AIPass/STATUS.md

# AIPass — System Status

> Auto-generated by `drone @prax status sync`. Do not edit manually.

**Last sync:** 2026-03-31 16:55  
**Summary:** 9 operational | 0 in-progress | 0 not started

---

<details><summary><strong>@ai_mail</strong> — Operational (2026-03-17 (session 14))</summary>

# @ai_mail

> Inter-branch email, dispatch, wake, bounce

**State:** Operational
**Last update:** 2026-03-17 (session 14)

## Milestones
- Send/receive/reply/close lifecycle
- Dispatch+wake pattern
- Sender identity fix (AIPASS_BRANCH_NAME env var)
- email.py split (840 to 420 lines)
- notify-send to dbus notifications
- mailbox_path bug fixed (relative→absolute in get_user_by_email, get_all_users)
- Health audit: 7 dead handlers archived, branch cleaned
- Seedgo compliance: 93% → 99% (json_structure 100%, introspection 100%)

## Current Work
- No active tasks. Inbox clear.

## Known Issues
- _find_repo_root() duplicated 9 times across handlers (consolidation candidate)
- get_all_branches() has 2 implementations (delivery.py vs registry/read.py)
- Registry shows 6 pytest test branches with /tmp paths (test pollution)
- Readme standard at 83% (only non-100% standard remaining)

## Architecture Notes
- trigger branch owns error_detected events; ai_mail provides delivery only
- extensions/, plugins/, json_templates/, json/ shim, persistence/ = repeatable skeleton (don't archive)
- Dead code was inherited from DevPass migration, not accumulated in AIPass
- .seedgo/bypass.json: email.py bypassed for introspection (inbox/sent/contacts need no args), json_utils/json_handler.py bypassed for json_structure (can't import itself)

</details>

<details><summary><strong>@api</strong> — Operational | **Seedgo:** 98% (Log_Structure 55% — known, separate fix) (2026-03-17)</summary>

# @api

> Centralized external API gateway — authenticated service clients for all external APIs

**State:** Operational | **Seedgo:** 98% (Log_Structure 55% — known, separate fix)
**Last update:** 2026-03-17

## Milestones
- OpenRouter client (get_response, models, test)
- Key management from ~/.secrets/aipass/
- Google provider module (Drive, Calendar, any Google API)
- Seedgo compliance: json_handler, introspection, diagnostics (PR #69 merged)

## Current Work
- Backup migration to use our Google module (pending backup)
- Unit tests — emailed @ai_mail for advice on test setup

## Known Issues
- Log_Structure 55% — seedgo working on this standard separately
- Seedgo introspection standard doesn't account for standalone commands (workaround in place)

## Recent (Session 4, 2026-03-17)
- Seedgo compliance: 88% → 98% (PR #69)
- json_handler wired in all 13 handlers
- Introspection gates in all 4 modules (with standalone command routing)
- Pyright directives for optional deps (3 files)
- Found + fixed bug: introspection gates breaking standalone commands
- git reset mishap — recovered, lesson learned

</details>

<details><summary><strong>@backup</strong> — Operational — seedgo 94% (23 files, 34 standards) (2026-03-24 (session 13))</summary>

# @backup

> Multi-mode backup — snapshot, versioned, Google Drive

**State:** Operational — seedgo 94% (23 files, 34 standards)
**Last update:** 2026-03-24 (session 13)

## Working Commands
- `drone @backup snapshot [--dry-run]` — full copy backup
- `drone @backup versioned [--dry-run]` — timestamped incremental
- `drone @backup all` — full cycle (Drive step will fail until @api migration)

## Active Modules
- backup_core (snapshot, versioned, all)
- google_drive_sync (drive-test, drive-sync, drive-stats, drive-clear-tracker)

## Seedgo Scores
- 94% overall
- Deferred: Deep_Nesting 82%, Test_Coverage 0%
- All other standards 91-100%

## Recently Completed
- Session 13: json_handler.py load_template→inline defaults. Json_Structure 100%.
- Session 12: Silent catch — 49 fixes across 12 files. 47%→91%.
- Session 11: DPLAN-0034 — archived 8 dead files, consolidated backup_data/

