feat: provider modules — ProviderProfile ABC, 30 providers, fetch_models, transport single-path

feat: provider modules — ProviderProfile ABC, 29 providers, fetch_models, transport single-path

Introduces providers/ as the single source of truth for every inference
provider. All 29 providers declared with correct data cross-checked against
auth.py, runtime_provider.py and auxiliary_client.py.

Rebased onto main (30307a980). Incorporates post-salvage fixes from
56724147e (gmi aux model google/gemini-3.1-flash-lite-preview, already set in providers/gmi.py).

acp_adapter/copilot_client.py

@@ -0,0 +1,632 @@
+"""OpenAI-compatible shim that forwards Hermes requests to `copilot --acp`.
+
+This adapter lets Hermes treat the GitHub Copilot ACP server as a chat-style
+backend. Each request starts a short-lived ACP session, sends the formatted
+conversation as a single prompt, collects text chunks, and converts the result
+back into the minimal shape Hermes expects from an OpenAI client.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import queue
+import re
+import shlex
+import subprocess
+import threading
+import time
+from collections import deque
+from pathlib import Path
+from types import SimpleNamespace
+from typing import Any
+
+from agent.file_safety import get_read_block_error, is_write_denied
+from agent.redact import redact_sensitive_text
+
+ACP_MARKER_BASE_URL = "acp://copilot"
+_DEFAULT_TIMEOUT_SECONDS = 900.0
+
+_TOOL_CALL_BLOCK_RE = re.compile(r"<tool_call>\s*(\{.*?\})\s*</tool_call>", re.DOTALL)
+_TOOL_CALL_JSON_RE = re.compile(
+    r"\{\s*\"id\"\s*:\s*\"[^\"]+\"\s*,\s*\"type\"\s*:\s*\"function\"\s*,\s*\"function\"\s*:\s*\{.*?\}\s*\}",
+    re.DOTALL,
+)
+
+
+def _resolve_command() -> str:
+    return (
+        os.getenv("HERMES_COPILOT_ACP_COMMAND", "").strip()
+        or os.getenv("COPILOT_CLI_PATH", "").strip()
+        or "copilot"
+    )
+
+
+def _resolve_args() -> list[str]:
+    raw = os.getenv("HERMES_COPILOT_ACP_ARGS", "").strip()
+    if not raw:
+        return ["--acp", "--stdio"]
+    return shlex.split(raw)
+
+
+def _jsonrpc_error(message_id: Any, code: int, message: str) -> dict[str, Any]:
+    return {
+        "jsonrpc": "2.0",
+        "id": message_id,
+        "error": {
+            "code": code,
+            "message": message,
+        },
+    }
+
+
+def _permission_denied(message_id: Any) -> dict[str, Any]:
+    return {
+        "jsonrpc": "2.0",
+        "id": message_id,
+        "result": {
+            "outcome": {
+                "outcome": "cancelled",
+            }
+        },
+    }
+
+
+def _format_messages_as_prompt(
+    messages: list[dict[str, Any]],
+    model: str | None = None,
+    tools: list[dict[str, Any]] | None = None,
+    tool_choice: Any = None,
+) -> str:
+    sections: list[str] = [
+        "You are being used as the active ACP agent backend for Hermes.",
+        "Use ACP capabilities to complete tasks.",
+        "IMPORTANT: If you take an action with a tool, you MUST output tool calls using <tool_call>{...}</tool_call> blocks with JSON exactly in OpenAI function-call shape.",
+        "If no tool is needed, answer normally.",
+    ]
+    if model:
+        sections.append(f"Hermes requested model hint: {model}")
+
+    if isinstance(tools, list) and tools:
+        tool_specs: list[dict[str, Any]] = []
+        for t in tools:
+            if not isinstance(t, dict):
+                continue
+            fn = t.get("function") or {}
+            if not isinstance(fn, dict):
+                continue
+            name = fn.get("name")
+            if not isinstance(name, str) or not name.strip():
+                continue
+            tool_specs.append(
+                {
+                    "name": name.strip(),
+                    "description": fn.get("description", ""),
+                    "parameters": fn.get("parameters", {}),
+                }
+            )
+        if tool_specs:
+            sections.append(
+                "Available tools (OpenAI function schema). "
+                "When using a tool, emit ONLY <tool_call>{...}</tool_call> with one JSON object "
+                "containing id/type/function{name,arguments}. arguments must be a JSON string.\n"
+                + json.dumps(tool_specs, ensure_ascii=False)
+            )
+
+    if tool_choice is not None:
+        sections.append(
+            f"Tool choice hint: {json.dumps(tool_choice, ensure_ascii=False)}"
+        )
+
+    transcript: list[str] = []
+    for message in messages:
+        if not isinstance(message, dict):
+            continue
+        role = str(message.get("role") or "unknown").strip().lower()
+        if role == "tool":
+            role = "tool"
+        elif role not in {"system", "user", "assistant"}:
+            role = "context"
+
+        content = message.get("content")
+        rendered = _render_message_content(content)
+        if not rendered:
+            continue
+
+        label = {
+            "system": "System",
+            "user": "User",
+            "assistant": "Assistant",
+            "tool": "Tool",
+            "context": "Context",
+        }.get(role, role.title())
+        transcript.append(f"{label}:\n{rendered}")
+
+    if transcript:
+        sections.append("Conversation transcript:\n\n" + "\n\n".join(transcript))
+
+    sections.append("Continue the conversation from the latest user request.")
+    return "\n\n".join(
+        section.strip() for section in sections if section and section.strip()
+    )
+
+
+def _render_message_content(content: Any) -> str:
+    if content is None:
+        return ""
+    if isinstance(content, str):
+        return content.strip()
