4189 Commits

Author	SHA1	Message	Date
Timoteo	23b152f494	fix: normalize subscribe for callback-only runtime sessions (#3504) ... ## Summary - normalize callback-only plugin sessions at the shared runtime boundary - preserve runtime-native subscriptions and isolate subscriber failures - strengthen ACP multi-delta, unsubscribe, and callback-delivery coverage - correct the task environment and unsubscribe contracts ## Why PR #3501 fixed the generic ACP adapter, but workflow steps still call `session.subscribe()` unconditionally. Bundled callback-only runtimes such as Hermes and the vendored Grok/Claude/OMP ACP clients can still return sessions without that method. Handling the compatibility once in `createResolvedAgentSession` closes every current runtime surface without copying the bridge into each adapter. ## Testing - `packages/engine`: `agent-session-helpers.test.ts` — 61 passed - `fusion-plugin-acp-runtime`: `runtime-adapter.test.ts` — 14 passed - `fusion-plugin-acp-runtime`: `process-manager.test.ts` — 15 passed - engine typecheck passed - ACP runtime typecheck passed - changeset format, FNXC date check, ESLint, and `git diff --check` passed <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Bug Fixes** - Improved compatibility with callback-based runtime sessions. - Added reliable subscriptions for text, thinking, and tool activity updates. - Preserved native subscription behavior where available. - Prevented subscriber errors from interrupting event delivery. - Improved unsubscribe behavior for removed handlers. - Improved event delivery during deferred runtime fallback. - Corrected task environment values passed to runtime subprocesses. - **Tests** - Expanded coverage for streaming updates, fallback handling, cleanup, and subscriber isolation. <!-- end of auto-generated comment: release notes by coderabbit.ai -->	2026-08-23 19:00:06 -07:00
gsxdsm	64cb17c100	FN-9204: advertise a valid memory MCP server version ... Make the built-in memory MCP server complete the SDK-validated initialize handshake. - Include a non-empty version in fusion-memory serverInfo responses. - Cover the real SDK handshake, malformed-response skip path, and JSON-RPC envelopes. - Document the protocol requirement and add a patch changeset. Files changed: .changeset/fn-9204-memory-mcp-handshake.md | 7 ++ docs/mcp.md | 2 + .../__tests__/mcp-memory-server-spawn.test.ts | 5 +- .../mcp/__tests__/memory-mcp-handler.test.ts | 7 +- packages/core/src/memory/mcp/memory-mcp-handler.ts | 8 +- .../src/__tests__/mcp-memory-handshake.test.ts | 120 +++++++++++++++++++++ 6 files changed, 146 insertions(+), 3 deletions(-) Fusion-Task-Id: FN-9204 Fusion-Task-Lineage: 0f68bdd5-56fe-4fdb-867f-2a5e0ea4de65 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>	2026-08-23 17:17:08 -07:00
gsxdsm	d6c1e27709	test: delete comment-pinning assertions in engine and desktop ... Part of the repo-wide census for the new "tests assert behavior, never source text or comments" rule. - merger-integration-worktree: deleted "keeps direct-reuse shortcut…", whose sole assertion pinned a `// …Skip acquireTaskWorktree's` comment in merger.ts. - auto-heal-review-lane-callsite-audit: deleted "the DELIBERATE-LITERAL note still claims…", whose sole assertion pinned a comment sentence in project-engine.ts. That file's two real AST/call-site cases are untouched. - electron-builder-config: deleted a pin on "intentionally deferred", which exists only inside YAML comments of desktop-windows.yml. Each of these had a comment as its entire subject, so there was no behavior to preserve — deleting the assertion is the complete fix. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 16:56:54 -07:00
Phil Larson	00b7078f79	fix: preserve reclaimed worktree branch provenance (#3507) ... ## Summary - persist engine branch-write provenance when reclaiming an existing task worktree - cover branch-conflict reclaim with a regression assertion for the branch, worktree, and provenance tuple ## Test plan - `pnpm --filter @fusion/engine exec vitest run src/__tests__/executor-worktree.test.ts --silent=passed-only --reporter=dot` - `pnpm --filter @fusion/engine typecheck` - `pnpm check:changesets -- --strict` - `pnpm check:fnxc-future-dates` - `pnpm build` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Improved recovery when reclaiming existing task worktrees. * Preserved task branch details and worktree paths during branch-conflict recovery. * Recorded whether branch updates originated from the system or an operator for more reliable task state tracking. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: gsxdsm <gsxdsm@users.noreply.github.com>	2026-08-23 16:53:38 -07:00
Phil Larson	c9f3f11a72	fix: allow worktree agents to read user skills (#3506) ... ## Summary - allow worktree sessions to read the standard user skill root at `~/.agents/skills` - keep sibling `~/.agents` files and all write/edit/Bash access outside the exception - canonicalize existing path components so symlinks cannot escape an allowed skill root - document the boundary and add a patch changeset This extends the same host-skill consistency fixed in #2384: Fusion should not tell an agent to load a skill and then block the skill body. ## Test plan - [x] 15 worktree-boundary tests - [x] `pnpm --filter @fusion/engine typecheck` - [x] scoped ESLint - [x] changeset and FNXC date checks - [x] `pnpm verify:fast` (20 steps, including build and boot smoke) - [x] CLI CI-shape test (72 tests) ## Local gate notes `pnpm test:gate` passed all static checks, 432 engine-core tests, and 184 core unit tests. Its PostgreSQL lane could not authenticate locally (`empty password returned by client`). The full `pi-create-fn-agent.test.ts` run also reaches an unrelated dashboard-chat principal assertion failure already present at the exact `origin/main` SHA; the 15 boundary tests pass. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Worktree agents can read and search skills installed in the standard `~/.agents/skills` directory. - **Bug Fixes** - Preserved worktree protections for writing, editing, and Bash operations. - Blocked access to unrelated files and prevented symlink-based boundary escapes across supported path operations. - Improved access validation for paths that do not yet exist. - **Documentation** - Updated worktree boundary documentation to describe skill access and its restrictions. <!-- end of auto-generated comment: release notes by coderabbit.ai -->	2026-08-23 16:53:10 -07:00
ischindl	8fcf4bdbaa	feat: Stash memory backend — session capture, per-chat backfill, opt-in vector search (#3494) ... ## Summary Adds the **Stash memory backend** (`memory.backendType=stash`) that connects Fusion's agent memory to the [Stash](https://github.com/Fergana-Labs/stash) product — *knowledge bases for the agent era* ([product site: joinstash.ai](https://joinstash.ai)). Fusion becomes a first-class Stash client: complete chat sessions and finished tasks are captured into Stash, memory is recalled during chat, and Stash sessions are kept in sync with the dashboard (including deletes and archival). **Product:** <https://github.com/Fergana-Labs/stash> · [joinstash.ai](https://joinstash.ai) ## What's included ### 1. Stash memory backend (RUFU-068 / RUFU-121) - New `StashMemoryBackend` (`memory.backendType=stash`) with `stashUrl` / `stashApiKey` settings (global secrets-store `stash-api-key` + per-project override). - **Complete-chat-session capture** keyed by ChatSession id. - Sessions are classified into **per-project folders** (get-or-create, `external_key fusion-<projectId>`, 1h per-process cache) and **soft-deleted with their chat** via `DELETE /api/chat/sessions/:id`. - Per-conversation **memory-focus** read-time scoping (new `0066_chat_session_memory_focus.sql` migration — sequence renumbered 0059→0060→0061→0065→0066 as origin/main claimed the lower numbers); event metadata enriched with `project` / `project_name` / `chat_title`. - Recall queries normalized to single-keyword / explicit-OR ASCII (≤100 chars); shared normalizer export reused by per-turn recall. ### 2. Per-task executor transcript capture (RUFU-122) Finished or failed tasks upload their executor transcript (`agent-log.jsonl`) to Stash as a task session. ### 3. Bulk archive Stash sync (RUFU-125) Archived task-planner chats soft-delete their Stash sessions on bulk archival (paged). The snapshot of doomed session ids is taken *before* the local bulk delete, and the Stash sync runs fire-and-forget so a Stash stall can never delay local archival. ### 4. Per-chat "Preserve to Stash" backfill (RUFU-136) A per-chat action that backfills a chat's full history into Stash, with client-side idempotency and a pre-check that skips already-uploaded content (fail-closed, no duplicate upload on transport failure). - **Session-folder naming fix:** the first project folder is now named "Fusion — &lt;project name&gt;" instead of the bare "Fusion" fallback (the backfill now resolves the central-registry project name, best-effort, never blocking the upload). ### 5. Opt-in semantic (vector) recall (RUFU-126) `stashVectorSearch` setting (default `false` — **zero behavior change until enabled**). For multi-word queries the backend tries Stash's semantic-search endpoint first, then falls back byte-identically to the keyword path. Definitive 404/405/501/503 responses are negatively cached per process. Requires a patched Stash server (new endpoint + `sentence-transformers` + embedding backfill); unpatched servers are transparently bypassed after the first 404. ## Safety - **Opt-in / inert by default:** the default backend remains `qmd`; the Stash backend is inert until `memoryBackendType=stash` + `stashUrl` are set. - All Stash I/O is **best-effort, fail-closed, and non-blocking** — a Stash outage never blocks chat, task completion, or archival. No run-audit content is emitted. ## Testing - Backfill + delete-sync suites (20/20), Stash backend suite (68/68), executor memory / session capture suites, `memory-focus-recalling`, description-guard — all green. - `tsc` clean across core / engine / dashboard. - Live verification: bulk backfill of 21/24 chats completed; the "Preserve to Stash" action is idempotent on re-run. ## Changesets - `@runfusion/fusion` **minor** — Stash memory backend + capture (RUFU-068/121), per-task transcript (RUFU-122), bulk archive sync (RUFU-125), per-chat backfill (RUFU-136), opt-in vector search (RUFU-126) - `@runfusion/fusion` **patch** — backfill session-folder naming fix ## Rebase Note (2026-08-23) Rebased onto `origin/main` `3f448f7292` (v0.77.0-beta.7). Conflicts resolved additively: - `packages/core/src/postgres/schema-applier.ts` + test — upstream's 0062-0065 migrations (task/subtask splitting removal, AI merge review reconciliation, task repository scope, FN-149 review convergence) unioned with this PR's `chat_sessions.memory_focus` migration, which is **renumbered 0065 → 0066** (upstream's FN-149 shipped 0065 canonically on origin/main); `SCHEMA_BASELINE_VERSION` advances to `0066`. - `packages/dashboard/app/components/ChatView.tsx` — upstream's docked chat sidebar resize handlers unioned with the RUFU-136 "Preserve to Stash" backfill handler. - New commit: `settings.memory.