Previously the vendored @fusion/pi-claude-cli extension was conditionally
loaded based on GlobalSettings.useClaudeCli. That forced a Fusion restart
every time the user toggled the provider card — confusing UX.
Key insight: pi-claude-cli registers a NEW provider id ("pi-claude-cli")
rather than overriding "anthropic", so loading it unconditionally is
safe — direct Anthropic auth and CLI-routed models coexist peacefully.
The extension also gracefully no-ops when the `claude` binary is missing
(see packages/pi-claude-cli/index.ts:106 — the throw is caught locally).
Changes:
- serve/daemon/dashboard: always append the resolved pi-claude-cli path
to discoverAndLoadExtensions, no settings lookup.
- resolveClaudeCliExtensionPaths() takes no args now; always returns the
resolved path.
- /api/models filter flipped: hide provider === "pi-claude-cli" when
the toggle is OFF (previously: restricted to those models when ON).
- POST /api/auth/claude-cli drops restartRequired semantics — toggling
now has immediate effect on the picker.
- Provider card UX updated to match: "Claude-CLI-routed models are
now visible/hidden from the model picker" instead of "Restart Fusion
to activate".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The shared per-IP mutation bucket (30/min) made common dashboard actions
like Respecify fail with "Too many requests" after light activity. Raise
mutation to 600/min, api to 1000/min, sse to 60/min for the local-first
use case.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- TaskCard: four catch((err: any) => err.message) promise handlers in
archive/unarchive/delete/move → catch((err) => getErrorMessage(err)).
- InlineCreateCard + QuickEntryBox: .catch((err: any)) model-load handlers
→ getErrorMessage(err) with existing @fusion/core import.
- TerminalModal: drop (navigator as any).maxTouchPoints — modern lib.dom
types already expose the property.
- serve.ts: remove unused any annotation on OpenRouter model mapper; the
array element type is already inferred from json.data.
- pi.js, runtime-resolution.ts, dashboard.ts, serve.ts, dev-server-port-
detect.ts, devserver-manager.ts: drop now-stale eslint-disable comments
that the cleanup made redundant.
Fix a prompt-builder regression surfaced by agent's `any` cleanup: toolCall
with a raw string `arguments` field must be preserved verbatim (JSON-quoted)
rather than coerced to `{}`; restores a previously-passing test.
Then promote @typescript-eslint/no-explicit-any from warn → error. Future
new anys must either come with a one-line disable + justification or use a
real type. Workspace is now lint-clean (0 problems).
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>
Clears the remaining no-unused-vars warnings across the dashboard app and
server, desktop main, and engine sources. Dead React state destructures are
collapsed to setter-only, unused props are underscore-prefixed to preserve
API shape, and unreferenced catch bindings are dropped. No behaviour change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three API shifts converge here:
- DefaultResourceLoaderOptions.agentDir is required as of 0.68 (the
old process.cwd() fallback was removed). Pass getFusionAgentDir()
explicitly in createFnAgent.
- createAgentSession({ tools }) is now a string[] allowlist of tool
names, not a Tool[] array (0.68). Our boundary-wrapping via
wrapToolsWithBoundary produces Tool instances, so we can no longer
pass them through \`tools\`. Move them into \`customTools\` and
suppress the built-in defaults with \`noTools: "builtin"\`. The
wrapped tools keep the same names (read, bash, ...) as the built-ins
they replace, so no call-site or prompt changes are needed.
- SettingsManager.create's first arg (cwd) became required (was
optional before). Dashboard routes that previously passed
\`undefined\` for a process-global settings view now pass
process.cwd() to match the existing DefaultPackageManager call below.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drops the .kb/kb.db migration path, legacy backup filename handling, and
backward-compat test suites. Renames internal kbDir identifiers to
fusionDir and hasKbProject/isValidKbProject to their fusion equivalents.
- Remove needsCentralMigration, autoMigrateToCentral, and the
"needs-migration" FirstRunState; checkAndMigrate and KB_SKIP_MIGRATION
env var are gone
- Remove LEGACY_BACKUP_DIR and canonicalizeBackupDir; listBackups no
longer matches kb-* filenames
- Delete backward-compat.test.ts and store-backward-compat.test.ts;
update remaining tests to new 3-state first-run model
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the stray useClaudeCli settings checkbox + onboarding question
with a proper provider-card UX. The card lives next to OAuth + API-key
cards in onboarding and settings, with Enable/Disable + Test actions.
