WIP: Gemini Code progress on #1014

Automated salvage commit — agent session ended (exit 124).
Work in progress, may need continuation.

scripts/update_ollama_models.py

@@ -0,0 +1,75 @@
+
+import subprocess
+import json
+import os
+import glob
+
+def get_models_from_modelfiles():
+    models = set()
+    modelfiles = glob.glob("Modelfile.*")
+    for modelfile in modelfiles:
+        with open(modelfile, 'r') as f:
+            for line in f:
+                if line.strip().startswith("FROM"):
+                    parts = line.strip().split()
+                    if len(parts) > 1:
+                        model_name = parts[1]
+                        # Only consider models that are not local file paths
+                        if not model_name.startswith('/') and not model_name.startswith('~') and not model_name.endswith('.gguf'):
+                            models.add(model_name)
+                    break # Only take the first FROM in each Modelfile
+    return sorted(list(models))
+
+def update_ollama_model(model_name):
+    print(f"Checking for updates for model: {model_name}")
+    try:
+        # Run ollama pull command
+        process = subprocess.run(
+            ["ollama", "pull", model_name],
+            capture_output=True,
+            text=True,
+            check=True,
+            timeout=900 # 15 minutes
+        )
+        output = process.stdout
+        print(f"Output for {model_name}:\n{output}")
+
+        # Basic check to see if an update happened.
+        # Ollama pull output will contain "pulling" or "downloading" if an update is in progress
+        # and "success" if it completed. If the model is already up to date, it says "already up to date".
+        if "pulling" in output or "downloading" in output:
+            print(f"Model {model_name} was updated.")
+            return True
+        elif "already up to date" in output:
+            print(f"Model {model_name} is already up to date.")
+            return False
+        else:
+            print(f"Unexpected output for {model_name}, assuming no update: {output}")
+            return False
+
+    except subprocess.CalledProcessError as e:
+        print(f"Error updating model {model_name}: {e}")
+        print(f"Stderr: {e.stderr}")
+        return False
+    except FileNotFoundError:
+        print("Error: 'ollama' command not found. Please ensure Ollama is installed and in your PATH.")
+        return False
+
+def main():
+    models_to_update = get_models_from_modelfiles()
+    print(f"Identified models to check for updates: {models_to_update}")
+
+    updated_models = []
+    for model in models_to_update:
+        if update_ollama_model(model):
+            updated_models.append(model)
+
+    if updated_models:
+        print("\nSuccessfully updated the following models:")
+        for model in updated_models:
+            print(f"- {model}")
+    else:
+        print("\nNo models were updated.")
+
+if __name__ == "__main__":
+    main()

src/dashboard/routes/models.py

@@ -5,6 +5,7 @@ to swarm agents.  Inspired by OpenClaw-RL's multi-model orchestration.
 """
 
 import logging
+import subprocess
 from pathlib import Path
 from typing import Any
 
@@ -59,6 +60,23 @@ class SetActiveRequest(BaseModel):
 # ── API endpoints ─────────────────────────────────────────────────────────────
 
 
+@api_router.post("/update-ollama")
+async def update_ollama_models():
+    """Trigger the Ollama model update script."""
+    logger.info("Ollama model update triggered")
+    script_path = Path(__file__).parent.parent.parent.parent / "scripts" / "update_ollama_models.py"
+    try:
+        subprocess.Popen(
+            ["python", str(script_path)],
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+        )
+        return {"message": "Ollama model update started in the background."}
+    except Exception as e:
+        logger.error(f"Failed to start Ollama model update: {e}")
+        raise HTTPException(status_code=500, detail="Failed to start model update script.") from e
+
+
 @api_router.get("")
 async def list_models(role: str | None = None) -> dict[str, Any]:
     """List all registered custom models."""

