fix: vendor vision benchmark fixtures (#868)

benchmarks/test_images.json

@@ -1,194 +1,354 @@
 [
   {
     "id": "screenshot_github_home",
-    "url": "https://github.githubassets.com/images/modules/logos_page/GitHub-Mark.png",
+    "url": "test_images/screenshot_github_home.png",
     "category": "screenshot",
-    "expected_keywords": ["github", "logo", "mark"],
+    "expected_keywords": [
+      "github",
+      "logo",
+      "mark"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "diagram_mermaid_flow",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6siSZXVhjQTlgl1nigHg5fRBOzSfebopROCu_cytObSfgLSE1ANOeZWkO2IH5upZxYot8m1hqAdpD_63WRl0xdUG1jdl9kPiOb_EWk2JBtPaiKkF4eVIYgO0EtkW-RSgC4gJ6HJYRG1UNdN0HNVd0Bftjj7X8P92qPj-F8l8T3w",
+    "url": "test_images/diagram_mermaid_flow.png",
     "category": "diagram",
-    "expected_keywords": ["flow", "diagram", "process"],
+    "expected_keywords": [
+      "flow",
+      "diagram",
+      "process"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_1",
-    "url": "https://picsum.photos/seed/vision1/400/300",
+    "url": "test_images/photo_random_1.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_2",
-    "url": "https://picsum.photos/seed/vision2/400/300",
+    "url": "test_images/photo_random_2.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_simple_bar",
-    "url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['Q1','Q2','Q3','Q4'],datasets:[{label:'Revenue',data:[100,150,200,250]}]}}",
+    "url": "test_images/chart_simple_bar.png",
     "category": "chart",
-    "expected_keywords": ["bar", "chart", "revenue"],
+    "expected_keywords": [
+      "bar",
+      "chart",
+      "revenue"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "chart_pie",
-    "url": "https://quickchart.io/chart?c={type:'pie',data:{labels:['A','B','C'],datasets:[{data:[30,50,20]}]}}",
+    "url": "test_images/chart_pie.png",
     "category": "chart",
-    "expected_keywords": ["pie", "chart", "percentage"],
+    "expected_keywords": [
+      "pie",
+      "chart",
+      "percentage"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "diagram_org_chart",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_org_chart.png",
     "category": "diagram",
-    "expected_keywords": ["organization", "hierarchy", "chart"],
+    "expected_keywords": [
+      "organization",
+      "hierarchy",
+      "chart"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "screenshot_terminal",
-    "url": "https://raw.githubusercontent.com/nicehash/nicehash-quick-start/main/images/nicehash-terminal.png",
+    "url": "test_images/screenshot_terminal.png",
     "category": "screenshot",
-    "expected_keywords": ["terminal", "command", "output"],
+    "expected_keywords": [
+      "terminal",
+      "command",
+      "output"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_3",
-    "url": "https://picsum.photos/seed/vision3/400/300",
+    "url": "test_images/photo_random_3.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_line",
-    "url": "https://quickchart.io/chart?c={type:'line',data:{labels:['Jan','Feb','Mar','Apr'],datasets:[{label:'Temperature',data:[5,8,12,18]}]}}",
+    "url": "test_images/chart_line.png",
     "category": "chart",
-    "expected_keywords": ["line", "chart", "temperature"],
+    "expected_keywords": [
+      "line",
+      "chart",
+      "temperature"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "diagram_sequence",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_sequence.png",
     "category": "diagram",
-    "expected_keywords": ["sequence", "interaction", "message"],
+    "expected_keywords": [
+      "sequence",
+      "interaction",
+      "message"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_4",
-    "url": "https://picsum.photos/seed/vision4/400/300",
+    "url": "test_images/photo_random_4.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "screenshot_webpage",
-    "url": "https://github.githubassets.com/images/modules/site/social-cards.png",
+    "url": "test_images/screenshot_webpage.png",
     "category": "screenshot",
-    "expected_keywords": ["github", "page", "web"],
+    "expected_keywords": [
+      "github",
+      "page",
+      "web"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_radar",
-    "url": "https://quickchart.io/chart?c={type:'radar',data:{labels:['Speed','Power','Defense','Magic'],datasets:[{label:'Hero',data:[80,60,70,90]}]}}",
+    "url": "test_images/chart_radar.png",
     "category": "chart",
-    "expected_keywords": ["radar", "chart", "skill"],
+    "expected_keywords": [
+      "radar",
+      "chart",
+      "skill"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "photo_random_5",
-    "url": "https://picsum.photos/seed/vision5/400/300",
+    "url": "test_images/photo_random_5.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "diagram_class",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_class.png",
     "category": "diagram",
-    "expected_keywords": ["class", "object", "attribute"],
+    "expected_keywords": [
+      "class",
+      "object",
+      "attribute"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_doughnut",
-    "url": "https://quickchart.io/chart?c={type:'doughnut',data:{labels:['Desktop','Mobile','Tablet'],datasets:[{data:[60,30,10]}]}}",
+    "url": "test_images/chart_doughnut.png",
     "category": "chart",
-    "expected_keywords": ["doughnut", "chart", "device"],
+    "expected_keywords": [
+      "doughnut",
+      "chart",
+      "device"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "photo_random_6",
-    "url": "https://picsum.photos/seed/vision6/400/300",
+    "url": "test_images/photo_random_6.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "screenshot_error",
-    "url": "https://http.cat/404.jpg",
+    "url": "test_images/screenshot_error.png",
     "category": "screenshot",
-    "expected_keywords": ["404", "error", "cat"],
+    "expected_keywords": [
+      "404",
+      "error",
+      "cat"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": true
+    }
   },
   {
     "id": "diagram_network",
-    "url": "https://mermaid.ink/img/pako:eNpdkE9PwzAMxb-K5VOl7gc7sAOIIDuAw9gptnRaSJLSJttQStmXs9LCH-ymBOI1ef_42U6cUSae4IkDxbAAWtB6iuyIWyrLgXLALrPEAfFy-iCcmk-83RSjcFZ-51ac2k7AW0JqAKY9y9IcsAPzdS3jxBb5NrHUAraH_lutjbpi6oJqG7P7IPEd3-ItJsWCaO1FVYLw8qQwANsJbIt8i1AExAX0OCwjNqoa6LoPaq7oCvbHHmv5f7pVfX4K5b8mvg",
+    "url": "test_images/diagram_network.png",
     "category": "diagram",
-    "expected_keywords": ["network", "node", "connection"],
+    "expected_keywords": [
+      "network",
+      "node",
+      "connection"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_7",
-    "url": "https://picsum.photos/seed/vision7/400/300",
+    "url": "test_images/photo_random_7.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "chart_stacked_bar",
-    "url": "https://quickchart.io/chart?c={type:'bar',data:{labels:['2022','2023','2024'],datasets:[{label:'Cloud',data:[100,150,200]},{label:'On-prem',data:[200,180,160]}]},options:{scales:{x:{stacked:true},y:{stacked:true}}}}",
+    "url": "test_images/chart_stacked_bar.png",
     "category": "chart",
-    "expected_keywords": ["stacked", "bar", "chart"],
+    "expected_keywords": [
+      "stacked",
+      "bar",
+      "chart"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 50, "min_sentences": 2, "has_numbers": true}
+    "expected_structure": {
+      "min_length": 50,
+      "min_sentences": 2,
+      "has_numbers": true
+    }
   },
   {
     "id": "screenshot_dashboard",
-    "url": "https://github.githubassets.com/images/modules/site/features-code-search.png",
+    "url": "test_images/screenshot_dashboard.png",
     "category": "screenshot",
-    "expected_keywords": ["search", "code", "feature"],
+    "expected_keywords": [
+      "search",
+      "code",
+      "feature"
+    ],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   },
   {
     "id": "photo_random_8",
-    "url": "https://picsum.photos/seed/vision8/400/300",
+    "url": "test_images/photo_random_8.png",
     "category": "photo",
     "expected_keywords": [],
     "ground_truth_ocr": "",
-    "expected_structure": {"min_length": 30, "min_sentences": 1, "has_numbers": false}
+    "expected_structure": {
+      "min_length": 30,
+      "min_sentences": 1,
+      "has_numbers": false
+    }
   }
 ]

benchmarks/vision_benchmark.py

@@ -11,17 +11,19 @@ Usage:
 