+    if isinstance(content, dict):
+        if "text" in content:
+            return str(content.get("text") or "").strip()
+        if "content" in content and isinstance(content.get("content"), str):
+            return str(content.get("content") or "").strip()
+        return json.dumps(content, ensure_ascii=True)
+    if isinstance(content, list):
+        parts: list[str] = []
+        for item in content:
+            if isinstance(item, str):
+                parts.append(item)
+            elif isinstance(item, dict):
+                text = item.get("text")
+                if isinstance(text, str) and text.strip():
+                    parts.append(text.strip())
+        return "\n".join(parts).strip()
+    return str(content).strip()
+
+
+def _extract_tool_calls_from_text(text: str) -> tuple[list[SimpleNamespace], str]:
+    if not isinstance(text, str) or not text.strip():
+        return [], ""
+
+    extracted: list[SimpleNamespace] = []
+    consumed_spans: list[tuple[int, int]] = []
+
+    def _try_add_tool_call(raw_json: str) -> None:
+        try:
+            obj = json.loads(raw_json)
+        except Exception:
+            return
+        if not isinstance(obj, dict):
+            return
+        fn = obj.get("function")
+        if not isinstance(fn, dict):
+            return
+        fn_name = fn.get("name")
+        if not isinstance(fn_name, str) or not fn_name.strip():
+            return
+        fn_args = fn.get("arguments", "{}")
+        if not isinstance(fn_args, str):
+            fn_args = json.dumps(fn_args, ensure_ascii=False)
+        call_id = obj.get("id")
+        if not isinstance(call_id, str) or not call_id.strip():
+            call_id = f"acp_call_{len(extracted) + 1}"
+
+        extracted.append(
+            SimpleNamespace(
+                id=call_id,
+                call_id=call_id,
+                response_item_id=None,
+                type="function",
+                function=SimpleNamespace(name=fn_name.strip(), arguments=fn_args),
+            )
+        )
+
+    for m in _TOOL_CALL_BLOCK_RE.finditer(text):
+        raw = m.group(1)
+        _try_add_tool_call(raw)
+        consumed_spans.append((m.start(), m.end()))
+
+    # Only try bare-JSON fallback when no XML blocks were found.
+    if not extracted:
+        for m in _TOOL_CALL_JSON_RE.finditer(text):
+            raw = m.group(0)
+            _try_add_tool_call(raw)
+            consumed_spans.append((m.start(), m.end()))
+
+    if not consumed_spans:
+        return extracted, text.strip()
+
+    consumed_spans.sort()
+    merged: list[tuple[int, int]] = []
+    for start, end in consumed_spans:
+        if not merged or start > merged[-1][1]:
+            merged.append((start, end))
+        else:
+            merged[-1] = (merged[-1][0], max(merged[-1][1], end))
+
+    parts: list[str] = []
+    cursor = 0
+    for start, end in merged:
+        if cursor < start:
+            parts.append(text[cursor:start])
+        cursor = max(cursor, end)
+    if cursor < len(text):
+        parts.append(text[cursor:])
+
+    cleaned = "\n".join(p.strip() for p in parts if p and p.strip()).strip()
+    return extracted, cleaned
+
+
+def _ensure_path_within_cwd(path_text: str, cwd: str) -> Path:
+    candidate = Path(path_text)
+    if not candidate.is_absolute():
+        raise PermissionError("ACP file-system paths must be absolute.")
+    resolved = candidate.resolve()
+    root = Path(cwd).resolve()
+    try:
+        resolved.relative_to(root)
+    except ValueError as exc:
+        raise PermissionError(
+            f"Path '{resolved}' is outside the session cwd '{root}'."
+        ) from exc
+    return resolved
+
+
+class _ACPChatCompletions:
+    def __init__(self, client: CopilotACPClient):
+        self._client = client
+
+    def create(self, **kwargs: Any) -> Any:
+        return self._client._create_chat_completion(**kwargs)
+
+
+class _ACPChatNamespace:
+    def __init__(self, client: CopilotACPClient):
+        self.completions = _ACPChatCompletions(client)
+
+
+class CopilotACPClient:
+    """Minimal OpenAI-client-compatible facade for Copilot ACP."""
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | None = None,
+        default_headers: dict[str, str] | None = None,
+        acp_command: str | None = None,
+        acp_args: list[str] | None = None,
+        acp_cwd: str | None = None,
+        command: str | None = None,
+        args: list[str] | None = None,
+        **_: Any,
+    ):
+        self.api_key = api_key or "copilot-acp"
+        self.base_url = base_url or ACP_MARKER_BASE_URL
+        self._default_headers = dict(default_headers or {})
+        self._acp_command = acp_command or command or _resolve_command()
+        self._acp_args = list(acp_args or args or _resolve_args())
+        self._acp_cwd = str(Path(acp_cwd or os.getcwd()).resolve())
+        self.chat = _ACPChatNamespace(self)
+        self.is_closed = False
+        self._active_process: subprocess.Popen[str] | None = None
+        self._active_process_lock = threading.Lock()
+
+    def close(self) -> None:
+        proc: subprocess.Popen[str] | None
+        with self._active_process_lock:
+            proc = self._active_process
+            self._active_process = None
+        self.is_closed = True
+        if proc is None:
+            return
+        try:
+            proc.terminate()
+            proc.wait(timeout=2)
+        except Exception:
+            try:
+                proc.kill()
+            except Exception:
+                pass
+
+    def _create_chat_completion(
+        self,
+        *,
+        model: str | None = None,
+        messages: list[dict[str, Any]] | None = None,
