@simbimbo/memory-ocmemog 0.1.5 → 0.1.6

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.1.6 — 2026-03-19
+
+Port-separation and publish-solid follow-up.
+
+### Highlights
+- Split ocmemog sidecar onto dedicated loopback port `17891` to avoid collision with the OpenClaw gateway/dashboard on `17890`
+- Restored the plain realtime dashboard on `/dashboard` and fixed the `local_html` template crash
+- Updated plugin/runtime defaults, scripts, and documentation to use the dedicated sidecar endpoint on `17891`
+- Added governance retrieval/governance-policy hardening plus expanded regression coverage for duplicate, contradiction, supersession, queue, audit, rollback, and auto-resolve flows
+- Aligned package/version metadata across npm, Python, and FastAPI surfaces
+
 ## 0.1.5 — 2026-03-18
 
 Repair and hardening follow-up after the 0.1.4 publish.

package/README.md

@@ -32,7 +32,7 @@ pip install -r requirements.txt
 ./scripts/ocmemog-sidecar.sh
 
 # then open
-# http://127.0.0.1:17890/dashboard
+# http://127.0.0.1:17891/dashboard
 ```
 
 ## Optional: transcript watcher (auto-ingest)
@@ -45,8 +45,8 @@ export OCMEMOG_TRANSCRIPT_DIR="$HOME/.openclaw/workspace/memory/transcripts"
 
 Default bind:
 
-- endpoint: `http://127.0.0.1:17890`
-- health: `http://127.0.0.1:17890/healthz`
+- endpoint: `http://127.0.0.1:17891`
+- health: `http://127.0.0.1:17891/healthz`
 
 ## Continuity proof / benchmark harness
 
@@ -193,7 +193,7 @@ plugins:
     memory-ocmemog:
       enabled: true
       config:
-        endpoint: http://127.0.0.1:17890
+        endpoint: http://127.0.0.1:17891
         timeoutMs: 30000
 ```
 

package/brain/runtime/inference.py

@@ -33,13 +33,43 @@ def _infer_ollama(prompt: str, model: str | None = None) -> dict[str, str]:
     return {"status": "ok", "output": str(output).strip()}
 
 
+def _looks_like_ollama_model(name: str) -> bool:
+    if not name:
+        return False
+    lowered = name.strip().lower()
+    if lowered.startswith("ollama:"):
+        return True
+    if "/" in lowered:
+        return False
+    return ":" in lowered
+
+
+def stats() -> dict[str, object]:
+    materialized_local = int(_LOCAL_INFER_STATS.get("local_success", 0)) + int(_LOCAL_INFER_STATS.get("cache_hits", 0))
+    est_prompt_tokens_saved = materialized_local * _AVG_PROMPT_TOKENS_SAVED
+    est_completion_tokens_saved = materialized_local * _AVG_COMPLETION_TOKENS_SAVED
+    est_cost_saved = (
+        (est_prompt_tokens_saved / 1000.0) * _EST_FRONTIER_INPUT_COST_PER_1K
+        + (est_completion_tokens_saved / 1000.0) * _EST_FRONTIER_OUTPUT_COST_PER_1K
+    )
+    return {
+        "cache_entries": len(_LOCAL_INFER_CACHE),
+        "warm_models": sorted(_MODEL_WARM_STATE.keys()),
+        "frontier_calls_avoided_est": materialized_local,
+        "prompt_tokens_saved_est": est_prompt_tokens_saved,
+        "completion_tokens_saved_est": est_completion_tokens_saved,
+        "cost_saved_usd_est": round(est_cost_saved, 4),
+        **{k: int(v) for k, v in _LOCAL_INFER_STATS.items()},
+    }
+
+
 def infer(prompt: str, provider_name: str | None = None) -> dict[str, str]:
     if not isinstance(prompt, str) or not prompt.strip():
         return {"status": "error", "error": "empty_prompt"}
 
     use_ollama = os.environ.get("OCMEMOG_USE_OLLAMA", "").lower() in {"1", "true", "yes"}
     model_override = provider_name or config.OCMEMOG_MEMORY_MODEL
-    if use_ollama or model_override.startswith("ollama:"):
+    if use_ollama or _looks_like_ollama_model(model_override):
         model = model_override.split(":", 1)[-1] if model_override.startswith("ollama:") else model_override
         return _infer_ollama(prompt, model)