mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-21 17:00:45 +00:00
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
This commit is contained in:
parent
82d4ac93e1
commit
213bc4df1c
11 changed files with 478 additions and 63 deletions
|
|
@ -12,6 +12,14 @@
|
|||
- ISO 8601 date field in log.jsonl for easy date-based grepping
|
||||
- Format: `"date":"2025-11-26T10:44:00.123Z"`
|
||||
- Enables queries like: `grep '"date":"2025-11-26' log.jsonl`
|
||||
- Centralized logging system (`src/log.ts`)
|
||||
- Structured, colored console output (green for user messages, yellow for mom activity, dim for details)
|
||||
- Consistent format: `[HH:MM:SS] [context] message`
|
||||
- Type-safe logging functions for all event types
|
||||
- Usage tracking and cost reporting
|
||||
- Tracks tokens (input, output, cache read, cache write) and costs per run
|
||||
- Displays summary at end of each agent run in console and Slack thread
|
||||
- Example: `💰 Usage: 12,543 in + 847 out (5,234 cache read, 127 cache write) = $0.0234`
|
||||
|
||||
### Changed
|
||||
|
||||
|
|
@ -26,6 +34,14 @@
|
|||
- Fixed jq patterns to handle null/empty attachments with `(.attachments // [])`
|
||||
- Recent messages in system prompt now formatted as TSV (43% token savings vs raw JSONL)
|
||||
- Enhanced security documentation with prompt injection risk warnings and mitigations
|
||||
- **Moved recent messages from system prompt to user message** for better prompt caching
|
||||
- System prompt is now mostly static (only changes when memory files change)
|
||||
- Enables Anthropic's prompt caching to work effectively
|
||||
- Significantly reduces costs on subsequent requests
|
||||
- Switched from Claude Opus 4.5 to Claude Sonnet 4.5 (~40% cost reduction)
|
||||
- Tool result display now extracts actual text instead of showing JSON wrapper
|
||||
- Slack thread messages now show cleaner tool call formatting with duration and label
|
||||
- All console logging centralized and removed from scattered locations
|
||||
|
||||
### Fixed
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue