docs: add grounded tensorzero evaluation packet (#860)

- add a script that inventories Hermes routing/evaluation surfaces relevant to a TensorZero cutover
- generate a markdown and JSON evaluation packet for issue #860
- score gateway replacement, config migration, canary rollout, session feedback, and eval-suite readiness
- add focused regression tests for touchpoint scanning, requirement scoring, and report rendering

Refs #860

agent/anthropic_adapter.py

@@ -1396,8 +1396,6 @@ def normalize_anthropic_response(
         "tool_use": "tool_calls",
         "max_tokens": "length",
         "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
     }
     finish_reason = stop_reason_map.get(response.stop_reason, "stop")
 
@@ -1411,42 +1409,3 @@ def normalize_anthropic_response(
         ),
         finish_reason,
     )
-
-
-def normalize_anthropic_response_v2(
-    response,
-    strip_tool_prefix: bool = False,
-) -> "NormalizedResponse":
-    """Normalize Anthropic response to NormalizedResponse.
-
-    Wraps the existing normalize_anthropic_response() and maps its output
-    to the shared transport types. This allows incremental migration
-    without disturbing the legacy call sites.
-    """
-    from agent.transports.types import NormalizedResponse, build_tool_call
-
-    assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
-
-    tool_calls = None
-    if assistant_msg.tool_calls:
-        tool_calls = [
-            build_tool_call(
-                id=tc.id,
-                name=tc.function.name,
-                arguments=tc.function.arguments,
-            )
-            for tc in assistant_msg.tool_calls
-        ]
-
-    provider_data = {}
-    if getattr(assistant_msg, "reasoning_details", None):
-        provider_data["reasoning_details"] = assistant_msg.reasoning_details
-
-    return NormalizedResponse(
-        content=assistant_msg.content,
-        tool_calls=tool_calls,
-        finish_reason=finish_reason,
-        reasoning=getattr(assistant_msg, "reasoning", None),
-        usage=None,
-        provider_data=provider_data or None,
-    )

agent/transports/__init__.py

@@ -1,57 +0,0 @@
-"""Transport layer types and registry for provider response normalization.
-
-Usage:
-    from agent.transports import get_transport
-    transport = get_transport("anthropic_messages")
-    result = transport.normalize_response(raw_response)
-"""
-
-from agent.transports.types import (  # noqa: F401
-    NormalizedResponse,
-    ToolCall,
-    Usage,
-    build_tool_call,
-    map_finish_reason,
-)
-
-_REGISTRY: dict = {}
-
-
-def register_transport(api_mode: str, transport_cls: type) -> None:
-    """Register a transport class for an api_mode string."""
-    _REGISTRY[api_mode] = transport_cls
-
-
-def get_transport(api_mode: str):
-    """Get a transport instance for the given api_mode.
-
-    Returns None if no transport is registered for this api_mode.
-    This allows gradual migration — call sites can check for None
-    and fall back to the legacy code path.
-    """
-    if not _REGISTRY:
-        _discover_transports()
-    cls = _REGISTRY.get(api_mode)
-    if cls is None:
-        return None
-    return cls()
-
-
-def _discover_transports() -> None:
-    """Import all transport modules to trigger auto-registration."""
-    try:
-        import agent.transports.anthropic  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.codex  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.chat_completions  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.bedrock  # noqa: F401
-    except ImportError:
-        pass

