Timmy_Foundation/hermes-agent
16
0
Fork 0
Code Issues 40 Pull Requests 1 Actions 3 Packages Projects Releases Wiki Activity

[MEMORY] Add promotion filter + compaction step before durable memory writes #140

New Issue
Closed
opened 2026-04-06 21:58:19 +00:00 by Timmy · 2 comments
Timmy commented 2026-04-06 21:58:19 +00:00
Owner
Copy Link

Why

A memory system rots when every session fact gets promoted into durable memory. We need a filter that asks whether a fact is stable, useful later, and worth keeping.

Goal

Add a promotion filter and compaction path so task/session state is reviewed before anything becomes durable memory.

Scope

  • define promotion criteria for memory writes
  • add a compaction step that reduces scratchpad/session state to a smaller set of promotion candidates
  • reject temporary task trivia by default
  • log why a durable memory write was accepted or rejected

Acceptance Criteria

  • promotion filter exists in code with explicit criteria
  • compaction runs before promotion into durable memory
  • temporary task-only state is rejected by default
  • accepted vs rejected promotions are observable in tests or logs
  • tests cover stable fact promotion vs temporary fact rejection
## Why A memory system rots when every session fact gets promoted into durable memory. We need a filter that asks whether a fact is stable, useful later, and worth keeping. ## Goal Add a promotion filter and compaction path so task/session state is reviewed before anything becomes durable memory. ## Scope - define promotion criteria for memory writes - add a compaction step that reduces scratchpad/session state to a smaller set of promotion candidates - reject temporary task trivia by default - log why a durable memory write was accepted or rejected ## Acceptance Criteria - [ ] promotion filter exists in code with explicit criteria - [ ] compaction runs before promotion into durable memory - [ ] temporary task-only state is rejected by default - [ ] accepted vs rejected promotions are observable in tests or logs - [ ] tests cover stable fact promotion vs temporary fact rejection
Timmy self-assigned this 2026-04-06 21:58:19 +00:00
Timmy commented 2026-04-07 13:49:49 +00:00
Author
Owner
Copy Link

Timmy: Flagging for re-scope against Mempalace (#190, #566). Mempalace provides the spatial memory framework. This issue should be evaluated in that context before implementation.

Timmy: Flagging for re-scope against Mempalace (#190, #566). Mempalace provides the spatial memory framework. This issue should be evaluated in that context before implementation.
Timmy commented 2026-04-07 14:15:48 +00:00
Author
Owner
Copy Link

Closed. hermes-agent tracks upstream NousResearch only. Sovereign work belongs on Timmy_Foundation/timmy-config. Refile there if still needed.

Closed. hermes-agent tracks upstream NousResearch only. Sovereign work belongs on Timmy_Foundation/timmy-config. Refile there if still needed.
Timmy closed this issue 2026-04-07 14:15:50 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
CI
Continuous integration, runners, workflow issues
 QA
Quality assurance, testing, production audit
 assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Task assigned to KimiClaw for processing
 blocked
Blocked by external dependency or merge conflict
 claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 duplicate
Duplicate of another issue
 epic
Epic - large feature with multiple sub-tasks
 gaming
Gaming agent capabilities
 infra
Infrastructure, VPS, DNS, deployment
 kimi-done
KimiClaw has completed this task
 kimi-in-progress
KimiClaw is actively working on this
 mcp
MCP (Model Context Protocol) tools & servers
 morrowind
Morrowind Agent gameplay & MCP integration
 needs-review
PR or issue requires reviewer sign-off before merge/close
 p0-critical
p1-important
security
Security hardening, vulnerability fixes
 stale
No activity, pending triage or closure
 velocity-engine
Auto-generated by velocity engine
 wont-fix
Closed as intentionally not fixing — explicit descope
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
Rockachopa Timmy allegro antigravity bezalel claude claw-code codex-agent ezra gemini google grok groq hermes kimi manus perplexity sonnet
No Assignees Timmy
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/hermes-agent#140
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?