src/dashboard/templates/models.html

@@ -53,7 +53,12 @@
 
   <!-- Registered Models -->
   <div class="mc-section" style="margin-top: 1.5rem;">
-    <h2>Registered Models</h2>
+    <div style="display: flex; justify-content: space-between; align-items: center;">
+      <h2>Registered Models</h2>
+      <button class="mc-btn" hx-post="/api/v1/models/update-ollama" hx-swap="none">
+        Update Ollama Models
+      </button>
+    </div>
     {% if models %}
     <table class="mc-table">
       <thead>

src/timmy/paperclip.py

@@ -13,8 +13,8 @@ from dataclasses import dataclass
 import httpx
 
 from config import settings
+from timmy.research_tools import get_llm_client, google_web_search
 from timmy.research_triage import triage_research_report
-from timmy.research_tools import google_web_search, get_llm_client
 
 logger = logging.getLogger(__name__)
 

src/timmy/research_tools.py

@@ -6,7 +6,6 @@ import logging
 import os
 from typing import Any
 
-from config import settings
 from serpapi import GoogleSearch
 
 logger = logging.getLogger(__name__)

src/timmy/tools.py

@@ -462,7 +462,8 @@ def consult_grok(query: str) -> str:
             inv = ln.create_invoice(sats, f"Grok query: {query[:_INVOICE_MEMO_MAX_LEN]}")
             invoice_info = f"\n[Lightning invoice: {sats} sats — {inv.payment_request[:40]}...]"
         except (ImportError, OSError, ValueError) as exc:
-            logger.warning("Tool execution failed (Lightning invoice): %s", exc)
+            logger.error("Lightning invoice creation failed: %s", exc)
+            return "Error: Failed to create Lightning invoice. Please check logs."
 
     result = backend.run(query)
 
@@ -533,7 +534,8 @@ def _register_web_fetch_tool(toolkit: Toolkit) -> None:
     try:
         toolkit.register(web_fetch, name="web_fetch")
     except Exception as exc:
-        logger.warning("Tool execution failed (web_fetch registration): %s", exc)
+        logger.error("Failed to register web_fetch tool: %s", exc)
+        raise
 
 
 def _register_core_tools(toolkit: Toolkit, base_path: Path) -> None:
@@ -565,8 +567,8 @@ def _register_grok_tool(toolkit: Toolkit) -> None:
             toolkit.register(consult_grok, name="consult_grok")
             logger.info("Grok consultation tool registered")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (Grok registration): %s", exc)
-        logger.debug("Grok tool not available")
+        logger.error("Failed to register Grok tool: %s", exc)
+        raise
 
 
 def _register_memory_tools(toolkit: Toolkit) -> None:
@@ -579,8 +581,8 @@ def _register_memory_tools(toolkit: Toolkit) -> None:
         toolkit.register(memory_read, name="memory_read")
         toolkit.register(memory_forget, name="memory_forget")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (Memory tools registration): %s", exc)
-        logger.debug("Memory tools not available")
+        logger.error("Failed to register Memory tools: %s", exc)
+        raise
 
 
 def _register_agentic_loop_tool(toolkit: Toolkit) -> None:
@@ -628,8 +630,8 @@ def _register_agentic_loop_tool(toolkit: Toolkit) -> None:
 
         toolkit.register(plan_and_execute, name="plan_and_execute")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (plan_and_execute registration): %s", exc)
-        logger.debug("plan_and_execute tool not available")
+        logger.error("Failed to register plan_and_execute tool: %s", exc)
+        raise
 
 
 def _register_introspection_tools(toolkit: Toolkit) -> None:
@@ -647,15 +649,16 @@ def _register_introspection_tools(toolkit: Toolkit) -> None:
         toolkit.register(get_memory_status, name="get_memory_status")
         toolkit.register(run_self_tests, name="run_self_tests")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (Introspection tools registration): %s", exc)
-        logger.debug("Introspection tools not available")
+        logger.error("Failed to register Introspection tools: %s", exc)
+        raise
 
     try:
         from timmy.mcp_tools import update_gitea_avatar
 
         toolkit.register(update_gitea_avatar, name="update_gitea_avatar")
     except (ImportError, AttributeError) as exc:
-        logger.debug("update_gitea_avatar tool not available: %s", exc)
+        logger.error("Failed to register update_gitea_avatar tool: %s", exc)
+        raise
 