+        timeout: float | None = None,
+        tools: list[dict[str, Any]] | None = None,
+        tool_choice: Any = None,
+        **_: Any,
+    ) -> Any:
+        prompt_text = _format_messages_as_prompt(
+            messages or [],
+            model=model,
+            tools=tools,
+            tool_choice=tool_choice,
+        )
+        # Normalise timeout: run_agent.py may pass an httpx.Timeout object
+        # (used natively by the OpenAI SDK) rather than a plain float.
+        if timeout is None:
+            _effective_timeout = _DEFAULT_TIMEOUT_SECONDS
+        elif isinstance(timeout, (int, float)):
+            _effective_timeout = float(timeout)
+        else:
+            # httpx.Timeout or similar — pick the largest component so the
+            # subprocess has enough wall-clock time for the full response.
+            _candidates = [
+                getattr(timeout, attr, None)
+                for attr in ("read", "write", "connect", "pool", "timeout")
+            ]
+            _numeric = [float(v) for v in _candidates if isinstance(v, (int, float))]
+            _effective_timeout = max(_numeric) if _numeric else _DEFAULT_TIMEOUT_SECONDS
+
+        response_text, reasoning_text = self._run_prompt(
+            prompt_text,
+            timeout_seconds=_effective_timeout,
+        )
+
+        tool_calls, cleaned_text = _extract_tool_calls_from_text(response_text)
+
+        usage = SimpleNamespace(
+            prompt_tokens=0,
+            completion_tokens=0,
+            total_tokens=0,
+            prompt_tokens_details=SimpleNamespace(cached_tokens=0),
+        )
+        assistant_message = SimpleNamespace(
+            content=cleaned_text,
+            tool_calls=tool_calls,
+            reasoning=reasoning_text or None,
+            reasoning_content=reasoning_text or None,
+            reasoning_details=None,
+        )
+        finish_reason = "tool_calls" if tool_calls else "stop"
+        choice = SimpleNamespace(message=assistant_message, finish_reason=finish_reason)
+        return SimpleNamespace(
+            choices=[choice],
+            usage=usage,
+            model=model or "copilot-acp",
+        )
+
+    def _run_prompt(
+        self, prompt_text: str, *, timeout_seconds: float
+    ) -> tuple[str, str]:
+        try:
+            proc = subprocess.Popen(
+                [self._acp_command] + self._acp_args,
+                stdin=subprocess.PIPE,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+                text=True,
+                bufsize=1,
+                cwd=self._acp_cwd,
+            )
+        except FileNotFoundError as exc:
+            raise RuntimeError(
+                f"Could not start Copilot ACP command '{self._acp_command}'. "
+                "Install GitHub Copilot CLI or set HERMES_COPILOT_ACP_COMMAND/COPILOT_CLI_PATH."
+            ) from exc
+
+        if proc.stdin is None or proc.stdout is None:
+            proc.kill()
+            raise RuntimeError("Copilot ACP process did not expose stdin/stdout pipes.")
+
+        self.is_closed = False
+        with self._active_process_lock:
+            self._active_process = proc
+
+        inbox: queue.Queue[dict[str, Any]] = queue.Queue()
+        stderr_tail: deque[str] = deque(maxlen=40)
+
+        def _stdout_reader() -> None:
+            if proc.stdout is None:
+                return
+            for line in proc.stdout:
+                try:
+                    inbox.put(json.loads(line))
+                except Exception:
+                    inbox.put({"raw": line.rstrip("\n")})
+
+        def _stderr_reader() -> None:
+            if proc.stderr is None:
+                return
+            for line in proc.stderr:
+                stderr_tail.append(line.rstrip("\n"))
+
+        out_thread = threading.Thread(target=_stdout_reader, daemon=True)
+        err_thread = threading.Thread(target=_stderr_reader, daemon=True)
+        out_thread.start()
+        err_thread.start()
+
+        next_id = 0
+
+        def _request(
+            method: str,
+            params: dict[str, Any],
+            *,
+            text_parts: list[str] | None = None,
+            reasoning_parts: list[str] | None = None,
+        ) -> Any:
+            nonlocal next_id
+            next_id += 1
+            request_id = next_id
+            payload = {
+                "jsonrpc": "2.0",
+                "id": request_id,
+                "method": method,
+                "params": params,
+            }
+            assert proc.stdin is not None  # always set: Popen(stdin=PIPE)
+            proc.stdin.write(json.dumps(payload) + "\n")
+            proc.stdin.flush()
+
+            deadline = time.time() + timeout_seconds
+            while time.time() < deadline:
+                if proc.poll() is not None:
+                    break
+                try:
+                    msg = inbox.get(timeout=0.1)
+                except queue.Empty:
+                    continue
+
+                if self._handle_server_message(
+                    msg,
+                    process=proc,
+                    cwd=self._acp_cwd,
+                    text_parts=text_parts,
+                    reasoning_parts=reasoning_parts,
+                ):
+                    continue
+
+                if msg.get("id") != request_id:
+                    continue
+                if "error" in msg:
+                    err = msg.get("error") or {}
+                    raise RuntimeError(
+                        f"Copilot ACP {method} failed: {err.get('message') or err}"
+                    )
+                return msg.get("result")
+
