## U12 part 11 — CONCEPTS.md taught the legacy enum as the model, and
one entry was simply false
Docs only. No changeset: AGENTS.md excludes internal docs from
changesets.
### The one that is an error, not staleness
`CONCEPTS.md` → **Column agent**:
> Requires both the workflow-columns and graph-executor flags; with
either off, bindings are inert at execution time.
**That kill switch was removed.** `executor.ts` says so at the binding
site:
> the former workflowColumns kill switch was removed, so stale persisted
false values cannot silently disable custom-node, seam, or watcher
bindings
So the shared vocabulary document was telling operators that a shipped
feature depends on a flag that no longer gates it — and, worse, that a
stale persisted `false` would disable it. Anyone debugging "why isn't my
column agent running?" would have been sent to a flag that has nothing
to do with it. Corrected, with the history kept in one clause so it
stays legible to anyone who remembers the old behaviour.
### The one the plan named
`CONCEPTS.md` → **Task** defined the entity as moving "through columns
(triage, todo, in-progress, in-review, done, archived)" — teaching the
legacy enum as the model, in the document whose whole job is shared
vocabulary. The plan lists this entry explicitly as U12 scope.
It now says a Task moves through the columns **its workflow declares**;
that two Tasks on the same board may have entirely different column
sets; and that the six familiar ids are the **Default workflow's
choice** — which is why they saturate stored data — rather than a
property of the model.
### The same class, one doc over
`docs/dashboard-guide.md` restated a trait rule as an id list: "Eligible
existing tasks (triage, todo, in-progress, in-review)". The
implementation gates on traits — `isMutableLiveColumn` is `complete !==
true && archived !== true`. Now stated as the trait rule, with the
Default workflow's ids as an illustration rather than the definition, so
a renamed or custom workflow reads correctly against this doc.
### Left alone deliberately
The **Column (workflow-defined)** and **Default workflow** entries
already describe the workflow-scoped model accurately. Their references
to the legacy enum are about the Default workflow *specifically*, which
is exactly where naming those ids is correct — removing them would make
the docs less true, not more. This is the same judgement as declining to
delete `downgradeIrToV1IfPure` earlier in the unit: legacy vocabulary
describing a legacy-shaped thing is not drift.
### Verification
Docs only, no code paths touched. The factual claims were checked
against source rather than assumed: the kill-switch removal against
`executor.ts`, and the trait rule against
`TaskContextMenu.isMutableLiveColumn`.
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Documents why self-healing force-removed a worktree a planning session was
using and parked the card branch-conflict-unrecoverable: planning gained a task
worktree but never took an active-session lease, so the reclaim sweep's liveness
guard had nothing to see, and a zero-commit branch classifies as
tip-already-merged by construction.
Captures the investigation's dead ends too — including reading maxConcurrent
from a multi-tenant config table without filtering by project_id, which produced
a confidently wrong root cause — and the three ways the first version of the fix
was itself wrong.
CONCEPTS.md: adds planning to the Active-session lease kinds (the entry had gone
stale), states the converse invariant that an unheld path reads as proof nothing
is running, and defines Top-level agent slot — the capacity concept whose
conflation with the worktree limit derailed the first hour of diagnosis.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
## Summary
Project workflow model lanes now apply to tasks on every workflow
instead of only tasks using the active default workflow. Model selection
consistently resolves task-specific choice -> project workflow baseline
-> global lane -> selected-workflow value -> project/global default for
primary models, fallback models, and thinking levels.
The active default workflow remains the storage owner for backward
compatibility, while runtime resolution keeps its project baseline
distinct from lower-priority selected-workflow values. Non-model
workflow policies remain isolated to their selected workflow.
## Validation
- Core workflow/model resolution: 60 tests passed
- Engine effective settings and session resolution: 59 tests passed
- Reviewer: 85 tests passed
- Scheduler: 154 tests passed
- Heartbeat: 90 tests passed
- Settings UI: 67 tests passed
- Workspace lint and core/engine/dashboard typechecks passed
- `pnpm verify:fast` passed workspace builds, the published CLI build,
and real `/api/health` boot smoke
---
[](https://github.com/EveryInc/compound-engineering-plugin)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added **Project workflow model lanes** to establish a project baseline
for model selection and thinking levels across workflows.