## Pending
- @api dispatch: Migrate Google Drive auth to API branch (email c19c8d0f — parked)
- Drive command return-value bug: handle_command returns False on failure instead of True
- Versioned backup needs initial seed run (stale data from old runs)

</details>

<details><summary><strong>@cli</strong> — Operational (2026-03-24)</summary>

# @cli

> Display service, Rich formatting for all branches

**State:** Operational
**Last update:** 2026-03-24
**Seedgo:** 97% (32/34 at 100%, Test_Coverage 40%, Log_Structure 75% prax bug)

## Milestones
- Console singleton
- Header/success/error/warning formatters
- Shared across all branches
- 100% seedgo compliance (2026-03-17)

## Current Work
- [x] FPLAN-0041: Migrated init_project.py from devpulse (2026-03-14)
  - handler: `apps/handlers/init/bootstrap.py`
  - module: `apps/modules/init_project.py`
  - wired: `drone @cli aipass init [target] [name]`
- [x] Seedgo 100% compliance (2026-03-17)
  - Created dropbox/, logs/ directories
  - Cleaned json_handler (removed prax dep)
  - Wired json_handler into display.py, templates.py, init_project.py
  - Bypassed bootstrap.py (pure Python by design)
  - Fixed introspection no-args gate (AST pattern: `not args`)
  - Updated README with init commands + architecture

- [x] Seedgo certification cleanup (2026-03-23)
  - json_handler: inline _create_default() replaces load_template()
  - Architecture: 5 template READMEs created
  - Naming: _trigger → _TRIGGER, __all__ bypassed
  - Unused functions removed (increment_counter, update_data_metrics)
  - 9 bypasses for circular import constraints
  - Emailed prax about log_structure branch detection

- [x] Unit test coverage (2026-03-24)
  - 108 tests, 4 files, 5/5 modules covered
  - 3-round agent audit: 91→108 tests, quality 8.5/10
  - Fixed pytest.ini addopts comments bug
  - Test_Coverage 0%→40%, overall 96%→97%

## Known Issues
- Log_Structure 75% — prax branch detection fails for CLI, logs land as unknown_branch_*. Prax investigating (2026-03-23).
- Test_Coverage 40% — 108 tests pass, seedgo wants higher % (threshold unclear)

</details>

<details><summary><strong>@commons</strong> — Operational — Seedgo 99% (2026-03-18)</summary>

# @commons

> Social network for branches — posts, rooms, artifacts

**State:** Operational — Seedgo 99%
**Last update:** 2026-03-18

## Seedgo Compliance (99%)

23/24 categories at 100%. Only Readme at 83% (minor tree check).

## Session 4 Summary (2026-03-17/18)

### Prax Log Routing Fix
- Stray `src/aipass/commons/` directory spotted by Patrick
- Root cause: prax `detect_branch_from_path()` didn't handle commons' non-standard path
- Dispatched to prax, who fixed 3 files. Verified: logs now write to `src/commons/logs/`

### 5-Branch Social Stress Test
- Tested with commons, drone, spawn, flow, memory
- 40+ commands: posts, comments, votes, rooms, artifacts, explore, search
- Identity detection via CWD: bulletproof across all 5 branches

### 3 Integration Gaps Fixed (DPLAN-0018, FPLAN-0097)
All same pattern: helper functions existed from Dev-Pass port but were never wired into production code.

1. **FTS5 search** — `sync_post_to_fts()`/`sync_comment_to_fts()` never called from post_ops/comment_ops. Added calls + `backfill_fts_index()` (indexed 6 posts + 17 comments)
2. **Visitor tracking** — No `room_visits` table. Added table to schema, `record_visit()` to space_ops, recording in `_cmd_enter()`. Updated `get_visitors_data()`.
3. **Post/comment counts** — `increment_post_count()`/`increment_comment_count()` never called. Catchup nudge showed wrong "haven't posted" tip. Wired into post_ops/comment_ops.

