Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 282 Pull Requests 87 Actions Packages Projects Releases Wiki Activity

[FEATURE] First-class live context snapshots for memory/debug evaluation #983

New Issue
Open
opened 2026-04-22 04:46:41 +00:00 by Rockachopa · 0 comments
Rockachopa commented 2026-04-22 04:46:41 +00:00
Owner
Copy Link

Goal

Promote the ad hoc memory eval snapshot harness into a first-class Hermes feature.

Why

We need grounded proof of what actually enters the live context window:

  • built-in memory injection
  • Holographic provider system prompt blocks
  • external memory prefetch output
  • final API-call user message after memory-context injection
  • full API message payload shape (minus secrets)

Right now this exists only as an external eval artifact flow. We want it in-core so users can enable snapshots and inspect raw context composition during real work.

Scope

  • Add a core context snapshot recorder in hermes-agent
  • Capture per-API-call artifacts to disk when enabled
  • Include system prompt, built-in memory blocks, external provider prompt block, prefetch raw text, final injected user message, and final API messages JSON
  • Make it configurable from core agent config / constructor
  • Add tests proving snapshots are written during run_conversation and include memory-context injection
  • Document the feature

Acceptance criteria

  • No-op when disabled
  • Safe file writes under HERMES_HOME
  • Works in CLI/gateway/cron because it lives in AIAgent
  • Produces inspectable raw artifacts for memory-provider evaluation
## Goal Promote the ad hoc memory eval snapshot harness into a first-class Hermes feature. ## Why We need grounded proof of what actually enters the live context window: - built-in memory injection - Holographic provider system prompt blocks - external memory prefetch output - final API-call user message after memory-context injection - full API message payload shape (minus secrets) Right now this exists only as an external eval artifact flow. We want it in-core so users can enable snapshots and inspect raw context composition during real work. ## Scope - Add a core context snapshot recorder in hermes-agent - Capture per-API-call artifacts to disk when enabled - Include system prompt, built-in memory blocks, external provider prompt block, prefetch raw text, final injected user message, and final API messages JSON - Make it configurable from core agent config / constructor - Add tests proving snapshots are written during run_conversation and include memory-context injection - Document the feature ## Acceptance criteria - No-op when disabled - Safe file writes under HERMES_HOME - Works in CLI/gateway/cron because it lives in AIAgent - Produces inspectable raw artifacts for memory-provider evaluation
claude self-assigned this 2026-04-22 04:51:41 +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
 accessibility
Auto-created for game epic
 assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Task assigned to KimiClaw for processing
 audit-finding
batch-pipeline
batch-pipeline label
 blocked
Blocked by external dependency or merge conflict
 bug
claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 critical
docs
Auto-created for game epic
 duplicate
Duplicate of another issue
 epic
Epic - large feature with multiple sub-tasks
 epic:memory
Unified Memory Architecture epic
 game
Auto-created for game epic
 gaming
Gaming agent capabilities
 implementation
Auto-created for game epic
 infra
Infrastructure, VPS, DNS, deployment
 infrastructure
Auto-created for game epic
 juice
Auto-created for game epic
 kimi-done
KimiClaw has completed this task
 kimi-in-progress
KimiClaw is actively working on this
 mcp
MCP (Model Context Protocol) tools & servers
 mechanics
Auto-created for game epic
 mobile
Auto-created for game epic
 morrowind
Morrowind Agent gameplay & MCP integration
 needs-review
PR or issue requires reviewer sign-off before merge/close
 ops
p0-critical
p1-important
performance
Auto-created for game epic
 phase:1-activate
Phase 1: Activate existing systems
 phase:2-operational
Phase 2: Operational memory bridge
 phase:3-episodic
Phase 3: Proactive episodic recall
 phase:4-hygiene
Phase 4: Memory hygiene and quality
 phase:5-integration
Phase 5: Integration and testing
 poka-yoke
polish
Auto-created for game epic
 priority-high
Auto-created for game epic
 priority-low
Auto-created for game epic
 priority-medium
Auto-created for game epic
 research
security
Security hardening, vulnerability fixes
 shared-infra
Shared infrastructure across projects (Playground + LPM)
 sovereign
Auto-created for game epic
 stale
No activity, pending triage or closure
 throughput-10x
throughput-10x label
 token-masterplan
token-masterplan label
 tool-evaluation
ux
Auto-created for game epic
 velocity-engine
Auto-generated by velocity engine
 visuals
Auto-created for game epic
 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 hermes kimi manus perplexity sonnet
No Assignees claude
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/hermes-agent#983
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?