* Updated model/fallback resolution to account for task overrides,
project baselines, global lanes, and selected-workflow values.
* **Bug Fixes**
* Improved effective settings merging so project baselines are applied
correctly (including scheduled/idle and heartbeat flows) while
preserving selected-workflow provenance.
* **Documentation**
* Refreshed settings and dashboard guidance for workflow lane
inheritance and resolution precedence.
* **Tests**
* Expanded unit test coverage for lane precedence, fallback detection,
and thinking-level behavior.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Summary
Adds a bundled **Quality** plugin (`fusion-plugin-quality`) that makes
task QA easier and more visual:
- **Task QA tab** (action-first): preview/test server for the task
worktree, allowlisted test runs, report viewer, screenshots CTA,
suggested test cases, CI handoff
- **Quality hub** (left sidebar): project-wide run history and preset
launches
- Host **task-detail slot context** (`taskId`, worktree, `projectId`) so
plugin tabs can scope correctly
- `superviseSpawn` re-exported on the plugin packaging shim for
published plugins
- Plan: `docs/plans/2026-07-14-001-feat-quality-plugin-plan.md`
## Design constraints
- Does **not** replace the merge gate — advisory orchestration only
- Composes Dev Server process patterns and artifact registry (no second
browser stack)
- Never free-form shell; never port 4040
- Full-suite requires explicit confirm
## Test plan
- [x] `pnpm --filter @fusion-plugin-examples/quality test` (15 tests)
- [x] PluginSlot unit tests still pass
- [ ] Enable Quality plugin in dashboard Settings → Built-in Plugins
- [ ] Open Task Detail → **QA** tab with a worktree; start preview, run
verify:fast, generate suggestions
- [ ] Open left sidebar **Quality** hub and list runs
- [ ] Confirm merge gate / PR checks unchanged
## Residual / follow-up (same plan, later units)
- Deeper hub CI (host route)
- Full browser-verification toggle UX + agent QA sessions (U7/U9/U10)
- Richer screenshots gallery wiring to live artifacts API
- Test plans CRUD polish
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added the Quality plugin with a project Quality hub and task-focused
QA tab.
* Added test runs, reports, preview server controls, suggested test
cases, and run history.
* Added configurable test presets, cancellation, status tracking, and
safe command execution.
* Added experimental-feature controls for enabling Quality
functionality.
* Bundled Quality with the CLI and made it available through the plugin
manager.
* **Documentation**
* Added Quality plugin guidance, terminology, configuration details, and
implementation planning documentation.
* **Bug Fixes**
* Improved process supervision so command failures and shutdown timers
are handled safely.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Summary
Bundled plugins now persist shared runtime state in project-scoped
PostgreSQL tables instead of maintaining independent SQLite authority.
Reports, CLI Printing Press, Compound Engineering, Roadmap, Even
Realities, and WhatsApp all follow the same ownership and startup
contract as Fusion core.
## Design decisions
- Plugin schema hooks run through the host’s PostgreSQL owner and
enforce project isolation.
- The SDK exposes the host contract needed by bundled plugins without
importing engine internals.
- Legacy Roadmap ownership fixtures use the supported empty-owner
sentinel, preserving current composite primary/foreign keys while
exercising backfill behavior.
- The lockfile travels with the Even Realities PostgreSQL dependency so
packaged installs remain reproducible.
## Validation
- All six affected plugin builds pass.
- Affected plugin suites pass: 773 tests across Printing Press, Compound
Engineering, Even Realities, Reports, Roadmap, and WhatsApp.
- `pnpm test:gate` passes all 478 gate tests.
- This PR changes 40 files.
## Stack
- Depends on #2110 → #2109 → #2108.
- The documentation/release PR completes the stack.
Related: #2105
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Breaking Changes**
* PostgreSQL is now required for runtime storage; SQLite files are used
only as one-time migration inputs.