### Files Modified
- `apps/handlers/posts/post_ops.py` — FTS sync + post count
- `apps/handlers/comments/comment_ops.py` — FTS sync + comment count
- `apps/handlers/search/search_queries.py` — backfill_fts_index()
- `apps/handlers/rooms/space_ops.py` — record_visit() + updated visitors query
- `apps/modules/space_module.py` — visit recording in enter
- `apps/handlers/database/schema.sql` — room_visits table
- `tools/backfill_fts.py` — one-time FTS backfill script

## Session 5: Module Rename (2026-03-18)

Removed `_module` suffix from all 21 module files per seedgo naming standard ("Path = Context, Name = Action"). DPLAN-0019 → FPLAN-0099 master plan.

- 21 agents deployed in 2 batches (10 + 11), running in parallel
- Each agent: renamed .py file, updated header + introspection string, renamed JSON tracking files
- Orchestrator: updated commons.py static import, .seedgo/bypass.json (9 entries)
- Old modules archived to `apps/modules/.archive/`
- System verified: all commands working, seedgo 99%

## Known Issues
- Readme 83% — likely missing dropbox/ in directory tree
- Pyright warnings (unused logger imports) — pre-existing, cosmetic

## Architecture
- 86+ Python files, 21 modules, 19 handler domains
- SQLite + WAL + FTS5, 17 tables (added room_visits)
- Lives at src/commons/ (standalone, outside aipass namespace)
- Imports own code as `from commons.apps.*`
- Uses aipass services: prax (logging), cli (display)

</details>

<details><summary><strong>@daemon</strong> — Operational (2026-03-23)</summary>

# @daemon

> Autonomous scheduled wake-ups

**State:** Operational
**Last update:** 2026-03-23
**Seedgo audit:** 94%

## Session 6 Summary
- Dispatch from devpulse: Fix Json_Structure and Introspection violations
- Json_Structure: replaced load_template() file-based approach with inline _default_template()
- Introspection: split combined no-args/--help gate into separate if-blocks
- Json_Structure 100%, Introspection 100%, Silent_Catch 100%

## Audit Scorecard (34 standards)
- 100%: Cli, Cli_Flags, Commented_Logger, Dead_Code, Debug_Print, Encapsulation, Error_Handling, Handlers, Hardcoded_Key, Introspection, Json_Structure, Log_Handler, Log_Level, Log_Structure, Log_Visibility, Meta, Modules, Permission_Flags, Readme, Shebang, Silent_Catch, Stderr_Routing, Testing, Todo, Trigger, Diagnostics
- 90%+: Architecture (90%), Help_Text (90%), Imports (96%), Unused_Function (96%)
- Below threshold: Deep_Nesting (50%), Documentation (87%), Naming (83%), Test_Coverage (12%)

## Known Issues
- Deep_Nesting in scheduler_cron.py, actions.py, schedule.py (refactoring needed)
- Test_Coverage at 12% (1/8 modules covered)

</details>

<details><summary><strong>@devpulse</strong> — Operational (2026-03-30)</summary>

# @devpulse

> Orchestration hub — coordinates via dispatch + agents (no apps/)

**State:** Operational
**Last update:** 2026-03-30

## Milestones
- 58 sessions of system coordination
- 20 diagnostic tools built, reviewed, accepted — Phase 1 COMPLETE
- 10 tools integrated into seedgo audit (32 total checks) — DPLAN-0041 COMPLETE
- **100% seedgo compliance across ALL 15 branches, ALL 32 standards — S58 night shift**
- Checker consolidation: testing→error_handling, test_coverage merged into test_quality v4.0 (S57)
- API branch compliance: 90% → 95% → 100% via multi-wave dispatch
- System-wide silent catch wave: 93% avg compliance across 14 branches (DPLAN-0052)
- 13 branches dispatched in single session — all completed silent catch fixes
- Seedgo cold wake to devpulse confirmed working
- TTS Listen sections added to all flow templates
- First autonomous dispatch cycle: 4 branches dispatched, all returned with verified fixes
- docs.local/ pattern established across all 15 branches
- Branch audit DPLANs: 0032-0036 created, dispatches completed for commons/ai_mail/spawn/backup