agent/transports/anthropic.py

@@ -1,95 +0,0 @@
-"""Anthropic Messages API transport.
-
-Delegates to the existing adapter functions in agent/anthropic_adapter.py.
-This transport owns format conversion and normalization — NOT client lifecycle.
-"""
-
-from typing import Any, Dict, List, Optional
-
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse
-
-
-class AnthropicTransport(ProviderTransport):
-    """Transport for api_mode='anthropic_messages'."""
-
-    @property
-    def api_mode(self) -> str:
-        return "anthropic_messages"
-
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        from agent.anthropic_adapter import convert_messages_to_anthropic
-
-        base_url = kwargs.get("base_url")
-        return convert_messages_to_anthropic(messages, base_url=base_url)
-
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        from agent.anthropic_adapter import convert_tools_to_anthropic
-
-        return convert_tools_to_anthropic(tools)
-
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        from agent.anthropic_adapter import build_anthropic_kwargs
-
-        return build_anthropic_kwargs(
-            model=model,
-            messages=messages,
-            tools=tools,
-            max_tokens=params.get("max_tokens", 16384),
-            reasoning_config=params.get("reasoning_config"),
-            tool_choice=params.get("tool_choice"),
-            is_oauth=params.get("is_oauth", False),
-            preserve_dots=params.get("preserve_dots", False),
-            context_length=params.get("context_length"),
-            base_url=params.get("base_url"),
-            fast_mode=params.get("fast_mode", False),
-        )
-
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        from agent.anthropic_adapter import normalize_anthropic_response_v2
-
-        strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
-        return normalize_anthropic_response_v2(response, strip_tool_prefix=strip_tool_prefix)
-
-    def validate_response(self, response: Any) -> bool:
-        if response is None:
-            return False
-        content_blocks = getattr(response, "content", None)
-        if not isinstance(content_blocks, list):
-            return False
-        if not content_blocks:
-            return False
-        return True
-
-    def extract_cache_stats(self, response: Any):
-        usage = getattr(response, "usage", None)
-        if usage is None:
-            return None
-        cached = getattr(usage, "cache_read_input_tokens", 0) or 0
-        written = getattr(usage, "cache_creation_input_tokens", 0) or 0
-        if cached or written:
-            return {"cached_tokens": cached, "creation_tokens": written}
-        return None
-
-    _STOP_REASON_MAP = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
-    }
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        return self._STOP_REASON_MAP.get(raw_reason, "stop")
-
-
-from agent.transports import register_transport  # noqa: E402
-
-register_transport("anthropic_messages", AnthropicTransport)

agent/transports/base.py

@@ -1,61 +0,0 @@
-"""Abstract base for provider transports.
-
-A transport owns the data path for one api_mode:
-  convert_messages → convert_tools → build_kwargs → normalize_response
-
-It does NOT own: client construction, streaming, credential refresh,
-prompt caching, interrupt handling, or retry logic. Those stay on AIAgent.
-"""
-
-from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
-
-from agent.transports.types import NormalizedResponse
-
-
-class ProviderTransport(ABC):
-    """Base class for provider-specific format conversion and normalization."""
-
-    @property
-    @abstractmethod
-    def api_mode(self) -> str:
-        """The api_mode string this transport handles."""
-        ...
-
-    @abstractmethod
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI-format messages to provider-native format."""
-        ...
-
-    @abstractmethod
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        """Convert OpenAI-format tool definitions to provider-native format."""
-        ...
-
-    @abstractmethod
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build the complete provider kwargs dict."""
-        ...
-
-    @abstractmethod
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize a raw provider response to the shared NormalizedResponse type."""
-        ...
-
-    def validate_response(self, response: Any) -> bool:
-        """Optional structural validation for raw responses."""
-        return True
-
-    def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
-        """Optional cache stats extraction."""
-        return None
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        """Optional stop-reason mapping. Defaults to passthrough."""
-        return raw_reason

agent/transports/types.py

@@ -1,58 +0,0 @@
-"""Shared types for normalized provider responses."""
-
-from __future__ import annotations
-
-import json
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-
-@dataclass
-class ToolCall:
-    """A normalized tool call from any provider."""
-
-    id: Optional[str]
-    name: str
-    arguments: str
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-@dataclass
-class Usage:
-    """Token usage from an API response."""
-
-    prompt_tokens: int = 0
-    completion_tokens: int = 0
-    total_tokens: int = 0
-    cached_tokens: int = 0
-
-
-@dataclass
-class NormalizedResponse:
-    """Normalized API response from any provider."""
-
-    content: Optional[str]
-    tool_calls: Optional[List[ToolCall]]
-    finish_reason: str
-    reasoning: Optional[str] = None
-    usage: Optional[Usage] = None
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-def build_tool_call(
-    id: Optional[str],
-    name: str,
-    arguments: Any,
-    **provider_fields: Any,
-) -> ToolCall:
-    """Build a ToolCall, auto-serialising dict arguments."""
-    args_str = json.dumps(arguments) if isinstance(arguments, dict) else str(arguments)
-    provider_data = dict(provider_fields) if provider_fields else None
-    return ToolCall(id=id, name=name, arguments=args_str, provider_data=provider_data)
-
-
-def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
-    """Translate a provider-specific stop reason to the normalized set."""
-    if reason is None:
-        return "stop"
-    return mapping.get(reason, "stop")

