Commit Graph

22 Commits

Author SHA1 Message Date
Fusion
234c2a5945 feat(FN-3968): add tests for task env inheritance and isolation in spawn/ch
Adds test coverage for task environment propagation through the spawn flow, covering child agents inheriting task env, workflow step task env, and spawn hook env isolation cases in `pi-create-fn-agent.test.ts`, with minor additions to `executor-step-session.test.ts` and `executor-pause.test.ts`.

Fusion-Task-Id: FN-3968
2026-05-10 23:36:10 -07:00
Fusion
bccc39f741 feat(FN-3961): propagate taskEnv into agent subprocess sessions
Propagates `taskEnv` (task-scoped environment variables) through the agent session creation pipeline, including executor sessions, spawned child agents, and workflow sessions. The engine's session factory (`agent-session-helpers.ts`), executor, PI agent creation (`pi.ts`), and step session executor

Fusion-Task-Id: FN-3961
2026-05-10 23:36:10 -07:00
Fusion
a1f4b53e21 feat(FN-3914): add durable heartbeat model fallback
Adds durable heartbeat model fallback logic to the engine's heartbeat subsystem (`agent-heartbeat.ts`, `agent-session-helpers.ts`, `pi.ts`), allowing heartbeats to gracefully use alternative AI models when the primary model is unavailable, with documentation updates to `agents.md` and `settings-refe

Fusion-Task-Id: FN-3914
2026-05-10 02:54:30 -07:00
Fusion
0bd460bb7f feat(FN-3855): bypass send-message binding in gate wrappers
- Remove hard dependency on sendMessage in pi agent wrappers so no-approval gates can run without chat bindings
- Add regression coverage for createFnAgent behavior when sendMessage is absent and when tool calls still execute
- Add changeset for @runfusion/fusion documenting the no-approval gate send-message fix

Fusion-Task-Id: FN-3855
2026-05-09 11:31:57 -07:00
Fusion
1130873b4d feat(FN-3852): bypass heartbeat terminal tool in workflow gates
Hardens workflow gate execution to bypass the heartbeat terminal tool, preventing it from blocking terminal gates; adds regression tests covering approval request store and SSE relay behavior, with tightened typing on the test policy.

Fusion-Task-Id: FN-3852
2026-05-09 10:31:06 -07:00
Fusion
6ee85daa47 feat(FN-3548): add agent action routes and approval pause/resume lifecycle
Merges the FN-3548 approval pause/resume system: agents now stall at workflow gates pending approval, with a full lifecycle spanning gate context lookup, action-gate pause/retry, executor and heartbeat pause callbacks, and dedicated approval decision routes. Also lands FN-3744 agent action routes an

Fusion-Task-Id: FN-3548
2026-05-08 20:30:40 -07:00
Fusion
fbc47ec49c feat(FN-3724): add coordination tools and permanent-agent action gating
This merge adds a direct-mode review tab to the task detail modal (FN-3278), improves mobile mailbox keyboard handling and fixes request hangs during wake dispatch (FN-3750/FN-3751), and reclassifies coordination tools with lock exemptions in the agent gating system (FN-3724), alongside GitHub route

Fusion-Task-Id: FN-3724
2026-05-08 11:43:11 -07:00
Fusion
ae2fe35483 fix(FN-3724): exempt internal coordination tools from action gate
- Expand action-gate exempt tool list to include internal heartbeat, task/agent coordination, messaging, evaluation, identity, and memory bookkeeping calls
- Prioritize exempt-tool classification in gate evaluation to ensure permanent-agent sessions cannot deadlock on internal runtime operations
- Add targeted engine tests covering exempt internal tool behavior and permanent-agent gating interactions
- Document the internal tool exemption policy in docs/agents.md
- Add a patch changeset for @runfusion/fusion describing the exemption behavior

Fusion-Task-Id: FN-3724
2026-05-08 01:37:43 -07:00
Fusion
4770b1225c feat(FN-3561): wire permanent-agent approval context in runtime paths
Wired permanent-agent approval context into runtime paths for FN-3561, updating the agents documentation and adding test coverage for the heartbeat executor to validate the runtime behavior.

Fusion-Task-Id: FN-3561
2026-05-07 23:21:05 -07:00
Fusion
2e3be32f1b feat(FN-3560): add permanent agent gating enforcement in pi with tool class
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
2026-05-07 18:07:12 -07:00
Fusion
667761a88a feat(FN-3547): add runtime action classification and gating system for agen
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
2026-05-07 13:52:43 -07:00
Fusion
80cf5f7345 feat(FN-3713): add web builtin tool opt-in for AI agents
Added agent permission policy model with persistence in core, and wired web-builtin tool opt-in enabling planning and synthesis web tools in the dashboard with corresponding docs and a changeset. Also added an inline fast-mode toggle wired into peer executor state, retry logic for cluster task-ID ov

Fusion-Task-Id: FN-3713
2026-05-07 12:06:49 -07:00
Fusion
3440d6aeda feat(FN-3621): harden thinking provider compatibility
- Normalize Anthropic/OpenAI thinking level handling before creating Fn agents
- Add regression tests for thinking-level conflict and provider compatibility behavior
- Document thinking provider compatibility guidance in settings reference
- Ref: Runfusion/Fusion#52

