3 changed files with 241 additions and 0 deletions
@@ -34,12 +34,54 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
  PR–issue label synchronization. The `issue-state-updater` syncs PR state labels whenever
  issue states change.

+- **Comprehensive Worker Tracking System**: All 16 supervisors now provide detailed
+  visibility into worker activities and health. Enhanced `product-builder`,
+  `implementation-orchestrator`, `continuous-pr-reviewer`, and `uat-tester` with
+  detailed session monitoring via the OpenCode API. Added actual cycle-time calculation
+  using timestamps, stale worker detection and restart, and proper tracking issue
+  lifecycle (delete previous, create new each cycle). Tracking extended to previously
+  uncovered supervisors: `architect`, `timeline-updater`, `docs-writer`,
+  `architecture-guard`.
+
+- **Centralized Automation Tracking Manager**: New `automation-tracking-manager`
+  subagent acts as the single source of truth for all tracking operations. Migrated
+  7 key agents (`system-watchdog`, `implementation-orchestrator`, `timeline-updater`,
+  `project-owner`, `product-builder`, `backlog-groomer`, and others) to use the
+  centralized manager. Fixes cycle-skipping and duplicate-issue bugs; ensures
+  sequential cycle numbers persist across agent restarts.
+
+- **Plan Action Argument Upsert**: `PlanLifecycleService` now upserts action arguments
+  during `plan use` to avoid `UNIQUE` constraint violations when reusing actions.
+  Includes batch-delete update with identity-map eviction, invariants unique constraint,
+  and an Alembic migration. (#4174)
+
 ### Changed

 - **Automation Tracking Format**: All automation tracking issues now use a standardized
  header format with mandatory `Reporting Interval: <interval> (Next report expected: <ts>)`
  declarations, enabling precise staleness detection.

+- **Product-Builder Tracking Migration**: `product-builder` now creates individual
+  per-cycle tracking issues (prefix `AUTO-PROD-BLDR`) instead of a long-running shared
+  session state issue. Each cycle closes the previous tracking issue and creates a fresh
+  one, providing better isolation and traceability.
+
+- **Implementation Orchestrator Scaling**: Scaled to 32 parallel workers. Reduced
+  dispatch loop sleep from 10s to 2s, simplified worker verification, reduced retry
+  delays from 15s to 2s, and reduced idle sleep from 60s to 10s for dramatically
+  faster throughput.
+
+### Fixed
+
+- **CI Lint**: Resolved 51 ruff violations in `scripts/validate_automation_tracking.py`
+  (import ordering, deprecated `typing` generics, unused imports, line-length, whitespace).
+- **CI Integration Tests**: Removed stale `tdd_expected_fail` tag from
+  `robot/coverage_threshold.robot` — the underlying bug (issue #4305) is resolved and
+  the tag was inverting a passing test to a failure. (#5266)
+- **Orchestrator Worker Dispatch**: Fixed `verify_worker_started()` to handle the dict
+  response format from the OpenCode API `/session/status` endpoint instead of an array.
+  Workers now dispatch and verify correctly, preventing incorrect session deletion.
+
 ---

 ## [3.8.0] — 2026-04-05
@@ -44,6 +44,14 @@ For emergency announcements or important messages:
 | system-watchdog | `AUTO-WATCHDOG` | `[AUTO-WATCHDOG] System Health (Cycle 8)` |
 | backlog-groomer | `AUTO-GROOMER` | `[AUTO-GROOMER] Grooming Report (Cycle 23)` |
 | human-liaison | `AUTO-LIAISON` | `[AUTO-LIAISON] Status Update (Cycle 67)` |
+| product-builder | `AUTO-PROD-BLDR` | `[AUTO-PROD-BLDR] Build Session (Cycle 5)` |
+| architect | `AUTO-ARCH` | `[AUTO-ARCH] Architecture Report (Cycle 3)` |
+| timeline-updater | `AUTO-TIMELINE` | `[AUTO-TIMELINE] Timeline Update (Cycle 12)` |
+| docs-writer | `AUTO-DOCS` | `[AUTO-DOCS] Documentation Report (Cycle 7)` |
+| architecture-guard | `AUTO-ARCH-GUARD` | `[AUTO-ARCH-GUARD] Guard Report (Cycle 9)` |
+| continuous-pr-reviewer | `AUTO-PR-REVIEW` | `[AUTO-PR-REVIEW] Review Status (Cycle 4)` |
+| uat-tester | `AUTO-UAT` | `[AUTO-UAT] UAT Status (Cycle 6)` |
+| project-owner | `AUTO-PROJ-OWN` | `[AUTO-PROJ-OWN] Owner Status (Cycle 11)` |