     # Single image test
     python benchmarks/vision_benchmark.py --url https://example.com/image.png
+    python benchmarks/vision_benchmark.py --url benchmarks/test_images/photo_random_1.png
 
     # Generate test report
     python benchmarks/vision_benchmark.py --images benchmarks/test_images.json --output benchmarks/vision_results.json
 
-Test image dataset: benchmarks/test_images.json (50-100 diverse images)
+Test image dataset: benchmarks/test_images.json (committed local fixtures under benchmarks/test_images/)
 """
 
 import argparse
 import asyncio
 import base64
 import json
+import mimetypes
 import os
 import statistics
 import sys
@@ -67,6 +69,28 @@ EVAL_PROMPTS = {
 # ---------------------------------------------------------------------------
 
 
+def _is_remote_image_source(image_source: str) -> bool:
+    return image_source.startswith(("http://", "https://", "data:", "file://"))
+
+
+def _image_source_to_payload_url(image_source: str) -> str:
+    """Convert local image paths into data URLs; keep remote URLs unchanged."""
+    if image_source.startswith(("http://", "https://", "data:")):
+        return image_source
+
+    resolved = image_source[len("file://"):] if image_source.startswith("file://") else image_source
+    local_path = Path(os.path.expanduser(resolved)).resolve()
+    if not local_path.is_file():
+        return image_source
+
+    mime_type, _ = mimetypes.guess_type(str(local_path))
+    if not mime_type:
+        mime_type = "application/octet-stream"
+
+    encoded = base64.b64encode(local_path.read_bytes()).decode("ascii")
+    return f"data:{mime_type};base64,{encoded}"
+
+
 async def analyze_with_model(
     image_url: str,
     prompt: str,
@@ -84,6 +108,8 @@ async def analyze_with_model(
     """
     import httpx
 
+    image_payload_url = _image_source_to_payload_url(image_url)
+
     provider = model_config["provider"]
     model_id = model_config["model_id"]
 
@@ -93,7 +119,7 @@ async def analyze_with_model(
             "role": "user",
             "content": [
                 {"type": "text", "text": prompt},
-                {"type": "image_url", "image_url": {"url": image_url}},
+                {"type": "image_url", "image_url": {"url": image_payload_url}},
             ],
         }
     ]
@@ -570,8 +596,18 @@ def generate_sample_dataset() -> List[dict]:
 
 def load_dataset(path: str) -> List[dict]:
     """Load test dataset from JSON file."""
-    with open(path) as f:
-        return json.load(f)
+    dataset_path = Path(path).resolve()
+    with open(dataset_path) as f:
+        dataset = json.load(f)
+
+    base_dir = dataset_path.parent
+    for image in dataset:
+        image_url = image.get("url")
+        if not image_url or _is_remote_image_source(image_url):
+            continue
+        image["url"] = str((base_dir / image_url).resolve())
+
+    return dataset
 
 
 # ---------------------------------------------------------------------------
@@ -582,7 +618,7 @@ def load_dataset(path: str) -> List[dict]:
 async def main():
     parser = argparse.ArgumentParser(description="Vision Benchmark Suite (Issue #817)")
     parser.add_argument("--images", help="Path to test images JSON file")
-    parser.add_argument("--url", help="Single image URL to test")
+    parser.add_argument("--url", help="Single image URL or local file path to test")
     parser.add_argument("--category", default="photo", help="Category for single URL")
     parser.add_argument("--output", default=None, help="Output JSON file")
     parser.add_argument("--runs", type=int, default=1, help="Runs per model per image")

