- Update executor, triage, and merger prompt strings to identify the product as "fn"
- Align branch/worktree documentation examples with fusion/fn-* naming conventions
- Rename dashboard websocket attachment guard from __kbWebSocketsAttached to __fnWebSocketsAttached
- Refresh engine tests, dashboard utility comments, and TUI header text to remove stale kb wording
- Add task_document_write and task_document_read factories with schemas, revision-aware responses, and error handling in agent-tools
- Wire document tools into executor and triage sessions and update prompts to persist and reuse planning artifacts across runs
- Export document tool factories and parameter schemas from engine public entrypoints while keeping executor re-export compatibility
- Add comprehensive tests covering write/read success paths, empty/not-found cases, and store failure handling
- Fix pause-abort handler using updateTask({status: undefined}) which was a
no-op, leaving tasks stuck in 'specifying' forever after a pause interrupts
a session post-APPROVE. Changed to status: null to actually clear the field.
- Apply same fix to transient-error retry and general error catch paths.
- Wire StuckTaskDetector into TriageProcessor: trackTask/untrackTask/recordActivity
on session lifecycle, markStuckAborted to prevent stuck kills from being
reported as errors, and clear status to null on stuck-kill for next-poll retry.
- Update dashboard.ts to pass stuckTaskDetector to TriageProcessor and call
triageRef.current?.markStuckAborted in the shared onStuck callback.
- Add 3 tests covering pause-abort status clearing and stuck detector wiring.
Co-Authored-By: Claude Sonnet 4.6 <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 planningModelProvider/planningModelId fields to task model and API batch-update endpoint
- Wire triage engine to use per-task planning model override with settings hierarchy fallback
- Add planning model selector to TaskDetailModal Model tab
- Add comprehensive tests for triage engine planning model resolution and dashboard API/routes
- 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
- Add project-memory module in @fusion/core with read/write/resolve helpers and upsert-on-store hook
- Bootstrap project memory during task creation (store) with structured task context
- Inject resolved project memory into executor and triage agent system prompts
- Add comprehensive tests for project-memory module, store integration, and agent prompt changes
- Document project memory architecture and usage in README
- 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
- Add memoryEnabled boolean setting to core types and default settings
- Add Memory section toggle to SettingsModal dashboard UI
- Integrate memoryEnabled check in executor and triage engine prompts
- Add tests for settings UI, executor prompt behavior, and triage prompt behavior
- Update SettingsModal section count test for the new Memory section
- Log the selected model provider and ID during triage so the agent log records which model was used
- Add agent-log entry capturing triage model choice for observability
- Add comprehensive tests for triage model logging behavior
- Update AgentsView component and dashboard docs for consistency
- Remove obsolete AgentsView test
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 state to tasks: persisted in DB, gates scheduler pickup to prevent immediate retry of transient failures
- Introduce shared recovery-policy module with bounded exponential backoff (1s → 60s, max 5 attempts)
- Wire recovery policy into executor, scheduler, and triage so all agents respect the same retry cadence
- Persist retry state (attempt count, next eligible time) in task metadata via store and DB schema
- Add DB migration for new retry columns and update schema tests
- Update README with recovery policy documentation
- Refactor dashboard Header component and styles, consolidate header tests
- Fix session-files route tests to align with updated route signatures
- 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
- Add rate-limit retry utility with exponential backoff, jitter, and configurable limits
- Integrate retry logic into executor, triage, and merger agent sessions
- Export retryOnRateLimit from engine package index
- Remove unused DirectoryPicker component, stale CSS, and dead dashboard routes
- Update SetupWizardModal and usage tests to reflect cleanup
- Rename data directory from .kb to .fusion across core, CLI, dashboard, and engine
- Update all path references in source files, tests, and CLI output
- Remove deprecated central-core infrastructure (central-core, central-db, central-integration)
- Remove obsolete test files (PlanningModeModal.test.tsx, ScheduleForm.test.tsx)
- Add changeset for the directory rename breaking change
- Subtasks now inherit parent task's executor and validator model settings
- When triage creates subtasks, modelProvider/modelId and validatorModelProvider/validatorModelId are copied from parent
- Clean up legacy mission-store code (mission-store.ts, mission-types.ts, and related tests)
- Add comprehensive tests for subtask model inheritance in triage, routes, and db
- Remove obsolete changeset for missions-database-schema
- 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
- Extend core Settings types with planningProvider, planningModelId, validatorProvider, validatorModelId fields
- Add model selectors in Settings UI for planning and validator models
- Use planning model for triage task specification generation
- Use validator model for specification review in triage
- Use validator model for code reviews in executor agent
- Update AGENTS.md with model hierarchy documentation
- Add breakIntoSubtasks flag to core Task model and persist to store
- Plumb subtask flag through dashboard API routes with validation
- Add subtask toggle UI to inline task creation card
- Update triage agent to handle automatic subtask breakdown when enabled
- Add comprehensive tests for store, API routes, and UI components