docs/evaluations/tensorzero-860-evaluation.md

@@ -0,0 +1,217 @@
+# 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

@@ -0,0 +1,318 @@
+#!/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/agent/test_anthropic_normalize_v2.py

@@ -1,213 +0,0 @@
-"""Regression tests: normalize_anthropic_response_v2 vs v1.
-
-Constructs mock Anthropic responses and asserts that the v2 function
-(returning NormalizedResponse) produces identical field values to the
-original v1 function (returning SimpleNamespace + finish_reason).
-"""
-
-from types import SimpleNamespace
-
-import pytest
-
-from agent.anthropic_adapter import (
-    normalize_anthropic_response,
-    normalize_anthropic_response_v2,
-)
-from agent.transports.types import NormalizedResponse
-
-
-def _text_block(text: str):
-    return SimpleNamespace(type="text", text=text)
-
-
-def _thinking_block(thinking: str, signature: str = "sig_abc"):
-    return SimpleNamespace(type="thinking", thinking=thinking, signature=signature)
-
-
-def _tool_use_block(id: str, name: str, input: dict):
-    return SimpleNamespace(type="tool_use", id=id, name=name, input=input)
-
-
-def _response(content_blocks, stop_reason="end_turn"):
-    return SimpleNamespace(
-        content=content_blocks,
-        stop_reason=stop_reason,
-        usage=SimpleNamespace(input_tokens=10, output_tokens=5),
-    )
-
-
-class TestTextOnly:
-    def setup_method(self):
-        self.resp = _response([_text_block("Hello world")])
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_type(self):
-        assert isinstance(self.v2, NormalizedResponse)
-
-    def test_content_matches(self):
-        assert self.v2.content == self.v1_msg.content
-
-    def test_finish_reason_matches(self):
-        assert self.v2.finish_reason == self.v1_finish
-
-    def test_no_tool_calls(self):
-        assert self.v2.tool_calls is None
-        assert self.v1_msg.tool_calls is None
-
-    def test_no_reasoning(self):
-        assert self.v2.reasoning is None
-        assert self.v1_msg.reasoning is None
-
-
-class TestWithToolCalls:
-    def setup_method(self):
-        self.resp = _response(
-            [
-                _text_block("I'll check that"),
-                _tool_use_block("toolu_abc", "terminal", {"command": "ls"}),
-                _tool_use_block("toolu_def", "read_file", {"path": "/tmp"}),
-            ],
-            stop_reason="tool_use",
-        )
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_finish_reason(self):
-        assert self.v2.finish_reason == "tool_calls"
-        assert self.v1_finish == "tool_calls"
-
-    def test_tool_call_count(self):
-        assert len(self.v2.tool_calls) == 2
-        assert len(self.v1_msg.tool_calls) == 2
-
-    def test_tool_call_ids_match(self):
-        for i in range(2):
-            assert self.v2.tool_calls[i].id == self.v1_msg.tool_calls[i].id
-
-    def test_tool_call_names_match(self):
-        assert self.v2.tool_calls[0].name == "terminal"
-        assert self.v2.tool_calls[1].name == "read_file"
-        for i in range(2):
-            assert self.v2.tool_calls[i].name == self.v1_msg.tool_calls[i].function.name
-
-    def test_tool_call_arguments_match(self):
-        for i in range(2):
-            assert self.v2.tool_calls[i].arguments == self.v1_msg.tool_calls[i].function.arguments
-
-    def test_content_preserved(self):
-        assert self.v2.content == self.v1_msg.content
-        assert "check that" in self.v2.content
-
-
-class TestWithThinking:
-    def setup_method(self):
-        self.resp = _response([
-            _thinking_block("Let me think about this carefully..."),
-            _text_block("The answer is 42."),
-        ])
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_reasoning_matches(self):
-        assert self.v2.reasoning == self.v1_msg.reasoning
-        assert "think about this" in self.v2.reasoning