*` stash-backend i18n keys added to all 6 secondary locales (RUFU-121/122 parity fix; `pnpm i18n:status` no longer reports any violation introduced by this PR). **Deploy note (operator environments that already ran a pre-rebase build of this PR):** the memory-focus SQL may already be in the schema under ledger row `0065`. Remap that row to `0066` (`UPDATE fusion_schema_migrations SET version = '0066' WHERE version = '0065';`) *before* first boot of a 0066-ceiling binary — otherwise the fresh upstream `0065_fn_149_review_convergence_stage.sql` would be skipped as "already applied". Clean databases (no prior memory-focus row) need no action. **CI note — Lint (lifecycle-column census) is red on the merge base:** `pnpm check:lifecycle-columns --strict` fails identically on pure `origin/main` `3f448f7292` with `packages/core/src/db/legacy-adoption.ts: 0 -> 3` (3 column guards in the U9b legacy-adoption table without a baseline entry or `DELIBERATE-LITERAL` marker). Verified by running the census on a clean origin/main checkout — inherited from the base, not introduced by this PR. Fix belongs upstream; tracked separately. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added Stash memory integration with project configuration and optional semantic search. * Added per-chat memory focus controls and a `/focus` command. * Added “Preserve to Stash” for uploading complete chat history. * Added automatic chat, task transcript, and completion-event capture. * Added project-specific Stash session folders and archive/delete synchronization. * **Bug Fixes** * Improved Stash folder naming and handling of missing branches during no-commit tasks. * **Documentation** * Added setup, configuration, integration, vector-search, and performance guidance. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Fusion <noreply@runfusion.ai> Co-authored-by: gsxdsm <gsxdsm@users.noreply.github.com>	2026-08-23 16:46:14 -07:00
Phil Larson	38edc2366b	fix(core): restore executor workflow creation guidance (#3513) ... ## Summary - restore explicit executor guidance for assigning workflows to tasks the agent creates - keep the existing prohibition on rerouting the task currently being executed - restore parity between both built-in executor prompt variants and their regression test ## Test plan - `pnpm --filter @fusion/core exec vitest run --silent=passed-only --reporter=dot src/__tests__/agent-prompts.test.ts` - `pnpm --filter @fusion/core typecheck` - `pnpm check:changesets` - `pnpm exec eslint packages/core/src/agents/agent-prompts.ts` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Improvements** * Executor workflow guidance now appears only when task creation or delegation capabilities are available. * Built-in executor prompts provide clearer task-assignment instructions based on available capabilities. * Custom executor prompts remain unchanged. * Removed outdated workflow-setting guidance when task-management capabilities are unavailable. * **Tests** * Added coverage for task creation, delegation, and capability-specific workflow guidance scenarios. <!-- end of auto-generated comment: release notes by coderabbit.ai -->	2026-08-23 16:45:03 -07:00
gsxdsm	08f8c26ec1	fix: honor the workflow-principal hold cooldown on the dispatch path ... The U4 executor peel (#3317) rewrote executor.ts from a pre-change base and dropped `isPrincipalHoldCoolingDown`, re-inlining the read inside executeWorkflowGraph behind `!opts?.alreadyClaimed` — a flag its only caller, executeCore, always sets. The ladder kept recording and clearing correctly, so it read as working while never once deferring a dispatch. Without it, an unroutable role pool re-enters the graph on every dispatch only to re-fence and re-park: one graph run, two work-item writes and two audit rows per pass, for a condition that clears only when an operator enables or adds an agent. The `!repeated` log suppression keeps that flood invisible after the first line. Restore the guard in executeCore, ahead of the graphRouting claim. Position is load-bearing in both directions: returning after the claim would strand it (graphRunnerOwnsClaim stops the finally from cleaning up), which is also why the inner check must keep its alreadyClaimed gate. Make the ladder a primitive with one exported writer and one exported reader so a lost reader is a lost reference the compiler can see, rather than a .get() that quietly moved somewhere its guard could never be true. Its test-mode zero is now read at record time; bound at module load it collapsed the cooldown to until === now under VITEST, so no test could have caught this. Regression test asserts the invariant on both entry surfaces plus the negatives that keep the guard from becoming a permanent block. Mutation-checked: with the guard disabled the two dispatch-deferral cases fail. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 15:45:20 -07:00
gsxdsm	39812f4898	test: quarantine one suite-only flake, record another, fix the lockstep guard ... Full engine suite at a97aa84a20: 3 failures out of 12,414. All three diagnosed: - self-healing-pending-wedge-notification's marker-selection case fails ONLY in a full-suite run (expects 1 elapsed marker, sees 2) and passes deterministically alone. This is its SECOND sighting, so per AGENTS.md it is an on-sight quarantine with no further discretion: ledger entry + matching vitest exclude, same commit, 2026-09-06 deletion deadline. - spec-drift-reconciler's exponential-backoff case shows the same shape on a FIRST sighting, so it is recorded in the observed register instead of evicting that file's other passing coverage. Both are timer-driven reconciler tests that only fail alongside other suites, pointing at cross-file fake-timer state. - merge-orphan-durable-write-inventory drift was pure lineHint movement (19 changed, zero newly unclassified entries) after product edits shifted lines. Regenerated. Also fixes check-quarantine-ledger.mjs, which could not see the exclude I added: its comment stripper treated the `/**` inside glob literals like "node_modules/**" and "src/**/*.slow.test.ts" as a block-comment opener and deleted through to the next "*/", swallowing whole array literals and every entry after them. It now scans string-aware, so the lockstep check actually holds. Nothing was appeased: no timeout widened, no retry added, no assertion relaxed. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 15:43:00 -07:00
Phil Larson	bc82d8e0e1	fix(core): thread review lanes through merge readiness (#3514) ... ## Summary - thread resolved review lanes through `isTaskReadyForMerge` - preserve required pre-merge step filtering - add coverage for a renamed review lane ## Test plan - `pnpm --filter @fusion/core exec vitest run --silent=passed-only --reporter=dot src/__tests__/task-merge.test.ts` - `pnpm --filter @fusion/core typecheck` - `pnpm check:lane-wiring` - `pnpm check:changesets` - `pnpm exec eslint packages/core/src/merge/task-merge.ts packages/core/src/__tests__/task-merge.test.ts` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Custom review lanes are now honored during merge-readiness checks and auto-merge processing. * Renamed workflow lanes correctly determine whether tasks can merge. * Tasks resumed from a paused state are routed and evaluated using the appropriate review lane. * The default `in-review` lane remains supported when no custom review lanes are configured. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: gsxdsm <gsxdsm@users.noreply.github.com>	2026-08-23 15:31:17 -07:00
gsxdsm	a97aa84a20	fix: remove debug probes swept into ab9789f0a8 by mistake ... ab9789f0a8 was committed with `git add -A` while an agent was mid-investigation in this same checkout, so it captured that agent's temporary instrumentation: eight `process.stderr.write('[F] …')` probe lines inside product code (executor/mark-stuck-aborted.ts) and a 359-line scratch copy of a test file. Both were pushed. Reverting both; no product behavior was ever intended to change in those files. Also lands the executor-stuck-requeue fix that investigation produced: the grace-timeout assertion ran before the product finished, because the callback continues past its timer into resetStepsIfWorkLost -> loadWorkspaceConfig, real async fs I/O that `vi.advanceTimersByTimeAsync` does not await. The test now awaits a completion barrier resolved by the requeue's own final moveTask rather than a timeout or retry. The product was correct. Lesson for this checkout: stage by explicit path while agents are running. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 15:05:27 -07:00
gsxdsm	ab9789f0a8	fix: correct workspace review fingerprint range and land-intent resolve gating ... Two product defects surfaced by workspace-e2e's remaining failures. 1. A merge-boundary fence silently did not apply. captureWorkspaceReviewEvidence computes a repository's file list over baseCommitSha..<resolved task branch>, but computeReviewDiffFingerprint hardcoded baseRef..HEAD. For a workspace entry whose checkout sits on the integration branch those are different ranges, so the fingerprint did not describe the files captured beside it: a diverged checkout hard-failed an approved repository as content-changed, and a checkout at the base produced an empty diff -> undefined fingerprint -> the repo dropped out of mergeBoundaryFingerprints, so BOTH the approval-missing and content-changed fences stopped applying to it at all. computeReviewDiffFingerprint now takes an optional headRef; workspace evidence passes the resolved task branch. The singular-review caller, whose worktree IS the branch, keeps the ambient HEAD default. 2. Land intents were recorded and resolved under different conditions. landOneRepo records an intent only when ctx.workspaceLand is set, which landWorkspaceTask passes only for remote targets, but the resolve side was gated on durableLandLease alone. A local-only land therefore resolved an intent that was never recorded, got "missing", and failed a fully-landed repo as a partial land AFTER its integration ref had advanced. Resolve now uses the same condition as record. The approveWorkspaceReview helper's "reviewStep called exactly once" constant only held because defect 1 suppressed a repository; it now derives the expected count from the same production capture the review loop uses. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 15:01:39 -07:00