+            stderr_text = "\n".join(stderr_tail).strip()
+            if proc.poll() is not None and stderr_text:
+                raise RuntimeError(f"Copilot ACP process exited early: {stderr_text}")
+            raise TimeoutError(
+                f"Timed out waiting for Copilot ACP response to {method}."
+            )
+
+        try:
+            _request(
+                "initialize",
+                {
+                    "protocolVersion": 1,
+                    "clientCapabilities": {
+                        "fs": {
+                            "readTextFile": True,
+                            "writeTextFile": True,
+                        }
+                    },
+                    "clientInfo": {
+                        "name": "hermes-agent",
+                        "title": "Hermes Agent",
+                        "version": "0.0.0",
+                    },
+                },
+            )
+            session = (
+                _request(
+                    "session/new",
+                    {
+                        "cwd": self._acp_cwd,
+                        "mcpServers": [],
+                    },
+                )
+                or {}
+            )
+            session_id = str(session.get("sessionId") or "").strip()
+            if not session_id:
+                raise RuntimeError("Copilot ACP did not return a sessionId.")
+
+            text_parts: list[str] = []
+            reasoning_parts: list[str] = []
+            _request(
+                "session/prompt",
+                {
+                    "sessionId": session_id,
+                    "prompt": [
+                        {
+                            "type": "text",
+                            "text": prompt_text,
+                        }
+                    ],
+                },
+                text_parts=text_parts,
+                reasoning_parts=reasoning_parts,
+            )
+            return "".join(text_parts), "".join(reasoning_parts)
+        finally:
+            self.close()
+
+    def _handle_server_message(
+        self,
+        msg: dict[str, Any],
+        *,
+        process: subprocess.Popen[str],
+        cwd: str,
+        text_parts: list[str] | None,
+        reasoning_parts: list[str] | None,
+    ) -> bool:
+        method = msg.get("method")
+        if not isinstance(method, str):
+            return False
+
+        if method == "session/update":
+            params = msg.get("params") or {}
+            update = params.get("update") or {}
+            kind = str(update.get("sessionUpdate") or "").strip()
+            content = update.get("content") or {}
+            chunk_text = ""
+            if isinstance(content, dict):
+                chunk_text = str(content.get("text") or "")
+            if kind == "agent_message_chunk" and chunk_text and text_parts is not None:
+                text_parts.append(chunk_text)
+            elif (
+                kind == "agent_thought_chunk"
+                and chunk_text
+                and reasoning_parts is not None
+            ):
+                reasoning_parts.append(chunk_text)
+            return True
+
+        if process.stdin is None:
+            return True
+
+        message_id = msg.get("id")
+        params = msg.get("params") or {}
+
+        if method == "session/request_permission":
+            response = _permission_denied(message_id)
+        elif method == "fs/read_text_file":
+            try:
+                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
+                block_error = get_read_block_error(str(path))
+                if block_error:
+                    raise PermissionError(block_error)
+                content = path.read_text() if path.exists() else ""
+                line = params.get("line")
+                limit = params.get("limit")
+                if isinstance(line, int) and line > 1:
+                    lines = content.splitlines(keepends=True)
+                    start = line - 1
+                    end = (
+                        start + limit if isinstance(limit, int) and limit > 0 else None
+                    )
+                    content = "".join(lines[start:end])
+                if content:
+                    content = redact_sensitive_text(content)
+                response = {
+                    "jsonrpc": "2.0",
+                    "id": message_id,
+                    "result": {
+                        "content": content,
+                    },
+                }
+            except Exception as exc:
+                response = _jsonrpc_error(message_id, -32602, str(exc))
+        elif method == "fs/write_text_file":
+            try:
+                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
+                if is_write_denied(str(path)):
+                    raise PermissionError(
+                        f"Write denied: '{path}' is a protected system/credential file."
+                    )
+                path.parent.mkdir(parents=True, exist_ok=True)
+                path.write_text(str(params.get("content") or ""))
+                response = {
+                    "jsonrpc": "2.0",
+                    "id": message_id,
+                    "result": None,
+                }
+            except Exception as exc:
+                response = _jsonrpc_error(message_id, -32602, str(exc))
+        else:
+            response = _jsonrpc_error(
+                message_id,
+                -32601,
+                f"ACP client method '{method}' is not supported by Hermes yet.",
+            )
+
+        process.stdin.write(json.dumps(response) + "\n")
+        process.stdin.flush()
+        return True

