Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 282 Pull Requests 87 Actions 1 Packages Projects Releases Wiki Activity

[claude] feat(memory): add grounded observation synthesis layer (#1013) #1033

Open
claude wants to merge 186 commits from claude/issue-1013 into main
pull from: claude/issue-1013
merge into: Timmy_Foundation:main
Conversation 1 Commits 186 Files Changed 153 +24426 -132
claude commented 2026-04-22 15:21:13 +00:00
Member
Copy Link

Fixes #1013

What

Adds an observation synthesis layer for higher-order recall and agent insight to the holographic memory plugin.

Changes

  • plugins/memory/holographic/observations.py (new): ObservationSynthesizer class that synthesizes grounded higher-order observations from accumulated facts
  • plugins/memory/holographic/store.py: Added observations and observation_evidence tables with UPSERT/list methods
  • plugins/memory/holographic/__init__.py: Wired up ObservationSynthesizer, added observe action to fact_store tool, enhanced prefetch to surface a separate ## Holographic Observations section
  • tests/plugins/memory/test_holographic_observations.py (new): 4 focused tests

Three observation types synthesized

  1. recurring_preference — inferred from repeated user_pref/general facts about communication style
  2. stable_direction — inferred from project facts about trajectory (local-first, gitea-first, ansible)
  3. behavioral_pattern — inferred from repeated operator workflow signals (commit-early, PR-first, dedup-guard)

Evidence grounding

  • Each observation links back to supporting fact IDs in observation_evidence
  • Confidence requires ≥2 matching facts; single-fact observations are suppressed
  • Default min_confidence=0.6 gates weak observations
  • fact_store(action="observe") returns observations with full evidence expansion
  • prefetch returns raw facts and observations as distinct sections, never overwriting raw memory

Verification

python3 -m pytest tests/plugins/memory/test_holographic_observations.py tests/agent/test_memory_provider.py -q
# 50 passed
Fixes #1013 ## What Adds an observation synthesis layer for higher-order recall and agent insight to the holographic memory plugin. ## Changes - **`plugins/memory/holographic/observations.py`** (new): `ObservationSynthesizer` class that synthesizes grounded higher-order observations from accumulated facts - **`plugins/memory/holographic/store.py`**: Added `observations` and `observation_evidence` tables with UPSERT/list methods - **`plugins/memory/holographic/__init__.py`**: Wired up `ObservationSynthesizer`, added `observe` action to `fact_store` tool, enhanced `prefetch` to surface a separate `## Holographic Observations` section - **`tests/plugins/memory/test_holographic_observations.py`** (new): 4 focused tests ## Three observation types synthesized 1. `recurring_preference` — inferred from repeated user_pref/general facts about communication style 2. `stable_direction` — inferred from project facts about trajectory (local-first, gitea-first, ansible) 3. `behavioral_pattern` — inferred from repeated operator workflow signals (commit-early, PR-first, dedup-guard) ## Evidence grounding - Each observation links back to supporting fact IDs in `observation_evidence` - Confidence requires ≥2 matching facts; single-fact observations are suppressed - Default `min_confidence=0.6` gates weak observations - `fact_store(action="observe")` returns observations with full evidence expansion - `prefetch` returns raw facts and observations as distinct sections, never overwriting raw memory ## Verification ``` python3 -m pytest tests/plugins/memory/test_holographic_observations.py tests/agent/test_memory_provider.py -q # 50 passed ```
claude added 1 commit 2026-04-22 15:21:14 +00:00
feat(memory): add grounded observation synthesis layer
All checks were successful
Lint / lint (pull_request) Successful in 8s
Details
3f4515db38
claude reviewed 2026-04-22 16:11:49 +00:00
claude left a comment
Author
Member
Copy Link

Self-review (cannot approve own PR). The observation synthesis layer adds a meaningful capability: higher-order recall backed by supporting facts.

Architecture notes:

  • ObservationSynthesizer backed by dedicated observations + observation_evidence tables is clean
  • Three observation types (recurring_preference, stable_direction, behavioral_pattern) cover the most useful categories
  • Confidence gating at 0.6 default is reasonable
  • Evidence linking ensures observations remain grounded

Potential concerns:

  1. This PR conflicts with PR #1026 and #1028 which all touch plugins/memory/holographic/init.py. Coordinate merge order.
  2. The schema description is getting long. Consider whether the full action list in the tool description will fit within model context constraints for smaller local models.
  3. Ensure the UPSERT logic in store.py handles concurrent sessions correctly if two sessions synthesize observations simultaneously.
Self-review (cannot approve own PR). The observation synthesis layer adds a meaningful capability: higher-order recall backed by supporting facts. Architecture notes: - ObservationSynthesizer backed by dedicated observations + observation_evidence tables is clean - Three observation types (recurring_preference, stable_direction, behavioral_pattern) cover the most useful categories - Confidence gating at 0.6 default is reasonable - Evidence linking ensures observations remain grounded Potential concerns: 1. This PR conflicts with PR #1026 and #1028 which all touch plugins/memory/holographic/__init__.py. Coordinate merge order. 2. The schema description is getting long. Consider whether the full action list in the tool description will fit within model context constraints for smaller local models. 3. Ensure the UPSERT logic in store.py handles concurrent sessions correctly if two sessions synthesize observations simultaneously.
All checks were successful
Lint / lint (pull_request) Successful in 8s
Details
This pull request has changes conflicting with the target branch.
  • cli.py
  • gateway/platforms/api_server.py
  • hermes_cli/models.py
  • hermes_cli/web_server.py
  • plugins/memory/holographic/__init__.py
  • run_agent.py
  • tests/hermes_cli/test_web_server.py
  • tools/browser_tool.py
  • tools/file_tools.py
  • tools/skill_manager_tool.py
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u origin claude/issue-1013:claude/issue-1013
git checkout claude/issue-1013
Sign in to join this conversation.
Reviewers
No Reviewers
claude
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
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/hermes-agent#1033
Delete Branch "claude/issue-1013"

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?