Commit graph

6 commits

Author SHA1 Message Date
Mario Zechner
d5fd685901 Enable more biome lints and fix things 2025-12-21 22:56:20 +01:00
Mario Zechner
706554a5d3 fix(mom): private channel messages not being logged
- Add message.groups to required bot events in README
- Add groups:history and groups:read to required scopes in README
- app_mention handler now logs messages directly instead of relying on message event
- Add deduplication in ChannelStore.logMessage() to prevent double-logging
- Remove redundant current message append in agent.ts (already in log)
2025-12-04 12:24:29 +01:00
Mario Zechner
f02194296d feat(mom): backfill missed messages on startup using conversations.history API
- Add getLastTimestamp() to ChannelStore to read last ts from log.jsonl
- Add backfillChannel() to fetch up to 3 pages (3000 messages) per channel
- Add backfillAllChannels() called in start() before socket connection
- Include mom's own messages (as bot) and user messages, exclude other bots
- Process attachments from backfilled messages
- Add logging: logBackfillStart, logBackfillChannel, logBackfillComplete
- Warn if attachment missing name instead of failing

fixes #103
2025-12-03 22:05:13 +01:00
Mario Zechner
213bc4df1c mom: add centralized logging, usage tracking, and improve prompt caching
Major improvements to mom's logging and cost reporting:

Centralized Logging System:
- Add src/log.ts with type-safe logging functions
- Colored console output (green=user, yellow=mom, dim=details)
- Consistent format: [HH:MM:SS] [context] message
- Replace scattered console.log/error calls throughout codebase

Usage Tracking & Cost Reporting:
- Track tokens (input, output, cache read/write) and costs per run
- Display summary at end of each run in console and Slack thread
- Example: 💰 Usage: 12,543 in + 847 out (5,234 cache read) = $0.0234

Prompt Caching Optimization:
- Move recent messages from system prompt to user message
- System prompt now mostly static (only changes with memory files)
- Enables effective use of Anthropic's prompt caching
- Significantly reduces costs on subsequent requests

Model & Cost Improvements:
- Switch from Claude Opus 4.5 to Sonnet 4.5 (~40% cost reduction)
- Fix Claude Opus 4.5 cache pricing in ai package (was 3x too expensive)
- Add manual override in generate-models.ts until upstream fix merges
- Submitted PR to models.dev: https://github.com/sst/models.dev/pull/439

UI/UX Improvements:
- Extract actual text from tool results instead of JSON wrapper
- Cleaner Slack thread formatting with duration and labels
- Tool args formatting shows paths with offset:limit notation
- Add chalk for colored terminal output

Dependencies:
- Add chalk package for terminal colors
2025-11-26 18:04:16 +01:00
Mario Zechner
4e01eca40e mom: add working memory system and improve log querying
- Add MEMORY.md files for persistent working memory
  - Global memory: workspace/MEMORY.md (shared across channels)
  - Channel memory: workspace/<channel>/MEMORY.md (channel-specific)
  - Automatically loaded into system prompt on each request

- Enhance JSONL log format with ISO 8601 dates
  - Add 'date' field for easy grepping (e.g., grep '"date":"2025-11-26"')
  - Migrated existing logs to include date field

- Improve log query efficiency
  - Add jq query patterns to prevent context overflow
  - Emphasize limiting NUMBER of messages (10-50), not truncating text
  - Show full message text and attachments in queries
  - Handle null/empty attachments with (.attachments // [])

- Optimize system prompt
  - Add current date/time for date-aware operations
  - Format recent messages as TSV (43% token savings vs raw JSONL)
  - Add efficient query examples with both JSON and TSV output

- Enhanced security documentation
  - Add prompt injection risk warnings
  - Document credential exfiltration scenarios
  - Provide mitigation strategies
2025-11-26 13:21:43 +01:00
Mario Zechner
aa9e058249 mom: Slack bot with abort support, streaming console output, removed sandbox 2025-11-26 00:27:21 +01:00