## Current Work
- **DPLAN-0052**: System-wide silent catch wave. 13 branches dispatched, all completed. System avg 93%. Skills bounced once, retried. Bypass entries added for spawn (7) + commons (9). Nesting deferred.
- **DPLAN-0049**: API branch seedgo compliance. API at 95%. Remaining: test_coverage, 19 commented logger.error() calls.
- **DPLAN-0031**: Drone audit. Not started beyond silent catch fix.
- **DPLAN-0033**: Commons audit. Silent catch 29%→100%. Orphan cleanup remaining.
- **DPLAN-0034**: Backup audit. Silent catch fixed. Remaining: scope/filtering, branding.
- **DPLAN-0035**: Spawn audit. Silent catch 45%→100%. Bypass in. Remaining: refactorable nesting (5 functions).
- **DPLAN-0036**: AI Mail audit. Silent catch 48%→100%. Remaining: refactorable nesting (14 functions).

## Completed DPLANs
- **DPLAN-0030**: Diagnostic tooling — Phase 1 COMPLETE. All 20 tools reviewed + accepted. Closed S46.
- **DPLAN-0041**: Seedgo checker integration — COMPLETE. 10 checkers built, verified on API. Closed S46.
- **DPLAN-0040**: 3-tier logging revision — Standard updated, API loggers uncommented. Remaining: uncomment across other branches (added to each branch audit DPLAN). Closed S46.
- **DPLAN-0032**: Local prompt template — template drafted. Rollout to stub branches tracked in STATUS todos.

## Cross-Branch Audit Tasks (apply to all branch audits)
- [ ] Uncomment handler logger calls (per DPLAN-0040 — standard now allows info/warning in handlers). API done (PR #109). Other 14 branches pending.
- [ ] Run `drone @seedgo audit aipass @branch` on each branch — first pass with new 34-check audit
- [ ] Add .seedgo/bypass.json entries for justified findings

## Known Issues
- **Seedgo audit display bug**: checkers scoring 75-99% show no violation details. Root cause: audit_display.py doesn't handle branch_level checkers. Affects: readme, todo, unused_function, commented_logger, test_coverage. → DPLAN-0049 standards issues log.
- **Seedgo bypass UX**: silent failure when lines field used but checker passes line=None. Needs: bypass add command, bypass verify command. → DPLAN-0049 standards issues log.
- **.seedgo/ gitignored**: should be unignored (bypass is system-level config). Patrick decided.
- **prax dashboard CLI routing**: argparse eats flags before module.
- **ruff CI**: 474 lint violations. Backlog.
- **wake.py no --model flag**: dispatched branches use CLI default model.
- **Claude Code scroll bug**: terminal auto-scrolls during output. Using prax monitor as workaround.
- **Memory bank venv missing**: `MEMORY_BANK/.venv/bin/python3` doesn't exist. Vectorization fails for deleted emails. Shows warning every time ai_mail archives. Needs: either rebuild venv or fix the vectorization path.
- **VS Code reload dumps terminal init into Claude Code input**: When VS Code reloads, terminal initialization commands leak into the Claude Code chat input. Reproducible, annoying. Root cause is VS Code behavior. Workaround: move cursor before reload. Could potentially fix with Claude Code extension or VS Code settings. (was DPLAN-0081, closed — doesn't need a full plan)

## Todos
- [ ] **Devpulse branch audit** — use `drone @git pr` for all commits/PRs instead of raw git. Full access stays, but PR workflow goes through drone like every other branch.
- [ ] Unignore .seedgo/ in .gitignore — system-level config needs to travel with PRs
- [ ] Local prompt rollout — dispatch 5 stub branches (DPLAN-0032)
- [ ] README generator relocation — extract from seedgo to shared utility
- [ ] Ruff cleanup FPLAN
- [ ] Add --model support to wake.py
- [x] Create DPLANs for remaining branches — DONE S59 (0074-cli, 0075-trigger, 0076-daemon, 0077-skills)
- [ ] Devpulse wake protection — only seedgo should be able to wake devpulse
- [ ] DPLAN-003 Phase 3: `drone aipass help` module

