The Qdrant index (commonwealth collection, 475 points) was stale —
pointing at old worktree paths from previous sprints with no
maintenance. Grep covers all current search needs.
Removed: qdrant_connector.py, wrapper scripts (qdrant-search,
qdrant-index, qdrant-health, qdrant-count), /docs-search skill,
Qdrant/Ollama config entries, and all active references in agents,
rules, briefings, DEVOPS, CLAUDE.md, and TEAM.md. The commonwealth
collection was dropped from tower-of-joy:6333.
Historical references in discussion archives and sprint briefings
are preserved as-is.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
sprint stop now clears assigned_to on all done tickets in the closing
sprint. Agents don't clean up after themselves — this was causing
5 bookkeeping warnings every sprint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add venv auto-activation to audio_batch, audio_connector,
image_connector, qdrant_connector, and trellis_connector.
Scripts re-exec into .venv/bin/python when invoked outside
the venv, with a friendly error if .venv is missing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Create tooling/db/common.py with resolve_db_path(), load_config(),
get_connection(), and ensure_venv(). Update ticket, sprint,
sqlite_connector.py, and decisions_sync.py to import from common
instead of duplicating. Fixes pre-existing NameError in
decisions_sync.py (missing import os). Add pyproject.toml with
ruff config (ruff==0.15.9, CVE-clean) and dev dependencies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Persistent worktrees (server, client, copy, audio, visual, ci, planning,
maintenance) caused agents crossing boundaries, stuck agents leaving
uncommitted work, and index.lock collisions. Replaced with ephemeral
sprint branches (sprint-{N}/{team}) and worktrees created on demand.
Changes:
- New start-sprint script replaces start-session (dynamic tabs per active team)
- Sprint teardown integrated into sprint-start skill (A1c step)
- SR_DB_PATH env var for database access from any directory
- CLAUDE.md team boundaries rewritten (scope-based, not directory-based)
- Agent Rule 0 updated to team scope dirs instead of worktree isolation
- PR review uses git show instead of cross-directory reads
- Briefing template updated for sprint-{N}/{team} branch naming
- Deleted worktree-update skill (obsolete)
- Removed WORKTREE_TEAM env var and cross-directory Read permissions
- All 8 persistent worktrees removed
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add session_hash to all API calls (maintains gr.State between
image_to_3d and extract_glb)
- Pass is_multiimage=False at position 2 (9-param image_to_3d)
- Pass output_buf=None at position 0 (3-param extract_glb)
- Document full API parameter reference and failure modes
- Add trellis-batch.sh for gentle sequential batch generation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Simplified image-gen SKILL.md, removed obsolete DDS/style references
(replaced by Gemini API connector). Updated audio_connector, gitignore,
and CLAUDE.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New skill for converting concept images to game-ready .glb models via
Trellis (image-to-3D) and Blender post-processing (scale normalization,
material setup, recolor mask generation).
Connectors: trellis_connector.py (Gradio API), image_connector.py
(Gemini API for concept art).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update wiki_sync.py and process-wiki-system-changes to remove
astronomical_id references. Add migrate-s-to-gj.py migration script.
Update generate-stubs.py and validate-ron for new schema.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New data flow: wiki → star-map.json + SQLite.
- tooling/process-wiki-system-changes: unified script that reads
wiki, updates star-map.json topology, syncs to SQLite
- tooling/db/wiki_sync.py: wiki frontmatter parser + SQLite upsert
- generate-stubs.py: updated for full-frontmatter wiki format
- Removed extract-csv.py (replaced by SQLite queries)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updated docstrings in sqlite_connector, qdrant_connector,
decisions_sync, schema.sql, and two doc comments in generator.rs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Consolidates all connector scripts under tooling/ per project
structure conventions. Symlink at db/connectors → tooling/db/
preserves backwards compatibility (remove after Sprint 22).
Updated references in CLAUDE.md, Makefile, DEVOPS.md, all skill
files, agent files, rules, schema comments, and Sprint 21
briefings. Python scripts updated with correct SCHEMA_PATH
(now relative to WORKTREE_ROOT/db/schema.sql).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
jpmschweitzerandClaude Opus 4.6