agent/auxiliary_client.py

@@ -151,23 +151,31 @@ def _fixed_temperature_for_model(
     return None
 
 # Default auxiliary models for direct API-key providers (cheap/fast for side tasks)
-_API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
-    "gemini": "gemini-3-flash-preview",
-    "zai": "glm-4.5-flash",
-    "kimi-coding": "kimi-k2-turbo-preview",
-    "stepfun": "step-3.5-flash",
-    "kimi-coding-cn": "kimi-k2-turbo-preview",
-    "gmi": "google/gemini-3.1-flash-lite-preview",
-    "minimax": "MiniMax-M2.7",
-    "minimax-cn": "MiniMax-M2.7",
+def _get_aux_model_for_provider(provider_id: str) -> str:
+    """Return the cheap auxiliary model for a provider.
+
+    Reads from ProviderProfile.default_aux_model first, falling back to the
+    legacy hardcoded dict for providers that predate the profiles system.
+    """
+    try:
+        from providers import get_provider_profile
+        _p = get_provider_profile(provider_id)
+        if _p and _p.default_aux_model:
+            return _p.default_aux_model
+    except Exception:
+        pass
+    return _API_KEY_PROVIDER_AUX_MODELS_FALLBACK.get(provider_id, "")
+
+
+# Fallback for providers not yet migrated to ProviderProfile.default_aux_model.
+# New providers should set default_aux_model on their profile instead.
+_API_KEY_PROVIDER_AUX_MODELS_FALLBACK: Dict[str, str] = {
     "anthropic": "claude-haiku-4-5-20251001",
-    "ai-gateway": "google/gemini-3-flash",
-    "opencode-zen": "gemini-3-flash",
-    "opencode-go": "glm-5",
-    "kilocode": "google/gemini-3-flash-preview",
-    "ollama-cloud": "nemotron-3-nano:30b",
 }
 
+# Legacy alias — callers that haven't been updated yet can still use this.
+_API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = _API_KEY_PROVIDER_AUX_MODELS_FALLBACK
+
 # Vision-specific model overrides for direct providers.
 # When the user's main provider has a dedicated vision/multimodal model that
 # differs from their main chat model, map it here.  The vision auto-detect
@@ -868,7 +876,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             base_url = _to_openai_base_url(
                 _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
             )
-            model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
+            model = _get_aux_model_for_provider(provider_id) or None
             if model is None:
                 continue  # skip provider if we don't know a valid aux model
             logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
@@ -877,14 +885,22 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
 
                 if is_native_gemini_base_url(base_url):
                     return GeminiNativeClient(api_key=api_key, base_url=base_url), model
-            extra = {}
-            if base_url_host_matches(base_url, "api.kimi.com"):
-                extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
-            elif base_url_host_matches(base_url, "api.githubcopilot.com"):
-                from hermes_cli.models import copilot_default_headers
+        extra = {}
+        if base_url_host_matches(base_url, "api.kimi.com"):
+            extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
+        elif base_url_host_matches(base_url, "api.githubcopilot.com"):
+            from hermes_cli.models import copilot_default_headers
 
-                extra["default_headers"] = copilot_default_headers()
-            return OpenAI(api_key=api_key, base_url=base_url, **extra), model
+            extra["default_headers"] = copilot_default_headers()
+        else:
+            try:
+                from providers import get_provider_profile as _gpf_aux
+                _ph_aux = _gpf_aux(provider_id)
+                if _ph_aux and _ph_aux.default_headers:
+                    extra["default_headers"] = dict(_ph_aux.default_headers)
+            except Exception:
+                pass
+        return OpenAI(api_key=api_key, base_url=base_url, **extra), model
 
         creds = resolve_api_key_provider_credentials(provider_id)
         api_key = str(creds.get("api_key", "")).strip()
@@ -894,7 +910,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         base_url = _to_openai_base_url(
             str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
         )
-        model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
+        model = _get_aux_model_for_provider(provider_id) or None
         if model is None:
             continue  # skip provider if we don't know a valid aux model
         logger.debug("Auxiliary text client: %s (%s)", pconfig.name, model)
@@ -910,6 +926,14 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             from hermes_cli.models import copilot_default_headers
 
             extra["default_headers"] = copilot_default_headers()
+        else:
+            try:
+                from providers import get_provider_profile as _gpf_aux2
+                _ph_aux2 = _gpf_aux2(provider_id)
+                if _ph_aux2 and _ph_aux2.default_headers:
+                    extra["default_headers"] = dict(_ph_aux2.default_headers)
+            except Exception:
+                pass
         return OpenAI(api_key=api_key, base_url=base_url, **extra), model
 
     return None, None
@@ -1258,7 +1282,7 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
 
     from agent.anthropic_adapter import _is_oauth_token
     is_oauth = _is_oauth_token(token)
-    model = _API_KEY_PROVIDER_AUX_MODELS.get("anthropic", "claude-haiku-4-5-20251001")
+    model = _get_aux_model_for_provider("anthropic") or "claude-haiku-4-5-20251001"
     logger.debug("Auxiliary client: Anthropic native (%s) at %s (oauth=%s)", model, base_url, is_oauth)
     try:
         real_client = build_anthropic_client(token, base_url)
@@ -1642,7 +1666,7 @@ def _to_async_client(sync_client, model: str, is_vision: bool = False):
     except ImportError:
         pass
     try:
-        from agent.copilot_acp_client import CopilotACPClient
+        from acp_adapter.copilot_client import CopilotACPClient
         if isinstance(sync_client, CopilotACPClient):
             return sync_client, model
     except ImportError:
@@ -1986,7 +2010,7 @@ def resolve_provider_client(
             str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
         )
 
-        default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
+        default_model = _get_aux_model_for_provider(provider)
         final_model = _normalize_resolved_model(model or default_model, provider)
 
         if provider == "gemini":
@@ -2056,7 +2080,7 @@ def resolve_provider_client(
                     "process credentials are incomplete"
                 )
                 return None, None
-            from agent.copilot_acp_client import CopilotACPClient
+            from acp_adapter.copilot_client import CopilotACPClient
 
             client = CopilotACPClient(
                 api_key=api_key,

agent/copilot_acp_client.py

@@ -1,646 +1,8 @@
-"""OpenAI-compatible shim that forwards Hermes requests to `copilot --acp`.
+"""Backward-compatibility shim.
 
-This adapter lets Hermes treat the GitHub Copilot ACP server as a chat-style
-backend. Each request starts a short-lived ACP session, sends the formatted
-conversation as a single prompt, collects text chunks, and converts the result
-back into the minimal shape Hermes expects from an OpenAI client.
+CopilotACPClient has moved to acp_adapter/copilot_client.py.
+This module re-exports it so existing callers continue to work.
 """
+from acp_adapter.copilot_client import CopilotACPClient  # noqa: F401
 