## Recently Completed
- Session 68: Night shift — FPLAN-0161 executed. Log scanner 981/1805/2000 → 0/0/0. Test log isolation via AIPASS_TEST_LOG_DIR env var (14 conftest + prax load.py + trigger json_handler.py). 4 audit fixes (api x2, trigger x2). 3,425 tests, 0 failures. PR #162. (2026-03-31)
- Session 67: Plan cleanup + APLAN template. Closed 8 devpulse root plans. Created APLAN template in flow (audit_plans/default.md). 15 branch audits reformatted to APLAN standard with Quick Status, proper checkboxes, owner-split todos. System baseline: 110 open, 104 resolved, 4 GREEN / 11 YELLOW. (2026-03-31)
- Session 60: Prax queue spam eliminated (144k/4hrs). 9 stale plans closed. Flow close bug dispatched. TTS summaries added to all 15 branch audits (pure plaintext). 15-agent verification wave fact-checked all DPLANs against live seedgo+pytest. System: 2,905 tests, 100% seedgo. DPLAN-0079 harness alignment reviewed. (2026-03-29)
- Session 59: Full system walkthrough + fixes. 11 agents audited all 15 branches (2,378 tests). Docker install verified. README rewritten + HERALD.md created. Dispatched 8 branches for fixes (stale refs, template, dedup, queue spam). 5 new DPLANs. PR #140 merged. (2026-03-28)
- Session 58: NIGHT SHIFT — 100% seedgo compliance across ALL 15 branches, ALL 32 standards. 7 agents fixed: commons (68→100% test_quality, bypasses for unused/arch/nesting), daemon (arch bypass for plugins), flow (watchdog bypasses), memory (88→100% test_quality), prax (public API bypasses), skills (README), spawn (empty_file test). (2026-03-28)
- Session 57: Checker consolidation (testing→error_handling, test_coverage→test_quality v4.0). PRs #132-135. 14-branch compliance dispatch. Prax fixed log_structure bug. Seedgo fixed display bug. Devpulse 82→99%. (2026-03-28)
- Session 56: Spawn template overhaul. PR #129 (168 files). 69 old remote branches deleted. (2026-03-25)
- Session 55: Test quality expanded (DPLAN-0061). Spawn template + Cortex investigation. PRs #127-128. (2026-03-25)
- Session 54: DPLAN-0059 execution. test_json_handler_template. Seedgo v2 checker. (2026-03-25)
- Session 52: Stale scanner + system test dispatch. 896 new tests. (2026-03-24)
- Session 51: Compliance wave dispatch. 96% avg. PR #122. (2026-03-24)
- Session 50: Night shift. PR #118. Persistent git branches. 95% avg. (2026-03-24)

## Notepad
> **SCRATCH SPACE — gets wiped at session start or topic change.**

Session 68 (night shift):
- FPLAN-0161 executed: 8-phase master plan for zero log scanner output
- Phase 1: Archived 238 log files (clean slate)
- Phase 2: Ran 15 branches fresh — 3,425 tests, 0 failures
- Phase 3: Triage — 100% test-generated noise, zero real runtime errors
- Phase 4: Fixed 4 audit items (api magic number + list_providers, trigger errors detail + help)
- Phase 5: Skipped (no log level issues)
- Phase 6: Test log isolation — AIPASS_TEST_LOG_DIR env var + prax config check. 14 conftest + 1 prax + 1 trigger file
- Phase 7: Final scan ZERO. PR #162 created.
- Result: 981/1805/2000 → 0/0/0
- commons datetime.utcnow() deprecation noted (minor, 2 warnings)

</details>

<details><summary><strong>@drone</strong> — Operational (2026-03-17)</summary>

# @drone

> Command router, @branch resolution, subprocess dispatch, custom commands, git workflow

**State:** Operational
**Last update:** 2026-03-17

## Milestones
- Core routing operational
- `drone systems` command
- @branch resolution
- `--help` for all branches
- Interactive tuple for human-facing commands (monitor, snapshot, versioned)
- Credential verification (RegistryMismatchError)
- Test suite: 335 tests, 9 files
- Seedgo audit: 99% (readme pre-existing)
- **Activated commands restored** (PR #74): scan, activate, list, remove, execute
- **drone @git module** (FPLAN-0094): pr, status, sync, lock, unlock

