- 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
- Move AgentsView to consume agents, loading state, and reload logic directly from useAgents
- Extend useAgents with filterState/showSystemAgents options and always pass includeEphemeral in fetch filters
- Remove duplicate initial fetch/SSE path in AgentsView and rely on hook-managed refresh behavior
- Add regression coverage for single initial load and system-agent visibility toggling behavior
- Update useAgents hook tests to assert the new includeEphemeral fetch contract
- Add explicit operation metadata to agent-generation and ai-session-store diagnostics for cleanup, recovery, and scheduled cleanup paths
- Extend dashboard guardrail coverage to explicitly enforce diagnostics protection for agent-generation.ts and ai-session-store.ts
- Stabilize plugin module reload imports by using temporary reload files with deterministic file URLs and cache updates
- Tighten CLI Vitest workspace cleanup to safely skip missing hidden dist directories during restore
- Add severity control markers to core and engine structured loggers while keeping info logs on stderr transport
- Parse and strip internal severity markers in dashboard TUI console capture so logger.log entries render with info icons instead of error icons
- Expand dashboard TUI tests to cover captured console severity mapping and structured logger behavior, plus logger unit tests in core/engine
- Add a patch changeset for @runfusion/fusion describing the TUI log severity icon fix
- Add structured ai-session diagnostics for summarize-title and agent-generation error paths in dashboard routes
- Emit debug-gated summarize request/model resolution diagnostics when FUSION_DEBUG_AI is enabled
- Add route tests that assert diagnostics payloads for summarize and agent generation failures
- Reduce test flakiness by increasing core Vitest timeouts and relaxing brittle extension-discovery argument matching
Vite/Vitest's resolver treats `#` as part of the filesystem path in some
environments, causing ERR_MODULE_NOT_FOUND on plugin reload.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
- All 8 vitest configs now default maxWorkers to \`cpus().length - 1\`
instead of the arbitrary \`Math.min(4, …)\` cap. Respects an explicit
VITEST_MAX_WORKERS override for constrained environments (CI, laptops
on battery). CLI keeps \`fileParallelism: false\` — audit found real
shared state (process.chdir in agent-import, dist/ races in build-exe
suites) that needs refactoring before we can flip it.
- packages/dashboard: move the mobile build-output smoke test (which
invokes \`pnpm build:client\` via execSync, ~3s per run) into a
dedicated \`test:build\` script so \`pnpm test\` isn't gated by it. A
matching root script keeps CI wiring simple.
- Root: bump --workspace-concurrency from 2 → 4 so core/engine/cli/
desktop can pipeline against dashboard's tail.
- Drop the now-redundant VITEST_MAX_WORKERS=4 prefix from the root
scripts; the per-package configs pick up cpu count themselves.
Dashboard test suite: 182s → 38s (5x) on a 10-core machine. Full
workspace run: ~3m15 → 2m29. All tests still pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- BackupManager.listBackups now matches kb-* and kb-pre-restore-* filenames
alongside the fusion-* pattern, parsing timestamps from either prefix.
- canonicalizeSettings rewrites autoBackupDir: ".kb/backups" to
".fusion/backups" so projects upgraded from the old brand keep working
(custom .kb/* paths remain untouched).
- createBackupManager applies the same canonicalization to settings it
receives, so the factory path also produces backups under .fusion/backups.
- Re-export getErrorMessage from core/src/types.ts so the dashboard's vite
"@fusion/core" alias (which points at types.ts) resolves the symbol for
client-side consumers — fixes the mobile build-output test.
Clears all 8 pre-existing kb → fn rename failures plus the 1 test that
regressed from the new getErrorMessage import surfacing the vite alias gap.
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>
Designed to replace the \`catch (err: any) { ... err.message ... }\` pattern
across the repo. Keeps the catch binding typed as \`unknown\` (TS default)
while still producing a readable message.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- no-useless-escape: drop needless backslashes in character classes and
URL/path regexes (gh-cli, store, task, modelFilter, useFileMention,
RoutineEditor, ScheduleForm).
- no-case-declarations: wrap case bodies in ProjectOverview and
SettingsModal with block scopes.
