Implements the `experiment-finalize` CLI command (FN-4222) and its companion dashboard API route, wiring the feature through the pi extension as a new callable tool. Includes the command implementation, extension tooling, API integration, and corresponding test coverage.
Fusion-Task-Id: FN-4222
- Add dashboard API routes and mission interview store support to list and inspect draft missions
- Update Mission Manager UI to surface draft interview sessions with styling and regression coverage
- Extend CLI mission commands and extension tools to expose draft listings consistently
- Document the draft surfacing behavior and include a changeset for the published CLI package
Fusion-Task-Id: FN-4124
Adds always-on web search capability to the research system, locking the web search provider in settings UI and updating the ResearchView to surface web search as a persistent toggle with agent tool integration, plus corresponding docs and test coverage.
Fusion-Task-Id: FN-4135
Adds zero-step retry classification to the task workflow routes and pi extension, with test coverage in both packages and documentation updates.
Fusion-Task-Id: FN-4130
Adds task priority support to the task creation flow, spanning the engine runtime (`agent-tools.ts`, `triage.ts`), the CLI extension interface (`extension.ts`), and corresponding documentation and tests. The changeset bumps `@runfusion/fusion` as a minor version.
Fusion-Task-Id: FN-4074
Fusion-Task-Lineage: 726c0ae6-90fb-4c13-ace1-215a2becb2a9
Added delegate collision detection and error surfacing across the task creation and delegation pipeline. The core store now throws a typed `DelegateCollisionError` when `createTask` encounters a duplicate task ID, the engine's `delegate_task` tool propagates these errors with context, and the CLI ex
Fusion-Task-Id: FN-4045
Centralized routing policy helpers in core and aligned both direct assignment and delegation to route engineer-role agents consistently, ensuring assigned tasks respect explicit engineer routing the same way delegated tasks do. Added comprehensive test coverage across core, CLI, dashboard, and engin
Fusion-Task-Id: FN-3935
Fusion-Task-Lineage: 069f4d54-f7a8-4bd3-a2c3-4de830de042f
Implements approval guards for agent provisioning (FN-3791), adding policy-gated create/delete flows with dedupe logic, CLI tool alignment, engine run-audit coverage, and corresponding test suites, plus documentation updates and a regression fix for verification/tool docs sync.
Fusion-Task-Id: FN-3791
Adds a `delegate_override` flag to the `delegate_task` tool that allows executor-role tasks to be assigned to non-executor agents. The override is persisted as metadata in the extension and honored by the heartbeat inbox guard, with test coverage across engine, core, and CLI packages plus updated do
Fusion-Task-Id: FN-3957
Completes FN-3939 audit work for PR #59 residual defects by refactoring the mission execution loop in the engine (halving its complexity), adding self-healing test coverage, and wiring in task workflow route improvements. Retry and validation behavior updates are documented in the changeset and skil
Fusion-Task-Id: FN-3939
Merged agent provisioning approval policies into the engine with guard controls that restrict which agents can be created and by whom, integrated through the CLI extension and core policy definitions.
Fusion-Task-Id: FN-3953
Implements invariant enforcement for blocked-by relationships in the scheduler and self-healing recovery, preventing tasks from being blocked by stale or invalid dependencies. The feature adds tests for both scheduler and self-healing behavior, updates the CLI extension and architecture docs, and sh
Fusion-Task-Id: FN-3924
Adds GitHub tracking controls to the create-task flow and task detail modal, with wired patch transport to persist the setting. Includes a CLI extension alignment (FN-3921) and a post-merge typecheck fix (FN-3925).
Fusion-Task-Id: FN-3925
Fixes assignment clearing in the CLI extension by normalizing nullable inputs, ensuring empty strings and literal null values properly clear agent assignments rather than being passed through unchanged; adds comprehensive test coverage for the normalization behavior and a patch changeset.
Fusion-Task-Id: FN-3799
The merge adds a builtin web-search research provider as the default, replacing the need for external research provider configuration and removing the setup gate for builtin defaults. Dashboard settings UX for research defaults was aligned (ResearchView, SettingsModal), CLI research commands were up
Fusion-Task-Id: FN-3901
Adds agent creation and deletion tools to the pi extension, with engine-side implementation in `agent-tools.ts`, core store integration for agent lifecycle management, and corresponding tests and documentation updates across the workspace.
Fusion-Task-Id: FN-3777
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
- Add shared agent role policy helpers for implementation task detection and executor-role enforcement
- Provide a standardized role-mismatch error formatter for delegation and assignment paths
- Update test isolation leak detection to ignore ephemeral fusion-test-home-root temp directories while preserving baseline checks
Fusion-Task-Id: FN-3716
This merge introduces two major themes. First, research tools in both the engine and CLI are now gated behind an experimental flag, using a shared helper from core — the research tools are documented as experimental and the dashboard settings reference is updated. Second, the testing suite receives
Fusion-Task-Id: FN-3705
Documentation delivery alignment completing Step 5 of FN-3369, updating the CLI reference, research docs, and research hardening preflight guide with consistent documentation delivery guidance across all three files.
Fusion-Task-Id: FN-3599
This merge restores the canonical agent lifecycle with termination scoped at the run level (FN-3580, 4 steps), adds sender-side wake recipient override for messages, and introduces test isolation CI enforcement with a stuck-requeue race fix. UI changes remove terminated-agent indicators from AgentDe
Fusion-Task-Id: FN-3580
- Add task provenance fields to extension task list/show outputs for better source visibility
- Expand CLI extension tests to cover provenance rendering in task list and task detail responses
- Add a changeset for @runfusion/fusion documenting the provenance output update
- Harden ensure-test-artifacts script and tests to cover incomplete runtime dist tree scenarios
Fusion-Task-Id: FN-3534
This merge adds three major features: an eval domain (`eval-store.ts`, `eval-types.ts`) with persistence schema for evaluation data; a plugin dashboard view registry with navigation integration for third-party dashboard extensions; and GitHub source metadata traceability that locks and enforces issu
Fusion-Task-Id: FN-3513
Adds test coverage for archived insights across the core store, `InsightsView` component, and `useInsights` hook — 156 lines of new tests covering FN-3315.
Fusion-Task-Id: FN-3315
This merge lands five features spanning the Fusion stack: research settings key renaming (FN-3313, Steps 2–7) across types, defaults, CLI, and engine packages; static plugin slot-host rendering contract documentation (FN-3260); Docker node provisioning routes with a planning modal (FN-3116); plannin
Fusion-Task-Id: FN-3313
Adds `wait_for_completion` polling support for research runs in the CLI extension, along with tests covering the research status schema and wait behavior, and ships a patch changeset for `@runfusion/fusion`.
Fusion-Task-Id: FN-3330
Documents research recovery semantics in the CLI reference and settings reference, adding 9 lines of documentation across both files.
Fusion-Task-Id: FN-3014
Adds `list_agents` and `delegate_task` tools to the pi extension for inter-agent delegation, along with supporting reference docs and 248 new tests. The sync script was also updated to keep the skill tools in sync with the extension implementation.
Fusion-Task-Id: FN-3327
This merge adds a changeset for feature FN-3349 (in-review retry behavior) and delivery documentation to the `@runfusion/fusion` package.
Fusion-Task-Id: FN-3349
Merges the final step for FN-3309, adding a changeset to document the removal of pi install references. The changeset is the only file changed, completing the feature work.
Fusion-Task-Id: FN-3309
Merges FN-2999 research hardening (idempotent cancel/retry routes, aligned SSE event wiring, and cleaned status handling in the core research store and orchestrator) plus UI improvements to AgentDetailView header actions and planning disclosure UX in the modal, with a CSS token fallback fix in Scrip
Fusion-Task-Id: FN-2999
This merge brings multiple substantial features: new research extension tools wired through the AI engine (with full test coverage and documentation), legacy routines agentId backward compatibility with migration paths, migration of experimental remote settings to the global scope, Nerd Font glyph a
Fusion-Task-Id: FN-2996
Fixes the insight tool filter typing in the CLI extension to use stricter types, preventing incorrect filter values from being passed through.