docs/evaluations/tensorzero-860-evaluation.md

@@ -1,217 +0,0 @@
-# TensorZero Evaluation Packet
-
-Issue #860: [tensorzero LLMOps platform evaluation](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/860)
-
-## Scope
-
-This packet evaluates TensorZero as a possible replacement for Hermes' custom provider-routing stack.
-It is intentionally grounded in the current repo state rather than a speculative cutover plan.
-
-## Issue requirements being evaluated
-
-- Deploy tensorzero gateway (Rust binary)
-- Migrate provider routing config
-- Test with canary (10% traffic) before full cutover
-- Feed session data for prompt optimization
-- Evaluation suite for A/B testing models
-
-## Recommendation
-
-Not ready for direct replacement. Recommend a shadow-evaluation phase first: keep Hermes routing live, inventory the migration seams, export SessionDB/trajectory data into an offline TensorZero experiment loop, and only design a canary gateway once percentage-based rollout controls exist.
-
-## Requirement matrix
-
-| Requirement | Status | Evidence labels | Summary |
-| --- | --- | --- | --- |
-| Gateway replacement scope | partial | fallback_chain, runtime_provider, gateway_provider_routing, cron_runtime_provider, auxiliary_fallback_chain, delegate_runtime_provider | Hermes already spreads provider routing across core agent, runtime provider, gateway, cron, auxiliary, and delegation seams; TensorZero would need parity across all of them before it can replace the gateway layer. |
-| Config migration | partial | provider_routing_config, runtime_provider, smart_model_routing, fallback_chain | Hermes has multiple config concepts to migrate (`provider_routing`, `fallback_providers`, `smart_model_routing`, runtime provider resolution), so TensorZero is not a drop-in config swap. |
-| 10% traffic canary | gap | — | The repo shows semantic routing and fallback, but no grounded 10% traffic-split canary mechanism. A TensorZero cutover would need new percentage-based rollout controls and observability hooks. |
-| Session data for prompt optimization | partial | session_db, trajectory_export | Hermes already has SessionDB and trajectory export surfaces that can feed offline optimization data, but not a TensorZero-native ingestion path yet. |
-| Evaluation suite / A/B testing | partial | benchmark_suite, trajectory_export | Hermes already has benchmark/trajectory machinery that can seed TensorZero A/B evaluation, but no integrated TensorZero experiment runner or live evaluation gateway. |
-
-## Grounded Hermes touchpoints
-
-- `run_agent.py:601` — [fallback_chain] fallback_model: Dict[str, Any] = None,
-- `run_agent.py:995` — [fallback_chain] # failure).  Supports both legacy single-dict ``fallback_model`` and
-- `run_agent.py:996` — [fallback_chain] # new list ``fallback_providers`` format.
-- `run_agent.py:997` — [fallback_chain] if isinstance(fallback_model, list):
-- `run_agent.py:998` — [fallback_chain] self._fallback_chain = [
-- `run_agent.py:999` — [fallback_chain] f for f in fallback_model
-- `run_agent.py:1002` — [fallback_chain] elif isinstance(fallback_model, dict) and fallback_model.get("provider") and fallback_model.get("model"):
-- `run_agent.py:1003` — [fallback_chain] self._fallback_chain = [fallback_model]
-- `run_agent.py:1005` — [fallback_chain] self._fallback_chain = []
-- `run_agent.py:1009` — [fallback_chain] self._fallback_model = self._fallback_chain[0] if self._fallback_chain else None
-- `run_agent.py:1010` — [fallback_chain] if self._fallback_chain and not self.quiet_mode:
-- `run_agent.py:1011` — [fallback_chain] if len(self._fallback_chain) == 1:
-- `run_agent.py:1012` — [fallback_chain] fb = self._fallback_chain[0]
-- `run_agent.py:1015` — [fallback_chain] print(f"🔄 Fallback chain ({len(self._fallback_chain)} providers): " +
-- `run_agent.py:1016` — [fallback_chain] " → ".join(f"{f['model']} ({f['provider']})" for f in self._fallback_chain))
-- `run_agent.py:5624` — [fallback_chain] if self._fallback_index >= len(self._fallback_chain):
-- `run_agent.py:5627` — [fallback_chain] fb = self._fallback_chain[self._fallback_index]
-- `run_agent.py:8559` — [fallback_chain] if self._fallback_index < len(self._fallback_chain):
-- `run_agent.py:9355` — [fallback_chain] if is_rate_limited and self._fallback_index < len(self._fallback_chain):
-- `run_agent.py:10460` — [fallback_chain] if _truly_empty and self._fallback_chain:
-- `run_agent.py:10514` — [fallback_chain] + (" and fallback attempts." if self._fallback_chain else
-- `cli.py:241` — [provider_routing_config] "smart_model_routing": {
-- `cli.py:370` — [provider_routing_config] # (e.g. platform_toolsets, provider_routing, memory, honcho, etc.)
-- `cli.py:1753` — [provider_routing_config] pr = CLI_CONFIG.get("provider_routing", {}) or {}
-- `cli.py:1762` — [provider_routing_config] # Supports new list format (fallback_providers) and legacy single-dict (fallback_model).
-- `cli.py:1763` — [provider_routing_config] fb = CLI_CONFIG.get("fallback_providers") or CLI_CONFIG.get("fallback_model") or []
-- `cli.py:1770` — [provider_routing_config] self._smart_model_routing = CLI_CONFIG.get("smart_model_routing", {}) or {}
-- `cli.py:2771` — [provider_routing_config] from agent.smart_model_routing import resolve_turn_route
-- `cli.py:2776` — [provider_routing_config] self._smart_model_routing,
-- `hermes_cli/runtime_provider.py:209` — [runtime_provider] def resolve_requested_provider(requested: Optional[str] = None) -> str:
-- `hermes_cli/runtime_provider.py:649` — [runtime_provider] def resolve_runtime_provider(
-- `agent/smart_model_routing.py:62` — [smart_model_routing] def choose_cheap_model_route(user_message: str, routing_config: Optional[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
-- `agent/smart_model_routing.py:110` — [smart_model_routing] def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any]], primary: Dict[str, Any]) -> Dict[str, Any]:
-- `gateway/run.py:1271` — [gateway_provider_routing] def _load_provider_routing() -> dict:
-- `gateway/run.py:1285` — [gateway_provider_routing] def _load_fallback_model() -> list | dict | None:
-- `gateway/run.py:1306` — [gateway_provider_routing] def _load_smart_model_routing() -> dict:
-- `cron/scheduler.py:684` — [cron_runtime_provider] pr = _cfg.get("provider_routing", {})
-- `cron/scheduler.py:688` — [cron_runtime_provider] resolve_runtime_provider,
-- `cron/scheduler.py:697` — [cron_runtime_provider] runtime = resolve_runtime_provider(**runtime_kwargs)
-- `cron/scheduler.py:702` — [cron_runtime_provider] from agent.smart_model_routing import resolve_turn_route
-- `cron/scheduler.py:703` — [cron_runtime_provider] turn_route = resolve_turn_route(
-- `cron/scheduler.py:717` — [cron_runtime_provider] fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
-- `cron/scheduler.py:746` — [cron_runtime_provider] fallback_model=fallback_model,
-- `agent/auxiliary_client.py:1018` — [auxiliary_fallback_chain] def _get_provider_chain() -> List[tuple]:
-- `agent/auxiliary_client.py:1107` — [auxiliary_fallback_chain] for label, try_fn in _get_provider_chain():
-- `agent/auxiliary_client.py:1189` — [auxiliary_fallback_chain] # ── Step 2: aggregator / fallback chain ──────────────────────────────
-- `agent/auxiliary_client.py:1191` — [auxiliary_fallback_chain] for label, try_fn in _get_provider_chain():
-- `agent/auxiliary_client.py:2397` — [auxiliary_fallback_chain] # error, fall through to the fallback chain below.
-- `agent/auxiliary_client.py:2417` — [auxiliary_fallback_chain] # auto (the default) = best-effort fallback chain.  (#7559)
-- `agent/auxiliary_client.py:2589` — [auxiliary_fallback_chain] # error, fall through to the fallback chain below.
-- `tools/delegate_tool.py:662` — [delegate_runtime_provider] # bundle (base_url, api_key, api_mode) via the same runtime provider system
-- `tools/delegate_tool.py:854` — [delegate_runtime_provider] provider) is resolved via the runtime provider system — the same path used
-- `tools/delegate_tool.py:909` — [delegate_runtime_provider] from hermes_cli.runtime_provider import resolve_runtime_provider
-- `tools/delegate_tool.py:910` — [delegate_runtime_provider] runtime = resolve_runtime_provider(requested=configured_provider)
-- `hermes_state.py:115` — [session_db] class SessionDB:
-- `batch_runner.py:320` — [trajectory_export] save_trajectories=False,  # We handle saving ourselves
-- `batch_runner.py:346` — [trajectory_export] trajectory = agent._convert_to_trajectory_format(
-- `batch_runner.py:460` — [trajectory_export] trajectory_entry = {
-- `batch_runner.py:474` — [trajectory_export] f.write(json.dumps(trajectory_entry, ensure_ascii=False) + "\n")