## Current Work
- @git module complete — awaiting Patrick's review
- FPLAN-0094 closed

## What Changed (Session 9)
- Built `drone @git` internal module from DPLAN-0008 spec
  - `git_module.py` — module + adapter, registered in _MODULE_REGISTRY
  - `handlers/git/lock_handler.py` — atomic O_CREAT|O_EXCL lockfile
  - `handlers/git/pr_handler.py` — 10-step PR workflow with finally cleanup
  - `handlers/git/status_handler.py` — scoped git status
  - `handlers/git/sync_handler.py` — safe main sync
- 46 new tests (335 total), all passing
- Fixed Pyright: handler __init__.py re-exports, unused imports

## Known Issues
- Pyright warns about `json` package name shadowing stdlib — works at runtime
- Production bug: resolver.handle_command("resolve"/"info", ["@NONEXISTENT"]) unhandled
- Pyright can't fully resolve handlers/git/ imports (handler guard __init__.py limitation)

</details>

<details><summary><strong>@flow</strong> — In progress — health check (DPLAN-0020) (2026-03-18)</summary>

# @flow

> Plan lifecycle — FPLANs, DPLANs, and any custom plan type via filesystem-driven template registry

**State:** In progress — health check (DPLAN-0020)
**Last update:** 2026-03-18

## Current Work
- DPLAN-0020: Flow health check — session 9 deep dive with Patrick
  - Introspection/help: DONE (all 8 modules)
  - Template rename + auto-discovery: DONE
  - Template registry + auto-heal: DONE (delete dir → full cleanup)
  - No-fallback errors: DONE
  - --dry-run for close: DONE
  - Registry cleanup: DONE (Docker artifacts, orphan FPLANs)
  - Post-close pipeline: DONE (foreground archival, flags set atomically)
  - Vector intake: DONE (process-plans + verify, visible in close output)
  - Remaining: dashboard push fix, README update, devpulse template updates

## Recently Completed (Session 9)
- Foreground archival: moved from background subprocess to close_ops.py, fixing race condition
- Registry flags: processed/cleanup_completed now set atomically on close
- Vector pipeline: drone @memory process-plans + is_plan_vectorized() wired into close output
- Template auto-heal: load_registry() prunes orphaned types + deletes plan registry JSON
- --dry-run flag: drone @flow close --all --dry-run
- Registry cleanup: removed 4 Docker-path entries, 7 orphan FPLANs archived
- Silent fallback removed from mbank/process.py vector intake
- Memory bug verified fixed (CWD), devpulse dispatch replied (--dry-run + orphan heal)
- Closed DPLAN-0022, 0024, 0026
- Cross-branch coordination: 3 email exchanges with @memory → path mismatch found + fixed

## Pending
- 2 devpulse dispatches: FPLAN template syntax updates + list→list open docs
- Dashboard push failing on close (non-critical, separate issue)
- README update (template system, new commands, pipeline changes)
- Final seedgo audit

## Active Plans
- DPLAN-0020: Flow health check (near completion)

## New Commands (Session 8-9)
```
drone @flow register <dir> <PREFIX>    # Register plan type
drone @flow unregister <dir>           # Remove plan type
drone @flow templates                  # List registered types
drone @flow scan                       # Find unregistered directories
drone @flow close --dry-run            # Preview what would close
drone @flow close --all --dry-run      # Preview close-all
```

## Known Issues
- Dashboard push fails on every close ("Failed to push flow section to branch dashboard")
- plan_type.json files still in templates/ dirs (orphaned — system ignores them)

</details>

<details><summary><strong>@memory</strong> — Operational — 99% seedgo compliant (2026-03-29 (s23))</summary>