gsxdsm	e37ebd5af9	chore(release): v0.77.0-beta.8 ... Version bump via changesets.	2026-08-23 14:49:26 -07:00
gsxdsm	455bdbc007	fix: repair the engine suite and the product regressions it was pointing at ... Six parallel agents worked the 150 remaining failures. Engine suite: 297 failing tests at baseline 3f448f7292 -> 8. 12,391 passing. The failures were mostly pointing at live regressions, not stale tests. Eleven product defects found and fixed: - Operator approval mail dropped from BOTH executor gate closures: a gate paused a task for approval and no mailbox row was ever written. - FN-8840 title-duplicate handling reverted in triage.ts, self-healing.ts, and scheduler.ts: a title-only "DUPLICATE: <id>" card consumed a full planner session, an operator-authored PROMPT.md could be erased, and a title-only redirect became dispatchable again. - A failed plan-admission audit write set its dedupe marker anyway, silencing the stall permanently (FN-8600 regression); engine now has an outcome-reporting bounded-audit seam mirroring core's FN-9182. - A best-effort plan mirror could abort a whole planning attempt after the authoritative PROMPT.md had already been written. - AI-merge cleanup lost its alreadyAbsent/idempotent signal on the real-git path. - Workspace merge-boundary file comparison ran without its review-evidence fence, hard-failing every file for callers with no review episode. - After a file-scope violation the retry re-selected the rejected squash and never re-merged. - Parallel step branches leaked: a name-based classifier read executor-created fusion/step-* branches as operator-owned and skipped cleanup. - workspace_coordination_leases / workspace_land_intents were missing from projectTableNames, so the PG harness never truncated them and leases leaked across tests. Four of those are silent reversions from ONE commit, 1cf86baa1c, labeled a behavior-preserving "executor pure peels" refactor. It passed its own targeted verification; only a full-suite audit found them. Test-side repairs are root-cause fixes at shared factories: required pre-merge gate declarations, branch-write provenance, fake stores missing production write seams, dead vi.mock specifiers that silently mocked nothing (allowlist ratcheted 11 -> 8), and stale expectations after deliberate IR/tool/error-class changes. Tests for deleted features were deleted with their removing commit cited. Left red deliberately (4): executor-worktree-liveness's unrouted-graph-run assertion and three workspace-e2e landing-stack layers, each needing a design ruling rather than a test edit. Two durable-write call sites remain flagged unresolved rather than given invented fencing verdicts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 12:31:25 -07:00
gsxdsm	29f9edf153	test: declare branch-write provenance in reliability fixtures ... Three more fixtures wrote a task branch without an origin, so the `updateTaskUnlockedImpl` provenance boundary threw before any scenario ran — the same guard, and the same missed-fixture class, as the shared reliability helper fixed earlier. Each fixture binds a task to its worktree branch on the engine's behalf, so each now says so. worktree-lifecycle-certification 0/4 -> 4/4, audit-and-recovery 1/3 -> 3/3, self-healing-interactions 6/7 -> 7/7. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 11:11:18 -07:00
gsxdsm	4f40c91b38	test: drop reviewer-prompt tests for the deliberately removed splitting feature ... Four tests asserted DEFAULT_REVIEWER_PROMPT still carried the task-SPLITTING contract: "Subtask breakdown", "12+ implementation steps", "The bar for splitting is high", and a REVISE directing the planner to fn_task_create 2-5 child tasks. FN-074 removed task splitting across core, dashboard, and engine, and FN-125 removed the reviewer's ability to create tasks at all. FN-074's message says it updated affected tests; these were missed and sat red asserting a contract the product deliberately dropped. Removed rather than repaired: restoring that prompt text to make them pass would re-add removed behaviour. The two tests in this block covering the prompt contract that still exists are untouched. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 10:28:33 -07:00
gsxdsm	324145c1e1	test: repair engine fixtures that predate shipped product guards ... The engine suite's failures are not independent bugs; they are a handful of systemic drifts where a guard shipped and its fixtures were never updated. - Required pre-merge gates (FN-158): the door refuses a card whose enabled optional groups produced no result, and the built-in workflow enables Plan and Code Review by default. Merge-mechanics fixtures now declare an explicit empty list, stating the intent they always had. group-merge-coordinator's "post-Code-Review member" instead gets real PASSING workflowStepResults, because recording the pass is what that fixture actually means. - Branch-write provenance: the shared reliability fixture creates a task with a branch, which now requires an explicit origin. It stands in for an engine-created branch, so it says so. - updateTaskAtomic: a production write seam missing from several fake stores, copied from the faithful fake in merger-ai.test.ts. - Durable-write inventory: eight unclassified TaskStore surfaces classified, including the two batched reads this branch added. - workflow-graph-merge-region-collapse asserted completion-summary AFTER code-review; the IR wires it before, and production logs agree. merger-ai.test.ts alone goes 37 -> 0. Engine failures 288 -> ~200. Also records a first-sighting suite-only flake in the observed register per the standing rule, rather than quarantining a file with substantial coverage. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 10:18:50 -07:00
gsxdsm	ea48af7ab5	fix: require a durable merge record for the step-finalization exemption ... Full-suite set-diff against 3f448f7292 caught three regressions the raw counts hid (that suite is chronically red: 297 failures at baseline, 294 with the change). The step exemption was too broad. It also applied to recoverAlreadyMergedReviewTasks, the content-scan recovery where mergeDetails is ABSENT and landing is inferred by finding matching content on the base branch. That heuristic can match a cherry-pick, so exempting incomplete steps there would launder a genuinely unfinished task to done on a guess — which is exactly what landed-content-soft-blocker.real-git.test.ts exists to prevent. The exemption now requires mergeConfirmed AND a commitSha: FN-9193's actual state, and nothing weaker. Content-scan recovery and no-op merges keep the blocker. Also seeds mergeSweepHoldReasons in the shared merge-lane fixture, which the fixture-drift guard requires of every auto-merge state field. Verified by set-diff: zero test files now fail that did not fail at baseline. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 09:45:10 -07:00
gsxdsm	a879ead0fc	fix: let a proven merge finalize even with unfinished steps ... FN-9193's branch landed on main as eaa1d47c, but a Code Review revision request had reset its steps while the approved merge was in flight. The card was left mergeConfirmed WITH incomplete steps, and every finalization site refused with "task has incomplete steps" — so it sat failed, re-reading its own contradiction. Restarting it made things worse: replanning issued seven fresh pending steps, so the retry re-created the exact condition blocking it. A loop with no exit. Holding a landed card out of done un-merges nothing; the code is on the target branch either way. All four finalization sites now use getMergeConfirmedFinalizationBlocker, which exempts incomplete steps once landing is proven and records the unfinished ones on the task instead of dropping them. A no-op merge that landed no content still blocks — that is the protective half of the guard being replaced, and the executor's no-op branch depends on it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 09:26:16 -07:00
gsxdsm	038f802ba4	fix: make the workflow graph the only merge authority ... ProjectEngine's in-review auto-merge sweep was a second merge authority. It judged eligibility from column, status, steps and retry budget alone, with no idea where the card sat in its workflow graph, so it merged work the graph had never authorized: FN-9191 merged ~2s after fn_task_done, before Code Review had ever started, and FN-9193 merged while Code Review was re-running — the gate then requested revision and reset the steps, but the in-flight merge landed the pre-remediation branch anyway and left the card mergeConfirmed WITH incomplete steps, unfinalizable for five hours. - classifyMergeSweepAdmission (core) admits only merge-confirmed finalization, a card parked at a merge-region node, an interrupted attempt, or a fenced quiescent stall. Every initiation is fenced on satisfied pre-merge gates. - All four doors prove authority: the sweep, the 300ms column-entry handoff (which matches FN-9191's timing better than any sweep tick), the unpause re-enqueue, and a position-only pre-dispatch re-check for cards the graph moved out of the merge lane while they were queued. - workflow-merge-region.ts holds the canonical merge-region predicate; INTERPRETER_ENTRY_NODE_KINDS now aliases it so the two cannot drift. - Multi-repo: branch-group integration/promotion are merge-region nodes, an in-flight sub-repo land reads as foreign liveness, and a cross-node merge-dispatch lease defers. - Sweep reads are batched, so admission costs O(1) queries per poll. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-23 03:29:32 -07:00
gsxdsm	012d42008f	chore(release): v0.77.0-beta.7 ... Version bump via changesets.	2026-08-22 19:27:22 -07:00
gsxdsm	b47fb70b81	fix: defer merge on unrun pre-merge gates instead of failing the task ... An enabled pre-merge gate that has not reported yet is a not-yet condition, not a failure. FN-9191 proved the difference is load-bearing: the in-review auto-merge sweep enqueued the card ~2s after fn_task_done and ~18s before the graph started its own Code Review node, the merge door correctly refused, and the auto-merge error path parked it status="failed". Code Review APPROVED two minutes later, but every subsequent merge — including the graph's own merge node — then died on "task is marked 'failed'". - Merge doors throw the typed PreMergeStepsNotRunError for that blocker. - The auto-merge error path treats it as a deferral: no status write, no mergeRetries burn, no operator handoff. - enqueueEligibleInReviewTasks holds a card out of the merge queue until every enabled pre-merge group has a result, so the race stops at admission. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-22 19:23:15 -07:00