-from __future__ import annotations
-
-import json
-import os
-import queue
-import re
-import shlex
-import subprocess
-import threading
-import time
-from collections import deque
-from pathlib import Path
-from types import SimpleNamespace
-from typing import Any
-
-from agent.file_safety import get_read_block_error, is_write_denied
-from agent.redact import redact_sensitive_text
-
-ACP_MARKER_BASE_URL = "acp://copilot"
-_DEFAULT_TIMEOUT_SECONDS = 900.0
-
-_TOOL_CALL_BLOCK_RE = re.compile(r"<tool_call>\s*(\{.*?\})\s*</tool_call>", re.DOTALL)
-_TOOL_CALL_JSON_RE = re.compile(r"\{\s*\"id\"\s*:\s*\"[^\"]+\"\s*,\s*\"type\"\s*:\s*\"function\"\s*,\s*\"function\"\s*:\s*\{.*?\}\s*\}", re.DOTALL)
-
-
-def _resolve_command() -> str:
-    return (
-        os.getenv("HERMES_COPILOT_ACP_COMMAND", "").strip()
-        or os.getenv("COPILOT_CLI_PATH", "").strip()
-        or "copilot"
-    )
-
-
-def _resolve_args() -> list[str]:
-    raw = os.getenv("HERMES_COPILOT_ACP_ARGS", "").strip()
-    if not raw:
-        return ["--acp", "--stdio"]
-    return shlex.split(raw)
-
-
-def _resolve_home_dir() -> str:
-    """Return a stable HOME for child ACP processes."""
-
-    try:
-        from hermes_constants import get_subprocess_home
-
-        profile_home = get_subprocess_home()
-        if profile_home:
-            return profile_home
-    except Exception:
-        pass
-
-    home = os.environ.get("HOME", "").strip()
-    if home:
-        return home
-
-    expanded = os.path.expanduser("~")
-    if expanded and expanded != "~":
-        return expanded
-
-    try:
-        import pwd
-
-        resolved = pwd.getpwuid(os.getuid()).pw_dir.strip()
-        if resolved:
-            return resolved
-    except Exception:
-        pass
-
-    # Last resort: /tmp (writable on any POSIX system). Avoids crashing the
-    # subprocess with no HOME; callers can set HERMES_HOME explicitly if they
-    # need a different writable dir.
-    return "/tmp"
-
-
-def _build_subprocess_env() -> dict[str, str]:
-    env = os.environ.copy()
-    env["HOME"] = _resolve_home_dir()
-    return env
-
-
-def _jsonrpc_error(message_id: Any, code: int, message: str) -> dict[str, Any]:
-    return {
-        "jsonrpc": "2.0",
-        "id": message_id,
-        "error": {
-            "code": code,
-            "message": message,
-        },
-    }
-
-
-def _permission_denied(message_id: Any) -> dict[str, Any]:
-    return {
-        "jsonrpc": "2.0",
-        "id": message_id,
-        "result": {
-            "outcome": {
-                "outcome": "cancelled",
-            }
-        },
-    }
-
-
-def _format_messages_as_prompt(
-    messages: list[dict[str, Any]],
-    model: str | None = None,
-    tools: list[dict[str, Any]] | None = None,
-    tool_choice: Any = None,
-) -> str:
-    sections: list[str] = [
-        "You are being used as the active ACP agent backend for Hermes.",
-        "Use ACP capabilities to complete tasks.",
-        "IMPORTANT: If you take an action with a tool, you MUST output tool calls using <tool_call>{...}</tool_call> blocks with JSON exactly in OpenAI function-call shape.",
-        "If no tool is needed, answer normally.",
-    ]
-    if model:
-        sections.append(f"Hermes requested model hint: {model}")
-
-    if isinstance(tools, list) and tools:
-        tool_specs: list[dict[str, Any]] = []
-        for t in tools:
-            if not isinstance(t, dict):
-                continue
-            fn = t.get("function") or {}
-            if not isinstance(fn, dict):
-                continue
-            name = fn.get("name")
-            if not isinstance(name, str) or not name.strip():
-                continue
-            tool_specs.append(
-                {
-                    "name": name.strip(),
-                    "description": fn.get("description", ""),
-                    "parameters": fn.get("parameters", {}),
-                }
-            )
-        if tool_specs:
-            sections.append(
-                "Available tools (OpenAI function schema). "
-                "When using a tool, emit ONLY <tool_call>{...}</tool_call> with one JSON object "
-                "containing id/type/function{name,arguments}. arguments must be a JSON string.\n"
-                + json.dumps(tool_specs, ensure_ascii=False)
-            )
-
-    if tool_choice is not None:
-        sections.append(f"Tool choice hint: {json.dumps(tool_choice, ensure_ascii=False)}")
-
-    transcript: list[str] = []
-    for message in messages:
-        if not isinstance(message, dict):
-            continue
-        role = str(message.get("role") or "unknown").strip().lower()
-        if role == "tool":
-            role = "tool"
-        elif role not in {"system", "user", "assistant"}:
-            role = "context"
-
-        content = message.get("content")
-        rendered = _render_message_content(content)
-        if not rendered:
-            continue
-
-        label = {
-            "system": "System",
-            "user": "User",
-            "assistant": "Assistant",
-            "tool": "Tool",
-            "context": "Context",
-        }.get(role, role.title())
-        transcript.append(f"{label}:\n{rendered}")
-
-    if transcript:
-        sections.append("Conversation transcript:\n\n" + "\n\n".join(transcript))
-
-    sections.append("Continue the conversation from the latest user request.")
-    return "\n\n".join(section.strip() for section in sections if section and section.strip())
-
-
-def _render_message_content(content: Any) -> str:
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content.strip()
-    if isinstance(content, dict):
-        if "text" in content:
-            return str(content.get("text") or "").strip()