 ## Required Labels

@@ -74,6 +82,14 @@ This enables automated health monitoring by the system-watchdog to detect stalle
 | human-liaison | Status Update | Every 20 minutes (10 cycles) | Human activity monitoring |
 | system-watchdog | Health Report | Every 30 minutes (6 cycles) | System-wide health check |
 | session-persister | Checkpoint | Event-driven (variable) | After significant state changes |
+| product-builder | Build Session | Every 10 cycles (~variable timing) | Full build session status |
+| architect | Architecture Report | Every 10 cycles (~variable timing) | Architecture supervision status |
+| timeline-updater | Timeline Update | Every 10 cycles (~variable timing) | Timeline maintenance status |
+| docs-writer | Documentation Report | Every 10 cycles (~3.3 hours) | Documentation update status |
+| architecture-guard | Guard Report | Every 10 cycles (~variable timing) | Codebase coherence check |
+| continuous-pr-reviewer | Review Status | Every 10 cycles (~variable timing) | PR review pool status |
+| uat-tester | UAT Status | Every 10 cycles (~variable timing) | UAT testing progress |
+| project-owner | Owner Status | Every 10 cycles (~variable timing) | Project ownership decisions |

 ### Automated Health Monitoring

@@ -267,6 +283,14 @@ label:"Automation Tracking" [AUTO-IMP-POOL] in:title
 label:"Automation Tracking" [AUTO-WATCHDOG] in:title
 label:"Automation Tracking" [AUTO-GROOMER] in:title
 label:"Automation Tracking" [AUTO-LIAISON] in:title
+label:"Automation Tracking" [AUTO-PROD-BLDR] in:title
+label:"Automation Tracking" [AUTO-ARCH] in:title
+label:"Automation Tracking" [AUTO-TIMELINE] in:title
+label:"Automation Tracking" [AUTO-DOCS] in:title
+label:"Automation Tracking" [AUTO-ARCH-GUARD] in:title
+label:"Automation Tracking" [AUTO-PR-REVIEW] in:title
+label:"Automation Tracking" [AUTO-UAT] in:title
+label:"Automation Tracking" [AUTO-PROJ-OWN] in:title
 ```

 **Recent tracking issues (last 24 hours):**
@@ -0,0 +1,175 @@
+# Invariant Reconciliation Module
+
+**Package:** `cleveragents.actor.reconciliation`
+**Introduced:** v3.8.0
+
+The Invariant Reconciliation Actor is a built-in actor that automatically runs at
+every plan phase transition to ensure all active invariants are consistent and
+correctly prioritised before any strategy or execution work begins.
+
+For the invariant data model and scope hierarchy, see
+[`docs/reference/invariants.md`](../reference/invariants.md).
+For the `InvariantService` API, see
+[`docs/api/core.md`](../api/core.md).
+
+---
+
+## Purpose
+
+Invariants are natural-language constraints on plan execution that can be defined
+at four scopes: global, project, action, and plan. When multiple invariants apply
+to the same plan, conflicts can arise — for example, a project-level invariant may
+contradict a plan-level one. The reconciliation actor resolves these conflicts
+deterministically using a precedence chain and records each decision in the audit
+trail.
+
+---
+
+## Automatic Invocation
+
+`PlanLifecycleService` automatically invokes the reconciliation actor at the start
+of three phase transitions:
+
+| Transition | Method |
+|------------|--------|
+| Strategize start | `start_strategize()` |
+| Execute start | `execute_plan()` |
+| Apply start | `apply_plan()` |
+
+If reconciliation fails, the phase transition is **blocked** with
+`ReconciliationBlockedError` and an `INVARIANT_VIOLATED` event is emitted on the
+event bus. The transition cannot proceed until the invariants are corrected.
+
+Post-correction reconciliation runs automatically via a `CORRECTION_APPLIED` event
+subscription (best-effort; does not block correction completion).
+
+---
+
+## Reconciliation Algorithm
+
+The actor follows a six-step algorithm (spec §19440–19600):
+
+1. **Collect** invariants from all four scopes: global, project, action, plan.
+2. **Group** by normalised text (case-insensitive, stripped).