gsxdsm	3edb843f9b	fix: start tailscaled in Docker image and preflight tailscale daemon readiness ... Tailscale remote access failed in the container with a bare "process exited 1": the image ships the `tailscale` CLI but nothing ever ran `tailscaled`, so the `tailscale funnel <port>` spawn died instantly on "failed to connect to local tailscaled". - Add scripts/docker-entrypoint.sh, which best-effort starts tailscaled in userspace-networking mode (needs neither NET_ADMIN nor /dev/net/tun, so the documented `docker run` is unchanged) and then execs the CLI with CMD verbatim. Opt out with FUSION_DISABLE_TAILSCALED=1. - Symlink /var/lib/tailscale into /home/node/.tailscale so the documented `-v <vol>:/home/node` mount persists the node login across container recreates, and pre-create the daemon's socket/log paths node-owned before the USER switch. - Preflight daemon reachability and backend state with `tailscale status --json` in evaluateRemoteLifecycle instead of only `which tailscale`, so unreachable, logged-out, and stopped backends all report an actionable runtime_prerequisite_missing reason rather than an unexplained exit 1. Regression coverage asserts the invariant across all three unusable-backend surfaces, not just the reported container repro. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-22 19:09:41 -07:00
Fusion Agent	bd7a41315c	fix(FN-158): remove residual conflict marker ... Fusion-Task-Id: FN-158	2026-08-23 01:38:45 +00:00
Fusion Agent	bfaa0f42da	FN-158: enforce workspace multi-repo merge boundaries ... Support workspace tasks across a shared root with scope-driven repositories and verifiable merge gates. - Route task work through one workspace directory with per-repository acquisition and isolation. - Add sandbox session policies and per-repository verification command handling. - Enforce required pre-merge checks and honest merge blocking for workspace changes. - Update workspace, workflow, and sandbox documentation and release metadata. Files changed: .changeset/fn-158-workspace-single-root.md | 7 + docs/sandbox.md | 6 +- docs/workflow-steps.md | 6 +- docs/workspaces.md | 12 +- .../core/src/__tests__/legacy-adoption.test.ts | 15 +- .../src/__tests__/required-pre-merge-steps.test.ts | 25 ++++ .../core/src/__tests__/store-bypass-review.test.ts | 24 ++- packages/core/src/__tests__/task-merge.test.ts | 24 +++ .../core/src/__tests__/worktree-layout.test.ts | 29 ++++ packages/core/src/db/legacy-adoption.ts | 20 ++- packages/core/src/index.gate.ts | 4 + packages/core/src/index.ts | 4 + .../core/src/merge/required-pre-merge-steps.ts | 26 ++++ packages/core/src/merge/task-merge.ts | 35 ++++- packages/core/src/store.ts | 59 ++++++-- packages/core/src/task-store/lifecycle-ops.ts | 1 + packages/core/src/task-store/merge-queue-ops.ts | 5 +- packages/core/src/task-store/moves.ts | 13 +- packages/core/src/task-store/task-artifacts-ops.ts | 11 +- packages/core/src/tasks/worktree-layout.ts | 43 +++++- packages/core/src/types/workflow/workflow-steps.ts | 3 +- .../executor-workspace-session-cwd.test.ts | 42 ++++-- .../src/__tests__/node-worktree-isolation.test.ts | 13 +- .../src/__tests__/pi-create-fn-agent.test.ts | 16 ++ .../engine/src/__tests__/project-engine.test.ts | 20 ++- .../src/__tests__/reviewer-workspace.test.ts | 30 +++- .../src/__tests__/run-verification-command.test.ts | 90 +++++++++++- .../__tests__/sandbox/sandbox-exec-policy.test.ts | 16 +- .../src/__tests__/sandbox/session-policy.test.ts | 45 ++++++ .../__tests__/workspace-add-repo-midflight.test.ts | 9 ++ .../engine/src/__tests__/workspace-e2e.test.ts | 13 +- .../workspace-root-worktree-routing.test.ts | 18 +-- packages/engine/src/agent-tools.ts | 15 +- packages/engine/src/agents/agent-runtime.ts | 19 +++ .../engine/src/agents/agent-session-helpers.ts | 15 ++ packages/engine/src/execution/hold-release.ts | 29 ++++ .../engine/src/execution/run-verification-tool.ts | 114 ++++++++++++++- .../create-authoritative-workflow-seams.ts | 20 +-- packages/engine/src/executor/deps-bags.ts | 5 +- .../executor/ensure-graph-custom-node-worktree.ts | 24 ++- .../executor/ensure-task-worktree-for-planning.ts | 36 ++--- .../engine/src/executor/execute-workflow-step.ts | 4 +- .../src/executor/finalize-already-reviewed-task.ts | 6 +- .../src/executor/prepare-graph-node-execution.ts | 14 +- .../engine/src/executor/run-graph-custom-node.ts | 161 +++++++++++++-------- packages/engine/src/executor/run-implementation.ts | 117 ++++++++++++--- packages/engine/src/merge/merger-ai.ts | 16 +- packages/engine/src/merger.ts | 20 ++- packages/engine/src/pi.ts | 150 ++++++++++++++++--- packages/engine/src/project-engine.ts | 10 +- packages/engine/src/runtimes/in-process-runtime.ts | 4 +- packages/engine/src/sandbox/bubblewrap-backend.ts | 55 ++++++- packages/engine/src/sandbox/bubblewrap-policy.ts | 10 +- packages/engine/src/sandbox/index.ts | 1 + .../engine/src/sandbox/sandbox-exec-backend.ts | 45 +++++- packages/engine/src/sandbox/sandbox-exec-policy.ts | 18 ++- packages/engine/src/sandbox/session-policy.ts | 41 ++++++ packages/engine/src/sandbox/types.ts | 11 ++ packages/engine/src/self-healing.ts | 1 + packages/engine/src/triage.ts | 10 ++ .../engine/src/worktree/worktree-acquisition.ts | 53 ++++--- 61 files changed, 1393 insertions(+), 315 deletions(-) Fusion-Task-Id: FN-158 Fusion-Task-Lineage: ba57f5a2-fa69-4210-8ea7-3d124be3deb2 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:37:58 +00:00
Fusion Agent	7d54e86e80	FN-159: filter AI merge protocol markers from blocking findings ... Prevent the AI merge reviewer from persisting its own protocol syntax as blocking review findings. - Register and filter all review protocol markers and disposition lines. - Aggregate reviewer prose into bounded findings and preserve reconciliation safety. - Release prior findings that are not re-confirmed on approved candidates. - Add reconciliation state, tests, documentation, and a patch changeset. Files changed: .../fn-159-ai-merge-protocol-marker-findings.md | 7 ++ docs/architecture.md | 2 +- packages/core/src/types/task/task-core.ts | 6 ++ .../engine/src/__tests__/merger-ai-prompts.test.ts | 39 ++++++++++ .../src/__tests__/merger-ai-squash-gates.test.ts | 6 ++ .../engine/src/__tests__/merger-ai.test.ts | 58 +++++++++++++++ .../engine/src/__tests__/workspace-merger.test.ts | 3 +- packages/engine/src/merge/merger-ai-prompts.ts | 53 +++++++++++--- packages/engine/src/merge/merger-ai.ts | 84 ++++++++++++++++++---- 9 files changed, 231 insertions(+), 27 deletions(-) Fusion-Task-Id: FN-159 Fusion-Task-Lineage: 6eea1dec-1252-4b8d-b227-c84c24ab60af Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:33 +00:00
Fusion Agent	c1818ea819	FN-151: make task reset always complete ... Make reset a reliable description-only fresh start by fencing active planning work and cleaning discarded execution state. - Add reset lifecycle disposal for planning sessions, locks, artifacts, and reset worktrees. - Preserve operator-provided descriptions while clearing stale execution and planning projections. - Expose reset routes and add core, dashboard, and engine regression coverage. Files changed: .changeset/fn-151-task-reset-always-completes.md | 7 + docs/architecture.md | 3 + docs/dashboard-guide.md | 6 +- .../postgres/task-reset-publication.pg.test.ts | 71 +++++++++- .../core/src/__tests__/task-move-disposer.test.ts | 38 ++++++ packages/core/src/index.gate.ts | 2 + packages/core/src/index.ts | 2 + packages/core/src/task-store/reset-lifecycle.ts | 38 +++++- packages/core/src/tasks/task-move-disposer.ts | 36 +++++- .../src/__tests__/task-reset-lifecycle.test.ts | 110 +++++++++++++++- .../src/routes/register-task-workflow-routes.ts | 29 +++-- .../src/__tests__/agent-document-tools.test.ts | 49 +++++++ .../src/__tests__/reset-worktree-removal.test.ts | 77 +++++++++++ .../__tests__/triage-reset-planning-fence.test.ts | 118 +++++++++++++++++ packages/engine/src/agent-tools.ts | 60 +++++++-- packages/engine/src/agents/planning-liveness.ts | 19 +++ packages/engine/src/index.ts | 4 + packages/engine/src/plan-artifact-writeback.ts | 27 +++- packages/engine/src/planning-reset-fence.ts | 26 +++ packages/engine/src/triage.ts | 143 +++++++++++++++++++-- packages/engine/src/worktree/remove-reset-worktree.ts | 65 ++++++++++ 21 files changed, 882 insertions(+), 48 deletions(-) Fusion-Task-Id: FN-151 Fusion-Task-Lineage: 1c25d58e-2d23-4340-a489-51f3e2d8a7f4 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:32 +00:00
Fusion Agent	a786c45bb9	FN-149: converge review cycles before human escalation ... Add bounded review convergence so disputed review gates can resolve independently before requiring operator intervention. - Add staged remediation, arbitration, dispute tooling, and stale-attempt fencing. - Preserve review history and findings while exposing convergence state in core, dashboard, and audit paths. - Add migration, configuration, documentation, changeset, and regression coverage. Files changed: .changeset/fn-149-review-convergence.md | 7 + AGENTS.md | 2 + docs/architecture.md | 4 + docs/dashboard-guide.md | 4 + docs/run-audit.md | 4 + docs/settings-reference.md | 4 + docs/workflow-steps.md | 8 + .../src/__tests__/default-workflow-hooks.test.ts | 13 + packages/core/src/__tests__/plan-approval.test.ts | 21 ++ .../src/__tests__/reopen-semantics-by-role.test.ts | 25 ++ packages/core/src/__tests__/review-severity-gate.test.ts | 18 +- packages/core/src/__tests__/workflow-step-results.test.ts | 52 +++- packages/core/src/config/settings-schema.ts | 6 + packages/core/src/index.gate.ts | 9 + packages/core/src/index.ts | 9 + packages/core/src/planner/plan-approval.ts | 27 +- .../0065_fn_149_review_convergence_stage.sql | 3 + packages/core/src/postgres/schema-applier.ts | 10 + packages/core/src/postgres/schema/project.ts | 2 + packages/core/src/store.ts | 2 +- packages/core/src/task-store/persistence.ts | 4 + packages/core/src/task-store/reset-lifecycle.ts | 2 + packages/core/src/task-store/serialization.ts | 2 + packages/core/src/task-store/task-mutation-ops.ts | 2 +- packages/core/src/task-store/task-row-mappers.ts | 2 +- packages/core/src/task-store/task-update.ts | 4 + packages/core/src/tasks/in-review-stall.ts | 21 ++ packages/core/src/tasks/manual-retry-reset.ts | 2 + packages/core/src/types/settings/settings-scope.ts | 7 + packages/core/src/types/task/task-core.ts | 3 + packages/core/src/types/task/task-review.ts | 2 +- packages/core/src/types/workflow/workflow-steps.ts | 24 +- .../src/workflows/builtin-workflow-settings.ts | 43 +++ .../core/src/workflows/default-workflow-hooks.ts | 10 +- .../core/src/workflows/workflow-step-results.ts | 185 ++++++++++++- .../dashboard/app/components/TaskReviewTab.tsx | 6 +- .../components/__tests__/TaskReviewTab.test.tsx | 6 +- .../dashboard/src/__tests__/routes-tasks.test.ts | 7 + .../src/routes/register-task-workflow-routes.ts | 4 +- .../__tests__/review-arbitration-release.test.ts | 46 ++++ .../src/__tests__/review-arbitration.test.ts | 57 ++++ .../__tests__/review-convergence-context.test.ts | 95 +++++++ .../review-convergence-escalation.test.ts | 135 +++++++++ .../src/__tests__/review-dispute-tool.test.ts | 113 +++++++ .../__tests__/review-finding-supersession.test.ts | 55 ++- .../review-findings-injection.test.ts | 19 +- .../__tests__/review-history-preservation.test.ts | 186 +++++++++++++ .../__tests__/review-ladder-entry-points.test.ts | 304 +++++++++++++++++++++ ...un-audit-sink-health-review-convergence.test.ts | 251 +++++++++++++++++ .../workflow-graph-optional-step-fix.test.ts | 59 ++-- packages/engine/src/execution/replan-target.ts | 6 +- .../clear-terminal-step-failures-for-retry.ts | 8 +- .../src/executor/create-review-dispute-tool.ts | 126 +++++++++ packages/engine/src/executor/deps-bags.ts | 2 +- .../engine/src/executor/execute-workflow-graph.ts | 71 ++++- packages/engine/src/executor/execute-workflow-step.ts | 16 +- packages/engine/src/executor/free-reexports.ts | 1 + packages/engine/src/executor/impl-bindings.ts | 1 + .../engine/src/executor/optional-step-revision.ts | 33 ++- .../src/executor/recover-failed-pre-merge-step.ts | 43 ++- .../request-pre-merge-optional-step-fix.ts | 85 +++--- packages/engine/src/executor/review-arbitration.ts | 233 +++++++++++++++ .../src/executor/review-convergence-ladder.ts | 237 +++++++++++++++ .../route-graph-failure-to-execution-resume.ts | 16 +- .../route-retryable-remediation.ts | 9 +- .../engine/src/executor/run-graph-custom-node.ts | 1 + packages/engine/src/executor/run-implementation.ts | 2 + .../src/executor/task-executor-session-facades.ts | 3 +- .../engine/src/executor/workflow-rerun-bounce.ts | 13 +- .../executor/workflow-step-failure-injection.ts | 23 +- .../engine/src/executor/workflow-step-failures.ts | 16 +- .../engine/src/executor/workflow-step-verdict.ts | 2 + packages/engine/src/self-healing.ts | 5 +- packages/engine/src/util/run-audit.ts | 9 +- .../src/workflows/workflow-graph-executor.ts | 8 +- .../engine/src/worktree/review-diff-fingerprint.ts | 21 +++ .../src/worktree/workspace-review-evidence.ts | 9 +- 77 files changed, 2719 insertions(+), 166 deletions(-) Fusion-Task-Id: FN-149 Fusion-Task-Lineage: 9330df9d-5086-4b40-8daa-66f0ea31cf3e Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:32 +00:00
Fusion Agent	e67403cd6a	FN-155: add expandable thinking traces to transcripts ... Add a reusable expandable thinking trace across chat and agent transcript surfaces. - Add the ThinkingTrace component, styling, localized labels, and documentation. - Render trace sections across chat, planning, mission, milestone, workflow, and agent log views. - Preserve streaming trace data and add regression and surface coverage. Files changed: .changeset/fn-155-thinking-trace.md | 7 ++ docs/dashboard-guide.md | 4 + .../dashboard/app/components/AgentLogViewer.tsx | 11 +- packages/dashboard/app/components/ChatView.css | 10 +- .../app/components/ConversationHistory.tsx | 3 +- .../components/MilestoneSliceInterviewModal.tsx | 3 +- .../app/components/MissionInterviewModal.tsx | 3 +- .../dashboard/app/components/PlanningModeModal.tsx | 9 +- .../app/components/StandardChatSurface.tsx | 21 ++-- packages/dashboard/app/components/TaskChatTab.tsx | 17 +-- .../dashboard/app/components/ThinkingTrace.css | 7 ++ .../dashboard/app/components/ThinkingTrace.tsx | 99 ++++++++++++++++++ .../app/components/WorkflowResultsTab.tsx | 4 + .../__tests__/ChatView.core-interactions.test.tsx | 25 +++++ .../MilestoneSliceInterviewModal.test.tsx | 15 ++- .../__tests__/MissionInterviewModal.test.tsx | 15 ++- .../PlanningModeModal.planning-flow.test.tsx | 33 +++++- .../app/components/__tests__/TaskChatTab.test.tsx | 16 +++ .../__tests__/ThinkingTrace.surfaces.test.tsx | 70 +++++++++++++ .../components/__tests__/ThinkingTrace.test.tsx | 115 +++++++++++++++++++++ .../dashboard/src/__tests__/chat-manager.test.ts | 11 ++ packages/engine/src/__tests__/agent-logger.test.ts | 15 +++ packages/engine/src/__tests__/streaming-delta.test.ts | 13 +++ packages/engine/src/execution/streaming-delta.ts | 4 + packages/i18n/locales/en/app.json | 8 ++ packages/i18n/locales/es/app.json | 8 ++ packages/i18n/locales/fr/app.json | 8 ++ packages/i18n/locales/ko/app.json | 8 ++ packages/i18n/locales/pt-BR/app.json | 8 ++ packages/i18n/locales/zh-CN/app.json | 8 ++ packages/i18n/locales/zh-TW/app.json | 8 ++ packages/i18n/src/resources.d.ts | 8 ++ 32 files changed, 539 insertions(+), 55 deletions(-) Fusion-Task-Id: FN-155 Fusion-Task-Lineage: 2aafff54-2146-4480-874b-393dc991d52b Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:13 +00:00
Fusion Agent	e5ac9c385a	FN-152: repair local PostgreSQL test provisioning ... Repair embedded PostgreSQL test-server staging and diagnostics for reliable local and worktree test runs. - Stage native PostgreSQL runtime files before startup and manage lifecycle state safely. - Add provisioning diagnostics, harness integration, regression tests, and troubleshooting documentation. - Expose PostgreSQL test-server lifecycle commands through package scripts. Files changed: ...server-libdir-plpgsql-and-missing-login-role.md | 15 + docs/testing.md | 10 + package.json | 3 + .../__test-utils__/pg-provisioning-diagnostics.ts | 25 ++ .../core/src/__test-utils__/pg-test-harness.ts | 5 + .../__tests__/pg-provisioning-diagnostics.test.ts | 30 ++ .../__tests__/reliability-interactions/_helpers.ts | 17 +- scripts/__tests__/pg-test-server.test.mjs | 73 +++++ scripts/pg-test-server.mjs | 332 +++++++++++++++++++++ 9 files changed, 505 insertions(+), 5 deletions(-) Fusion-Task-Id: FN-152 Fusion-Task-Lineage: ead05f6e-00fc-42a0-8599-bf4cb2269527 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:12 +00:00
Fusion Agent	d42a60ea06	FN-142: fix plan confirmation read-back and no-op routing ... Make plan persistence confirmations observe the filesystem-backed prompt and let valid no-op reviews terminate cleanly.\n\n- Verify PROMPT.md by querying the task after writes across planning and review surfaces.\n- Add coverage for workspace scope, duplicate plans, failed read-backs, and mirror failures.\n- Route CLOSE_NO_OP Plan Review outcomes through an explicit terminal workflow action.\n- Document the persistence failure mode and publish a patch changeset.\n\nFiles changed:\n .changeset/fn-142-prompt-write-read-back.md | 7 ++\n .../prompt-write-read-back-queries-the-task-row.md | 51 +++++++++++\n .../core/src/__tests__/builtin-workflows.test.ts | 22 +++++\n packages/core/src/workflows/builtin-workflows.ts | 12 +++\n .../src/__tests__/agent-document-tools.test.ts | 101 ++++++++++++++++++++-\n .../__tests__/plan-prompt-write-surfaces.test.ts | 77 +++++++++++++++\n packages/engine/src/agent-tools.ts | 15 ++-\n 7 files changed, 283 insertions(+), 2 deletions(-) Fusion-Task-Id: FN-142 Fusion-Task-Lineage: adddffb3-8786-4372-996a-eefef176f31b Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:12 +00:00
Fusion Agent	33f4797ceb	FN-126: fix inert sync-lane validation ... Prevent inert synchronization lanes from bypassing merge-gate validation while preserving task-lane cache and archive lifecycle behavior. - Reject sync-resolved lane conversions in the static validator. - Preserve task-lane cache emissions and active-session cleanup across task mutations and archival. - Add regression coverage, baseline updates, documentation, and a release changeset. Files changed: .changeset/fn-126-inert-sync-lane.md | 7 + .../a-falling-count-is-not-evidence.md | 12 + .../task-lane-cache-emitter-preservation.test.ts | 269 +++++++++++++++++++++ .../core/src/task-store/archive-lifecycle-2.ts | 3 +- packages/core/src/task-store/moves.ts | 3 +- packages/core/src/task-store/task-artifacts-ops.ts | 3 +- packages/core/src/task-store/task-update.ts | 3 +- packages/core/src/task-store/update-task-deps.ts | 3 +- ...xecutor-archive-releases-active-session.test.ts | 80 ++++++ packages/engine/src/executor.ts | 4 +- .../src/executor/executor-side-effect-hosts.ts | 2 +- .../executor/is-backward-move-out-of-planning.ts | 7 +- .../src/executor/task-executor-graph-facades.ts | 2 +- .../engine/src/executor/task-executor-imports.ts | 1 - .../engine/src/executor/wire-executor-lifecycle.ts | 18 +- .../check-inert-sync-lane-conversions.test.mjs | 83 +++++-- scripts/check-inert-sync-lane-conversions.mjs | 19 +- scripts/lib/inert-sync-lane-baseline.json | 6 +- 18 files changed, 479 insertions(+), 46 deletions(-) Fusion-Task-Id: FN-126 Fusion-Task-Lineage: 0c7a1a3a-9446-44f8-955d-df6c402dfd31 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:12 +00:00
Fusion Agent	8b681775ae	FN-122: fix local workspace integration across repositories ... Make multi-repository workspace merges resolve and land against the correct local integration targets. - Add local integration-target resolution and durable merge-dispatch leasing. - Harden workspace merge fencing, failure handling, audit logging, and CLI/dashboard controls. - Document the workflow and add regression coverage for workspace integration and task-log deduplication. - Complete the CLI engine mock for the new public lease export. Files changed: .changeset/fn-122-local-workspace-integration.md | 7 + docs/architecture.md | 1 + docs/dashboard-guide.md | 4 + docs/settings-reference.md | 4 +- docs/testing.md | 10 ++ .../task-command-github-import-tracking.test.ts | 2 + packages/cli/src/commands/__tests__/task.test.ts | 1 + packages/cli/src/commands/dashboard.ts | 15 +- packages/cli/src/commands/task.ts | 14 +- .../__tests__/postgres/task-log-dedupe.pg.test.ts | 30 ++++ packages/core/src/index.ts | 2 +- packages/core/src/store.ts | 5 +- packages/core/src/task-store/audit-ops.ts | 38 ++++ packages/core/src/types.ts | 2 + packages/core/src/types/task/task-core.ts | 16 +- packages/core/src/types/task/task-log.ts | 2 + .../app/components/WorkspaceWorktreesSummary.tsx | 15 +- .../settings/sections/WorktreesSection.tsx | 3 +- .../engine/src/__tests__/workspace-e2e.test.ts | 198 ++++++++++++++++----- .../__tests__/workspace-integration-target.test.ts | 75 ++++++++ .../src/__tests__/workspace-merger-lease.test.ts | 42 ++++- packages/engine/src/index.ts | 6 + packages/engine/src/merge/merger-ai.ts | 152 +++++++++++----- packages/engine/src/merge/workspace-fence-ref.ts | 17 +- .../src/merge/workspace-integration-target.ts | 87 +++++++++ .../engine/src/merge/workspace-land-failure.ts | 6 +- .../src/merge/workspace-merge-dispatch-lease.ts | 54 ++++++ packages/engine/src/project-engine.ts | 25 +++ 28 files changed, 715 insertions(+), 118 deletions(-) Fusion-Task-Id: FN-122 Fusion-Task-Lineage: 9364bba4-cebc-44e7-b2ae-60967fbc025c Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:12 +00:00
