Commit Graph

7 Commits

Author SHA1 Message Date
Cal Corum
f0f075461e Reorganize cognitive-memory skill: consolidate scripts, systemd, dev subdirs
- Move session_memory.py, ensure-symlinks.sh into skills/cognitive-memory/scripts/
- Copy systemd units into skills/cognitive-memory/systemd/ with README
- Move PROJECT_PLAN.json, migrate.py into skills/cognitive-memory/dev/
- Add mtime-based embeddings cache to client.py (6x faster semantic recall)
- Default recall to semantic+keyword merge (was keyword-only)
- Update settings.json SessionEnd hook path, MCP allow entry
- Update SKILL.md, feature.json, mcp_server.py docs for new defaults

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 16:02:20 -06:00
Cal Corum
aed98a3cc8 Rebalance semantic/keyword merge weights to 60/40
Normalize both signals to 0-1 range so semantic similarity scores
aren't drowned out by keyword position scores. Jellyfin DB recovery
now ranks #1 for "media server database broken sqlite error" instead
of being buried behind keyword noise matches on "error".

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 15:07:43 -06:00
Cal Corum
4770c15429 Add --if-changed flag to embed, configurable Ollama model, hourly timer
- embed --if-changed compares memory ID sets to skip when unchanged
- --ollama-model config flag to switch models without code changes
- _ollama_embed now accepts model param, respects config throughout
- Switched default to qwen3-embedding:8b (70+ MTEB vs nomic's ~52)
- Hourly systemd timer for embedding, daily timer no longer embeds
- Fixed PATH for uv in both systemd services

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 14:54:21 -06:00
Cal Corum
a2d18ef0c2 Cognitive Memory v3.0: rich edges, hybrid embeddings, MCP server
Add first-class edge files in graph/edges/ with bidirectional frontmatter
refs, hybrid Ollama/OpenAI embedding providers with fallback chain, and
native MCP server (18 tools) for direct Claude Code integration.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 14:11:18 -06:00
Cal Corum
08b74ec6d6 Fix decay baseline so new memories start Active instead of Fading
Changed zero-access usage_factor from 0.5 to 1.0 in calculate_decay_score().
Previously, a freshly stored solution (importance=0.7, weight=1.2) scored
0.42 (Fading); now scores 0.84 (Active) as intended.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 19:20:07 -06:00
Cal Corum
b2b024f0e3 Replace gitea-create-pr.sh script with tea CLI
Removed custom PR creation script in favor of native tea CLI tool.

Before: /home/cal/.claude/scripts/gitea-create-pr.sh cal/repo branch main "Title"
After: tea pulls create --repo cal/repo --head branch --base main --title "Title"

Benefits:
- No custom script maintenance
- Native Gitea CLI with better error handling
- Support for labels, assignees, milestones
- Consistent with other Gitea operations

Updated CLAUDE.md with tea pulls create examples.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-13 15:20:56 -06:00
Cal Corum
047ec745eb Add new skills, commands, scripts; update Paper Dynasty workflows
New:
- backlog, cognitive-memory, optimise-claude skills
- commands/ and scripts/ directories
- usage-data tracking

Updated:
- Paper Dynasty: consolidated workflows, updated API client and CLI
- .gitignore, CLAUDE.md, settings.json

Removed:
- Deprecated Paper Dynasty workflows (card-refresh, database-sync,
  discord-app-troubleshooting, gauntlet-cleanup, custom-player-db)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 14:10:21 -06:00