Fusion-Task-Id: FN-3035
fn_task_create and fn_task_update accepted any string as `agentId` and
wrote it verbatim onto `task.assignedAgentId`, letting hallucinated IDs
(e.g. `agent-executor-001`) appear as agent badges in the dashboard.
Mirror the validation already used by fn_delegate: look the agent up via
AgentStore and reject unknown or ephemeral/runtime-managed agents. Null
still clears the field on update.
Also clean up two stale failures in bundle-output.test that predated this
change:
- pi-claude-cli no longer imports cross-spawn, so drop the dependency and
its orphan type-decl file.
- Loosen the spawn-import regex to match `spawn` anywhere in the
destructured import (the source has additional named imports).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Subtask, mission-interview, and milestone/slice-interview sessions could pin
their `generating` state forever when the underlying provider stream stalled
silently or a tool call hung. Wrap each `agent.session.prompt()` in a new
GenerationGuard helper (per-session AbortController + timer) so a stuck turn
becomes a bounded error users can retry. Adds matching `stop*Generation`
exports and threads abort through cleanup so dismissing a modal cancels the
in-flight call instead of leaking it.
Also closes the gh-cli tool hang vector: `runGhAsync` / `runGhJsonAsync` now
accept `{ signal, timeoutMs }` (default 30s). Github-touching extension tools
forward the AI tool's signal so an aborted agent kills the `gh` child instead
of orphaning it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add a core node-override-guard module, export it from @fusion/core, and enforce conflicts in store updates
- Add API route and CLI extension safeguards so nodeId override updates are blocked when ownership would conflict
- Wire node override routing and validation through dashboard quick-create, list, modal, settings, and task form/detail surfaces
- Add focused unit and integration tests for core guard logic, workflow routes, and dashboard node override UX
Replace process.env.HOME fallbacks with os.homedir() in dashboard usage
probes and the hermes plugin profile resolver so unset HOME no longer
yields literal "~" paths. Skip POSIX process-group semantics on Windows
in engine/merger and dashboard-tui's pgrep-based vitest killer. Add
shell: true to npx spawns in CLI skills/extension so .cmd shims resolve
on Windows, and route test:build-exe through cross-env.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Parallel subagent pass: four typescript-pro agents on non-overlapping scopes.
Patterns applied:
- catch (err: any) { ... err.message ... } → catch (err) { ... getErrorMessage(err) ... }
using the new @fusion/core helper. Bare catch {} where the error was unused.
- SQLite row types: defined typed XxxRow interfaces per table and cast
.all()/.get() results via `as unknown as XxxRow[]` (the double cast is
required because better-sqlite3 returns Record<string, SQLOutputValue>).
- rowToX(row: any) converters: typed argument with the matching row interface.
- Dynamic settings key writes: (settings as Record<string, unknown>)[key].
- React event handlers and setState callbacks: inferred types or concrete
React.{Mouse,Change,Form}Event<...> where needed.
- pi-claude-cli: local PiMessage / PiContext duck types to avoid re-typing
pi-ai concrete shapes; typed Claude stream event message fields.
72 files changed, ~400 anys eliminated. Typecheck passes across the workspace.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Eliminates no-unused-vars warnings across the CLI package by dropping
dead type imports, unused destructured helpers, and simplifying try/catch
blocks whose caught errors and intermediate results were never read.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The pi-coding-agent SDK moved from @sinclair/typebox 0.34.x to the new
typebox 1.x package in 0.69. Our direct imports in merger.ts and
extension.ts need to follow so tool schemas resolve to the same TSchema
the SDK consumes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- 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