Fusion Agent	0b4dbd219b	FN-125: prevent workflow agents from creating tasks ... Stop workflow executor agents from creating ordinary tasks while preserving explicit self-spawned dependency handling. - Gate task creation by session identity and execution context. - Add self-spawned dependency support, validation, and persistence coverage. - Update agent prompts, tools, documentation, and CLI integration. - Add a published-package changeset. Files changed: .changeset/fn-125-removal.md | 7 +++ docs/agents.md | 2 +- docs/dashboard-guide.md | 2 +- docs/settings-reference.md | 6 +- .../cli/skill/fusion/references/engine-tools.md | 10 ++-- .../extension-task-execution-task-creation.test.ts | 70 ++++++++++++++++++++++ packages/cli/src/extension.ts | 49 +++++++++++++-- .../postgres/store-self-spawned-dep.pg.test.ts | 56 +++++++++++++++++ .../src/__tests__/self-spawned-dependency.test.ts | 18 ++++++ .../__tests__/session-identity-registry.test.ts | 14 ++++- packages/core/src/agents/agent-prompts.ts | 27 ++++----- .../src/agents/task-execution-task-creation.ts | 19 ++++++ packages/core/src/index.ts | 7 +++ packages/core/src/session-identity-registry.ts | 7 +++ packages/core/src/store.ts | 2 + packages/core/src/task-store/errors.ts | 21 +++++++ packages/core/src/task-store/task-update.ts | 10 +++- packages/core/src/task-store/update-task-deps.ts | 12 +++- .../__tests__/ephemeral-task-create-gate.test.ts | 18 +++--- .../src/__tests__/executor-review-verdicts.test.ts | 3 +- packages/engine/src/agent-tools.ts | 4 ++ packages/engine/src/agents/agent-runtime.ts | 2 + .../engine/src/execution/step-session-executor.ts | 15 ++--- .../executor/attempt-executor-verification-fix.ts | 1 + .../engine/src/executor/create-spawn-agent-tool.ts | 1 + .../engine/src/executor/create-task-done-tool.ts | 18 +++++- .../engine/src/executor/create-task-update-tool.ts | 12 +++- .../engine/src/executor/execute-workflow-step.ts | 1 + packages/engine/src/executor/run-implementation.ts | 18 +++--- packages/engine/src/executor/system-prompt.ts | 21 +++---- packages/engine/src/executor/task-add-dep-tool.ts | 14 ++++- packages/engine/src/pi.ts | 15 ++++- 32 files changed, 401 insertions(+), 81 deletions(-) Fusion-Task-Id: FN-125 Fusion-Task-Lineage: da3d69f6-c9cb-45fd-8691-3dfaf7007514 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:12 +00:00
Fusion Agent	10c399d01e	FN-120: fix workspace review evidence and landing recovery ... Harden workspace review evidence and automatic landing recovery across workflow execution and merge paths. - Preserve per-repository review evidence and reroute recoverable workspace review failures. - Improve workflow lifecycle validation, continuation handling, and automatic recovery for workspace landing. - Add regression coverage and document the updated workspace behavior. Files changed: .changeset/fn-120-workspace-review-landing.md | 7 ++ docs/architecture.md | 4 + ...e-empty-merge-boundary-finalization-livelock.md | 4 + docs/testing.md | 4 + docs/workflow-steps.md | 4 + docs/workspaces.md | 6 + .../__tests__/builtin-coding-workflow-ir.test.ts | 11 +- ...workspace-worktrees-concurrent-merge.pg.test.ts | 20 +++ packages/core/src/db/legacy-adoption.ts | 4 + packages/core/src/store.ts | 5 +- .../task-store/async/async-workflow-workitems.ts | 21 ++++ packages/core/src/task-store/task-mutation-ops.ts | 20 ++- .../src/task-store/workflow-workitems-ops-2.ts | 6 +- .../workflows/builtin-coding-ideas-workflow-ir.ts | 9 +- .../src/workflows/builtin-coding-workflow-ir.ts | 20 ++- .../builtin-stepwise-coding-workflow-ir.ts | 21 +++- ...tin-stepwise-final-review-coding-workflow-ir.ts | 13 +- .../src/workflows/workflow-lifecycle-validation.ts | 28 ++++- .../__tests__/builtin-workflows-lifecycle.test.ts | 4 + .../engine/src/__tests__/project-engine.test.ts | 79 ++++++++++++ .../graph-node-missing-worktree-recovery.test.ts | 32 ++++- .../src/__tests__/reviewer-workspace.test.ts | 2 + .../src/__tests__/task-pipeline-smoke.test.ts | 10 +- .../src/__tests__/workflow-task-runtime.test.ts | 10 +- .../engine/src/__tests__/workspace-e2e.test.ts | 29 +++++ .../engine/src/__tests__/workspace-merger.test.ts | 4 +- .../__tests__/workspace-review-evidence.test.ts | 58 +++++++++ packages/engine/src/execution/reviewer.ts | 2 + .../create-authoritative-workflow-seams.ts | 59 +++++---- .../engine/src/executor/execute-workflow-graph.ts | 29 ++++- packages/engine/src/executor/graph-failure-pure.ts | 6 + .../engine/src/executor/handle-graph-failure.ts | 26 ++++ ...-unusable-worktree-graph-failure-to-recovery.ts | 22 +++- .../engine/src/executor/run-graph-custom-node.ts | 4 +- .../src/executor/workspace-review-per-repo.ts | 55 +++++---- packages/engine/src/merge/merger-ai.ts | 137 ++++++++++----------- .../engine/src/merge/workspace-review-reroute.ts | 52 ++++++++ packages/engine/src/project-engine.ts | 47 +++++++ .../self-healing/auto-recover-worktree-session.ts | 2 +- .../src/workflows/workflow-graph-executor.ts | 28 ++++- .../engine/src/workflows/workflow-merge-nodes.ts | 6 +- .../src/worktree/workspace-review-evidence.ts | 110 +++++++++++++++++ .../engine/src/worktree/worktree-acquisition.ts | 24 +++- 43 files changed, 874 insertions(+), 170 deletions(-) Fusion-Task-Id: FN-120 Fusion-Task-Lineage: 61c36613-89bd-44ca-8676-de77662bf53e Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:36:12 +00:00
Fusion Agent	2430ce69b0	FN-112: capture workspace merge evidence from task worktrees ... Capture workspace merge evidence from immutable acquisition baselines to persisted task branches so real linked task worktrees land reviewed changes reliably. - Compare review fingerprints and landing ranges against the persisted task branch rather than the live worktree HEAD. - Add linked-task-worktree regression coverage for per-repository landing proof and exactly-once finalization. - Document the regression and publish the workspace merge fix in a patch changeset. Files changed: .../fn-112-workspace-task-worktree-evidence.md | 7 ++++ docs/architecture.md | 1 + ...e-empty-merge-boundary-finalization-livelock.md | 8 +++- .../engine/src/__tests__/_workspace-fixture.ts | 15 ++++++++ .../engine/src/__tests__/workspace-e2e.test.ts | 31 ++++++++++++--- .../__tests__/workspace-merger-scope-gates.test.ts | 2 +- .../engine/src/__tests__/workspace-merger.test.ts | 45 +++++++++++++++++++++- packages/engine/src/merge/merger-ai.ts | 29 ++++++++++++-- 8 files changed, 125 insertions(+), 13 deletions(-) Fusion-Task-Id: FN-112 Fusion-Task-Lineage: 66e8498e-13f2-461b-ae38-bf750383115b Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-23 01:35:06 +00:00
Phil Larson	8fe69ac5c8	test: align workspace callback fixtures and gate (#3500) ... ## Summary - update workspace worktree test stores for callback-based entry mutations - preserve validation, existing-entry, and singular-routing behavior in the fakes - canonicalize the macOS worktree path fixture before comparing persisted state - remove the stale inert-seam exception left after the review-column callback became fully supplied ## Test plan - `pnpm --filter @fusion/engine exec vitest run src/__tests__/node-worktree-isolation.test.ts src/__tests__/workspace-root-worktree-routing.test.ts src/__tests__/worktree-acquisition.test.ts --silent=passed-only --reporter=dot` - `pnpm --filter @fusion/engine exec vitest run src/__tests__/worktree-acquisition-workspace.test.ts --silent=passed-only --reporter=dot` - Directly changed engine workspace suite with PostgreSQL-dependent blocks skipped: 338 passed, 4 skipped - `pnpm --filter @fusion/engine typecheck` - `node scripts/check-inert-flag-seams.mjs` - `node --test scripts/__tests__/check-inert-flag-seams.test.mjs` - `pnpm lint` - `pnpm check:changesets` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Improved recovery of orphaned worktrees by consistently using canonical paths. * Strengthened worktree assignment and updates to preserve existing entries and prevent stale task state. * Improved synchronization and validation during concurrent workspace updates. * Refined self-healing recovery so branch metadata changes only when necessary. * Improved handling of stalled tasks, retry exhaustion, and clearing obsolete worktree or branch information. <!-- end of auto-generated comment: release notes by coderabbit.ai -->	2026-08-21 19:31:08 -07:00
XiaoHuo888-hue	41c23adf15	feat: add OrcaRouter as a named model provider (#3502) ... ## Summary Adds [OrcaRouter](https://www.orcarouter.ai) as a first-class named model provider, mirroring the existing OpenRouter integration. OrcaRouter is an OpenAI-compatible gateway — `https://api.orcarouter.ai/v1` — that routes to models from many providers (Anthropic, OpenAI, DeepSeek, Google, Grok, Qwen, Zhipu, and more) through a single API key. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes. What this PR does: - **Catalog sync**: `syncStartupModels` now fetches the OrcaRouter `/v1/models` catalog at startup (gated by a new `orcarouterModelSync` global setting, default enabled) and registers an `openai-completions` provider at `https://api.orcarouter.ai/v1`. The key resolves from the `ORCAROUTER_API_KEY` environment variable. - **Auth + onboarding**: OrcaRouter appears in the API-key auth catalog, onboarding setup copy + key hints, and quick-start provider list (key format `sk-orca-...`, dashboard link to `https://www.orcarouter.ai`). - **Icons**: New OrcaRouter brand mark (`OrcaRouterIcon`) with a dedicated color token, wired into `ProviderIcon` and `inferProviderIconKey` so `orcarouter/...` model ids render the brand mark everywhere. - **Settings**: Startup-sync toggle under **Settings → Global Models**, settings search entry, and save-split allowlists. - **Docs + i18n**: `docs/settings-reference.md` / `docs/storage.md` rows and `en` + secondary-locale catalog keys. - **Changeset**: `.changeset/add-orcarouter-provider.md` (minor). Disclosure: I'm an engineer on the OrcaRouter team. ## Test plan - `pnpm --filter @runfusion/fusion exec vitest run src/commands/__tests__/startup-model-sync.test.ts` — 18 passed - `pnpm --filter @fusion/core exec vitest run src/__tests__/settings-parity.test.ts` — 80 passed - `pnpm --filter @fusion/dashboard exec vitest run app/components/__tests__/ProviderIcon.test.tsx` — 115 passed - `pnpm --filter @fusion/dashboard exec vitest run app/components/__tests__/AuthenticationSection.test.tsx app/components/__tests__/ModelOnboardingModal.test.tsx` — 222 passed - `tsc --noEmit` in `@fusion/cli`, `@fusion/core`, `@fusion/dashboard`, `@fusion/engine` — all clean - `pnpm lint` on changed files — clean - `pnpm check:changesets` — clean - **L3 live test**: exercised the production `syncStartupModels` path against the live OrcaRouter API — catalog sync registered 209 models and a real chat completion returned **HTTP 200** (`finish_reason: "stop"`). Note: `pnpm i18n:status` reports pre-existing Jira key-parity gaps in the `app.json` catalogs on a clean checkout (unrelated to this change); the `common.json` catalogs touched here are in parity. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added OrcaRouter as a built-in OpenAI-compatible provider. - Added API-key setup, validation, authentication, onboarding guidance, provider branding, and model catalog visibility. - Added automatic startup synchronization of OrcaRouter models, enabled by default. - Added a global setting to enable or disable model synchronization. - **Documentation** - Documented the new synchronization setting and its configuration. - **Localization** - Added OrcaRouter setup and usage text across supported languages. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: XiaoHuo888-hue <jinhao.song@myflashcloud.com> Co-authored-by: XiaoHuo888-hue <jinhao.song@myflashcloud.com> Co-authored-by: Claude <noreply@anthropic.com>	2026-08-21 19:30:08 -07:00
