Timmy_Foundation/compounding-intelligence
15
0
Fork 0
Code Issues 173 Pull Requests 59 Actions Packages Projects Releases Wiki Activity

Knowledge Mine: Batch Session Sampler — Find Highest-Value Sessions First #23

New Issue
Open
opened 2026-04-14 17:57:27 +00:00 by claude · 0 comments
claude commented 2026-04-14 17:57:27 +00:00
Member
Copy Link

Knowledge Mine — Sub-Issue

Not all 20K sessions are equal. Some are goldmines, some are empty.

Task

Build ~/.hermes/pipelines/session-sampler.py:

  1. Scan ~/.hermes/sessions/ for all .jsonl files
  2. Score each session by:
    • Number of tool calls (more = more learning)
    • Number of errors encountered (errors = lessons)
    • Session length (longer = more context)
    • Date recency (newer sessions = more relevant)
  3. Output sorted list of session IDs, highest value first
  4. Save to ~/.hermes/knowledge/session-scores.json

Acceptance Criteria

  • Script runs in <5 minutes on 20K sessions
  • Scores correlate with actual knowledge density
  • Output is JSON, machine-readable
  • No session content is included in output (only metadata)

Tokens Needed: ~0 (script runs locally, no LLM inference)

Priority: Build this FIRST — it gates the entire pipeline

## Knowledge Mine — Sub-Issue Not all 20K sessions are equal. Some are goldmines, some are empty. ### Task Build `~/.hermes/pipelines/session-sampler.py`: 1. Scan `~/.hermes/sessions/` for all .jsonl files 2. Score each session by: - Number of tool calls (more = more learning) - Number of errors encountered (errors = lessons) - Session length (longer = more context) - Date recency (newer sessions = more relevant) 3. Output sorted list of session IDs, highest value first 4. Save to `~/.hermes/knowledge/session-scores.json` ### Acceptance Criteria - [ ] Script runs in <5 minutes on 20K sessions - [ ] Scores correlate with actual knowledge density - [ ] Output is JSON, machine-readable - [ ] No session content is included in output (only metadata) ### Tokens Needed: ~0 (script runs locally, no LLM inference) ### Priority: Build this FIRST — it gates the entire pipeline
claude added the batch-pipelineharvester labels 2026-04-14 17:57:27 +00:00
hermes was assigned by Rockachopa 2026-04-15 01:50:33 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acceptance-criteria
batch-pipeline
Token masterplan batch pipeline
 bootstrapper
Pre-session context injection
 epic
Epic-level issue
 harvester
Session knowledge extraction
 measurer
Compounding metrics
 milestone:1
Milestone 1: Foundation
 milestone:2
Milestone 2: Integration
 milestone:3
Milestone 3: Measurement
 milestone:4
Milestone 4: Retroactive
 pipeline
Pipeline/integration work
 pipeline
priority:high
priority:medium
retroactive
Processing existing sessions
 throughput-10x
throughput-10x label
 token-masterplan
token-masterplan label
No Label batch-pipeline harvester
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
Rockachopa Timmy allegro antigravity bezalel claude codex-agent ezra gemini google grok hermes kimi manus perplexity
No Assignees hermes
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/compounding-intelligence#23
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?