Backend:
- Vendors rchern/pi-claude-cli@0.3.1 as packages/pi-claude-cli
(MIT, attribution in UPSTREAM.md). Lets us bump peer-dep on
pi-coding-agent in lockstep with Fusion (upstream pinned ^0.52.0
vs ours ^0.62.0) and fix bugs without waiting on upstream.
- Adds @fusion/pi-claude-cli as a workspace dep of @runfusion/fusion
so users don't have to `npm install -g pi-claude-cli` manually.
- serve/daemon/dashboard conditionally load the extension via
discoverAndLoadExtensions() when GlobalSettings.useClaudeCli is on;
no side-effects on user ~/.fusion/agent/settings.json.
- New GET /api/providers/claude-cli/status: claude --version probe
+ toggle state + cached extension resolution.
- New POST /api/auth/claude-cli: flips useClaudeCli, refuses if the
claude binary is missing, fires the existing skill-backfill hook.
- /api/auth/status now injects a synthetic {id:"claude-cli", type:"cli"}
provider entry so onboarding + settings see a consistent list.
Frontend:
- New ClaudeCliProviderCard component shared between ModelOnboardingModal
and SettingsModal's Authentication section.
- New AuthProvider.type = "cli" variant.
- Removed the old "Route AI calls through the Claude CLI" checkbox from
Global Models settings and the opt-in step from the onboarding wizard.
- ProviderIcon gets a composite Anthropic-mark-plus-terminal glyph for
the claude-cli provider id.
Tests:
- 8 unit tests for extension resolution (@fusion/pi-claude-cli is
workspace-linked so these run in-tree).
- 2 unit tests for the binary probe.
- Existing /auth/status tests filter out the new synthetic entry so
they keep asserting structural OAuth/API-key behavior in isolation.
- The vendored package's own 296 tests still pass unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The in-progress/in-review Changes tab was inflating file counts by
preferring a stale task.baseCommitSha over the live merge-base with the
base branch. Once upstream commits are merged into a feature branch,
baseCommitSha..HEAD includes every upstream file as well, producing
counts far larger than the branch's own changes.
resolveDiffBase now prefers merge-base(HEAD, [origin/]baseBranch), falling
back to baseCommitSha only when no merge-base is available or when the
merge-base equals HEAD (task sitting on the base branch with no
divergence, e.g. unit-test scenarios).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PUT /api/settings/global now fires an onUseClaudeCliToggled hook on an
actual transition so the UI toggle has immediate effect — serve/daemon/
dashboard wire it to ensureClaudeSkillsForAllProjectsOnStartup so every
registered project picks up .claude/skills/fusion without a restart.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PluginStore's constructor treats its rootDir arg as a project root and
internally appends `.fusion` before opening the SQLite DB. Several CLI
call sites were passing the already-resolved `.fusion` directory,
producing a doubled `.fusion/.fusion/fusion.db` that the dashboard
process kept recreating on every project load.
Pass the project root instead so the DB lands in the canonical
`.fusion/fusion.db` alongside the rest of the project's state.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Use shared nonfatal diagnostics wrapper when disposing agent-generation AI sessions
- Emit structured error context (sessionId and operation) instead of silently swallowing dispose failures
- Add regression coverage verifying generation succeeds while dispose failures are logged as nonfatal diagnostics
- Add normalizeErrorForLog helper and use it to emit consistent structured error fields
- Replace string-interpolated rehydrate and cleanup logs with structured summary payloads including source, ttl, and totals
- Emit structured warning/error diagnostics for settings fallback, initial/scheduled cleanup failures, and dev-server shutdown cleanup failures
- Add server startup tests covering structured cleanup success, failure, and settings-fallback logging behavior
- Replace raw console diagnostics in agent-generation with structured ai-session diagnostics events
- Add a test-only cleanup hook and regression tests for cleanup telemetry and AI generation failure logging
- Expand diagnostics guardrail coverage to include agent-generation and generalize guardrail naming to AI-session modules
- Add a shared runtime logger contract and dashboard runtime logger implementation for structured diagnostics
- Route dashboard CLI/runtime logs through the TUI sink and replace ad-hoc console diagnostics in server paths
- Update CLI and dashboard tests to assert structured runtime logging behavior across sync and error flows
- Document the structured logging architecture updates and include a changeset for @runfusion/fusion
- Update AgentImportModal preview to preselect all agents and skills, support per-item toggles plus select-all/clear controls, and keep directory preview enabled when parsed files exist.
