Gap 1: Spec-declared workspace now bypasses tool-level path checks for
filesystem ops. Direct filesystem operations when workspace differs from
default, executor's own PolicyEngine check is sufficient.
Gap 2: shell_allowlist in spec constraints extends PolicyEngine's base
allowlist per-spec. Specs can allow additional commands without weakening
global security.
Gap 3: New edit_file tool — targeted find-and-replace. Reads file, verifies
old_text exists exactly once, replaces with new_text. Safer than full
overwrite for cross-repo work. Wired through PolicyEngine, TOOL_REGISTRY,
facade, and spec schema.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Dial in Codemine chassis for OpenRouter + HF Spaces deployment
args.get('key', '') returns None when key exists with null value.
Changed to args.get('key') or '' which handles both missing and null.
Wired policy_engine module into RecursiveContextManager for belt-and-suspenders.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PRD: Faux_Clawdbot_Refactoring_PRD_v0.1
Build: Queen Bitch orchestrated, TQB agents built
Blocks:
- B (Anvil): PolicyEngine — Cricket-shaped rim + mesh + audit JSONL
- C (Chisel): Tool class split — RecursiveContextManager → tools/ facade
- E (Switchblade): Model swap — Kimi K2.5 → Claude native tool_use
- F (Forge): Worker NeuroGraph — code-judgment SNN, three-factor learning
- A (Razor): Security hardening — path traversal, shell=False, ZIP bomb, file size guard
- D (Torch): Error handling — zero bare except, structured logging
- G (Hammer): Agent loop — tool registry, PolicyEngine gates, token-aware context
System-level acceptance:
- Zero bare except in any Python file
- Zero regex in tool call parsing
- Zero Kimi/K2.5 references
- Zero shell=True
- Foundation layer (neuro_foundation.py, universal_ingestor.py, openclaw_hook.py) untouched
- Substrate validation passed (17 nodes, 45 synapses, 2 hyperedges)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Integrate NeuroGraph cognitive memory layer into Clawdbot
Claude
Unverified signature
e9073c0
Replaces the custom flat-vector xet storage with NeuroGraph's full
5-stage cognitive pipeline (extract→chunk→embed→register→associate),
backed by STDP learning, hypergraph pattern detection, and predictive
coding. The Clawdbot shell (agent loop, tool system, Gradio UI, HF
Spaces deployment) is unchanged; only the memory layer is swapped.
Key changes:
- Add neuro_foundation.py, universal_ingestor.py, openclaw_hook.py,
neurograph_migrate.py from NeuroGraph v0.5.0
- recursive_context.py: NeuroGraphMemory singleton replaces xet_store
and InferenceClient embeddings; search_code/search_conversations/
search_testament now use semantic NeuroGraph recall; save_conversation_turn
ingests into SNN and runs STDP steps; HF Dataset sync now uploads
NeuroGraph msgpack checkpoint instead of flat JSON vectors
- app.py: import NeuroGraphMemory; inject top-5 recalled memories into
system prompt on each turn; ingest user message before LLM call; add
ingest_workspace tool; update build_system…