gsxdsm	a010dc42bf	FN-9185: enforce effective task concurrency limits ... Unify task concurrency around authoritative project settings and expose the effective admission ceiling. - Resolve maxConcurrent and maxWorktrees through a shared core capacity model with consistent defaults. - Apply the effective limit across scheduler, engine, runtime, CLI, API, and project-manager admission paths. - Surface configured and binding concurrency values in dashboard controls, status views, diagnostics, and documentation. - Add regression coverage for settings persistence, routing, scheduling, UI surfaces, and worktree-bound capacity. Files changed: .../fn-9185-max-concurrent-effective-limit.md | 7 + docs/architecture.md | 8 +- docs/cli-reference.md | 1 + docs/dashboard-guide.md | 4 + docs/settings-reference.md | 4 +- .../dashboard-concurrency-settings.test.ts | 166 +++++++++++++++++++++ packages/cli/src/commands/dashboard.ts | 28 ++-- packages/cli/src/commands/onboard.ts | 4 +- packages/cli/src/project-resolver.ts | 27 +++- .../concurrency-capacity-resolver.test.ts | 46 ++++++ .../src/__tests__/worktree-capacity-limit.test.ts | 51 +++++-- packages/core/src/index.gate.ts | 2 +- packages/core/src/index.ts | 2 +- packages/core/src/workflows/workflow-capacity.ts | 61 ++++++-- packages/dashboard/app/App.tsx | 2 + .../app/__tests__/concurrency-ui-surfaces.test.tsx | 155 +++++++++++++++++++ .../scheduling-effective-concurrency.test.tsx | 48 ++++++ packages/dashboard/app/api/projects/projects.ts | 10 +- packages/dashboard/app/api/settings/settings.ts | 14 +- packages/dashboard/app/components/Board.tsx | 7 +- packages/dashboard/app/components/Column.tsx | 13 +- .../dashboard/app/components/EngineControlMenu.tsx | 17 ++- .../command-center/CommandCenterControls.tsx | 17 ++- .../components/command-center/areas/TeamArea.tsx | 10 +- .../app/components/dashboard/MainContent.tsx | 3 + .../dashboard/app/components/dashboard/types.ts | 2 + .../settings/sections/SchedulingSection.tsx | 12 +- packages/dashboard/app/hooks/useAppSettings.ts | 9 +- packages/dashboard/app/hooks/useExecutorStats.ts | 10 +- .../app/utils/__tests__/worktreeGrouping.test.ts | 12 +- packages/dashboard/app/utils/worktreeGrouping.ts | 8 +- packages/dashboard/src/routes.ts | 6 +- ...concurrency-authoritative-source-routes.test.ts | 90 +++++++++++ .../register-config-mcp-pi-settings-routes.test.ts | 29 +++- .../register-config-mcp-pi-settings-routes.ts | 17 ++- .../src/routes/register-project-routes.ts | 14 +- .../concurrency-effective-limit-surfaces.test.ts | 34 +++++ .../src/__tests__/project-engine-manager.test.ts | 19 +++ .../__tests__/scheduler-workflow-cutover.test.ts | 6 +- packages/engine/src/concurrency/concurrency.ts | 23 ++- packages/engine/src/concurrency/hybrid-executor.ts | 35 ++++- .../engine/src/executor/create-spawn-agent-tool.ts | 8 +- packages/engine/src/project-engine-manager.ts | 50 +++++-- packages/engine/src/project-engine.ts | 12 +- packages/engine/src/project/project-manager.ts | 26 +++- packages/engine/src/runtimes/in-process-runtime.ts | 12 +- packages/engine/src/scheduler.ts | 31 ++-- packages/engine/src/triage.ts | 15 +- 48 files changed, 1028 insertions(+), 159 deletions(-) Fusion-Task-Id: FN-9185 Fusion-Task-Lineage: 6294456c-d417-40a5-a5fa-2035c6b964a6 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>	2026-08-21 10:57:44 -07:00
gsxdsm	1a3230ff93	FN-9186: Bound no-progress self-healing requeues ... Bound no-progress self-healing retries so persistent failures stop consuming agent sessions. - Persist a three-attempt retry budget with exponential backoff and an idempotent terminal sentinel. - Prevent restart and wedge recovery paths from reopening exhausted failures. - Emit bounded retry and exhaustion audit events with regression coverage and operator documentation. Files changed: .changeset/fn-9186-no-progress-requeue-budget.md | 7 ++ AGENTS.md | 1 + docs/architecture.md | 2 + docs/run-audit.md | 2 + docs/self-healing-backward-move-audit.md | 2 +- .../src/__tests__/default-workflow-hooks.test.ts | 18 +++ .../non-executor-run-audit-sink-health.test.ts | 43 +++++++ .../__tests__/restart-recovery-coordinator.test.ts | 14 +++ ...self-healing-no-progress-requeue-budget.test.ts | 131 +++++++++++++++++++++ packages/engine/src/__tests__/self-healing.test.ts | 59 ++++++---- .../src/healing/no-progress-requeue-budget.ts | 7 ++ .../src/healing/restart-recovery-coordinator.ts | 10 +- .../__tests__/task-wedge-notification.test.ts | 10 +- .../src/notification/task-wedge-notification.ts | 9 ++ packages/engine/src/self-healing.ts | 95 +++++++++++++-- packages/engine/src/util/run-audit.ts | 3 + 16 files changed, 378 insertions(+), 35 deletions(-) Fusion-Task-Id: FN-9186 Fusion-Task-Lineage: 06d29a60-b6ad-4506-a3c1-f3c52411946a Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>	2026-08-21 09:21:52 -07:00
gsxdsm	96ad20c93d	FN-9187: Bound auto-archive failure retries ... Prevent stale done-task retention from retrying permanently blocked archives forever. - Pre-filter tasks with live lineage children while honoring renamed archive lanes. - Bound repeated archive failures by reason and reset budgets when candidates or failure classes change. - Emit one bounded audit event and operator-facing task log when retries are exhausted. - Cover retry, escalation, reset, lineage, and renamed-lane behavior and document the retention contract. Files changed: .changeset/fn-9187-bounded-auto-archive.md | 7 ++ AGENTS.md | 1 + docs/architecture.md | 2 + docs/run-audit.md | 1 + docs/settings-reference.md | 2 +- .../live-lineage-children-lanes.pg.test.ts | 3 +- .../core/src/task-store/archive-lifecycle-2.ts | 11 +- packages/engine/src/__tests__/self-healing.test.ts | 117 +++++++++++++++++++++ .../engine/src/run-audit/run-audit-catalogue.ts | 3 + packages/engine/src/self-healing.ts | 93 +++++++++++++++- packages/engine/src/util/run-audit.ts | 2 + 11 files changed, 231 insertions(+), 11 deletions(-) Fusion-Task-Id: FN-9187 Fusion-Task-Lineage: cc9a6adc-4b6d-44da-a84b-5633d4b80a10 Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>	2026-08-21 08:25:18 -07:00
Phil Larson	5ec47e58de	fix: resolve late-acquire lifecycle and plugin API drift (#3492) ... ## Summary - resolves renamed review, complete, and archived workflow columns before admitting late workspace repositories - avoids workflow resolution when an existing repository or landing state already decides the result - syncs the bundled dependency-graph plugin with the current TaskCard and scoped-storage APIs ## Test plan - `pnpm --filter @fusion/engine exec vitest run src/__tests__/workspace-add-repo-midflight.test.ts --silent=passed-only --reporter=dot` - `pnpm --filter @fusion/engine typecheck` - `pnpm --filter @fusion-plugin-examples/dependency-graph test` - `pnpm --filter @fusion-plugin-examples/dependency-graph build` - `pnpm check:plugin-interop-drift` - `pnpm check:lifecycle-columns` - `pnpm check:changesets` - `pnpm lint` - `pnpm build` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Late workspace repository acquisition now respects renamed review, complete, and archived workflow columns. * Tasks entering a blocked lifecycle state during acquisition are refused safely. * Existing safeguards for merge status, landed worktrees, legacy terminal identifiers, and existing worktrees remain supported. * Concurrent acquisition attempts now avoid duplicate worktrees and preserve task updates reliably. * **Improvements** * Improved dependency-graph dashboard interoperability with current task-card and storage APIs. <!-- end of auto-generated comment: release notes by coderabbit.ai -->	2026-08-21 07:48:23 -07:00
gsxdsm	704d74c9ba	chore(release): v0.77.0-beta.6 ... Version bump via changesets.	2026-08-21 07:44:32 -07:00
Fusion Agent	c91e5ce42d	FN-106: prevent workspace finalization livelock ... Repair workspace merge-boundary finalization so empty repository sets cannot loop indefinitely. - Track workspace merge readiness and durable per-repository obligations. - Gate landing and recovery on scope, blockers, leases, and checkout ownership. - Preserve remediation state, add recovery paths, documentation, and regression coverage. Files changed: .../fn-106-workspace-finalization-livelock.md | 7 ++ docs/architecture.md | 6 ++ ...e-empty-merge-boundary-finalization-livelock.md | 40 ++++++++++ docs/workflow-steps.md | 4 + packages/cli/src/commands/__tests__/task.test.ts | 2 + ...workspace-worktrees-concurrent-merge.pg.test.ts | 23 ++++++ packages/core/src/store.ts | 9 ++- packages/core/src/task-store/task-mutation-ops.ts | 49 +++++++++++- packages/core/src/task-store/task-update.ts | 6 +- packages/core/src/types/task/task-core.ts | 7 ++ .../engine/src/__tests__/executor-test-helpers.ts | 6 ++ .../executor-workspace-main-checkout-guard.test.ts | 8 +- .../executor-workspace-session-cwd.test.ts | 37 +++++++++ .../engine/src/__tests__/project-engine.test.ts | 14 +++- .../src/__tests__/reviewer-workspace.test.ts | 72 ++++++++++++++++- .../__tests__/workspace-merge-readiness.test.ts | 46 +++++++++++ .../workspace-merger-idempotency.slow.test.ts | 15 ++-- .../src/__tests__/workspace-merger-lease.test.ts | 4 +- .../workspace-root-worktree-routing.test.ts | 47 +++++++++++ .../create-authoritative-workflow-seams.ts | 2 + .../engine/src/executor/create-task-done-tool.ts | 15 ++++ .../executor/ensure-graph-custom-node-worktree.ts | 8 ++ .../request-pre-merge-optional-step-fix.ts | 49 +++++++++++- .../engine/src/executor/run-graph-custom-node.ts | 24 ++++-- packages/engine/src/executor/run-implementation.ts | 9 +++ packages/engine/src/executor/send-task-back-for-fix.ts | 4 +- .../src/executor/workspace-main-checkout-guard.ts | 26 +++++- .../src/executor/workspace-review-remediation.ts | 54 +++++++++++++ .../src/executor/worktree-verify-invariants.ts | 2 +- packages/engine/src/merge/merger-ai.ts | 93 +++++++++++++++++----- .../engine/src/merge/workspace-merge-readiness.ts | 64 +++++++++++++++ packages/engine/src/project-engine.ts | 37 +++++++-- packages/engine/src/self-healing.ts | 54 ++++++++++--- .../engine/src/worktree/worktree-acquisition.ts | 20 ++++- 34 files changed, 787 insertions(+), 76 deletions(-) Fusion-Task-Id: FN-106 Fusion-Task-Lineage: 70b5c13d-9e17-419d-90ac-7258697657ef Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-21 14:41:37 +00:00