* The legacy `FUSION_NO_EMBEDDED_PG` fallback has been removed.
* **New Features**
* Added project-isolated PostgreSQL storage for plugins, reports, tasks,
notifications, and other plugin data.
* Added agent tools for reports and CLI service drafts.
* Added PostgreSQL schema initialization support for plugin authors.
* **Bug Fixes**
* Improved migration and recovery of legacy plugin state.
* Prevented cross-project data access and strengthened transactional
schema updates.
* **Documentation**
* Updated storage, migration, deployment, plugin authoring, CLI, and
dashboard guidance for PostgreSQL.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Agents were composing plans (e.g. reboot/wait-and-retry loops) that assumed they could keep acting even after the Fusion platform itself shut down, since prompts never told them they run inside Fusion. This adds a shared, docs-grounded self-awareness preamble prepended to chat, heartbeat, and executor base prompts so agents know their own runtime constraints.
- Added FUSION_RUNTIME_SELF_AWARENESS shared preamble in packages/core/src/agent-prompts.ts, exported via packages/core/src/index.ts
- Prepended the preamble to the chat system prompt (packages/dashboard/src/chat.ts)
- Prepended the preamble to the heartbeat session prompt (packages/engine/src/agent-heartbeat.ts)
- Prepended the preamble to the executor base prompt (packages/engine/src/executor.ts)
- Updated docs/agents.md and CONCEPTS.md to document the new self-awareness/capability-grounding behavior
- Added regression tests across core, dashboard, and engine covering the new prompt content
- Added changeset for @runfusion/fusion (minor, fix category)
Files changed:
.changeset/fn-7675-agent-runtime-self-awareness.md | 7 ++++
CONCEPTS.md | 4 +-
docs/agents.md | 17 ++++++++
packages/core/src/__tests__/agent-prompts.test.ts | 41 ++++++++++++++++++++
packages/core/src/agent-prompts.ts | 32 ++++++++++++++-
packages/core/src/index.ts | 1 +
packages/dashboard/src/__tests__/chat-system-prompt.test.ts | 17 ++++++++
packages/dashboard/src/chat.ts | 6 ++-
packages/engine/src/__tests__/executor-prompt.test.ts | 45 ++++++++++++++++++++++
packages/engine/src/__tests__/heartbeat-session-prompt.test.ts | 35 +++++++++++++++++
packages/engine/src/agent-heartbeat.ts | 10 +++--
packages/engine/src/executor.ts | 7 +++-
12 files changed, 213 insertions(+), 9 deletions(-)
Fusion-Task-Id: FN-7675
Fusion-Task-Lineage: 126d04a6-2c68-4347-9789-591b274277bf
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds a docs/solutions learning: a Task field is silently dropped on persist
unless it has a SQLite column + defineTaskColumn + rowToTask mapping (applyTaskPatch
writes the DB-round-tripped task back over task.json). Plus a CONCEPTS.md entry for
the active-session lease (the path-keyed exclusivity/liveness registry whose key
choice caused the concurrent-workspace collision).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Workspace tasks (no task.worktree, populated workspaceWorktrees) now render in
existing task views without crashing or going blank. New read-only
WorkspaceWorktreesSummary component (placeholder "N repos acquired" + a flat
repo→worktree/branch list — within the "doesn't look broken" ceiling, not a rich
status UI); TaskCard and TaskDetailModal nil-guard on isWorkspaceTask. Single-repo
rendering unchanged. CONCEPTS.md notes workspace-task merges are non-atomic
(repos land independently on local integration refs; partial-land is local and
operator-resettable). Tests 8/8; TaskCard regression 251/251.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Document the code-review P1 as a logic-errors learning: a per-task graph
toggle (enabledWorkflowSteps, keyed by optional-group node id) collided with
the legacy step-template namespace and was silently remapped by the store
resolver, bypassing an enabled group. Cross-references the per-task-override
blast-radius cousins as the id-namespace-collision variant of that class.
