Enhance the system watchdog with OpenCode Server API session introspection
to read actual supervisor conversations, tool calls, and todo lists.
Upgrade Audit 6 (Zombie Detection) to use message-based analysis instead
of only checking Forgejo activity — reads last 5 messages from each
supervisor session to detect sleep-only patterns, error loops, and
identical repeated tool calls.
Add Audit 11 (Quick Session Spot-Check) running every 5-minute cycle:
scans the 3 most recently active sessions for critical policy violations
including force_merge usage, direct pushes to master, and type:ignore
suppressions in written code.
Add Audit 12 (Deep Session Introspection) running every 30 minutes:
full analysis of all 16 supervisor sessions reading last 10 messages
and todo lists. Detects misbehavior patterns, progress stalls via todo
list analysis, conversation health metrics (error rates, sleep ratios),
context exhaustion signals, and cross-agent conflicts (multiple agents
touching the same PR or issue).
Update action dispatch to handle new finding types: force_merge_detected,
direct_push_to_master, stuck_supervisor, looping_supervisor, high_error_rate,
context_exhaustion, and cross_agent_pr_conflict.
Add ca-system-watchdog (16th supervisor) for continuous system health
monitoring with quality gate auditing, zombie detection, ticket state
reconciliation, and priority enforcement. Add ca-quality-enforcer and
ca-state-reconciler as one-off fix agents dispatched by the watchdog.
Critical fix: remove all force_merge: true usage from ca-pr-self-reviewer
which was bypassing branch protection and allowing PRs to merge with
failing CI. Replace with strict CI-gating merge logic that respects
branch protection rules per CONTRIBUTING.md.
Update product-builder to launch 16 supervisors, strengthen anti-return
language with explicit context hygiene, add tracking ticket lifecycle
management (one open at a time, closed on completion).
Update ca-project-bootstrapper with strict branch protection config
requiring status-check CI context, 2 approvals, and dismiss stale reviews.
Fix label set to match CONTRIBUTING.md exactly.
Update issue-implementor with priority gate enforcing lowest-milestone-first
and critical-bugs-first ordering. Update ca-backlog-groomer with closed
issue state reconciliation, PAT for REST API dependency operations, and
health signaling. Update ca-spec-updater with proactive full-scan mode.
Add health signaling and context self-management to 7 continuous
supervisors to prevent zombie sessions from context exhaustion.
Strengthen state label transitions in ca-pr-self-reviewer, ca-pr-api-creator,
ca-issue-state-updater, and ca-backlog-groomer to ensure closed issues
always have correct terminal state labels.
Add Forgejo PAT and REST API curl templates for dependency link creation
to ca-backlog-groomer and ca-project-owner since the MCP does not support
dependency manipulation.
Add reference documentation for three new TUI features:
- docs/reference/tui_shell_safety.md: Full reference for the shell danger
detection subsystem (DangerousPatternDetector, ShellDangerLevel,
DangerousPattern, DangerousCommandWarning, DEFAULT_PATTERNS registry).
Covers all built-in patterns across CRITICAL/HIGH/MEDIUM/LOW levels,
usage examples, and custom pattern extension.
- docs/reference/tui_permission_question.md: Full reference for the inline
PermissionQuestionWidget (issue #997). Documents InlinePermissionQuestion,
PermissionRequestType, PermissionDecision, render_permission_question(),
PermissionDecisionEvent, and PermissionQuestionWidget with key bindings
and usage examples.
- docs/reference/tui.md: Extended with First-Run Experience section
(ActorSelectionOverlay, first_run helpers), Inline Permission Questions
section, shell danger detection note in Shell Mode, updated module table,
and links to new reference pages.
Added critical warning block and step-by-step checklist to product-builder.md
to ensure the agent always follows the correct workflow:
1. Launch 15 supervisors via curl to http://localhost:4096/session/:id/prompt_async
2. Monitor them with bash sleep loop (60 seconds between checks)
3. Re-launch any that exit
Key changes:
- ⚠️ Critical execution model warning at top (what to do / what NOT to do)
- 📊 Execution flow diagram showing all phases
- ✅ Step-by-step Phase C checklist (C.1: Pre-flight, C.2: Launch, C.3: Monitor)
- 🔒 Clearer permission blocks with explicit bans on implementation agents
- 📝 Comments explaining why supervisors use curl not Task tool
This prevents the product-builder from trying to implement issues directly,
which is the supervisors' job. Product-builder is a process supervisor (like
systemd), not a worker.
This TDD test captures the buggy behavior where `NamespacedName.validate_namespace()`
and `validate_name()` accept names starting with digits, violating the spec requirement
that namespace and name components must start with a letter (consistent with
`_BARE_NAME_RE` in project.py).
Three failing scenarios demonstrate the bug:
1. parse() accepting namespace starting with digit ("123abc/my-action")
2. constructor accepting name starting with digit (local/"123-action")
3. constructor accepting namespace starting with digit ("999org"/valid-name)
Tagged with @tdd_expected_fail per Bug Fix Workflow.