-- `benchmarks/tool_call_benchmark.py:3` — [benchmark_suite] Tool-Calling Benchmark — Gemma 4 vs mimo-v2-pro regression test.
-- `benchmarks/tool_call_benchmark.py:9` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py                  # full 100-call suite
-- `benchmarks/tool_call_benchmark.py:10` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py --limit 10       # quick smoke test
-- `benchmarks/tool_call_benchmark.py:11` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py --models nous     # single model
-- `benchmarks/tool_call_benchmark.py:12` — [benchmark_suite] python3 benchmarks/tool_call_benchmark.py --category file   # single category
-- `benchmarks/tool_call_benchmark.py:37` — [benchmark_suite] class ToolCall:
-- `benchmarks/tool_call_benchmark.py:51` — [benchmark_suite] ToolCall("file-01", "file", "Read the file /tmp/test_bench.txt and show me its contents.",
-- `benchmarks/tool_call_benchmark.py:53` — [benchmark_suite] ToolCall("file-02", "file", "Write 'hello benchmark' to /tmp/test_bench_out.txt",
-- `benchmarks/tool_call_benchmark.py:55` — [benchmark_suite] ToolCall("file-03", "file", "Search for the word 'import' in all Python files in the current directory.",
-- `benchmarks/tool_call_benchmark.py:57` — [benchmark_suite] ToolCall("file-04", "file", "Read lines 1-20 of /etc/hosts",
-- `benchmarks/tool_call_benchmark.py:59` — [benchmark_suite] ToolCall("file-05", "file", "Patch /tmp/test_bench_out.txt: replace 'hello' with 'goodbye'",
-- `benchmarks/tool_call_benchmark.py:61` — [benchmark_suite] ToolCall("file-06", "file", "Search for files matching *.py in the current directory.",
-- `benchmarks/tool_call_benchmark.py:63` — [benchmark_suite] ToolCall("file-07", "file", "Read the first 10 lines of /etc/passwd",
-- `benchmarks/tool_call_benchmark.py:65` — [benchmark_suite] ToolCall("file-08", "file", "Write a JSON config to /tmp/bench_config.json with key 'debug': true",
-- `benchmarks/tool_call_benchmark.py:67` — [benchmark_suite] ToolCall("file-09", "file", "Search for 'def test_' in Python test files.",
-- `benchmarks/tool_call_benchmark.py:69` — [benchmark_suite] ToolCall("file-10", "file", "Read /tmp/bench_config.json and tell me what's in it.",
-- `benchmarks/tool_call_benchmark.py:71` — [benchmark_suite] ToolCall("file-11", "file", "Create a file /tmp/bench_readme.md with one line: '# Benchmark'",
-- `benchmarks/tool_call_benchmark.py:73` — [benchmark_suite] ToolCall("file-12", "file", "Search for 'TODO' comments in all .py files.",
-- `benchmarks/tool_call_benchmark.py:75` — [benchmark_suite] ToolCall("file-13", "file", "Read /tmp/bench_readme.md",
-- `benchmarks/tool_call_benchmark.py:77` — [benchmark_suite] ToolCall("file-14", "file", "Patch /tmp/bench_readme.md: replace '# Benchmark' with '# Tool Benchmark'",
-- `benchmarks/tool_call_benchmark.py:78` — [benchmark_suite] "patch", "Tool Benchmark"),
-- `benchmarks/tool_call_benchmark.py:79` — [benchmark_suite] ToolCall("file-15", "file", "Write a Python one-liner to /tmp/bench_hello.py that prints hello.",
-- `benchmarks/tool_call_benchmark.py:81` — [benchmark_suite] ToolCall("file-16", "file", "Search for all .json files in /tmp/.",
-- `benchmarks/tool_call_benchmark.py:83` — [benchmark_suite] ToolCall("file-17", "file", "Read /tmp/bench_hello.py and verify it has print('hello').",
-- `benchmarks/tool_call_benchmark.py:85` — [benchmark_suite] ToolCall("file-18", "file", "Patch /tmp/bench_hello.py to print 'hello world' instead of 'hello'.",
-- `benchmarks/tool_call_benchmark.py:87` — [benchmark_suite] ToolCall("file-19", "file", "List files matching 'bench*' in /tmp/.",
-- `benchmarks/tool_call_benchmark.py:89` — [benchmark_suite] ToolCall("file-20", "file", "Read /tmp/test_bench.txt again and summarize its contents.",
-- `benchmarks/tool_call_benchmark.py:93` — [benchmark_suite] ToolCall("term-01", "terminal", "Run `echo hello world` in the terminal.",
-- `benchmarks/tool_call_benchmark.py:95` — [benchmark_suite] ToolCall("term-02", "terminal", "Run `date` to get the current date and time.",
-- `benchmarks/tool_call_benchmark.py:97` — [benchmark_suite] ToolCall("term-03", "terminal", "Run `uname -a` to get system information.",
-- `benchmarks/tool_call_benchmark.py:99` — [benchmark_suite] ToolCall("term-04", "terminal", "Run `pwd` to show the current directory.",
-- `benchmarks/tool_call_benchmark.py:101` — [benchmark_suite] ToolCall("term-05", "terminal", "Run `ls -la /tmp/ | head -20` to list temp files.",
-- `benchmarks/tool_call_benchmark.py:103` — [benchmark_suite] ToolCall("term-06", "terminal", "Run `whoami` to show the current user.",
-- `benchmarks/tool_call_benchmark.py:105` — [benchmark_suite] ToolCall("term-07", "terminal", "Run `df -h` to show disk usage.",
-- `benchmarks/tool_call_benchmark.py:107` — [benchmark_suite] ToolCall("term-08", "terminal", "Run `python3 --version` to check Python version.",
-- `benchmarks/tool_call_benchmark.py:109` — [benchmark_suite] ToolCall("term-09", "terminal", "Run `cat /etc/hostname` to get the hostname.",
-- `benchmarks/tool_call_benchmark.py:111` — [benchmark_suite] ToolCall("term-10", "terminal", "Run `uptime` to see system uptime.",
-- `benchmarks/tool_call_benchmark.py:113` — [benchmark_suite] ToolCall("term-11", "terminal", "Run `env | grep PATH` to show the PATH variable.",
-- `benchmarks/tool_call_benchmark.py:115` — [benchmark_suite] ToolCall("term-12", "terminal", "Run `wc -l /etc/passwd` to count lines.",
-- `benchmarks/tool_call_benchmark.py:117` — [benchmark_suite] ToolCall("term-13", "terminal", "Run `echo $SHELL` to show the current shell.",
-- `benchmarks/tool_call_benchmark.py:119` — [benchmark_suite] ToolCall("term-14", "terminal", "Run `free -h || vm_stat` to check memory usage.",
-- `benchmarks/tool_call_benchmark.py:121` — [benchmark_suite] ToolCall("term-15", "terminal", "Run `id` to show user and group IDs.",
-- `benchmarks/tool_call_benchmark.py:123` — [benchmark_suite] ToolCall("term-16", "terminal", "Run `hostname` to get the machine hostname.",
-- `benchmarks/tool_call_benchmark.py:125` — [benchmark_suite] ToolCall("term-17", "terminal", "Run `echo {1..5}` to test brace expansion.",
-- `benchmarks/tool_call_benchmark.py:127` — [benchmark_suite] ToolCall("term-18", "terminal", "Run `seq 1 5` to generate a number sequence.",
-- `benchmarks/tool_call_benchmark.py:129` — [benchmark_suite] ToolCall("term-19", "terminal", "Run `python3 -c 'print(2+2)'` to compute 2+2.",
-- `benchmarks/tool_call_benchmark.py:131` — [benchmark_suite] ToolCall("term-20", "terminal", "Run `ls -d /tmp/bench* 2>/dev/null | wc -l` to count bench files.",
-- `benchmarks/tool_call_benchmark.py:135` — [benchmark_suite] ToolCall("code-01", "code", "Execute a Python script that computes factorial of 10.",
-- `benchmarks/tool_call_benchmark.py:137` — [benchmark_suite] ToolCall("code-02", "code", "Run Python to read /tmp/test_bench.txt and count its words.",
-- `benchmarks/tool_call_benchmark.py:139` — [benchmark_suite] ToolCall("code-03", "code", "Execute Python to generate the first 20 Fibonacci numbers.",
-- `benchmarks/tool_call_benchmark.py:141` — [benchmark_suite] ToolCall("code-04", "code", "Run Python to parse JSON from a string and print keys.",
-- `benchmarks/tool_call_benchmark.py:143` — [benchmark_suite] ToolCall("code-05", "code", "Execute Python to list all files in /tmp/ matching 'bench*'.",
-- `benchmarks/tool_call_benchmark.py:145` — [benchmark_suite] ToolCall("code-06", "code", "Run Python to compute the sum of squares from 1 to 100.",
-- `benchmarks/tool_call_benchmark.py:147` — [benchmark_suite] ToolCall("code-07", "code", "Execute Python to check if 'racecar' is a palindrome.",
-- `benchmarks/tool_call_benchmark.py:149` — [benchmark_suite] ToolCall("code-08", "code", "Run Python to create a CSV string with 5 rows of sample data.",
-- `benchmarks/tool_call_benchmark.py:151` — [benchmark_suite] ToolCall("code-09", "code", "Execute Python to sort a list [5,2,8,1,9] and print the result.",
-- `benchmarks/tool_call_benchmark.py:153` — [benchmark_suite] ToolCall("code-10", "code", "Run Python to count lines in /etc/passwd.",
-- `benchmarks/tool_call_benchmark.py:155` — [benchmark_suite] ToolCall("code-11", "code", "Execute Python to hash the string 'benchmark' with SHA256.",
-- `benchmarks/tool_call_benchmark.py:157` — [benchmark_suite] ToolCall("code-12", "code", "Run Python to get the current UTC timestamp.",
-- `benchmarks/tool_call_benchmark.py:159` — [benchmark_suite] ToolCall("code-13", "code", "Execute Python to convert 'hello world' to uppercase and reverse it.",
