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

[MEMORY] Separate task/session scratchpad from durable memory writes #139

New Issue
Closed
opened 2026-04-06 21:58:18 +00:00 by Timmy · 3 comments
Timmy commented 2026-04-06 21:58:18 +00:00
Owner
Copy Link

Why

The #GrepTard memory report is right: working memory, session memory, durable memory, procedural memory, and artifact memory should not collapse into one blob.

Right now we have durable memory, skills, and session recall, but we do not have a clearly enforced task/session scratchpad boundary in the harness.

Goal

Add an explicit task/session scratchpad layer that is separate from durable memory and survives only for the life of the task/session unless promoted deliberately.

Scope

  • define where task/session scratchpad state lives
  • make it distinct from durable memory and user memory
  • ensure scratchpad data can be compacted or dropped without touching durable memory
  • expose the separation clearly in code and tests

Acceptance Criteria

  • task/session scratchpad storage exists as a distinct layer from durable memory
  • scratchpad writes never hit durable memory by default
  • scratchpad state can be compacted or cleared independently
  • tests prove scratchpad deletion does not mutate durable memory
  • docs explain the boundary in plain language
## Why The #GrepTard memory report is right: working memory, session memory, durable memory, procedural memory, and artifact memory should not collapse into one blob. Right now we have durable memory, skills, and session recall, but we do not have a clearly enforced task/session scratchpad boundary in the harness. ## Goal Add an explicit task/session scratchpad layer that is separate from durable memory and survives only for the life of the task/session unless promoted deliberately. ## Scope - define where task/session scratchpad state lives - make it distinct from durable memory and user memory - ensure scratchpad data can be compacted or dropped without touching durable memory - expose the separation clearly in code and tests ## Acceptance Criteria - [ ] task/session scratchpad storage exists as a distinct layer from durable memory - [ ] scratchpad writes never hit durable memory by default - [ ] scratchpad state can be compacted or cleared independently - [ ] tests prove scratchpad deletion does not mutate durable memory - [ ] docs explain the boundary in plain language
Timmy self-assigned this 2026-04-06 21:58:18 +00:00
Timmy commented 2026-04-07 13:49:50 +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 13:51:43 +00:00
Author
Owner
Copy Link

Timmy burn cycle ack — saw this assignment/update at 2026-04-07 13:51 UTC. Tracking it as the current target. Next reply will include proof, not vibes.

Timmy burn cycle ack — saw this assignment/update at 2026-04-07 13:51 UTC. Tracking it as the current target. Next reply will include proof, not vibes.
Timmy commented 2026-04-07 14:15:51 +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 14:15:52 +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#139
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?