-
-    def test_reasoning_details_in_provider_data(self):
-        v1_details = self.v1_msg.reasoning_details
-        v2_details = self.v2.provider_data.get("reasoning_details") if self.v2.provider_data else None
-        assert v1_details is not None
-        assert v2_details is not None
-        assert len(v2_details) == len(v1_details)
-
-    def test_content_excludes_thinking(self):
-        assert self.v2.content == "The answer is 42."
-
-
-class TestMixed:
-    def setup_method(self):
-        self.resp = _response(
-            [
-                _thinking_block("Planning my approach..."),
-                _text_block("I'll run the command"),
-                _tool_use_block("toolu_xyz", "terminal", {"command": "pwd"}),
-            ],
-            stop_reason="tool_use",
-        )
-        self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
-        self.v2 = normalize_anthropic_response_v2(self.resp)
-
-    def test_all_fields_present(self):
-        assert self.v2.content is not None
-        assert self.v2.tool_calls is not None
-        assert self.v2.reasoning is not None
-        assert self.v2.finish_reason == "tool_calls"
-
-    def test_content_matches(self):
-        assert self.v2.content == self.v1_msg.content
-
-    def test_reasoning_matches(self):
-        assert self.v2.reasoning == self.v1_msg.reasoning
-
-    def test_tool_call_matches(self):
-        assert self.v2.tool_calls[0].id == self.v1_msg.tool_calls[0].id
-        assert self.v2.tool_calls[0].name == self.v1_msg.tool_calls[0].function.name
-
-
-class TestStopReasons:
-    @pytest.mark.parametrize("stop_reason,expected", [
-        ("end_turn", "stop"),
-        ("tool_use", "tool_calls"),
-        ("max_tokens", "length"),
-        ("stop_sequence", "stop"),
-        ("refusal", "content_filter"),
-        ("model_context_window_exceeded", "length"),
-        ("unknown_future_reason", "stop"),
-    ])
-    def test_stop_reason_mapping(self, stop_reason, expected):
-        resp = _response([_text_block("x")], stop_reason=stop_reason)
-        _v1_msg, v1_finish = normalize_anthropic_response(resp)
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.finish_reason == v1_finish == expected
-
-
-class TestStripToolPrefix:
-    def test_prefix_stripped(self):
-        resp = _response(
-            [_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
-            stop_reason="tool_use",
-        )
-        v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=True)
-        v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=True)
-        assert v1_msg.tool_calls[0].function.name == "terminal"
-        assert v2.tool_calls[0].name == "terminal"
-
-    def test_prefix_kept(self):
-        resp = _response(
-            [_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
-            stop_reason="tool_use",
-        )
-        v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=False)
-        v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=False)
-        assert v1_msg.tool_calls[0].function.name == "mcp_terminal"
-        assert v2.tool_calls[0].name == "mcp_terminal"
-
-
-class TestEdgeCases:
-    def test_empty_content_blocks(self):
-        resp = _response([])
-        v1_msg, _v1_finish = normalize_anthropic_response(resp)
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.content == v1_msg.content
-        assert v2.content is None
-
-    def test_no_reasoning_details_means_none_provider_data(self):
-        resp = _response([_text_block("hi")])
-        v2 = normalize_anthropic_response_v2(resp)
-        assert v2.provider_data is None
-
-    def test_v2_returns_dataclass_not_namespace(self):
-        resp = _response([_text_block("hi")])
-        v2 = normalize_anthropic_response_v2(resp)
-        assert isinstance(v2, NormalizedResponse)
-        assert not isinstance(v2, SimpleNamespace)

tests/agent/transports/test_transport.py

@@ -1,208 +0,0 @@
-"""Tests for the transport ABC, registry, and AnthropicTransport."""
-
-from types import SimpleNamespace
-
-import pytest
-
-from agent.transports import _REGISTRY, get_transport, register_transport
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse
-
-
-class TestProviderTransportABC:
-    def test_cannot_instantiate_abc(self):
-        with pytest.raises(TypeError):
-            ProviderTransport()
-
-    def test_concrete_must_implement_all_abstract(self):
-        class Incomplete(ProviderTransport):
-            @property
-            def api_mode(self):
-                return "test"
-
-        with pytest.raises(TypeError):
-            Incomplete()
-
-    def test_minimal_concrete(self):
-        class Minimal(ProviderTransport):
-            @property
-            def api_mode(self):
-                return "test_minimal"
-
-            def convert_messages(self, messages, **kw):
-                return messages
-
-            def convert_tools(self, tools):
-                return tools
-
-            def build_kwargs(self, model, messages, tools=None, **params):
-                return {"model": model, "messages": messages}
-
-            def normalize_response(self, response, **kw):
-                return NormalizedResponse(content="ok", tool_calls=None, finish_reason="stop")
-
-        t = Minimal()
-        assert t.api_mode == "test_minimal"
-        assert t.validate_response(None) is True
-        assert t.extract_cache_stats(None) is None
-        assert t.map_finish_reason("end_turn") == "end_turn"
-
-
-class TestTransportRegistry:
-    def test_get_unregistered_returns_none(self):
-        assert get_transport("nonexistent_mode") is None
-
-    def test_anthropic_registered_on_import(self):
-        import agent.transports.anthropic  # noqa: F401
-
-        t = get_transport("anthropic_messages")
-        assert t is not None
-        assert t.api_mode == "anthropic_messages"
-
-    def test_register_and_get(self):
-        class DummyTransport(ProviderTransport):
-            @property
-            def api_mode(self):
-                return "dummy_test"
-
-            def convert_messages(self, messages, **kw):
-                return messages
-
-            def convert_tools(self, tools):
-                return tools
-
-            def build_kwargs(self, model, messages, tools=None, **params):
-                return {}
-
-            def normalize_response(self, response, **kw):
-                return NormalizedResponse(content=None, tool_calls=None, finish_reason="stop")
-
-        register_transport("dummy_test", DummyTransport)
-        t = get_transport("dummy_test")
-        assert t.api_mode == "dummy_test"
-        _REGISTRY.pop("dummy_test", None)
-
-
-class TestAnthropicTransport:
-    @pytest.fixture
-    def transport(self):
-        import agent.transports.anthropic  # noqa: F401
-
-        return get_transport("anthropic_messages")
-
-    def test_api_mode(self, transport):
-        assert transport.api_mode == "anthropic_messages"
-
-    def test_convert_tools_simple(self, transport):
-        tools = [{
-            "type": "function",
-            "function": {
-                "name": "test_tool",
-                "description": "A test",
-                "parameters": {"type": "object", "properties": {}},
-            },
-        }]
-        result = transport.convert_tools(tools)
-        assert len(result) == 1
-        assert result[0]["name"] == "test_tool"
-        assert "input_schema" in result[0]
-
-    def test_validate_response_none(self, transport):
-        assert transport.validate_response(None) is False
-
-    def test_validate_response_empty_content(self, transport):
-        r = SimpleNamespace(content=[])
-        assert transport.validate_response(r) is False
-
-    def test_validate_response_valid(self, transport):
-        r = SimpleNamespace(content=[SimpleNamespace(type="text", text="hello")])