# @memory

> Vector memory archive — ChromaDB, sentence-transformers

**State:** Operational — 99% seedgo compliant
**Last update:** 2026-03-29 (s23)

## Milestones
- ChromaDB integration
- Auto-rollover at 600 lines (v2 entry-count mode)
- Searchable vector archive
- FPLAN-0026 complete (rollover E2E, search, plans archival)
- **DPLAN-0073 COMPLETE** — 100% seedgo audit, all 24 standards passing
- **FPLAN-0128 COMPLETE** — verify command + config fix (PR #94)
- **Session 16: CRITICAL FIX** — batch vectorization, decoupled from startup trigger (PR #95)
- 113 plan files vectorized (2019 chunks) in ~1 min at ~20% CPU

## Current Work
- No active DPLANs or FPLANs — all caught up
- Handler test coverage thin (3/29 handlers tested) — future expansion opportunity
- Future: wire up watchdog watcher via `drone @memory watch` to replace startup trigger dependency

## Known Issues
- `search` fails without torch/sentence-transformers installed
- Search returns semantically similar plans, not exact ID matches — use `verify` for ID lookup
- ~~Plan vectorization system overload~~ FIXED in PR #95 (batch mode + decoupled from startup)
- ~~Plan vectorization path mismatch~~ FIXED in PR #95 (correct path: src/aipass/backup/processed_plans)
- ~~Flow plan registry broken~~ FIXED in PR #71
- Old memory bank had ~4,180 vectors. Current has 2,200+ (207 rollover + 2019 plans). Growing.

## New Commands
- `drone @memory verify FPLAN-XXXX` — check if plan is vectorized in chroma
- `drone @memory process-plans` — explicit batch vectorization (NOT auto-triggered)

## Architecture Notes
- Dual vector storage: local (`{branch}/.chroma/`) + global (`memory/.chroma/`). Local fails gracefully, global is critical (restores backup on failure).
- Plan vectorization decoupled from startup trigger. `_check_plans()` = count only. Processing via explicit command.
- Watchdog infrastructure exists in memory_watcher.py but not exposed via drone yet.
- Startup trigger chain: prax logger → trigger.fire('startup') → check_and_rollover(). Keep this lightweight — NEVER put heavy processing here.

## Notepad
- Session 16: INCIDENT — vectorization overloaded system. 228 subprocess calls × 5 concurrent drone commands. Fixed with batch mode + decoupling. PR #95. Full report sent to devpulse.
- Session 15: FPLAN-0128 — verify command + config fix. PR #94.
- Session 14: Processed 4 @flow emails. Path mismatch root cause found.
- Emailed trigger about startup.py _run_memory_bank_check() weight — needs review
- handlers/__init__.py guard blocks cross-branch imports — always expose via modules layer

</details>

<details><summary><strong>@prax</strong> — Operational (2026-03-18)</summary>

# @prax

> Logging, monitoring, dashboard infrastructure

**State:** Operational
**Last update:** 2026-03-18

## Milestones
- System-wide logging via `from aipass.prax import logger`
- Monitor: polling fallback, caller attribution, agent tracking (Phases 1-3)
- Dashboard infrastructure
- Seedgo audit: 100% (25/25 categories)

## Current Work
- No active plans — all closed
- 4 active commands: monitor, status, log-audit, dashboard
- 5 dead modules archived (init, shutdown, run, terminal, discover)

## Seedgo Audit: 100%
- 25 of 25 categories at 100%

## Recently Completed (Session 17)
- Introspection standard: all modules compliant
- Monitor Phase 1: PollingObserver fallback, degradation notices, clean startup
- Monitor Phase 2: Caller attribution via drone [CALLER:BRANCH] markers
- Monitor Phase 3: Agent intelligence (tool use, thinking, responses)
- Archived 5 dead modules, stripped verbose flag, cleaned help
- Found + reported seedgo silent checker bug — fixed same session
- Final 3 introspection violations fixed (status.py, agent_status.py, logger.py)
- Cleaned stale logs/.archive/

## Known Issues
- System inotify watches near-exhausted. Monitor uses polling fallback — functional but slower.
- Phase 4 (interactive filtering) deferred — not needed now

</details>

<details><summary><strong>@seedgo</strong> — Operational — 33/33 standards passing, 98% overall (2026-03-27 (session 33))</summary>