- prefer-const: convert a never-reassigned slug binding in agent-import;
annotate legitimate forward-declared let bindings in dashboard.ts that
callbacks close over before assignment.
- no-fallthrough: add missing break after settings-subcommand error.
- no-empty-interface/no-empty-object-type: convert ProjectManifest from
empty interface extension to a type alias.
- no-unused-expressions: replace `x && x.method()` short-circuits in
TerminalModal with optional chaining.
Then ratchet these rules from warn → error so regressions are blocked.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drops orphaned imports and the never-referenced V4 migration SQL constant
(V4 was inlined into runMigrations). Also drops the unused TypedEventEmitter
helper type and unused destructured values from stores.
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>
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>
- Add a task-store logger and funnel activity listeners through a shared helper that logs source-event failures
- Replace silent catches with structured warn/error logs for workflow default resolution, title summarization, fs.watch, and polling paths
- Preserve best-effort behavior for activity recording and async summarization while attaching actionable error context
- Expand TaskStore tests to validate logging behavior for activity insert failures, listener rejections, workflow fallback, and watch/poll error handling
- Replace free-text Reports To input with a manager select populated from fetched agents
- Exclude the current agent from manager candidates and preserve unknown manager IDs as a fallback option
- Save selected manager IDs through updateAgent, including clearing reportsTo when No manager is selected
- Expand AgentDetailView settings tests for manager selection behavior and increase task document cascade test timeout stability
On Node builds whose bundled node:sqlite was compiled without
SQLITE_ENABLE_FTS5 (older 22.x LTS), `fn dashboard` crashed on first
run with `Error: no such module: fts5` during schema migration 21.
Database and ArchiveDatabase now probe FTS5 at startup via a disposable
virtual table. When unavailable, migrations 21 and 35 skip the tasks_fts
DDL, ArchiveDatabase skips the archived_tasks_fts block, and
TaskStore.searchTasks / ArchiveDatabase.search fall back to LIKE scans
over id/title/description/comments with ESCAPE-aware patterns.
Set FUSION_DISABLE_FTS5=1 to force the fallback on runtimes where FTS5
is available but undesirable (e.g. reproducing fresh-install behavior
in tests).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- 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
- Reorder dashboard TUI sections so System is tab [1] and the initial active view
- Update header rendering across wide, medium, and narrow terminal layouts to reflect the new tab order
- Expand dashboard TUI tests to assert system-first labels and default active section behavior
- Document system-first startup behavior in CLI reference and add a patch changeset for @runfusion/fusion
Adds a new worktree setting that fetches the configured remote and rebases
the task branch onto the latest default-branch tip before the merger attempts
to merge it back. Catches concurrent pushes from other collaborators or
fusion workers on other hosts before they surface as merge conflicts —
anything the rebase can't fast-forward flows into the existing smart/AI
resolve pipeline (attempts 1–3) rather than needing new handling.
- `settings.worktreeRebaseBeforeMerge` (bool, default true) — gates the step.
- `settings.worktreeRebaseRemote` (string, default "") — which remote to
fetch; empty falls back to git's configured remote for the default branch,
then to the sole remote if there's only one, then to "origin".
- Rebase runs inside the task's worktree; failure aborts and falls through
to the merge cascade. Rebase errors are warn-logged but never throw.
- Dashboard SettingsModal Worktrees section now has a toggle for the setting
plus a remote dropdown populated from `/api/git/remotes/detailed`. The
dropdown defaults to "Use git default" so no explicit selection is needed
on first configure.
Also aligns the Last/Next heartbeat spans on the agent list card — both now
share the `.agent-heartbeat-last, .agent-heartbeat-next, .agent-heartbeat-saving`
font-size rule with a consistent line-height and inline-flex alignment so
the labels don't drift vertically when they share a row.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
- HeartbeatMonitor.executeHeartbeat() now checks if resolved task is done/archived
and exits before session creation with reason 'task_closed'
- When stale task came from persisted agent.taskId, clears the linkage to prevent
repeated stale activations
- HeartbeatTriggerScheduler.watchAssignments() now skips assignment callback dispatch
when assigned task is done/archived (when taskStore is available)
- Added comprehensive tests for stale-task activation guard behavior
Backup automation now emits `npx runfusion.ai backup --create` so scheduled
backups work for users on the zero-install path where `fn` is not on PATH.