-        assert transport.validate_response(r) is True
-
-    def test_map_finish_reason(self, transport):
-        assert transport.map_finish_reason("end_turn") == "stop"
-        assert transport.map_finish_reason("tool_use") == "tool_calls"
-        assert transport.map_finish_reason("max_tokens") == "length"
-        assert transport.map_finish_reason("stop_sequence") == "stop"
-        assert transport.map_finish_reason("refusal") == "content_filter"
-        assert transport.map_finish_reason("model_context_window_exceeded") == "length"
-        assert transport.map_finish_reason("unknown") == "stop"
-
-    def test_extract_cache_stats_none_usage(self, transport):
-        r = SimpleNamespace(usage=None)
-        assert transport.extract_cache_stats(r) is None
-
-    def test_extract_cache_stats_with_cache(self, transport):
-        usage = SimpleNamespace(cache_read_input_tokens=100, cache_creation_input_tokens=50)
-        r = SimpleNamespace(usage=usage)
-        result = transport.extract_cache_stats(r)
-        assert result == {"cached_tokens": 100, "creation_tokens": 50}
-
-    def test_extract_cache_stats_zero(self, transport):
-        usage = SimpleNamespace(cache_read_input_tokens=0, cache_creation_input_tokens=0)
-        r = SimpleNamespace(usage=usage)
-        assert transport.extract_cache_stats(r) is None
-
-    def test_normalize_response_text(self, transport):
-        r = SimpleNamespace(
-            content=[SimpleNamespace(type="text", text="Hello world")],
-            stop_reason="end_turn",
-            usage=SimpleNamespace(input_tokens=10, output_tokens=5),
-            model="claude-sonnet-4-6",
-        )
-        nr = transport.normalize_response(r)
-        assert isinstance(nr, NormalizedResponse)
-        assert nr.content == "Hello world"
-        assert nr.tool_calls is None or nr.tool_calls == []
-        assert nr.finish_reason == "stop"
-
-    def test_normalize_response_tool_calls(self, transport):
-        r = SimpleNamespace(
-            content=[
-                SimpleNamespace(type="tool_use", id="toolu_123", name="terminal", input={"command": "ls"}),
-            ],
-            stop_reason="tool_use",
-            usage=SimpleNamespace(input_tokens=10, output_tokens=20),
-            model="claude-sonnet-4-6",
-        )
-        nr = transport.normalize_response(r)
-        assert nr.finish_reason == "tool_calls"
-        assert len(nr.tool_calls) == 1
-        tc = nr.tool_calls[0]
-        assert tc.name == "terminal"
-        assert tc.id == "toolu_123"
-        assert '"command"' in tc.arguments
-
-    def test_normalize_response_thinking(self, transport):
-        r = SimpleNamespace(
-            content=[
-                SimpleNamespace(type="thinking", thinking="Let me think..."),
-                SimpleNamespace(type="text", text="The answer is 42"),
-            ],
-            stop_reason="end_turn",
-            usage=SimpleNamespace(input_tokens=10, output_tokens=15),
-            model="claude-sonnet-4-6",
-        )
-        nr = transport.normalize_response(r)
-        assert nr.content == "The answer is 42"
-        assert nr.reasoning == "Let me think..."
-
-    def test_build_kwargs_returns_dict(self, transport):
-        messages = [{"role": "user", "content": "Hello"}]
-        kw = transport.build_kwargs(
-            model="claude-sonnet-4-6",
-            messages=messages,
-            max_tokens=1024,
-        )
-        assert isinstance(kw, dict)
-        assert "model" in kw
-        assert "max_tokens" in kw
-        assert "messages" in kw
-
-    def test_convert_messages_extracts_system(self, transport):
-        messages = [
-            {"role": "system", "content": "You are helpful."},
-            {"role": "user", "content": "Hi"},
-        ]
-        system, msgs = transport.convert_messages(messages)
-        assert system is not None
-        assert len(msgs) >= 1