Seeds an "Optional step group" entry in CONCEPTS.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Allow registering a non-git parent directory that contains multiple git
repositories as a single Fusion project. The agent acquires per-repo
worktrees on demand via a new `fn_acquire_repo_worktree` tool as it
discovers it needs to work in each sub-repo.
This commit lays the foundation:
- detectWorkspaceRepos / loadWorkspaceConfig / saveWorkspaceConfig in
@fusion/core (config persisted to .fusion/workspace.json)
- Task.workspaceWorktrees data model + store plumbing (per-repo
worktree/branch map, distinct from the singular task.worktree)
- acquireWorkspaceRepoWorktree wraps acquireTaskWorktree per sub-repo,
clearing the singular worktree/branch fields so each sub-repo gets a
fresh worktree instead of resuming a sibling repo's worktree
- fn_acquire_repo_worktree agent tool + workspace prompt injection
- executor git-repository validation bypassed when a workspace config
is present
- CLI `fn init` detects a non-git dir containing sub-repos and writes a
workspace config
Known gap (intentionally left for design discussion, see PR): the
executor's main worktree-acquisition path still assumes a single git
root and is not yet workspace-aware. End-to-end execution (skipping the
root acquisition, per-repo merge, per-repo session scoping) is a
follow-on once the execution model is agreed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Document the false "engine not running" banner root cause and fix as a
docs/solutions learning, and add an "Engine Singleton Lock" entry to
CONCEPTS.md: a failed per-machine lock acquisition is proof an engine is
running elsewhere, not "no engine."
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolve conflicts from main's analytics schema additions (plugin
activations, per-model token buckets) against the PR's contract-assertion
type column:
- db.ts: renumber behavioral-verification migration 124 -> 126, bump
SCHEMA_VERSION to 126 so it follows main's migrations 124/125
- core/roadmap tests: adopt main's SCHEMA_VERSION-constant assertions
instead of stale literal 124
- test-quarantine.json: keep all four quarantine entries from both sides
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Document the test-changed shared-infra catch-all trap (gate mode replaces
affected-package coverage instead of augmenting it) under docs/solutions/,
and add an "Affected-package test selection" concept to CONCEPTS.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Widens the stranded-done recovery branch so a reaped task-less validating/done
feature is re-driven to a terminal verdict instead of stalling its slice forever
(closes the reaper->slice-deadlock P0). Adds a Surface Enumeration + adversarial
re-drive reliability suite (git-clean, no duplicate Fix Features, terminal
verdict, no deadlock) gating release. Updates missions docs + CONCEPTS for the
default-to-fail posture, non-mutating verification, and inconclusive verdict.
Adds changeset.
Turn on the workflow rollout flags by default and update docs/tests for the new opt-out behavior.
- default workflowColumns, workflowGraphExecutor, workflowInterpreterDualObserve, and workflowInterpreterAuthoritative to enabled in global settings
- update workflow docs and concepts to describe explicit flag-off overrides instead of default-off rollout gating
- remove redundant demo/test setup that manually enabled workflow columns and keep characterization coverage for both enabled and disabled states
- add a changeset for the published CLI package documenting the default-on workflow rollout
Files changed:
.changeset/fn-6126-workflow-flags-default-on.md | 5 +++++
CONCEPTS.md | 4 ++--
demo/seed.ts | 1 -
docs/workflow-steps.md | 10 +++++-----
packages/core/src/__tests__/move-task-characterization.test.ts | 4 +---
packages/core/src/settings-schema.ts | 7 ++++++-
packages/core/src/types.ts | 4 +++-
packages/core/src/workflow-columns-settings.ts | 4 ++--
8 files changed, 24 insertions(+), 15 deletions(-)
Fusion-Task-Id: FN-6126
Fusion-Task-Lineage: 334283a6-e80a-42d0-bf66-68f88a12e287
Adds the requirements brainstorm and implementation plan for replacing
fusion's split PR machinery with a first-class PR entity whose lifecycle
is expressed as workflow-graph nodes (pr-create, pr-respond, pr-merge),
plus CONCEPTS.md entries for the PR entity and review-response loop.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