-- `benchmarks/tool_call_benchmark.py:161` — [benchmark_suite] ToolCall("code-14", "code", "Run Python to create a dictionary of system info (platform, python version).",
-- `benchmarks/tool_call_benchmark.py:163` — [benchmark_suite] ToolCall("code-15", "code", "Execute Python to check internet connectivity by resolving google.com.",
-- `benchmarks/tool_call_benchmark.py:167` — [benchmark_suite] ToolCall("deleg-01", "delegate", "Use a subagent to find all .log files in /tmp/.",
-- `benchmarks/tool_call_benchmark.py:169` — [benchmark_suite] ToolCall("deleg-02", "delegate", "Delegate to a subagent: what is 15 * 37?",
-- `benchmarks/tool_call_benchmark.py:171` — [benchmark_suite] ToolCall("deleg-03", "delegate", "Use a subagent to check if Python 3 is installed and its version.",
-- `benchmarks/tool_call_benchmark.py:173` — [benchmark_suite] ToolCall("deleg-04", "delegate", "Delegate: read /tmp/test_bench.txt and summarize it in one sentence.",
-- `benchmarks/tool_call_benchmark.py:175` — [benchmark_suite] ToolCall("deleg-05", "delegate", "Use a subagent to list the contents of /tmp/ directory.",
-- `benchmarks/tool_call_benchmark.py:177` — [benchmark_suite] ToolCall("deleg-06", "delegate", "Delegate: count the number of .py files in the current directory.",
-- `benchmarks/tool_call_benchmark.py:179` — [benchmark_suite] ToolCall("deleg-07", "delegate", "Use a subagent to check disk space with df -h.",
-- `benchmarks/tool_call_benchmark.py:181` — [benchmark_suite] ToolCall("deleg-08", "delegate", "Delegate: what OS are we running on?",
-- `benchmarks/tool_call_benchmark.py:183` — [benchmark_suite] ToolCall("deleg-09", "delegate", "Use a subagent to find the hostname of this machine.",
-- `benchmarks/tool_call_benchmark.py:185` — [benchmark_suite] ToolCall("deleg-10", "delegate", "Delegate: create a temp file /tmp/bench_deleg.txt with 'done'.",
-- `benchmarks/tool_call_benchmark.py:189` — [benchmark_suite] ToolCall("todo-01", "todo", "Add a todo item: 'Run benchmark suite'",
-- `benchmarks/tool_call_benchmark.py:190` — [benchmark_suite] "todo", "benchmark"),
-- `benchmarks/tool_call_benchmark.py:191` — [benchmark_suite] ToolCall("todo-02", "todo", "Show me the current todo list.",
-- `benchmarks/tool_call_benchmark.py:193` — [benchmark_suite] ToolCall("todo-03", "todo", "Mark the first todo item as completed.",
-- `benchmarks/tool_call_benchmark.py:195` — [benchmark_suite] ToolCall("todo-04", "todo", "Add a todo: 'Review benchmark results' with status pending.",
-- `benchmarks/tool_call_benchmark.py:197` — [benchmark_suite] ToolCall("todo-05", "todo", "Clear all completed todos.",
-- `benchmarks/tool_call_benchmark.py:199` — [benchmark_suite] ToolCall("todo-06", "memory", "Save this to memory: 'benchmark ran on {date}'".format(
-- `benchmarks/tool_call_benchmark.py:201` — [benchmark_suite] "memory", "benchmark"),
-- `benchmarks/tool_call_benchmark.py:202` — [benchmark_suite] ToolCall("todo-07", "memory", "Search memory for 'benchmark'.",
-- `benchmarks/tool_call_benchmark.py:203` — [benchmark_suite] "memory", "benchmark"),
-- `benchmarks/tool_call_benchmark.py:204` — [benchmark_suite] ToolCall("todo-08", "memory", "Add a memory note: 'test models are gemma-4 and mimo-v2-pro'.",
-- `benchmarks/tool_call_benchmark.py:206` — [benchmark_suite] ToolCall("todo-09", "todo", "Add three todo items: 'analyze', 'report', 'cleanup'.",
-- `benchmarks/tool_call_benchmark.py:208` — [benchmark_suite] ToolCall("todo-10", "memory", "Search memory for any notes about models.",
-- `benchmarks/tool_call_benchmark.py:212` — [benchmark_suite] ToolCall("skill-01", "skills", "List all available skills.",
-- `benchmarks/tool_call_benchmark.py:214` — [benchmark_suite] ToolCall("skill-02", "skills", "View the skill called 'test-driven-development'.",
-- `benchmarks/tool_call_benchmark.py:216` — [benchmark_suite] ToolCall("skill-03", "skills", "Search for skills related to 'git'.",
-- `benchmarks/tool_call_benchmark.py:218` — [benchmark_suite] ToolCall("skill-04", "skills", "View the 'code-review' skill.",
-- `benchmarks/tool_call_benchmark.py:220` — [benchmark_suite] ToolCall("skill-05", "skills", "List all skills in the 'devops' category.",
-- `benchmarks/tool_call_benchmark.py:222` — [benchmark_suite] ToolCall("skill-06", "skills", "View the 'systematic-debugging' skill.",
-- `benchmarks/tool_call_benchmark.py:224` — [benchmark_suite] ToolCall("skill-07", "skills", "Search for skills about 'testing'.",
-- `benchmarks/tool_call_benchmark.py:226` — [benchmark_suite] ToolCall("skill-08", "skills", "View the 'writing-plans' skill.",
-- `benchmarks/tool_call_benchmark.py:228` — [benchmark_suite] ToolCall("skill-09", "skills", "List skills in 'software-development' category.",
-- `benchmarks/tool_call_benchmark.py:230` — [benchmark_suite] ToolCall("skill-10", "skills", "View the 'pr-review-discipline' skill.",
-- `benchmarks/tool_call_benchmark.py:234` — [benchmark_suite] ToolCall("file-21", "file", "Write a Python snippet to /tmp/bench_sort.py that sorts [3,1,2].",
-- `benchmarks/tool_call_benchmark.py:236` — [benchmark_suite] ToolCall("file-22", "file", "Read /tmp/bench_sort.py back and confirm it exists.",
-- `benchmarks/tool_call_benchmark.py:238` — [benchmark_suite] ToolCall("file-23", "file", "Search for 'class' in all .py files in the benchmarks directory.",
-- `benchmarks/tool_call_benchmark.py:240` — [benchmark_suite] ToolCall("term-21", "terminal", "Run `cat /etc/os-release 2>/dev/null || sw_vers 2>/dev/null` for OS info.",
-- `benchmarks/tool_call_benchmark.py:242` — [benchmark_suite] ToolCall("term-22", "terminal", "Run `nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null` for CPU count.",
-- `benchmarks/tool_call_benchmark.py:244` — [benchmark_suite] ToolCall("code-16", "code", "Execute Python to flatten a nested list [[1,2],[3,4],[5]].",
-- `benchmarks/tool_call_benchmark.py:246` — [benchmark_suite] ToolCall("code-17", "code", "Run Python to check if a number 17 is prime.",
-- `benchmarks/tool_call_benchmark.py:248` — [benchmark_suite] ToolCall("deleg-11", "delegate", "Delegate: what is the current working directory?",
-- `benchmarks/tool_call_benchmark.py:250` — [benchmark_suite] ToolCall("todo-11", "todo", "Add a todo: 'Finalize benchmark report' status pending.",
-- `benchmarks/tool_call_benchmark.py:252` — [benchmark_suite] ToolCall("todo-12", "memory", "Store fact: 'benchmark categories: file, terminal, code, delegate, todo, memory, skills'.",
-- `benchmarks/tool_call_benchmark.py:254` — [benchmark_suite] ToolCall("skill-11", "skills", "Search for skills about 'deployment'.",
-- `benchmarks/tool_call_benchmark.py:256` — [benchmark_suite] ToolCall("skill-12", "skills", "View the 'gitea-burn-cycle' skill.",
-- `benchmarks/tool_call_benchmark.py:258` — [benchmark_suite] ToolCall("skill-13", "skills", "List all available skill categories.",
-- `benchmarks/tool_call_benchmark.py:260` — [benchmark_suite] ToolCall("skill-14", "skills", "Search for skills related to 'memory'.",
-- `benchmarks/tool_call_benchmark.py:262` — [benchmark_suite] ToolCall("skill-15", "skills", "View the 'mimo-swarm' skill.",
-- `benchmarks/tool_call_benchmark.py:311` — [benchmark_suite] """Create prerequisite files for the benchmark."""
-- `benchmarks/tool_call_benchmark.py:313` — [benchmark_suite] "This is a benchmark test file.\n"
-- `benchmarks/tool_call_benchmark.py:349` — [benchmark_suite] "You are a benchmark test runner. Execute the user's request by calling "
-- `benchmarks/tool_call_benchmark.py:406` — [benchmark_suite] """Generate markdown benchmark report."""
-- `benchmarks/tool_call_benchmark.py:428` — [benchmark_suite] f"# Tool-Calling Benchmark Report",
-- `benchmarks/tool_call_benchmark.py:535` — [benchmark_suite] parser = argparse.ArgumentParser(description="Tool-calling benchmark")
-- `benchmarks/tool_call_benchmark.py:544` — [benchmark_suite] help="Output report path (default: benchmarks/gemma4-tool-calling-YYYY-MM-DD.md)")
-- `benchmarks/tool_call_benchmark.py:565` — [benchmark_suite] output_path = Path(args.output) if args.output else REPO_ROOT / "benchmarks" / f"gemma4-tool-calling-{date_str}.md"
-- `benchmarks/tool_call_benchmark.py:575` — [benchmark_suite] print(f"Benchmark: {len(suite)} tests × {len(model_specs)} models = {len(suite) * len(model_specs)} calls")
-
-## Suggested next slice
-
-1. Build an exporter that emits SessionDB + trajectory data into a TensorZero-friendly offline dataset.
-2. Define percentage-based canary controls before attempting any gateway replacement.
-3. Keep Hermes routing authoritative until TensorZero proves parity across CLI, gateway, cron, auxiliary, and delegation surfaces.

