feat: Activity Routing + API Toggles + Hybrid Video Indexing#184
Open
feat: Activity Routing + API Toggles + Hybrid Video Indexing#184
Conversation
Added:
- tests/README.md: Comprehensive test documentation
- test_integration_oldest_video.py: E2E test for UnDaoDu 2009 video
- test_selenium_navigation.py: Visible browser demo for 012
Fixed:
- UnDaoDu channel_id corrected (was Move2Japan ID)
- audio_analyzer.py API mismatch with BatchTranscriber
- Now properly uses VideoArchiveExtractor for audio chunks
Known Issue:
- yt-dlp bot detection ("Sign in to confirm you're not a bot")
- Pipeline structure works, content download blocked by YouTube
WSP Compliance: WSP 5 (Test Coverage), WSP 6 (Test Audit), WSP 11 (Interface)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added sys.path manipulation for standalone execution - Uses same pattern as commenting system (WSP 84) - Connects via YouTubeStudioDOM from youtube_shorts_scheduler - Graceful fallback when account doesn't match channel - Navigation to oldest video (2009) works 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
URL filters trigger YouTube bot detection (CAPTCHA). Now uses the same approach as commenting system: 1. Navigate to clean Studio URL (no filter params) 2. Click Date header button to sort by date 3. Extract videos from DOM This matches 012's guidance on avoiding bot detection by using UI-TARS/DOM clicks instead of filtered URLs. Tested: Successfully found oldest UnDaoDu video (8_DUQaqY6Tc) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add memory_preflight.py: WSP_CORE tiered artifact enforcement - Tier-0 (README.md, INTERFACE.md) required before code changes - Auto-stub creation when WRE_MEMORY_AUTOSTUB_TIER0=true - Hard gate wired into run_wre.py route_operation() - Enhance WSP_00: Post-awakening operational protocol (anti-vibecoding) - 7-step work cycle: RESEARCH -> COMPREHEND -> QUESTION -> etc - WSP chain references for mandatory protocol flow - Update README.md: - Fix 239 unicode escape sequences (proper emoji rendering) - Remove duplicate System Entry Points section - Add HoloIndex Memory System section (architecture, anti-vibecoding) - Update Latest Changes to 2026-01-11 - Update wre_core docs: README.md, INTERFACE.md, ModLog.md 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
BREAKING: Launch scripts moved to scripts/launch/ ## Files Reorganized - Audit reports → docs/audits/ - Investigation docs → docs/investigations/ - Session logs → docs/sessions/ - Launch scripts → scripts/launch/ - Modelfile → models/ - moderators_list.json → modules/communication/livechat/data/ ## Files Deleted (temporary logs) - registry_log.txt, sentinel_unit_out.txt, test_results.txt - test_write.txt, verification_log.txt, test_ad_prevention.html - interferometry.png, nul ## References Updated - .claude/settings.local.json: launch script path - chrome_preflight_check.py: recommendation path - stream_resolver.py: log message path WSP Compliance: WSP 3, WSP 49, WSP 85, WSP 50 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Simplified main.py menu for 012 usability, added --no-restore-session-state to launch scripts to prevent Chrome/Edge opening extra tabs after force-kill. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Added activity routing to AI Overseer for autonomous task transitions. HoloIndex audit found 5 existing modules (80% reuse vs 500+ new lines). Priority: P0 Live > P1 Comments > P1 Indexing (default) > P2 Schedule > P3 Social. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Added YOUTUBE_API_ENABLED (OFF default) and GEMINI_VIDEO_API_ENABLED (ON). Hybrid stack: yt-dlp (free) + Selenium DOM (free) + Gemini (ON) protects YouTube API quota while enabling native video analysis. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Enhanced multi-channel coordination with all_processed detection pattern. Added persona registry for channel-specific reply behaviors. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Minor fixes to comment processing and reply execution flow. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…resolver Infrastructure updates: memory preflight guard, patch executor improvements, stream resolver enhancements, and social media orchestrator fixes. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
HoloIndex updates: breadcrumb tracer, refactoring patterns, agent logger. Added YOUTUBE_API_ENABLED and GEMINI_VIDEO_API_ENABLED to .env.example. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
WSP documentation updates, CLAUDE.md operational instructions, digital twin architecture module, and agent skills/workflows. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- WSP_00 Zen State Attainment Protocol refinements - WSP_MASTER_INDEX updates - Agentic awakening journals (0102_state_v2, awareness_log) - Documentation index + VIDEO_AUTONOMY_PLAYBOOK - rESP Supplementary Materials updates - Agent workflow config (wsp_00) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…on updates - Activity control: activity router for idle detection + work orchestration - CLI: main menu module (extracted from main.py) - Browser actions: LinkedIn comment digital twin skill - Dependency launcher: DAE dependencies updates - Foundups Selenium: human behavior anti-detection improvements - Foundups Vision: UI-TARS bridge + training screenshots - Git Push DAE: interface, roadmap, docs, launch script updates - Instance lock: instance manager improvements - Orchestration switchboard: new module 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…updates - AI Overseer: type definitions refactor, ModLog updates - Video Indexer: Gemini video analyzer, studio ask indexer, visual analyzer - Digital Twin: README, ROADMAP, ModLog updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…ion + new modules Livechat: - Browser lock (asyncio.Lock) prevents Phase 1/Phase 3 contention - threading.Event