Fusion-Task-Id: FN-3621
2026-05-06 21:44:06 -07:00
gsxdsm
6488110239 Revert "fix(dashboard): lazy-init useMobileKeyboard so remount has no stale render"
This reverts commit eb111f526e.
2026-05-06 21:41:16 -07:00
gsxdsm
eb111f526e fix(dashboard): lazy-init useMobileKeyboard so remount has no stale render
When ChatView remounted (e.g. tab switch with keyboard still up), the
hook started with keyboardOpen=false and corrected itself only after
the effect ran. That single stale-state render briefly unhid the
executor status bar, which appeared as a blank pane covering half the
input box before the next state update settled it.

useState initializers now call getKeyboardMetrics() lazily on first
render so the very first paint already reflects the live keyboard
state.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 21:38:50 -07:00
Fusion
00cdc8a1ac feat(FN-3338): fix project root resolution in registerExtensionProviders an
The merge adds an auto-reload setting (FN-3334) with UI controls in the settings modal, documentation, and a new version-check module, while also fixing a bug (FN-3338) where extension providers incorrectly resolved the project root when invoked from git worktrees — moving the project-root resolutio

Fusion-Task-Id: FN-3338
2026-05-03 16:34:56 -07:00
Fusion
d7e2a3ec42 feat(FN-3335): fix worktree project root resolution in createFnAgent and ad
Merges FN-3335 (worktree project resolution) and FN-3333 (spurious version reloads). The engine's `createFnAgent` now resolves project root from the worktree's cwd rather than the parent process, with `resolveProjectRoot` added to skill-resolver for consistency. The dashboard's `versionCheck` was up

Fusion-Task-Id: FN-3335
2026-05-03 16:01:17 -07:00
Fusion
11fafcbe13 feat(FN-3140): add readonly custom tools and plugin SDK
This merge adds readonly custom tool preservation (FN-3140) with new plugin SDK types and documentation, fixes PluginManager responsive overflow (FN-3093), and integrates the fn-3065 branch with enhanced plugin authoring capabilities. The core plugin-types module was significantly expanded with 230+

Fusion-Task-Id: FN-3140
2026-05-01 16:54:42 -07:00
Fusion
a039e2cf27 feat(FN-3018): merge fusion/fn-3018
- **feat(engine): sanitize cwd from createFnAgent startup log** — prevents worktree paths from leaking into engine diagnostic logs
- **test(engine): add regression test for cwd redaction** — verifies working directory is not present in logged output
- **test(engine): update routes-agent-skills test** — minimal addition to coverage
- **test(dashboard): stabilize TaskCard test** — fixes flakiness in full-suite gate

Commits merged:
- test(FN-3018): stabilize dashboard tests for full-suite gate
- test(FN-3018): complete Step 2 — add cwd redaction regression
- feat(FN-3018): complete Step 1 — sanitize createFnAgent startup log

Files changed:
.../app/components/__tests__/TaskCard.test.tsx     |  2 +-
 .../src/__tests__/routes-agent-skills.test.ts      |  1 +
 .../src/__tests__/pi-create-fn-agent.test.ts       | 28 ++++++++++++++++++++++
 packages/engine/src/pi.ts                          |  2 +-
 4 files changed, 31 insertions(+), 2 deletions(-)

Fusion-Task-Id: FN-3018
2026-04-29 22:09:05 -07:00
Fusion
38f5159719 feat(FN-2962): merge fusion/fn-2962
- Add changeset for `@runfusion/fusion` minor release introducing custom provider registration support

Commits merged:
- feat(FN-2962): complete Step 8 — add changeset and documentation

Files changed:
.changeset/register-custom-providers.md | 5 +++++
 1 file changed, 5 insertions(+)

Fusion-Task-Id: FN-2962
2026-04-29 21:42:44 -07:00
gsxdsm
b9e084364f fix(engine): register grep/find/ls alongside read/bash/edit/write for coding sessions
pi-coding-agent 0.70's createCodingTools preset only includes read/bash/edit/write,
but pi-claude-cli's tool-mapping translates Claude's Glob→find and Grep→grep.
Triage sessions running through Claude CLI hit "Tool find not found" the moment
the model called Glob and looped on the error.

Compose the built-in set explicitly so every tool referenced by tool-mapping.ts
is registered. Read-only sessions also gain ls (was silently dropped earlier
when readonly was redefined upstream).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 16:34:31 -07:00
gsxdsm
bdcb048e20 chore: consolidate test files into __tests__/ dirs and clean stray engine artifacts
- Move all co-located *.test.* files into sibling __tests__/ directories so the
  layout is consistent across packages (159 renames + content-rewrite moves).
  Updates relative imports, vi.mock specifiers, and __dirname/import.meta.url
  path resolutions where tests read fixtures from disk.
- Drop tracked tsc-emit alongside engine .ts sources (auth-storage/logger/
  skill-resolver/context-limit-detector/pi.{js,d.ts,*.map}). These were
  accidentally committed in a merge and the stale pi.js was masking a real
  test-mock vs source mismatch (tests imported "../pi.js" and vite preferred
  the stale build over pi.ts).
- Add packages/engine/.gitignore to block future src/*.{js,d.ts,map}.
- Refactor plugin pi-module seams (openclaw/paperclip/hermes) to ESM-import
  createFnAgent / promptWithFallback / describeModel from @fusion/engine
  instead of require()-ing packages/engine/src/pi.js. Adds @fusion/engine to
  the two plugin package.jsons that were missing it; exports describeModel
  from the engine public API.
- Fix engine test mocks now that they run against current pi.ts: add
  ModelRegistry.create static to mocks in pi.test.ts and pi-create-fn-agent
  .test.ts; switch three boundary-result toEqual assertions to toMatchObject
  so the new content/isError fields don't trip exact-match comparison.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-24 19:39:20 -07:00