spawned via fn_review_spec / fn_review_step
even with globalPause on, because reviewer.ts had no pause awareness.
Stuck detector also kept running, treating pause-disposed sessions as
inactivity and re-queuing tasks. Pause-transition listeners only called
session.dispose(), which doesn't always interrupt an in-flight LLM
stream — letting reviewer spawns leak through after pause flipped.
- reviewer.ts: re-read settings, return UNAVAILABLE without spawning
when globalPause/enginePaused is on.
- stuck-task-detector.ts: skip checkStuckTasks() while paused.
- triage.ts / executor.ts: call session.abort() before dispose() in the
pause-transition listener to interrupt in-flight work.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Fix triage planning model resolution to fall back through project/global planning settings and default overrides
- Fix reviewer model selection to honor validator-specific settings before default provider/model overrides
- Update merger model resolution to apply default override fallback and align shared task setting types/executor flow
- Add regression coverage for triage, reviewer, and merger fallback behavior and update settings hierarchy documentation
- 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
Every agent-facing quality gate that used to pair tests with typecheck now
also includes lint. Specifically:
- core/src/types.ts: QA Check skill prompt runs lint, tests, typecheck (was
tests only) and gates task_done() on all three.
- core/src/agent-prompts.ts + engine/src/reviewer.ts: "Do NOT issue REVISE"
exclusion list now covers lint as well, so out-of-scope fixes that
restore lint remain allowed (matches the already-lint-aware completion
gate text at the top of the same prompts).
- engine/src/executor.ts: task_done() pre-flight checklist adds an explicit
"if the repo has a lint command, run it and fix failures" bullet, mirrors
the typecheck bullet, and expands the CRITICAL line from "ALL test
failures" to "ALL lint, test, and typecheck failures".
- core/src/store.ts: default Step 2 checklist (Testing & Verification) now
includes Lint and Typecheck alongside "All tests pass".
- cli/src/commands/plugin-scaffold.ts: generated plugin README and the
"Next steps" CLI output include \`pnpm lint\` between install and test.
Existing prompts that already paired lint with tests+typecheck (the
Completion section, hard quality gates, triage testing requirements) are
unchanged.
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
- 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
- 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
- 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 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
An AI review agent (FN-1506) killed the running dashboard by finding
the process on port 4040 via lsof and running kill -9, causing exit
code 137 (SIGKILL) with no logs. This adds multi-layer guardrails:
- AGENTS.md: project-level rule reserving port 4040
- Executor/reviewer system prompts: explicit prohibition on killing
port 4040 processes, with instruction to use --port 0 instead
- Core agent-prompts.ts: same guardrails in all prompt variants
- Reviewer told to issue REVISE if executor violates the rule
- SIGHUP handlers in dashboard.ts and serve.ts for resilience
- Background engine reconciliation in dashboard/serve startup
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add instructionsPath and instructionsText fields to Agent type and AgentStore
- Create agent-instructions resolver module in engine with priority-based resolution
- Wire custom instructions into executor, triage, reviewer, and merger agents
- Add PATCH /agents/:id/instructions API endpoint with file and text support
- Add instructions editor UI to dashboard agent detail config tab
- Add comprehensive tests for instructions resolver and AgentStore integration
- Add changeset for published package bump
- Add AgentPromptTemplate and AgentPromptsConfig types to ProjectSettings
- Create agent-prompts module with 7 built-in prompt templates and role resolver
- Wire engine agents (executor, reviewer, merger, triage) to use resolved prompts
- Add 25 test cases covering template resolution, role assignment, and validation
- Export new types from @fusion/core package
- Document agentPrompts configuration and built-in templates in AGENTS.md
- Update triage agent to proactively suggest splitting large tasks into subtasks during specification
- Tighten reviewer guidance to flag undersplit tasks that should be broken down further
- Add comprehensive tests for proactive subtask creation in triage (192 lines)
- Add reviewer tests for undersplit task detection (12 lines)
- Update README with documentation on proactive subtask splitting behavior
- Include user comments as context during AI triage spec generation and spec review
- Invalidate stale spec approvals when new user comments are added after approval
- Add lastApprovedAt tracking to task metadata for approval freshness detection
- Add comprehensive tests for comment-aware triage, review, and stale approval logic
- Add changeset for published package and update README with feature documentation
- Strengthen TRIAGE_SYSTEM_PROMPT with explicit subtask guidance rules and examples
- Strengthen buildSpecificationPrompt to reinforce proper subtask decomposition
- Add undersplit detection to spec reviewer to flag oversized or overly broad tasks
- Add test assertions for improved prompts covering undersplit detection and subtask guidance
The body-scan fallback (includes("APPROVE") etc.) would misclassify verdicts
when the reviewer mentioned a keyword in context without it being the actual
verdict — e.g. "this does not yet merit APPROVE". Replaced with a
line-anchored regex that only matches "Verdict: X" lines, and expanded the
primary regex to also catch bold/italic formatted verdicts like **Verdict: APPROVE**.