# @seedgo

> Standards enforcement, 34-standard audit pack + seedgo proof system (CERTIFIED) + hook ownership

**State:** Operational — 33/33 standards passing, 98% overall
**Last update:** 2026-03-27 (session 33)

## Session 33 Summary

Test checker consolidation (devpulse dispatch). Renamed testing→error_handling (new triplet). Merged test_coverage into test_quality v4.0 as 11th category (module_coverage: 3 items). 51 items across 11 categories. Archived 6 old files. Updated bypass.json across 4 branches. 34→33 standards. Verified: 218 tests pass, self-audit 98%, api/drone/memory audits clean.

## Active Plans

- **FPLAN-0135** — Audit display dynamic rendering. Phases 1-5 DONE. Ready to close.
- **DPLAN-0051** — Seedgo self-audit. 34/34 passing, 100% overall. COMPLETE.
- **DPLAN-0053** — Drone architecture (commons boardroom). Seedgo side: @ validation done.
- **DPLAN-0047** — audit_display dynamic rendering. DONE via FPLAN-0135.
- **DPLAN-0012** — Hook Management. PARKED.

## Audit State (seedgo branch)

33/33 passing | Overall 98% | Error_Handling 100% | Test_Quality 86% | Unused Function 85%

## TODO

- **Bypass CLI** — Feature request from devpulse
- **.seedgo/ unignore** — Patrick's decision

## Known Issues
- audit_display.py still has depth 5-6 nesting (bypassed, DPLAN-0047 addressed display logic not nesting)
- unused_function_check: importlib/getattr dynamic discovery still needs bypass (checker limitation, documented)
- documentation_check has 5-line lookahead limitation for multi-line function signatures
- dead_code_check doesn't recognize iterdir() discovery patterns
- naming_check flags __init__.py and local variables (checker bugs, bypassed)
- Duplicate PostToolUse hooks (PARKED)

</details>

<details><summary><strong>@skills</strong> — Operational (2026-03-17)</summary>

# @skills

> Capability framework — discoverable, executable skill units

**State:** Operational
**Last update:** 2026-03-17

## Milestones
- Skill discovery
- Execution framework
- --help
- 5 handle_commands
- Seedgo 100% compliance (all 24 standards)

## Current Work
- Session 7: Full seedgo compliance cleanup complete (91% → 100%)
- DPLAN-0070 created for planning

## Known Issues
- None known

</details>

<details><summary><strong>@spawn</strong> — Operational (2026-03-24)</summary>

# @spawn

> Branch lifecycle — create, update, delete, sync

**State:** Operational
**Last update:** 2026-03-24

## Milestones
- Full lifecycle manager (create/update/delete/sync-registry/sync-templates)
- Citizen classes (builder/birthright/manager)
- SHA-256 file tracking
- 113+ tests passing
- Seedgo audit: 99% (34 standards, 32 at 100%)

## Current Work
- Seedgo certification: 99% (20 bypasses added for architectural/false-positive violations)
- Silent catch fixes complete — 20 violations fixed across 12 files
- DPLAN-0035 complete — template modernization (.gitkeep→README.md, instructional local prompt, stale meta cleanup, --help interception)
- PR #68 open: feat/spawn-seedgo-compliance (awaiting merge)

## Known Issues
- 6 stale test entries in AIPASS_REGISTRY.json (test pollution — conftest needs backup/restore)
- Update rename detection noisy on freshly-created branches

</details>

<details><summary><strong>@trigger</strong> — Operational (2026-03-17)</summary>

# @trigger

> Event bus — 12 events, error registry, circuit breaker

**State:** Operational
**Last update:** 2026-03-17

## Milestones
- 12 event types
- fire/status/list commands
- Error registry
- handle_command routing
- Seedgo 98% (22/23 at 100%)
- json_handler wired to all 21 modules/handlers
- Introspection gates on all 5 modules + config.py
- Type errors resolved (stub definitions for conditional imports)

## Current Work
- DPLAN-0071: JSON Structure Compliance (completed)

## Known Issues
- log_structure at 55% — seedgo checker backlog, not a trigger issue

</details>