+3. **Detect conflicts** — same text at different scopes, or contradictory constraints
+   that cannot be automatically resolved.
+4. **Resolve** using specificity precedence:
+   ```
+   plan > action > project > global
+   ```
+   Exception: `non_overridable` global invariants always win regardless of scope.
+5. **Record** an `invariant_enforced` decision for each active invariant in the
+   decision service.
+6. **Return** a `ReconciliationResult` containing the reconciled `InvariantSet` and
+   all conflict records.
+
+---
+
+## Key Classes
+
+### `InvariantReconciliationActor`
+
+```python
+from cleveragents.actor.reconciliation import InvariantReconciliationActor
+
+actor = InvariantReconciliationActor(
+    invariant_service=container.invariant_service(),
+    decision_service=container.decision_service(),
+)
+result = actor.run(plan_id="...", project_name="...", action_name="...")
+```
+
+| Method | Description |
+|--------|-------------|
+| `run(plan_id, project_name, action_name) → ReconciliationResult` | Execute reconciliation for the given plan context |
+
+### `ReconciliationResult`
+
+Frozen dataclass returned by `InvariantReconciliationActor.run()`.
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `reconciled_set` | `InvariantSet` | The final effective set of invariants |
+| `conflicts` | `list[ConflictRecord]` | All detected conflicts with resolution details |
+| `enforced_decision_ids` | `list[str]` | ULIDs of `invariant_enforced` decisions recorded |
+
+### `ConflictRecord`
+
+Frozen dataclass describing a single resolved conflict.
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `key` | `str` | Normalised invariant text used for grouping |
+| `winner` | `Invariant` | The invariant that prevailed after resolution |
+| `losers` | `list[Invariant]` | Invariants that were overridden |
+| `reason` | `str` | Human-readable explanation of the resolution |
+
+---
+
+## DI Registration
+
+`InvariantService` is registered as a **Singleton** provider in the DI container:
+
+```python
+from cleveragents.application.container import Container
+
+container = Container()
+invariant_service = container.invariant_service()
+```
+
+Never construct `InvariantService` directly — always resolve it from the container.
+
+---
+
+## Error Handling
+
+| Exception | When raised |
+|-----------|-------------|
+| `ReconciliationBlockedError` | Reconciliation fails; phase transition is blocked |
+
+When `ReconciliationBlockedError` is raised:
+- The `INVARIANT_VIOLATED` event is emitted on the event bus.
+- The phase transition is aborted.
+- The plan remains in its current phase until the invariant conflict is resolved.
+- Once resolved, a `CORRECTION_APPLIED` event triggers a best-effort re-run.
+
+---
+
+## Usage Example
+
+```python
+from cleveragents.application.container import Container
+from cleveragents.actor.reconciliation import InvariantReconciliationActor
+
+container = Container()
+
+actor = InvariantReconciliationActor(
+    invariant_service=container.invariant_service(),
+    decision_service=container.decision_service(),
+)
+
+result = actor.run(
+    plan_id="01HXYZ...",
+    project_name="my-project",
+    action_name="refactor-auth",
+)
+
+# Inspect the reconciled invariant set
+for inv in result.reconciled_set.invariants:
+    print(f"[{inv.scope}] {inv.text}")
+
+# Inspect conflicts
+for conflict in result.conflicts:
+    print(f"Conflict: {conflict.key!r}")
+    print(f"  Winner: [{conflict.winner.scope}] {conflict.winner.text}")
+    print(f"  Reason: {conflict.reason}")
+```
+
+---
+
+## Related Documentation
+
+- [Invariants reference](../reference/invariants.md) — data model, scope hierarchy, merge semantics
+- [Plan Lifecycle](../architecture.md#plan-lifecycle) — phase transitions and gating
+- [Decision Service](../reference/decision_service.md) — audit trail for enforced decisions
+- [Architecture Overview](../architecture.md#invariant-reconciliation) — system-level context