scripts/tensorzero_eval_packet.py

@@ -1,318 +0,0 @@
-#!/usr/bin/env python3
-"""Generate a grounded TensorZero evaluation packet for Hermes.
-
-This script inventories the current Hermes routing/evaluation surfaces, then
-builds a markdown packet assessing how much of issue #860 can be satisfied by
-TensorZero and where the migration risk still lives.
-"""
-
-from __future__ import annotations
-
-import argparse
-import json
-import re
-from dataclasses import asdict, dataclass
-from pathlib import Path
-from typing import Iterable
-
-ISSUE_NUMBER = 860
-ISSUE_TITLE = "tensorzero LLMOps platform evaluation"
-ISSUE_URL = "https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/860"
-DEFAULT_OUTPUT = Path("docs/evaluations/tensorzero-860-evaluation.md")
-DEFAULT_JSON_OUTPUT = Path("docs/evaluations/tensorzero-860-evaluation.json")
-
-
-@dataclass(frozen=True)
-class TouchpointPattern:
-    label: str
-    file_path: str
-    regex: str
-    description: str
-
-
-@dataclass(frozen=True)
-class Touchpoint:
-    label: str
-    file_path: str
-    line_number: int
-    matched_text: str
-
-
-@dataclass(frozen=True)
-class RequirementStatus:
-    key: str
-    name: str
-    status: str
-    evidence_labels: tuple[str, ...]
-    summary: str
-
-
-@dataclass(frozen=True)
-class EvaluationReport:
-    issue_number: int
-    issue_title: str
-    issue_url: str
-    recommendation: str
-    touchpoints: tuple[Touchpoint, ...]
-    requirements: tuple[RequirementStatus, ...]
-
-
-PATTERNS: tuple[TouchpointPattern, ...] = (
-    TouchpointPattern(
-        label="fallback_chain",
-        file_path="run_agent.py",
-        regex=r"_fallback_chain|fallback_providers|fallback_model",
-        description="Primary agent fallback-provider chain in the core conversation loop.",
-    ),
-    TouchpointPattern(
-        label="provider_routing_config",
-        file_path="cli.py",
-        regex=r"provider_routing|fallback_providers|smart_model_routing",
-        description="CLI-owned provider routing and fallback configuration surfaces.",
-    ),
-    TouchpointPattern(
-        label="runtime_provider",
-        file_path="hermes_cli/runtime_provider.py",
-        regex=r"def resolve_runtime_provider|def resolve_requested_provider",
-        description="Central runtime provider resolution for CLI, gateway, cron, and helpers.",
-    ),
-    TouchpointPattern(
-        label="smart_model_routing",
-        file_path="agent/smart_model_routing.py",
-        regex=r"def resolve_turn_route|def choose_cheap_model_route",
-        description="Cheap-vs-strong turn routing that TensorZero would need to absorb or replace.",
-    ),
-    TouchpointPattern(
-        label="gateway_provider_routing",
-        file_path="gateway/run.py",
-        regex=r"def _load_provider_routing|def _load_fallback_model|def _load_smart_model_routing",
-        description="Gateway-specific loading of routing, fallback, and smart-model policies.",
-    ),
-    TouchpointPattern(
-        label="cron_runtime_provider",
-        file_path="cron/scheduler.py",
-        regex=r"resolve_runtime_provider|resolve_turn_route|provider_routing|fallback_model",
-        description="Cron execution path that re-resolves providers and routing on every run.",
-    ),
-    TouchpointPattern(
-        label="auxiliary_fallback_chain",
-        file_path="agent/auxiliary_client.py",
-        regex=r"fallback chain|_get_provider_chain|provider chain",
-        description="Auxiliary task routing/fallback chain outside the main inference path.",
-    ),
-    TouchpointPattern(
-        label="delegate_runtime_provider",
-        file_path="tools/delegate_tool.py",
-        regex=r"runtime provider system|resolve the full credential bundle|resolve_runtime_provider",
-        description="Subagent/delegation routing path that would also need TensorZero parity.",
-    ),
-    TouchpointPattern(
-        label="session_db",
-        file_path="hermes_state.py",
-        regex=r"class SessionDB",
-        description="Session persistence surface that could feed TensorZero optimization/eval data.",
-    ),
-    TouchpointPattern(
-        label="trajectory_export",
-        file_path="batch_runner.py",
-        regex=r"trajectory_entry|save_trajectories|_convert_to_trajectory_format",
-        description="Trajectory export surface for offline optimization and replay data.",
-    ),
-    TouchpointPattern(
-        label="benchmark_suite",
-        file_path="benchmarks/tool_call_benchmark.py",
-        regex=r"ToolCall\(|class ToolCall|benchmark",
-        description="Existing benchmark/evaluation harness that could map to TensorZero experiments.",
-    ),
-)
-
-
-def _iter_matches(pattern: TouchpointPattern, text: str) -> Iterable[Touchpoint]:
-    regex = re.compile(pattern.regex, re.IGNORECASE)
-    for line_number, line in enumerate(text.splitlines(), start=1):
-        if regex.search(line):
-            yield Touchpoint(
-                label=pattern.label,
-                file_path=pattern.file_path,
-                line_number=line_number,
-                matched_text=line.strip(),
-            )
-
-
-def scan_touchpoints(repo_root: Path) -> list[Touchpoint]:
-    touchpoints: list[Touchpoint] = []
-    for pattern in PATTERNS:
-        path = repo_root / pattern.file_path
-        if not path.exists():
-            continue
-        text = path.read_text(encoding="utf-8")
-        touchpoints.extend(_iter_matches(pattern, text))
-    return touchpoints
-
-
-def build_requirement_matrix(touchpoints: list[Touchpoint]) -> list[RequirementStatus]:
-    labels = {tp.label for tp in touchpoints}
-
-    matrix: list[RequirementStatus] = []
-    gateway_labels = (
-        "fallback_chain",
-        "runtime_provider",
-        "gateway_provider_routing",
-        "cron_runtime_provider",
-        "auxiliary_fallback_chain",
-        "delegate_runtime_provider",
-    )
-    gateway_hits = tuple(label for label in gateway_labels if label in labels)
-    gateway_status = "partial" if len(gateway_hits) >= 4 else "gap"
-    gateway_summary = (
-        "Hermes already spreads provider routing across core agent, runtime provider, gateway, cron, auxiliary, and delegation seams; "
-        "TensorZero would need parity across all of them before it can replace the gateway layer."
-        if gateway_hits else
-        "No grounded routing surfaces were found for a gateway replacement assessment."
-    )
-    matrix.append(RequirementStatus("gateway_replacement", "Gateway replacement scope", gateway_status, gateway_hits, gateway_summary))
-
-    config_labels = (
-        "provider_routing_config",
-        "runtime_provider",
-        "smart_model_routing",
-        "fallback_chain",
-    )
-    config_hits = tuple(label for label in config_labels if label in labels)