- Send selectedAgents and selectedSkills from paste, directory, and browse import flows, with dynamic import CTA labels and guardrails when nothing is selected.
- Extend /agents/import to accept selection filters, allow skill-only imports, and parse downloaded company archives directly without shell tar extraction.
- Expand dashboard import tests to cover directory parsing, subset selection, browse-mode skill visibility, and related UI/style assertions.
- Restore full-suite CLI test reliability by adding workspace alias mappings in vitest config and retrying slow cross-platform binary help probes.
- Replace the server-computed settings flag with prAuthAvailable and document it in shared Settings types
- Compute PR auth availability from gh CLI auth first, with GITHUB_TOKEN as fallback in GET /api/settings
- Rename dashboard settings state/props/hooks from githubTokenConfigured to prAuthAvailable and strip server-owned auth fields on save
- Update PR section messaging to guide users to run 'gh auth login' and refresh related route/component tests
- Refine the dashboard loopback integration helper with documented helper contracts and centralized skipped-name formatting
- Keep loopback bind detection memoized so all gated integration suites share one environment probe
- Update loopback-gated dashboard suites to use consistent, explicit scope labels in skip output
- Refresh skipped-test inventory docs with the new audit commands and loopback helper usage details
- Add a shared createLoopbackIntegrationTest helper that probes 127.0.0.1 binding once and caches the result
- Use the helper in webhook, websocket, and static asset integration tests to replace duplicated loopback detection logic
- Improve skip diagnostics by including a consistent skip reason and integration scope in skipped test names
- Add a new dashboard TUI renderer with logs, system, utilities, stats, and settings sections
- Wire runDashboard to auto-enable TUI in TTY sessions with reactive task/agent updates and utility keybindings
- Keep non-TTY behavior unchanged by falling back to the existing plain-text startup output
- Add CLI tests and docs for TUI behavior, keyboard shortcuts, and auth/usage guidance
- Ensure dashboard WebSocket auth checks respect --no-auth consistently
Three orthogonal fixes bundled together so they re-land as a unit after
earlier worktree-based reverts kept wiping them individually.
1. `--no-auth` flag now actually disables auth. Previously a stale
FUSION_DAEMON_TOKEN in .env silently re-armed bearer-token auth despite
the CLI flag. Added a `noAuth` option to ServerOptions; auth-middleware's
isDaemonAuthActive/getDaemonToken short-circuit to false/undefined when
set; CLI plumbs opts.noAuth through both createServer call sites.
2. Workflow review failures no longer reset every completed step. Previously
a single CSS nit from a workflow reviewer could drag 5+ already-approved
steps back through plan review, code review, and re-execution because
determineRevisionResetStart fuzzy-matched feedback tokens against step
names. handleWorkflowRevisionRequest, handleWorkflowStepFailure, and
sendTaskBackForFix now call a new reopenLastStepForRevision helper that
flips only the last non-pending step back to pending (with currentStep
rewind via a newly-accepted updateTask field) — all earlier done steps
stay done, and the agent applies the feedback as an in-place patch per
the updated PROMPT.md instructions. determineRevisionResetStart stays
exported as @deprecated so existing unit tests still link.
3. Heartbeat scheduling is now state-driven. Previously a non-ephemeral
agent with a stale runtimeConfig.enabled=false on disk would never tick
and the Pause/Resume button couldn't arm the timer without also flipping
that hidden flag. HeartbeatTriggerScheduler's watchAgentLifecycle now
registers on transitions into active/running and clears on transitions
out; the tick and assignment-trigger guards key off state + ephemeral
classification. InProcessRuntime's created/updated listeners and startup
scan mirror the same semantics. runtimeConfig.enabled is only retained
for ephemeral (task-worker) opt-out.