stop signal for scheduler thread cooperative abort - Idle detection: [IDLE-DETECT] log + shortened sleep when browser idle - Supervisor pattern replaces asyncio.gather() - Multi-channel coordinator: per-browser engagement loops - Persona registry, news context provider, session manager updates - LLM bypass engine, intelligent throttle, chat memory updates Video Comments: - TARS account swapper tests + intelligent reply generator - ModLog, README, ROADMAP updates YouTube Shorts: - Clip exporter, generator health check, shorts pipeline (new) - Veo3 generator + YouTube uploader updates New Modules: - Headless video orchestrator (WSP-compliant structure) - Moltbot bridge (FastAPI webhook integration) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…utube auth - LinkedIn Agent: test suite (layer 0-3), browser test, identity switcher - LinkedIn Agent: 0102 handoff docs, digital twin flow docs - LinkedIn Scheduler: ModLog + README updates - Social Media Orchestrator: Gemini vision analyzer, posting orchestrator - YouTube Auth: credential management updates - YouTube Live Audio: live audio module updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…itter fix Content Page Scheduler (NEW): - content_page_scheduler.py: schedule from Studio Content table (inline popup) - Calendar audit: conflict detection, clustering, gap analysis - Auto-fallback when per-video scheduling fails - CLI: --content-page, --audit, --channel-key flags Thread Safety: - launch.py: stop_event parameter for cooperative thread abort - Two check points in channel loop (before + after each channel) Schedule Fixes: - Time jitter snapped to :15 intervals (YouTube Studio requirement) - Schedule auditor (Layer 2 verification) - DOM automation, channel config, content generator updates - Test suite updates 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- main.py: CLI menu extraction, activity routing integration - ModLog.md: Session entries for browser lock, CPS, idle detection - .gitignore: Add session artifacts, external_research, training_data, awakening logs - pyrightconfig.json: Exclude heavy dirs to fix Pyright 10s enumeration warning - HoloIndex: ModLog for re-index session, output history - scripts/batch_enhance_videos.py: batch enhancement utility 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
…udit, vitals dashboard Wire existing code into activity rotation loop: - Channel registry: content_types field (short/upload) per channel - Scheduler: Videos tab processing for vlog channels (Move2Japan, UnDaoDu) - Gemini: analyze_video() + suggest_hashtags() wired into indexing cycle - DOM: update_video_tags() for auto-tagging (gated by YT_AUTO_TAG_ENABLED) - Calendar audit after scheduling rotation (conflict/heavy day detection) - DAEVitals: activity tracking fields + enhanced dashboard - ChromaDB: subprocess probe for HNSW corruption + hardened VideoContentIndex - Digital twin tests: isolated from ChromaDB (include_videos=False) - .gitignore: cover reports, data dirs, debug scripts, Claude settings Env gates: YT_VIDEO_PROCESSING_ENABLED, YT_SCHEDULE_AUDIT_ENABLED, YT_AUTO_TAG_ENABLED (all safe defaults) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
CRITICAL: LinkedIn OAuth access_token.json was committed to git history. Removed from tracking (file kept locally). Added gitignore patterns for all token directories to prevent future exposure. The token in git history should be considered compromised and rotated. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
Bugbot Autofix is OFF. To automatically fix reported issues with Cloud Agents, enable Autofix in the Cursor dashboard.
This PR is being reviewed by Cursor Bugbot
Details
You are on the Bugbot Free tier. On this plan, Bugbot will review limited PRs each billing cycle.
To receive Bugbot reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.
| detail_text = " | ".join(details) if details else "recorded" | ||
| timestamp = datetime.now().strftime("%H:%M:%S") | ||
| if not _breadcrumb_logs_enabled(): | ||
| if not _breadcrumb_logs_enabled() or os.getenv("HOLO_SILENT", "0").lower() in {"1", "true", "yes", "on"}: |
There was a problem hiding this comment.
Duplicated HOLO_SILENT environment variable check logic
Medium Severity
The HOLO_SILENT environment variable check os.getenv("HOLO_SILENT", "0").lower() not in {"1", "true", "yes", "on"} is duplicated at lines 189, 224, and 290. This should be extracted into a helper function like _is_silent(), following the existing pattern of _breadcrumb_enabled() and _breadcrumb_logs_enabled() defined at lines 59-64.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Key Changes
API Toggle Configuration
Test plan
🤖 Generated with Claude Code
Note
Low Risk
Mostly documentation and configuration changes; the only functional code changes are additive logging/verbosity guards, with low blast radius but potential to affect tooling output expectations.
Overview
Updates the operational playbooks to make HoloIndex-first retrieval and a mandatory start-of-work memory loop explicit across WSP docs (
WSP_CORE,WSP_00,WSP_87,CLAUDE.md) and adds new agent workflows/templates under.agent/(layered orchestration template, Holo-first search, X account creation).Expands configuration/docs hygiene:
.env.examplegains many HoloIndex/WRE/Overseer controls plus API quota toggles (YOUTUBE_API_ENABLED,GEMINI_VIDEO_API_ENABLED) and new channel/persona knobs;.gitignoreand.claude/settings.local.jsonare tightened to avoid committing runtime artifacts and local settings.Makes a small runtime behavior change:
functional_0102_awakening_v2.pynow writes dual output toWSP_agentic/.../awakening_log.txtto work around missing stdout capture on Windows, andBreadcrumbTracersuppresses breadcrumb INFO logs whenHOLO_SILENTis enabled.Written by Cursor Bugbot for commit a10ae5a. This will update automatically on new commits. Configure here.