Fusion Agent	3717fc5af1	FN-107: block single-repository worktree acquisition ... Prevent single-repository worktree acquisition from proceeding without explicit multi-repository workspace context. - Require workspace-aware acquisition for single-repository tasks. - Propagate acquisition origin and workspace configuration through executor, merger, and recovery paths. - Add regression coverage, documentation, and a release changeset for the blocked behavior. Files changed: .changeset/fn-107-single-repo-worktree.md | 7 ++ docs/architecture.md | 4 + docs/testing.md | 4 + packages/core/src/branch/branch-assignment.ts | 12 +++ packages/core/src/index.gate.ts | 1 + packages/core/src/index.ts | 1 + packages/core/src/task-store/task-creation.ts | 4 +- packages/core/src/task-store/task-update.ts | 4 +- .../src/routes/register-planning-subtask-routes.ts | 1 + .../engine/src/__tests__/executor-test-helpers.ts | 12 +++ .../engine/src/__tests__/executor-worktree.test.ts | 44 ++++++--- .../src/__tests__/node-worktree-isolation.test.ts | 7 +- .../task-branch-write-origin-census.test.ts | 49 ++++++++++ .../worktree-acquisition-workspace.test.ts | 6 +- .../src/__tests__/worktree-acquisition.test.ts | 103 ++++++++++++++++++--- .../engine/src/executor/handle-graph-failure.ts | 16 +++ .../src/executor/workspace-config-resolver.ts | 1 + .../executor/worktree-branch-conflict-handle.ts | 1 + packages/engine/src/merger.ts | 3 +- packages/engine/src/self-healing.ts | 6 + .../self-healing/auto-recover-worktree-session.ts | 10 +- .../src/workflows/workflow-graph-executor.ts | 7 +- .../engine/src/worktree/worktree-acquisition.ts | 73 +++++++++++++- 23 files changed, 334 insertions(+), 42 deletions(-) Fusion-Task-Id: FN-107 Fusion-Task-Lineage: 80df9dae-59a0-416e-8a02-6ab2dba9bb00 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-21 14:41:37 +00:00
gsxdsm	9e0f64af9a	chore(release): v0.77.0-beta.5 ... Version bump via changesets.	2026-08-20 22:40:47 -07:00
Fusion Agent	bbca7a1ffc	FN-094: add mono- and multi-repository lifecycle parity ... Extend workspace lifecycle behavior so mono-repository and multi-repository tasks share the same durable scope, workflow, review, and merge semantics. - Add repository-scope persistence, migrations, serialization, and task mutation support. - Align dashboard task creation, detail, and workspace worktree views with repository-aware lifecycle state. - Extend executor, reviewer, merger, triage, and self-healing paths with parity coverage and tests. - Document the lifecycle contract and publish the operator-facing changeset. Files changed: .changeset/fn-094-multi-repository-lifecycle.md | 7 + docs/agents.md | 8 + docs/architecture.md | 6 + docs/dashboard-guide.md | 4 + docs/multi-project.md | 6 + docs/settings-reference.md | 2 +- docs/testing.md | 12 ++ docs/workspaces.md | 6 + ...workspace-worktrees-concurrent-merge.pg.test.ts | 19 +++ packages/core/src/index.ts | 2 +- .../core/src/postgres/migrations/0000_initial.sql | 1 + .../0064_fn_094_task_repository_scope.sql | 2 + packages/core/src/postgres/schema-applier.ts | 13 +- packages/core/src/postgres/schema/project.ts | 2 + packages/core/src/store.ts | 21 ++- .../core/src/task-store/branch-and-pr-entities.ts | 2 +- packages/core/src/task-store/persistence.ts | 4 +- packages/core/src/task-store/serialization.ts | 2 + packages/core/src/task-store/task-creation.ts | 31 ++++ packages/core/src/task-store/task-mutation-ops.ts | 131 +++++++++++++++- packages/core/src/task-store/task-row-mappers.ts | 2 +- packages/core/src/task-store/task-update.ts | 55 +++++-- packages/core/src/tasks/repository-scope.ts | 29 ++++ packages/core/src/types.ts | 4 + packages/core/src/types/task/task-core.ts | 35 ++++- packages/core/src/types/workflow/workflow-steps.ts | 21 +++ packages/dashboard/app/api/tasks/tasks.ts | 14 ++ packages/dashboard/app/components/NewTaskModal.tsx | 16 +- .../dashboard/app/components/TaskDetailModal.css | 27 ++++ .../dashboard/app/components/TaskDetailModal.tsx | 15 +- .../app/components/WorkspaceWorktreesSummary.tsx | 68 ++++++++- .../app/components/__tests__/NewTaskModal.test.tsx | 1 + .../__tests__/WorkspaceWorktreesSummary.test.tsx | 27 +++- .../src/routes/register-task-workflow-routes.ts | 48 ++++++ .../__tests__/executor-workspace-taskdone.test.ts | 20 +++ .../src/__tests__/reviewer-workspace.test.ts | 170 ++++++++++++++++++++- .../src/__tests__/self-healing-workspace.test.ts | 4 + .../workflow-graph-optional-group.test.ts | 32 ++++ .../workflow-graph-optional-step-fix.test.ts | 58 +++++++ .../engine/src/__tests__/workspace-e2e.test.ts | 91 ++++++++++- .../__tests__/workspace-lifecycle-parity.test.ts | 61 ++++++++ .../src/__tests__/workspace-merger-lease.test.ts | 25 +++ .../__tests__/workspace-merger-scope-gates.test.ts | 58 +++++++ .../engine/src/__tests__/workspace-merger.test.ts | 59 ++++++- packages/engine/src/agent-tools.ts | 92 ++++++++++- packages/engine/src/execution/reviewer.ts | 10 +- .../create-authoritative-workflow-seams.ts | 95 ++++++++++-- .../engine/src/executor/execute-workflow-graph.ts | 37 ++++- .../request-pre-merge-optional-step-fix.ts | 70 +++++++++ .../engine/src/executor/run-graph-custom-node.ts | 124 ++++++++++----- .../engine/src/executor/workflow-step-verdict.ts | 6 +- .../src/executor/workspace-review-per-repo.ts | 118 +++++++++++++- .../src/executor/worktree-task-done-scope-leak.ts | 109 ++++++++++++- packages/engine/src/merge/merger-ai.ts | 88 ++++++++++- packages/engine/src/self-healing.ts | 19 ++- packages/engine/src/triage.ts | 9 ++ .../src/workflows/workflow-graph-executor.ts | 73 +++++++-- .../engine/src/workflows/workflow-node-handlers.ts | 12 +- 58 files changed, 1962 insertions(+), 121 deletions(-) Fusion-Task-Id: FN-094 Fusion-Task-Lineage: 483f958f-cc67-474e-9383-26856c329543 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-21 04:35:58 +00:00
Fusion Agent	f714e45bda	FN-090: reconcile AI merge review state ... Reconcile AI merge-review outcomes with durable task state and operator-visible workflow controls. - Persist merge-review findings and reconciliation metadata through the core task store and schema migration. - Update merger prompts, execution, recovery handling, and workflow routes for approved review outcomes. - Add dashboard task-detail presentation and release documentation for the reconciliation flow. Files changed: .../fn-090-ai-merge-review-reconciliation.md | 7 + docs/architecture.md | 6 + .../src/__tests__/postgres/schema-applier.test.ts | 2 +- .../0063_fn_090_ai_merge_review_reconciliation.sql | 2 + packages/core/src/postgres/schema-applier.ts | 19 +- packages/core/src/postgres/schema/project.ts | 1 + packages/core/src/store.ts | 24 +- packages/core/src/task-store/persistence.ts | 2 + packages/core/src/task-store/reset-lifecycle.ts | 1 + packages/core/src/task-store/serialization.ts | 1 + packages/core/src/task-store/task-mutation-ops.ts | 2 +- packages/core/src/task-store/task-row-mappers.ts | 2 +- packages/core/src/task-store/task-update.ts | 5 + packages/core/src/types/task/task-core.ts | 27 ++ .../dashboard/app/api/tasks/tasks-lifecycle.ts | 9 + .../dashboard/app/components/TaskDetailModal.css | 19 ++ .../dashboard/app/components/TaskDetailModal.tsx | 29 ++ .../src/routes/register-task-workflow-routes.ts | 17 ++ .../src/__tests__/merge-error-recovery.test.ts | 5 +- packages/engine/src/__tests__/merger-ai.test.ts | 234 +++++---------- packages/engine/src/merge/merger-ai-prompts.ts | 31 +- packages/engine/src/merge/merger-ai.ts | 319 ++++++++++----------- packages/engine/src/project-engine.ts | 4 +- 23 files changed, 416 insertions(+), 352 deletions(-) Fusion-Task-Id: FN-090 Fusion-Task-Lineage: 13450a9f-f17f-46b4-ab39-4887520c2a82 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-21 04:34:43 +00:00
Fusion Agent	ab812880d0	FN-087: resume failed workspace merges ... Recover retryable workspace merge failures immediately while preserving ownership and safety guards. - Dispatch operator retries only after a fail-closed pending-owner check. - Reconcile partial workspace lands during startup using existing guarded recovery logic. - Add dashboard and self-healing regression coverage. Files changed: .../routes-task-retry-stale-merge-status.test.ts | 110 ++++++++++++++++++++- .../src/routes/register-task-workflow-routes.ts | 24 ++++- .../src/__tests__/self-healing-workspace.test.ts | 29 ++++++ packages/engine/src/self-healing.ts | 7 ++ 4 files changed, 164 insertions(+), 6 deletions(-) Fusion-Task-Id: FN-087 Fusion-Task-Lineage: fbfc4db5-e154-4e41-90b4-4b4514627f47 Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-21 04:34:10 +00:00
Fusion Agent	926dda6fc7	FN-078: repair multi-repository workspace merge coordination ... Keep long-running workspace land operations live and enforce repository-local scope isolation. - Renew workspace land leases throughout dependency sync, AI merge, push, and intent resolution. - Abort stale land bodies before durable or remote commit points and fence lease-dependent writes. - Centralize repository File Scope resolution across squash, completion, and checkout guards. - Add regression coverage, architecture documentation, and a patch changeset. Files changed: .changeset/fn-078-workspace-lease-and-scope.md | 7 + docs/architecture.md | 3 +- .../executor-workspace-main-checkout-guard.test.ts | 13 ++ .../__tests__/executor-workspace-taskdone.test.ts | 21 +++ .../src/__tests__/workspace-merger-lease.test.ts | 195 ++++++++++++++++++++- .../src/executor/workspace-main-checkout-guard.ts | 4 +- .../src/executor/worktree-task-done-scope-leak.ts | 4 +- .../engine/src/merge/merger-ai-squash-gates.ts | 9 +- packages/engine/src/merge/merger-ai.ts | 55 +++++- packages/engine/src/worktree/workspace-paths.ts | 26 +++ 10 files changed, 321 insertions(+), 16 deletions(-) Fusion-Task-Id: FN-078 Fusion-Task-Lineage: 8ddfa438-d6c0-4d3a-972a-3594bfc05ffb Co-authored-by: Fusion <noreply@runfusion.ai>	2026-08-21 04:32:53 +00:00