Tests updated: agent-heartbeat.test.ts — one test renamed from "skips
registration when enabled is false" (obsolete behavior) to
"registers regardless of the legacy enabled flag"; 4 assignment-watching
tests now pass a realistic `state: "active"` on mock agents. 207 heartbeat
tests + 330 executor tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add ExecutionMode type contracts and executionMode field to core task interfaces
- Persist executionMode through SQLite schema mappings and TaskStore read/write paths
- Validate executionMode in dashboard route handlers and API request handling
- Expand core and dashboard test coverage for executionMode persistence and route behavior
- Migrate mission, milestone-slice, and subtask breakdown flows to shared ai-session-diagnostics logging
- Add a planning-flow guardrail test that fails on raw console.* diagnostics across planning modules
- Update mission and subtask breakdown tests to use structured diagnostics sink hooks instead of console spies
- Keep backward-compatible diagnostics test hooks and reset injected sinks to avoid cross-test leakage
- Extend core task types/store and dashboard API route handling to persist task reviewLevel
- Add review level controls to TaskForm, NewTaskModal, and TaskDetailModal flows
- Improve workflow step selector presentation in WorkflowResultsTab and styles for clearer review settings UX
- Document the new review level behavior and add route/form/modal tests to cover create and edit scenarios
- Add a reusable scoped diagnostics contract for AI session flows with typed levels and structured context
- Add sink injection hooks to capture and reset diagnostics output in tests without console monkey-patching
- Add nonfatal and nonfatalAsync wrappers that log failures via errorFromException and continue execution
- Add comprehensive Vitest coverage for scope isolation, sink behavior, error serialization, and non-fatal semantics
The bearer-token middleware was mounted globally on the Express app, so
the initial GET /?token=<token> request for index.html was rejected with
401 before the frontend JS could even load and capture the token from
the URL. The server-side query-string fallback only accepts fn_token=,
while the banner URL uses ?token= (which only the frontend captures), so
the bootstrap request had no valid auth path.
Fix: gate auth on /api/* only. The SPA shell (index.html, /assets/*,
favicon) is public — it contains no secrets, and the frontend auth.ts
module captures the token into localStorage and installs a fetch wrapper
that injects Authorization: Bearer on every /api/* call.
Also: add .env / .env.local to .gitignore so local FUSION_DAEMON_TOKEN
values don't accidentally get committed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pre-release polish. Two related changes bundled because they both land the
project on public-release footing:
Dashboard auth
- fn dashboard now gates the HTTP API + terminal/badge WebSockets behind a
bearer token by default. Token resolution order: --token flag,
FUSION_DASHBOARD_TOKEN env, FUSION_DAEMON_TOKEN env (back-compat), or an
auto-generated fn_<32 hex>. --no-auth disables. The startup banner prints
a click-to-open URL with ?token=<token> embedded.
- Auth middleware now also accepts fn_token=<token> as a query-string
fallback so EventSource and WebSocket clients (which can't set custom
headers) still authenticate.
- setupTerminalWebSocket / setupBadgeWebSocket now refuse unauthenticated
upgrades with a proper 401 + socket close.
- Frontend: new auth.ts module captures ?token= off the URL into
localStorage (key fn.authToken), strips it from the visible URL via
replaceState, and installs a window.fetch wrapper that injects
Authorization: Bearer <token> on every same-origin /api/* request.
EventSource/WebSocket URL builders (api.ts, sse-bus.ts, useTerminal,
useBadgeWebSocket) route through appendTokenQuery().
MIT license
- LICENSE file at repo root.
- license: "MIT" on root package.json and every packages/*/package.json,
plus description/bugs metadata on the CLI package.
Docs
- docs/cli-reference.md documents --token / --no-auth / FUSION_DASHBOARD_TOKEN
and the click-to-open auth flow.
- docs/getting-started.md, docs/docker.md, README.md point at the new flow
and the CLI reference section.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the engine restarts mid-step, an in-progress step may have already
passed plan + code review but not yet been flipped to done by the agent's
next task_update call. Previously, the next executor pass re-entered the
step and replayed both reviews — measured at 5-20 min of pure waste per
restart (observed in FN-2215 Step 1 and FN-2207 Step 6).
recoverApprovedStepsOnResume scans the task log for any in-progress step
whose most recent "code review Step N: APPROVE" entry is newer than its
most recent "Step N → pending" transition, and marks those steps done
before execute() runs. Safely skips steps that were reset after approval
(e.g. by a workflow revision) or only received REVISE verdicts.
Called from both the engine-restart path (resumeOrphaned) and the
unpause path, matching the two places the task log shows as vulnerable
to this race.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add typed dev server models and constants for configs, session state, runtime metadata, and bounded log history
- Add JSON persistence helpers for .fusion/devserver.json with tolerant parsing and session reconstruction
- Add dev command auto-detection across root and workspace package.json scripts with framework inference and priority sorting
- Implement DevServerManager lifecycle controls, preview URL detection, port probing fallback, and singleton manager helpers
- Add Vitest coverage for devserver types, detection/persistence behavior, and manager lifecycle/events
- Replace the silent stale-session eviction catch with a terminal error log in setupTerminalWebSocket
- Add regression tests that assert evictStaleSessions runs on each 60s interval tick
- Verify eviction errors are logged without stopping future ticks and interval cleanup runs on server close
- Add dev-server port detection utilities and wire detected preview state into process/manager lifecycle
- Normalize dev-server status API responses with preview URL, detected port, and manual override compatibility
- Introduce useDevServerLogs and DevServerLogViewer, and integrate them into the DevServer dashboard view
- Expand dashboard test coverage for detection edges, process/routes behavior, log history handling, and CSS regressions
- Extend dev server store with config defaults, normalization, and JSON persistence alongside runtime state.