- Include changeset for patch release documenting the new feature
- 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
- Change post-session gate from only blocking REVISE to requiring explicit APPROVE verdict
- Block tasks from reaching executor when review_spec was never called (null verdict)
- Block tasks on RETHINK, UNAVAILABLE, and reviewer-error paths
- Add tests for all non-APPROVE verdict paths: null, RETHINK, UNAVAILABLE, reviewer throw
- Update existing tests to invoke review_spec with APPROVE so they pass the stricter gate
- Remove agent termination listeners for enginePaused in executor and triage
- Update Settings.enginePaused JSDoc to document soft-pause semantics
- Update executor/triage/integration tests to assert sessions are NOT disposed on enginePaused
- Remove pause-abort tracking for enginePaused (only globalPause hard-stops agents)
- Add changeset for the behavioral change
- 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 enginePaused agent termination to executor (kills sessions, moves tasks back to todo)
- Add enginePaused agent termination to triage processor (kills sessions, clears specifying status)
- Update enginePaused JSDoc to reflect new termination behavior vs old graceful drain
- Add unit tests for executor/triage pause termination and integration tests for restart flow
- Include changeset for engine pause behavior change
- Add enginePaused field to Settings type with soft-pause semantics (drain queue, don't kill agents)
- Gate scheduler, triage, auto-merge, and periodic merge retry on enginePaused
- Add Pause and Stop buttons to dashboard Header replacing single toggle
- Wire enginePaused state through App with optimistic toggle and unpause resume logic
- Add tests for scheduler, triage, dashboard CLI, Header, and App covering pause behavior
- 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
- Change poll() to fire specifyTask() with `void` instead of `await`, enabling concurrent task specification bounded by AgentSemaphore
- Add JSDoc to poll() documenting concurrent dispatch and re-entrance guard behavior
- Add tests for concurrent dispatch, semaphore limiting, polling flag reset, and overlapping poll discovery
- Update existing re-entrance guard test to block on listTasks (discovery) rather than specifyTask
- Fix existing paused-tasks and globalPause tests for non-blocking dispatch timing
- Add settings:updated listener in Scheduler to trigger schedule() on globalPause true→false transition
- Add settings:updated listener in TriageProcessor to trigger poll() on globalPause true→false transition
- Add unpause handler in dashboard to resume orphaned executor tasks and sweep merge queue
- Guard all resume paths against no-op transitions (false→false, true→true) and stopped state
- Add tests for all three resume paths covering transition edge cases
- Add settings:updated event to TaskStore with previous/new settings payload
- Kill all active executor agent sessions when globalPause transitions false→true
- Kill all active triage specification sessions on global pause with clean status reset
- Track and dispose active merger session on global pause via onSession callback
- Add JSDoc documenting global pause behavior on executor and triage constructors
- Add re-entrance guard to triage poll() to prevent overlapping poll cycles
- Move status update to 'specifying' inside semaphore callback so queued tasks don't appear active
- Fix scheduler double-counting specifying tasks when semaphore is present
- Add tests for poll re-entrance guard, semaphore-aware status transitions, and scheduler slot counting
- Add changeset for patch release
- Add UsageLimitPauser class and isUsageLimitError detector for rate limits, overloaded, and quota errors
- Integrate usage limit detection into executor, triage, and merger error handlers
- Wire shared UsageLimitPauser instance in dashboard startup across all agents
- Export UsageLimitPauser and isUsageLimitError from @kb/engine public API
- Add comprehensive tests for detector patterns and agent integration
- Add globalPause setting to core Settings type with default false
- Guard scheduler, triage, and auto-merge queue to skip work when globalPause is active
- Add pause/play toggle button in dashboard Header with optimistic UI and rollback on failure
- Add tests for scheduler, triage, Header, and App global pause behavior
- Include minor changeset for the new feature
- Add parseDependenciesFromPrompt to TaskStore to extract task IDs from ## Dependencies section
- Call dependency parser in specifyTask after PROMPT.md is written by triage agent
- Extract size (S/M/L) and review level from PROMPT.md front-matter into task metadata
- Extend updateTask to accept size and reviewLevel fields
- Add comprehensive tests for dependency parsing and triage integration
- Add priority levels (PRIORITY_MERGE=2, PRIORITY_EXECUTE=1, PRIORITY_SPECIFY=0) to AgentSemaphore
- Update acquire() and run() to accept a numeric priority parameter with FIFO ordering within same level
- Wire priority constants into executor (PRIORITY_EXECUTE) and triage (PRIORITY_SPECIFY) callers
- Add comprehensive tests for priority ordering, FIFO within same priority, and dynamic limit interaction
- Include changeset for the priority-based agent scheduling feature
- 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
- Create logger module with log levels and structured output (packages/engine/src/logger.ts)
- Replace console.log/warn/error calls with structured logger across engine modules
- Export logger from engine package index
- Add comprehensive tests for logger functionality
- Clean up CI/release workflows and update docs
- Extend Settings type with model provider and model name fields
- Add backend API endpoint to list available models
- Add frontend API client for fetching models
- Add model settings section to SettingsModal with provider/model dropdowns
- Update engine executor to use the selected model from settings