UNAVAILABLE is now the honest fallback when no structured verdict is found,
triggering a retry rather than silently misclassifying.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1. Scoping rules in agent prompts: executor, triage template, and reviewer
now explicitly forbid deleting/gutting modules, settings, interfaces,
exports, or test files outside the task's declared File Scope. Reviewer
will REVISE if out-of-scope removals are detected.
2. Pre-merge diffstat scope check: merger.ts validates the git diffstat
against the task's PROMPT.md File Scope before merging. Large deletions
outside scope are logged as warnings on the task (soft guardrail).
3. Changeset requirement for feature removal: triage template now requires
a .changeset/ entry when removing existing functionality. Executor and
reviewer enforce this requirement.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add describeModel() helper in pi.ts to format provider/model info for logging
- Log resolved model details in executor, reviewer, and triage agent creation
- Update executor and reviewer to call describeModel before session start
- Add unit tests for describeModel covering all input combinations
- Fix test mocks to account for new describeModel dependency
- Rename @kb/core, @kb/dashboard, @kb/engine to @fusion/* namespace
- Update all import statements across 143+ files to use new package names
- Update workspace dependencies and root package.json references
- Fix bundler configurations (tsup, vite) for new package names
- Update test files and fix typecheck issues
- Add changeset file documenting the package rename
- Add section expansion state management with localStorage persistence
- Update section headers with chevron toggle controls
- Implement conditional task row rendering based on section state
- Add Expand All / Collapse All toolbar controls
- Add CSS styles for chevron rotation animation and section headers
- Add comprehensive tests for collapsible section behavior
- Extend reviewer with 'spec' review type and spec review format template
- Add review_spec tool to triage agent for independent spec quality evaluation
- Implement APPROVE/REVISE/RETHINK loop with conversation rewind on RETHINK
- Add post-session gate to block tasks with unresolved REVISE verdicts from moving to todo
- Add tests for reviewer spec support and triage review loop (APPROVE, REVISE, RETHINK paths)
- Add checkSessionError helper that re-raises errors stored on session.state.error after prompt() resolves silently when retries are exhausted
- Integrate checkSessionError in executor, triage, merger, and reviewer agents so existing catch blocks with isUsageLimitError can trigger UsageLimitPauser
- Add tests for checkSessionError and for each agent's error propagation path
- Add audit report documenting the error propagation gap
- Add changeset for the fix
- Extend AgentLogEntry with agent field and new event types (thinking, tool_end)
- Expand AgentLogger with thinking, tool_end callbacks and agent role support
- Wire new logging callbacks in createKbAgent and all agent call-sites (executor, merger, reviewer, triage, pi)
- Update AgentLogViewer with agent role badges and rendering for new entry types
- Export AgentRole and AgentLogType from core package and add tests for new functionality
- Add defaultThinkingLevel to core Settings types and exports
- Thread thinking level through engine executor, merger, reviewer, triage, and pi
- Add effort dropdown to Model settings UI in SettingsModal
- Add tests for thinking effort dropdown in SettingsModal
- Rename npm packages from @kb/* to @hai/* and update all workspace references
- Rename CLI binary from kb to hai and config directory from .kb to .hai
- Update dashboard UI branding, titles, and references from kb to hai
- Update all test files, CI workflows, and documentation to reflect new naming
- Run comprehensive grep verification to ensure no stale kb references remain