- Add GET/PUT /api/dev-server/config endpoints with strict request validation for nullable fields and preview URLs.
- Add dashboard API helpers plus a useDevServerConfig hook to load and update selected script, source, command, and preview override.
- Update DevServerView and styles to support saved script selection, change/clear actions, and synchronized command/preview inputs.
- Expand dev server store/routes/component tests and document the config endpoint in architecture docs.
- Rename the dashboard markdown files route to /files/markdown-list.
- Update fetchProjectMarkdownFiles to call the new markdown-list endpoint.
- Adjust useDocuments test mocks and assertions to match the renamed route.
- Extend auth status API typing to include optional ghCli availability/authentication metadata.
- Update /api/auth/status to return ghCli readiness using isGhAvailable() and isGhAuthenticated().
- Treat setup GitHub readiness as satisfied when either GitHub OAuth or authenticated gh CLI is present.
- Add hook tests covering gh CLI authenticated, unauthenticated, combined OAuth, and missing-ghCli fallback cases.
- Add optional summary payload support to planning create-task and start-breakdown API client calls
- Pass edited summary data from PlanningModeModal when creating a task or starting breakdown
- Parse and validate summary overrides in planning routes and prioritize override data when present
- Add and update dashboard tests to verify override handling and modal call expectations
- Emit tool_start/tool_end SSE events from dashboard chat backend and parse them in streaming client helpers
- Track in-flight and completed tool calls in useChat/useQuickChat to preserve tool output summaries alongside assistant messages
- Render collapsed tool call preview blocks in ChatView and QuickChatFAB with dedicated tokenized styles for compact output summaries
- Expand frontend and backend test coverage for SSE tool events, hook state transitions, and collapsed preview rendering behavior
- Add a changeset for @gsxdsm/fusion documenting the new tool-call display behavior
Root cause: during a triage split the AI could set a child task's
`dependencies` to the parent id. The parent is hard-deleted after the split,
and the scheduler's dep check treats a missing id as unmet — permanently
blocking the dependent. This stranded FN-2164 behind the deleted FN-2163.
- core/store.deleteTask: refuse to delete when any live task still has the id
in its `dependencies` array. Throws TaskHasDependentsError listing dependents
so callers can rewrite or recover. Covers the triage-split path and any
future caller.
- engine/triage task_create: validate each proposed dependency before creating
a child — reject the parent id, reject unknown task ids, allow siblings
created earlier in the same split or pre-existing tasks.
- engine/triage split cleanup: wrap the parent deleteTask in try/catch that
keeps the parent alive (safer than stranding dependents) and logs the reason.
- engine/triage prompts: both the mandatory-split and proactive-split prompts
now explicitly state that subtask deps must never reference the parent.
- dashboard/routes /subtasks/create-tasks: reject parent-id deps, drop unknown
deps with an audit log entry, surface parentTaskCloseError + droppedDependencies
in the response instead of silently swallowing them.
- engine/executor: on execute entry, detect the drift state (in-progress task
with no worktree) and emit a loud log + task log entry; the existing
fresh-worktree path then recovers. Prevents silent "operating without a
worktree" behavior that we saw on FN-2152.
Tests:
core: 2907/2907 pass (+5 new, incl. deleteTask guard regression)
engine: 2554/2554 pass (+17 new, incl. task_create dep validation)
dashboard: 9064/9064 pass (+2 new for /subtasks/create-tasks).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Rename core loader, dashboard server chat/planning routes, and frontend agent IDs/storage keys from kb-agent to fn-agent naming
- Update dashboard hooks and components (agent list, chat view, quick chat) to use the new fn agent key prefixes consistently
- Refresh engine, dashboard, core, and CLI tests/mocks to remove remaining kb-agent route and temp prefix references
- Update storage/gap-analysis docs to reflect fn agent key names and add a @gsxdsm/fusion patch changeset for the rename
- 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