     try:
         from timmy.session_logger import self_reflect, session_history
@@ -663,8 +666,8 @@ def _register_introspection_tools(toolkit: Toolkit) -> None:
         toolkit.register(session_history, name="session_history")
         toolkit.register(self_reflect, name="self_reflect")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (session_history registration): %s", exc)
-        logger.debug("session_history tool not available")
+        logger.error("Failed to register session_history tool: %s", exc)
+        raise
 
 
 def _register_delegation_tools(toolkit: Toolkit) -> None:
@@ -676,8 +679,8 @@ def _register_delegation_tools(toolkit: Toolkit) -> None:
         toolkit.register(delegate_to_kimi, name="delegate_to_kimi")
         toolkit.register(list_swarm_agents, name="list_swarm_agents")
     except Exception as exc:
-        logger.warning("Tool execution failed (Delegation tools registration): %s", exc)
-        logger.debug("Delegation tools not available")
+        logger.error("Failed to register Delegation tools: %s", exc)
+        raise
 
 
 def _register_gematria_tool(toolkit: Toolkit) -> None:
@@ -687,8 +690,8 @@ def _register_gematria_tool(toolkit: Toolkit) -> None:
 
         toolkit.register(gematria, name="gematria")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (Gematria registration): %s", exc)
-        logger.debug("Gematria tool not available")
+        logger.error("Failed to register Gematria tool: %s", exc)
+        raise
 
 
 def _register_artifact_tools(toolkit: Toolkit) -> None:
@@ -699,8 +702,8 @@ def _register_artifact_tools(toolkit: Toolkit) -> None:
         toolkit.register(jot_note, name="jot_note")
         toolkit.register(log_decision, name="log_decision")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (Artifact tools registration): %s", exc)
-        logger.debug("Artifact tools not available")
+        logger.error("Failed to register Artifact tools: %s", exc)
+        raise
 
 
 def _register_thinking_tools(toolkit: Toolkit) -> None:
@@ -710,8 +713,8 @@ def _register_thinking_tools(toolkit: Toolkit) -> None:
 
         toolkit.register(search_thoughts, name="thought_search")
     except (ImportError, AttributeError) as exc:
-        logger.warning("Tool execution failed (Thinking tools registration): %s", exc)
-        logger.debug("Thinking tools not available")
+        logger.error("Failed to register Thinking tools: %s", exc)
+        raise
 
 
 def create_full_toolkit(base_dir: str | Path | None = None):

tests/integrations/test_gabs_observer.py

@@ -10,14 +10,12 @@ from __future__ import annotations
 
 import json
 import socket
-from pathlib import Path
 from unittest.mock import MagicMock, patch
 
 import pytest
 
 from integrations.bannerlord.gabs_client import GabsClient, GabsError
 
-
 # ── GabsClient unit tests ─────────────────────────────────────────────────────
 
 

tests/scripts/test_export_trajectories.py

@@ -9,10 +9,8 @@ import json
 from pathlib import Path
 
 import pytest
-
 import scripts.export_trajectories as et
 
-
 # ── Fixtures ──────────────────────────────────────────────────────────────────
 
 

tests/timmy/test_dispatcher.py

@@ -4,8 +4,6 @@ from __future__ import annotations
 
 from unittest.mock import AsyncMock, MagicMock, patch
 
-import pytest
-
 from timmy.dispatcher import (
     AGENT_REGISTRY,
     AgentType,
@@ -21,7 +19,6 @@ from timmy.dispatcher import (
     wait_for_completion,
 )
 
-
 # ---------------------------------------------------------------------------
 # Agent registry
 # ---------------------------------------------------------------------------

tests/unit/test_retrain_loop.py

@@ -9,19 +9,15 @@ Refs: #1105
 from __future__ import annotations
 
 import json
-import tempfile
 from datetime import UTC, datetime, timedelta
 from pathlib import Path
 
-import pytest
-
 from timmy_automations.retrain.quality_filter import QualityFilter, TrajectoryQuality
 from timmy_automations.retrain.retrain import RetrainOrchestrator
 from timmy_automations.retrain.training_dataset import TrainingDataset
 from timmy_automations.retrain.training_log import CycleMetrics, TrainingLog
 from timmy_automations.retrain.trajectory_exporter import Trajectory, TrajectoryExporter
 
-
 # ── Fixtures ─────────────────────────────────────────────────────────────────