Implements #2145
Blocks #2147
Both slow_integration_tests and e2e_tests sessions require a database
(via setup_workspace() in helper scripts) but were not using the
pre-migrated template DB optimization already present in unit_tests,
integration_tests, and coverage_report.
Changes:
- slow_integration_tests: add _create_template_db() call, set
CLEVERAGENTS_TEMPLATE_DB env var, upgrade from robot to pabot for
parallel execution, add NO_COLOR/PYTHONPATH/PATH/compileall setup,
add --include slow / --exclude discovery/code_blocks/wip/E2E/tdd_fixture
tag filters, and update docstring.
- e2e_tests: add _create_template_db() call and set
CLEVERAGENTS_TEMPLATE_DB env var. The existing setup_workspace()
in helper_e2e_common.py already checks this env var and copies the
template instead of running 25+ Alembic migrations.
No changes to test helper files are required since setup_workspace()
already implements the fast-path copy logic when CLEVERAGENTS_TEMPLATE_DB
is set.
ISSUES CLOSED: #2334
Agent evolver identified a critical systematic pattern:
- Pattern: The backlog groomer was closing PRs as 'duplicates' of their
linked tracking issues. A PR containing 'Closes #N' was being treated
as a duplicate of issue #N, when it is actually the implementation
delivery vehicle for that issue.
- Evidence: At least 12 PRs were incorrectly closed (#1219, #1236, #1247,
#1269, #1267, #953, #1198, #1220, #1237, #1238, #1246, #1248) — all
with the same 'Duplicate Detected' comment pattern from groomer-1.
- Fix: Added explicit instructions to skip PRs during duplicate detection,
added a guard in the analysis loop pseudocode, and added a rule in the
Important Rules section.
This change requires human approval before taking effect.
ISSUES CLOSED: #2180
Add PermissionQuestionWidget API documentation to docs/api/tui.md including
method table, key bindings, PermissionDecisionEvent dataclass, and
render_permission_question() helper reference. Add corresponding CHANGELOG
entry under [Unreleased] Added section.
Refs: #997
Implement inline permission question widget for quick allow/reject
decisions within the conversation stream with file diff context.
ISSUES CLOSED: #997
Align Unicode box-drawing blocks and related tables in specification.md,
ADR-044/045/046, and reference pages for consistent MkDocs rendering.
ISSUES CLOSED: #1171
Consolidate duplicate Added/Fixed headings in [Unreleased] section into single canonical sections per Keep a Changelog format. Add new entries for DomainBaseModel (#1941) and TDD bug-capture test (#1094).
Co-authored-by: Jeffrey Phillips Freeman <the@jeffreyfreeman.me>
Co-committed-by: Jeffrey Phillips Freeman <the@jeffreyfreeman.me>
Add a new Behave TDD regression scenario that persists corrupt automation-profile JSON and verifies repository reads do not leak raw JSONDecodeError. The scenario is tagged with @tdd_bug, @tdd_bug_989, and @tdd_expected_fail so it currently inverts the intentional assertion failure and will require tag removal when bug #989 is fixed.\n\nAlso stabilize an unrelated integration fixture in robot/resource_dag.robot by sharing a single SQLAlchemy session in inline scripts; this removes nondeterministic visibility of flushed resource-type rows and keeps required nox integration quality gates deterministic for this branch.\n\nISSUES CLOSED: #1094
Agent evolver identified a systematic pattern:
- Pattern: PR stale/conflict cascade
- Evidence: 11+ PRs were approved but closed without merge due to
conflicts. PRs #1248, #1247, #1237, #1236, #1220, #1219, #1238,
#1246, #1269 were all bulk-closed as stale. Reviewer notes on
#1248, #1220, #1219, #1252 explicitly mention 'merge blocked by
conflicts'. With 16 parallel workers, master moves fast and branches
created minutes earlier are already behind by the time PRs are created.
- Fix: Add a rebase-onto-latest-master step (Phase 3, Step 3.0) in
ca-issue-worker before committing and creating the PR. This ensures
the branch is current when the PR is opened, dramatically reducing
the chance of merge conflicts when the reviewer processes it.
This change requires human approval before taking effect.
Agent evolver identified a systematic pattern:
- Pattern: UAT tester filing bugs for features already being implemented
- Evidence: 25+ UAT bugs filed for TUI MainScreen features (#1329-#1355)
that already had open implementation PRs (#1219, #1236, #1237, #1238,
#1246, #1247, #1248, etc.). The tester reported 'missing sidebar',
'missing tab bar', 'missing escape navigation' etc. while PRs
implementing these exact features were open and under review.
- Fix: Add step 4 to duplicate avoidance requiring the tester to check
for open PRs before filing 'missing feature' bugs.
This change requires human approval before taking effect.