`runfusion.ai` also exposes `fn` and `fusion` bins, so `npm i -g runfusion.ai`
puts them on PATH (npm does not link dep bins globally). Alias only defaults
to the dashboard when invoked as `runfusion.ai` / `runfusion`; `fn` / `fusion`
forward args verbatim so bare `fn` still prints help.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add global settings schema/types fields for persisted dashboard session state (selected project and node)
- Refactor NodeContext and current-project hooks to read/write project and node selection via global settings instead of project-local state
- Update App wiring to use the new selection flow across dashboard startup and switching behavior
- Add and expand dashboard tests for NodeContext, useCurrentProject, and view-state persistence behavior
- DevServerView.preview.test.tsx: drop manual-preview-override assertion
(the component hard-codes isManualPreviewOverride=false under the new
session model, so the badge is always "Auto"), provide both legacy and
current-API fields from createDevServerHookState, and mirror
embedContext into blockReason in createPreviewEmbedState so the
fallback panel picks up the reason text under the new destructure.
- runtime-adapter.test.ts: skip the createSession / promptWithFallback /
describeModel blocks with a TODO — the adapter loads pi.js via
CommonJS require() which vi.mock does not intercept, so the mocked
module is never actually installed. Needs a dynamic import seam
before these can run; tracking separately.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Extend core/plugin-sdk types with runtime manifest metadata, runtime factory, and runtime registration exports
- Add runtime validation in plugin manifest parsing, including runtimeId slug and semver checks
- Add PluginLoader.getPluginRuntimes() and PluginRunner runtime cache/invalidation plumbing across plugin lifecycle events
- Expand plugin loader/runner test coverage for runtime discovery and cache behavior, and document runtime registration in PLUGIN_AUTHORING.md
- 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
- 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
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>
- Extend isEphemeralAgent to treat metadata.internal agents as internal system agents
- Add legacy fallback detection for executor agents named verification-agent with no reportsTo
- Update AgentsView list and org tree filtering to honor the Show system agents toggle
- Add regression coverage in core and dashboard tests for default filtering and includeEphemeral visibility
- 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.
Fixes two classes of task failures found while investigating stuck in-review
tasks FN-2165 (worktree base ref missing) and FN-2152 (stray .tmp-fn-2152
gitlink accidentally committed via merger amend).
FN-2165 — stale baseBranch:
- resolveWorktreeStartPoint now returns null instead of throwing
NonRetryableWorktreeError when the stored baseBranch is gone. Caller clears
task.baseBranch and falls back to branching from the default base (HEAD) so
the task self-heals instead of failing permanently.
- New TaskStore.clearStaleBaseBranchReferences() nulls baseBranch on any
dependent task when its upstream branch is deleted. Wired into
cleanupBranchForTask (archive/delete), merger branch cleanup, self-healing
orphan-branch sweep, executor dep-abort and conflict-cleanup paths, and
stale-branch recovery.
Nested worktrees:
- assertWorktreePathNotNested guard in tryCreateWorktree refuses to create a
worktree inside another registered worktree (previously produced pathological
paths like .worktrees/green-finch/.worktrees/amber-panda when rootDir pointed
at a worktree instead of the main repo).
Context-overflow recovery (FN-2182 class):
- Reduced-prompt retry budget raised from 1 → 3 within the same session.
- Adds a fresh-session requeue path when same-session retries still overflow:
task moves back to todo with worktree retained, bounded by
computeRecoveryDecision / MAX_RECOVERY_RETRIES. Prevents late-step context
exhaustion from becoming terminal.
Gitlink prevention (FN-2152 class):
- .gitignore now excludes .tmp-fn-* and .tmp-kb-* so stray worktrees at the
repo root cannot be captured by git add -A.
- Merger amend flow now scans staged entries for 160000 gitlinks and unstages
them with a loud warning; the project uses no submodules, so any such entry
is a bug (this is how f8f90f26 landed in HEAD as .tmp-fn-2152).
Tests: new coverage for baseBranch fallback, nested-worktree guard, and
clearStaleBaseBranchReferences. Full engine + core + dashboard + cli suites
pass (15349 tests).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
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