-    config_status = "partial" if len(config_hits) >= 3 else "gap"
-    config_summary = (
-        "Hermes has multiple config concepts to migrate (`provider_routing`, `fallback_providers`, `smart_model_routing`, runtime provider resolution), "
-        "so TensorZero is not a drop-in config swap."
-        if config_hits else
-        "No current config migration surface was found."
-    )
-    matrix.append(RequirementStatus("config_migration", "Config migration", config_status, config_hits, config_summary))
-
-    canary_hits: tuple[str, ...] = tuple()
-    canary_summary = (
-        "The repo shows semantic routing and fallback, but no grounded 10% traffic-split canary mechanism. "
-        "A TensorZero cutover would need new percentage-based rollout controls and observability hooks."
-    )
-    matrix.append(RequirementStatus("canary_rollout", "10% traffic canary", "gap", canary_hits, canary_summary))
-
-    session_labels = ("session_db", "trajectory_export")
-    session_hits = tuple(label for label in session_labels if label in labels)
-    session_status = "partial" if len(session_hits) == len(session_labels) else "gap"
-    session_summary = (
-        "Hermes already has SessionDB and trajectory export surfaces that can feed offline optimization data, "
-        "but not a TensorZero-native ingestion path yet."
-        if session_hits else
-        "No session-data surface was found for prompt optimization."
-    )
-    matrix.append(RequirementStatus("session_feedback", "Session data for prompt optimization", session_status, session_hits, session_summary))
-
-    eval_labels = ("benchmark_suite", "trajectory_export")
-    eval_hits = tuple(label for label in eval_labels if label in labels)
-    eval_status = "partial" if "benchmark_suite" in eval_hits else "gap"
-    eval_summary = (
-        "Hermes already has benchmark/trajectory machinery that can seed TensorZero A/B evaluation, "
-        "but no integrated TensorZero experiment runner or live evaluation gateway."
-        if eval_hits else
-        "No evaluation harness was found to support TensorZero A/B testing."
-    )
-    matrix.append(RequirementStatus("evaluation_suite", "Evaluation suite / A/B testing", eval_status, eval_hits, eval_summary))
-
-    return matrix
-
-
-def build_report(touchpoints: list[Touchpoint], requirement_matrix: list[RequirementStatus]) -> EvaluationReport:
-    recommendation = (
-        "Not ready for direct replacement. Recommend a shadow-evaluation phase first: keep Hermes routing live, "
-        "inventory the migration seams, export SessionDB/trajectory data into an offline TensorZero experiment loop, "
-        "and only design a canary gateway once percentage-based rollout controls exist."
-    )
-    return EvaluationReport(
-        issue_number=ISSUE_NUMBER,
-        issue_title=ISSUE_TITLE,
-        issue_url=ISSUE_URL,
-        recommendation=recommendation,
-        touchpoints=tuple(touchpoints),
-        requirements=tuple(requirement_matrix),
-    )
-
-
-def build_markdown(report: EvaluationReport) -> str:
-    lines: list[str] = []
-    lines.append("# TensorZero Evaluation Packet")
-    lines.append("")
-    lines.append(f"Issue #{report.issue_number}: [{report.issue_title}]({report.issue_url})")
-    lines.append("")
-    lines.append("## Scope")
-    lines.append("")
-    lines.append("This packet evaluates TensorZero as a possible replacement for Hermes' custom provider-routing stack.")
-    lines.append("It is intentionally grounded in the current repo state rather than a speculative cutover plan.")
-    lines.append("")
-    lines.append("## Issue requirements being evaluated")
-    lines.append("")
-    lines.append("- Deploy tensorzero gateway (Rust binary)")
-    lines.append("- Migrate provider routing config")
-    lines.append("- Test with canary (10% traffic) before full cutover")
-    lines.append("- Feed session data for prompt optimization")
-    lines.append("- Evaluation suite for A/B testing models")
-    lines.append("")
-    lines.append("## Recommendation")
-    lines.append("")
-    lines.append(report.recommendation)
-    lines.append("")
-    lines.append("## Requirement matrix")
-    lines.append("")
-    lines.append("| Requirement | Status | Evidence labels | Summary |")
-    lines.append("| --- | --- | --- | --- |")
-    for row in report.requirements:
-        evidence = ", ".join(row.evidence_labels) if row.evidence_labels else "—"
-        lines.append(f"| {row.name} | {row.status} | {evidence} | {row.summary} |")
-    lines.append("")
-    lines.append("## Grounded Hermes touchpoints")
-    lines.append("")
-    if report.touchpoints:
-        for tp in report.touchpoints:
-            lines.append(f"- `{tp.file_path}:{tp.line_number}` — [{tp.label}] {tp.matched_text}")
-    else:
-        lines.append("- No routing/evaluation touchpoints were found.")
-    lines.append("")
-    lines.append("## Suggested next slice")
-    lines.append("")
-    lines.append("1. Build an exporter that emits SessionDB + trajectory data into a TensorZero-friendly offline dataset.")
-    lines.append("2. Define percentage-based canary controls before attempting any gateway replacement.")
-    lines.append("3. Keep Hermes routing authoritative until TensorZero proves parity across CLI, gateway, cron, auxiliary, and delegation surfaces.")
-    lines.append("")
-    return "\n".join(lines).rstrip() + "\n"
-
-
-def write_outputs(report: EvaluationReport, markdown_path: Path, json_path: Path | None = None) -> None:
-    markdown_path.parent.mkdir(parents=True, exist_ok=True)
-    markdown_path.write_text(build_markdown(report), encoding="utf-8")
-    if json_path is not None:
-        json_path.parent.mkdir(parents=True, exist_ok=True)
-        json_path.write_text(json.dumps(asdict(report), indent=2), encoding="utf-8")
-
-
-def parse_args() -> argparse.Namespace:
-    parser = argparse.ArgumentParser(description="Generate a grounded TensorZero evaluation packet for Hermes")
-    parser.add_argument("--repo-root", default=".", help="Hermes repo root to scan")
-    parser.add_argument("--output", default=str(DEFAULT_OUTPUT), help="Markdown output path")
-    parser.add_argument("--json-output", default=str(DEFAULT_JSON_OUTPUT), help="Optional JSON output path")
-    return parser.parse_args()
-
-
-def main() -> int:
-    args = parse_args()
-    repo_root = Path(args.repo_root).resolve()
-    touchpoints = scan_touchpoints(repo_root)
-    matrix = build_requirement_matrix(touchpoints)
-    report = build_report(touchpoints, matrix)
-    json_output = Path(args.json_output) if args.json_output else None
-    write_outputs(report, Path(args.output), json_output)
-    print(f"Wrote {args.output}")
-    if json_output is not None:
-        print(f"Wrote {json_output}")
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