tests/agent/transports/test_types.py

@@ -1,130 +0,0 @@
-"""Tests for agent/transports/types.py — dataclass construction + helpers."""
-
-import json
-
-from agent.transports.types import (
-    NormalizedResponse,
-    ToolCall,
-    Usage,
-    build_tool_call,
-    map_finish_reason,
-)
-
-
-class TestToolCall:
-    def test_basic_construction(self):
-        tc = ToolCall(id="call_abc", name="terminal", arguments='{"cmd": "ls"}')
-        assert tc.id == "call_abc"
-        assert tc.name == "terminal"
-        assert tc.arguments == '{"cmd": "ls"}'
-        assert tc.provider_data is None
-
-    def test_none_id(self):
-        tc = ToolCall(id=None, name="read_file", arguments="{}")
-        assert tc.id is None
-
-    def test_provider_data(self):
-        tc = ToolCall(
-            id="call_x",
-            name="t",
-            arguments="{}",
-            provider_data={"call_id": "call_x", "response_item_id": "fc_x"},
-        )
-        assert tc.provider_data["call_id"] == "call_x"
-        assert tc.provider_data["response_item_id"] == "fc_x"
-
-
-class TestUsage:
-    def test_defaults(self):
-        u = Usage()
-        assert u.prompt_tokens == 0
-        assert u.completion_tokens == 0
-        assert u.total_tokens == 0
-        assert u.cached_tokens == 0
-
-    def test_explicit(self):
-        u = Usage(prompt_tokens=100, completion_tokens=50, total_tokens=150, cached_tokens=80)
-        assert u.total_tokens == 150
-
-
-class TestNormalizedResponse:
-    def test_text_only(self):
-        r = NormalizedResponse(content="hello", tool_calls=None, finish_reason="stop")
-        assert r.content == "hello"
-        assert r.tool_calls is None
-        assert r.finish_reason == "stop"
-        assert r.reasoning is None
-        assert r.usage is None
-        assert r.provider_data is None
-
-    def test_with_tool_calls(self):
-        tcs = [ToolCall(id="call_1", name="terminal", arguments='{"cmd":"pwd"}')]
-        r = NormalizedResponse(content=None, tool_calls=tcs, finish_reason="tool_calls")
-        assert r.finish_reason == "tool_calls"
-        assert len(r.tool_calls) == 1
-        assert r.tool_calls[0].name == "terminal"
-
-    def test_with_reasoning(self):
-        r = NormalizedResponse(
-            content="answer",
-            tool_calls=None,
-            finish_reason="stop",
-            reasoning="I thought about it",
-        )
-        assert r.reasoning == "I thought about it"
-
-    def test_with_provider_data(self):
-        r = NormalizedResponse(
-            content=None,
-            tool_calls=None,
-            finish_reason="stop",
-            provider_data={"reasoning_details": [{"type": "thinking", "thinking": "hmm"}]},
-        )
-        assert r.provider_data["reasoning_details"][0]["type"] == "thinking"
-
-
-class TestBuildToolCall:
-    def test_dict_arguments_serialized(self):
-        tc = build_tool_call(id="call_1", name="terminal", arguments={"cmd": "ls"})
-        assert tc.arguments == json.dumps({"cmd": "ls"})
-        assert tc.provider_data is None
-
-    def test_string_arguments_passthrough(self):
-        tc = build_tool_call(id="call_2", name="read_file", arguments='{"path": "/tmp"}')
-        assert tc.arguments == '{"path": "/tmp"}'
-
-    def test_provider_fields(self):
-        tc = build_tool_call(
-            id="call_3",
-            name="terminal",
-            arguments="{}",
-            call_id="call_3",
-            response_item_id="fc_3",
-        )
-        assert tc.provider_data == {"call_id": "call_3", "response_item_id": "fc_3"}
-
-    def test_none_id(self):
-        tc = build_tool_call(id=None, name="t", arguments="{}")
-        assert tc.id is None
-
-
-class TestMapFinishReason:
-    ANTHROPIC_MAP = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-    }
-
-    def test_known_reason(self):
-        assert map_finish_reason("end_turn", self.ANTHROPIC_MAP) == "stop"
-        assert map_finish_reason("tool_use", self.ANTHROPIC_MAP) == "tool_calls"
-        assert map_finish_reason("max_tokens", self.ANTHROPIC_MAP) == "length"
-        assert map_finish_reason("refusal", self.ANTHROPIC_MAP) == "content_filter"
-
-    def test_unknown_reason_defaults_to_stop(self):
-        assert map_finish_reason("something_new", self.ANTHROPIC_MAP) == "stop"
-
-    def test_none_reason(self):
-        assert map_finish_reason(None, self.ANTHROPIC_MAP) == "stop"

tests/test_tensorzero_eval_packet.py

@@ -0,0 +1,149 @@
+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