- Add missing 'nox -s format -- --check' step (parity with ci.yml)
- Add NOX_DEFAULT_VENV_BACKEND: uv to global env and each nox step
- Fix quality gates script invocation (was using invalid nox session '3.13')
- Fix report artifact paths to match actual nox session output locations
(build/coverage.json and build/bandit-report.json instead of build/reports/)
- Add mkdir for build/reports before writing quality-trend.json
ISSUES CLOSED: #1537
BREAKING CHANGE: Supervisors can no longer use Task tool to launch workers
Major refactor of the permission model for product-builder and all 15
continuous supervisors to enforce strict separation: supervisors MUST use
curl/prompt_async via bash to launch workers, and CANNOT use the Task tool.
Key Changes:
1. Product-Builder Permissions (product-builder.md):
- Removed ALL Task permissions for supervisors (previously had 17)
- Kept Task permissions ONLY for 7 one-shot agents:
ca-project-bootstrapper, ca-ref-reader, ca-issue-finder,
ca-session-persister, ca-product-verifier, ca-milestone-reviewer,
ca-final-reporter
- Restricted bash to: echo, curl, sleep, jq only
- Removed Phase B (Architecture) and Phase C.1 (Planning)
- Updated to launch 15 supervisors (up from 13)
2. New Continuous Supervisors:
- ca-architect: Converted from one-shot to continuous supervisor
Monitors for spec needs, new milestones, ambiguities
- ca-epic-planner: Converted from one-shot to continuous supervisor
Monitors for milestones without issues, incomplete epics
3. All 15 Supervisors - Standardized Permissions:
- Removed ALL Task permissions for launching workers
- Workers MUST be launched via curl to OpenCode Server prompt_async API
- Added 'jq *' for JSON parsing (replacing python3)
- Restricted bash to specific commands only (deny all, allow specific)
- Git commands restricted to specific operations (clone*, fetch*, etc.)
- Directory operations (cd, mkdir, rm -rf) only where needed
4. Supervisor-Specific Updates:
- issue-implementor: Removed ca-issue-worker task permission
- ca-continuous-pr-reviewer: Added git + directory ops, removed worker tasks
- ca-uat-tester: Added read-only file/git commands, removed self-dispatch
- ca-bug-hunter: Restricted git to read-only, removed self-dispatch
- ca-test-infra-improver: Added read-only commands, removed self-dispatch
- ca-human-liaison: Removed ca-epic-planner/ca-architect task permissions
- ca-agent-evolver: Added git + directory operations
- ca-architecture-guard: Added read-only + git clone operations
- ca-spec-updater: Added git + directory operations
- ca-backlog-groomer: Removed ca-epic-planner task permission
- ca-docs-writer: Added git + directory operations
- ca-timeline-updater: Added git + directory operations
- ca-project-owner: Minimal permissions (curl, jq, sleep only)
Impact:
- Proper separation of concerns: supervisors orchestrate, workers execute
- No possibility of supervisors blocking on Task tool calls
- True fire-and-forget worker launching via prompt_async
- Consistent permission model across all 15 supervisors
- Maximum parallelism with proper isolation
Architecture now enforces: Product-builder → 15 supervisors → N workers
All launched via curl/prompt_async, NO Task tool for supervisors.
Introduce DomainBaseModel in src/cleveragents/domain/models/base.py that
defines the single shared model_config (str_strip_whitespace, validate_assignment,
arbitrary_types_allowed=False, populate_by_name, use_enum_values) previously
duplicated verbatim across five domain model files.
Update 14 classes across five files to inherit from DomainBaseModel instead
of pydantic.BaseModel directly, removing all inline model_config duplication:
- aimodelscredentials/ai_models_credentials.py (ModelProviderOption)
- aimodelserrors/ai_models_errors.py (ModelError, FallbackResult)
- aimodelsproviders/ai_models_providers.py (ModelProviderExtraAuthVars,
ModelProviderConfigSchema)
- auth/auth.py (AuthHeader, TrialPlansExceededError, TrialMessagesExceededError,
BillingError, ApiError, ClientAccount, ClientAuth)
- planconfig/plan_config.py (PlanConfig, ConfigSetting)
Pure structural refactor — no behavioral changes. Models with different
configurations (acms, aimodels_custom, etc.) are left untouched.
Add BDD feature (22 scenarios) and Robot integration tests (8 test cases)
verifying inheritance, config correctness, and no-duplication invariants.
ISSUES CLOSED: #1941
Centralize E2E initialization in common suite setup so DB-dependent CLI commands no longer rely on per-suite or per-test init workarounds. This also sanitizes suite-home names to prevent invalid path-derived initialization failures in isolated Robot runs.
ISSUES CLOSED: #1023
Add explicit aiohttp>=3.13.4 dependency constraint to pyproject.toml to remediate CVE-2026-34515, a high-severity open redirect vulnerability. The lockfile already resolves aiohttp to 3.13.5 which satisfies the constraint.
Closes#1544
freemo
eugen.thaci
brent.edwards