tests/test_tensorzero_eval_packet.py

@@ -1,149 +0,0 @@
-from pathlib import Path
-import sys
-
-SCRIPT_DIR = Path(__file__).resolve().parents[1] / "scripts"
-sys.path.insert(0, str(SCRIPT_DIR))
-
-import tensorzero_eval_packet as tz
-
-
-def test_scan_touchpoints_finds_expected_matches(tmp_path):
-    (tmp_path / "run_agent.py").write_text(
-        "self._fallback_chain = []\n# Provider fallback chain\n"
-    )
-    (tmp_path / "hermes_cli").mkdir()
-    (tmp_path / "hermes_cli" / "runtime_provider.py").write_text(
-        "def resolve_runtime_provider():\n    return {}\n"
-    )
-    (tmp_path / "agent").mkdir()
-    (tmp_path / "agent" / "smart_model_routing.py").write_text(
-        "def resolve_turn_route(user_message, routing_config, primary):\n    return primary\n"
-    )
-    (tmp_path / "gateway").mkdir()
-    (tmp_path / "gateway" / "run.py").write_text(
-        "def _load_provider_routing():\n    return {}\n"
-    )
-    (tmp_path / "cron").mkdir()
-    (tmp_path / "cron" / "scheduler.py").write_text(
-        "runtime = resolve_runtime_provider()\nturn_route = resolve_turn_route('x', {}, {})\n"
-    )
-    (tmp_path / "hermes_state.py").write_text("class SessionDB:\n    pass\n")
-    (tmp_path / "benchmarks").mkdir()
-    (tmp_path / "benchmarks" / "tool_call_benchmark.py").write_text(
-        "class ToolCall: ...\n"
-    )
-
-    touchpoints = tz.scan_touchpoints(tmp_path)
-
-    labels = {tp.label for tp in touchpoints}
-    assert "fallback_chain" in labels
-    assert "runtime_provider" in labels
-    assert "smart_model_routing" in labels
-    assert "gateway_provider_routing" in labels
-    assert "cron_runtime_provider" in labels
-    assert "session_db" in labels
-    assert "benchmark_suite" in labels
-
-
-def test_build_requirement_matrix_marks_canary_as_gap_without_split_support():
-    touchpoints = [
-        tz.Touchpoint(
-            label="runtime_provider",
-            file_path="hermes_cli/runtime_provider.py",
-            line_number=10,
-            matched_text="def resolve_runtime_provider",
-        ),
-        tz.Touchpoint(
-            label="provider_routing_config",
-            file_path="cli.py",
-            line_number=20,
-            matched_text='provider_routing',
-        ),
-        tz.Touchpoint(
-            label="fallback_chain",
-            file_path="run_agent.py",
-            line_number=21,
-            matched_text='_fallback_chain = []',
-        ),
-        tz.Touchpoint(
-            label="smart_model_routing",
-            file_path="agent/smart_model_routing.py",
-            line_number=30,
-            matched_text='resolve_turn_route',
-        ),
-        tz.Touchpoint(
-            label="gateway_provider_routing",
-            file_path="gateway/run.py",
-            line_number=35,
-            matched_text='def _load_provider_routing',
-        ),
-        tz.Touchpoint(
-            label="cron_runtime_provider",
-            file_path="cron/scheduler.py",
-            line_number=36,
-            matched_text='runtime = resolve_runtime_provider()',
-        ),
-        tz.Touchpoint(
-            label="session_db",
-            file_path="hermes_state.py",
-            line_number=40,
-            matched_text='class SessionDB',
-        ),
-        tz.Touchpoint(
-            label="trajectory_export",
-            file_path="batch_runner.py",
-            line_number=50,
-            matched_text='trajectory_entry',
-        ),
-        tz.Touchpoint(
-            label="benchmark_suite",
-            file_path="benchmarks/tool_call_benchmark.py",
-            line_number=60,
-            matched_text='ToolCall',
-        ),
-    ]
-
-    matrix = tz.build_requirement_matrix(touchpoints)
-    by_key = {row.key: row for row in matrix}
-
-    assert by_key["gateway_replacement"].status == "partial"
-    assert by_key["config_migration"].status == "partial"
-    assert by_key["canary_rollout"].status == "gap"
-    assert by_key["session_feedback"].status == "partial"
-    assert by_key["evaluation_suite"].status == "partial"
-
-
-def test_build_markdown_renders_recommendation_and_touchpoints():
-    touchpoints = [
-        tz.Touchpoint(
-            label="runtime_provider",
-            file_path="hermes_cli/runtime_provider.py",
-            line_number=10,
-            matched_text="def resolve_runtime_provider",
-        ),
-        tz.Touchpoint(
-            label="session_db",
-            file_path="hermes_state.py",
-            line_number=40,
-            matched_text='class SessionDB',
-        ),
-    ]
-    matrix = tz.build_requirement_matrix(touchpoints)
-    report = tz.build_report(touchpoints, matrix)
-    markdown = tz.build_markdown(report)
-
-    assert "# TensorZero Evaluation Packet" in markdown
-    assert "gateway_replacement" not in markdown  # human labels, not raw keys
-    assert "Gateway replacement scope" in markdown
-    assert "Not ready for direct replacement" in markdown
-    assert "hermes_cli/runtime_provider.py:10" in markdown
-    assert "hermes_state.py:40" in markdown
-
-
-def test_issue_context_is_embedded_in_report():
-    report = tz.build_report([], [])
-    markdown = tz.build_markdown(report)
-
-    assert "Issue #860" in markdown
-    assert "tensorzero" in markdown.lower()
-    assert "10% traffic" in markdown

tests/test_vision_benchmark.py

@@ -11,12 +11,14 @@ import pytest
 sys.path.insert(0, str(Path(__file__).parent.parent / "benchmarks"))
 
 from vision_benchmark import (
+    analyze_with_model,
     compute_ocr_accuracy,
     compute_description_completeness,
     compute_structural_accuracy,
     aggregate_results,
     to_markdown,
     generate_sample_dataset,
+    load_dataset,
     MODELS,
     EVAL_PROMPTS,
 )
@@ -197,6 +199,71 @@ class TestMarkdown:
 
 
 class TestDataset:
+    def test_repo_dataset_uses_local_image_paths(self):
+        dataset_path = Path(__file__).parent.parent / "benchmarks" / "test_images.json"
+        dataset = json.loads(dataset_path.read_text())
+
+        assert dataset, "benchmark dataset should not be empty"
+        assert all(not entry["url"].startswith(("http://", "https://")) for entry in dataset)
+
+    def test_load_dataset_resolves_relative_local_paths(self, tmp_path):
+        images_dir = tmp_path / "images"
+        images_dir.mkdir()
+        image_path = images_dir / "sample.png"
+        image_path.write_bytes(b"png-bytes")
+
+        dataset_path = tmp_path / "dataset.json"
+        dataset_path.write_text(json.dumps([
+            {
+                "id": "sample",
+                "url": "images/sample.png",
+                "category": "photo",
+                "expected_keywords": [],
+                "expected_structure": {"min_length": 30, "min_sentences": 1},
+            }
+        ]))
+
+        loaded = load_dataset(str(dataset_path))
+
+        assert loaded[0]["url"] == str(image_path.resolve())
+
+    @pytest.mark.asyncio
+    async def test_analyze_with_model_encodes_local_file_as_data_url(self, tmp_path, monkeypatch):
+        image_path = tmp_path / "tiny.png"
+        image_path.write_bytes(
+            bytes.fromhex(
+                "89504E470D0A1A0A"
+                "0000000D49484452000000010000000108060000001F15C489"
+                "0000000D49444154789C6360000002000154A24F5D00000000"
+                "49454E44AE426082"
+            )
+        )
+
+        fake_response = MagicMock()
+        fake_response.raise_for_status.return_value = None
+        fake_response.json.return_value = {
+            "choices": [{"message": {"content": "Looks like a tiny image."}}],
+            "usage": {"prompt_tokens": 1, "completion_tokens": 2, "total_tokens": 3},
+        }
+
+        fake_client = MagicMock()
+        fake_client.post = AsyncMock(return_value=fake_response)
+        fake_ctx = MagicMock()
+        fake_ctx.__aenter__ = AsyncMock(return_value=fake_client)
+        fake_ctx.__aexit__ = AsyncMock(return_value=None)
+
+        monkeypatch.setenv("OPENROUTER_API_KEY", "test-key")
+        with patch("httpx.AsyncClient", return_value=fake_ctx):
+            result = await analyze_with_model(
+                str(image_path),
+                "Describe this image",
+                {"provider": "openrouter", "model_id": "fake/model"},
+            )
+
+        assert result["success"] is True
+        sent_url = fake_client.post.await_args.kwargs["json"]["messages"][0]["content"][1]["image_url"]["url"]
+        assert sent_url.startswith("data:image/png;base64,")
+
     def test_sample_dataset_has_entries(self):
         dataset = generate_sample_dataset()
         assert len(dataset) >= 4