-        if "content" in content and isinstance(content.get("content"), str):
-            return str(content.get("content") or "").strip()
-        return json.dumps(content, ensure_ascii=True)
-    if isinstance(content, list):
-        parts: list[str] = []
-        for item in content:
-            if isinstance(item, str):
-                parts.append(item)
-            elif isinstance(item, dict):
-                text = item.get("text")
-                if isinstance(text, str) and text.strip():
-                    parts.append(text.strip())
-        return "\n".join(parts).strip()
-    return str(content).strip()
-
-
-def _extract_tool_calls_from_text(text: str) -> tuple[list[SimpleNamespace], str]:
-    if not isinstance(text, str) or not text.strip():
-        return [], ""
-
-    extracted: list[SimpleNamespace] = []
-    consumed_spans: list[tuple[int, int]] = []
-
-    def _try_add_tool_call(raw_json: str) -> None:
-        try:
-            obj = json.loads(raw_json)
-        except Exception:
-            return
-        if not isinstance(obj, dict):
-            return
-        fn = obj.get("function")
-        if not isinstance(fn, dict):
-            return
-        fn_name = fn.get("name")
-        if not isinstance(fn_name, str) or not fn_name.strip():
-            return
-        fn_args = fn.get("arguments", "{}")
-        if not isinstance(fn_args, str):
-            fn_args = json.dumps(fn_args, ensure_ascii=False)
-        call_id = obj.get("id")
-        if not isinstance(call_id, str) or not call_id.strip():
-            call_id = f"acp_call_{len(extracted)+1}"
-
-        extracted.append(
-            SimpleNamespace(
-                id=call_id,
-                call_id=call_id,
-                response_item_id=None,
-                type="function",
-                function=SimpleNamespace(name=fn_name.strip(), arguments=fn_args),
-            )
-        )
-
-    for m in _TOOL_CALL_BLOCK_RE.finditer(text):
-        raw = m.group(1)
-        _try_add_tool_call(raw)
-        consumed_spans.append((m.start(), m.end()))
-
-    # Only try bare-JSON fallback when no XML blocks were found.
-    if not extracted:
-        for m in _TOOL_CALL_JSON_RE.finditer(text):
-            raw = m.group(0)
-            _try_add_tool_call(raw)
-            consumed_spans.append((m.start(), m.end()))
-
-    if not consumed_spans:
-        return extracted, text.strip()
-
-    consumed_spans.sort()
-    merged: list[tuple[int, int]] = []
-    for start, end in consumed_spans:
-        if not merged or start > merged[-1][1]:
-            merged.append((start, end))
-        else:
-            merged[-1] = (merged[-1][0], max(merged[-1][1], end))
-
-    parts: list[str] = []
-    cursor = 0
-    for start, end in merged:
-        if cursor < start:
-            parts.append(text[cursor:start])
-        cursor = max(cursor, end)
-    if cursor < len(text):
-        parts.append(text[cursor:])
-
-    cleaned = "\n".join(p.strip() for p in parts if p and p.strip()).strip()
-    return extracted, cleaned
-
-
-
-def _ensure_path_within_cwd(path_text: str, cwd: str) -> Path:
-    candidate = Path(path_text)
-    if not candidate.is_absolute():
-        raise PermissionError("ACP file-system paths must be absolute.")
-    resolved = candidate.resolve()
-    root = Path(cwd).resolve()
-    try:
-        resolved.relative_to(root)
-    except ValueError as exc:
-        raise PermissionError(f"Path '{resolved}' is outside the session cwd '{root}'.") from exc
-    return resolved
-
-
-class _ACPChatCompletions:
-    def __init__(self, client: "CopilotACPClient"):
-        self._client = client
-
-    def create(self, **kwargs: Any) -> Any:
-        return self._client._create_chat_completion(**kwargs)
-
-
-class _ACPChatNamespace:
-    def __init__(self, client: "CopilotACPClient"):
-        self.completions = _ACPChatCompletions(client)
-
-
-class CopilotACPClient:
-    """Minimal OpenAI-client-compatible facade for Copilot ACP."""
-
-    def __init__(
-        self,
-        *,
-        api_key: str | None = None,
-        base_url: str | None = None,
-        default_headers: dict[str, str] | None = None,
-        acp_command: str | None = None,
-        acp_args: list[str] | None = None,
-        acp_cwd: str | None = None,
-        command: str | None = None,
-        args: list[str] | None = None,
-        **_: Any,
-    ):
-        self.api_key = api_key or "copilot-acp"
-        self.base_url = base_url or ACP_MARKER_BASE_URL
-        self._default_headers = dict(default_headers or {})
-        self._acp_command = acp_command or command or _resolve_command()
-        self._acp_args = list(acp_args or args or _resolve_args())
-        self._acp_cwd = str(Path(acp_cwd or os.getcwd()).resolve())
-        self.chat = _ACPChatNamespace(self)
-        self.is_closed = False
-        self._active_process: subprocess.Popen[str] | None = None
-        self._active_process_lock = threading.Lock()
-
-    def close(self) -> None:
-        proc: subprocess.Popen[str] | None
-        with self._active_process_lock:
-            proc = self._active_process
-            self._active_process = None
-        self.is_closed = True
-        if proc is None:
-            return
-        try:
-            proc.terminate()
-            proc.wait(timeout=2)
-        except Exception:
-            try:
-                proc.kill()
-            except Exception:
-                pass
-
-    def _create_chat_completion(
-        self,
-        *,
-        model: str | None = None,
-        messages: list[dict[str, Any]] | None = None,
-        timeout: float | None = None,
-        tools: list[dict[str, Any]] | None = None,
-        tool_choice: Any = None,
-        **_: Any,
-    ) -> Any:
-        prompt_text = _format_messages_as_prompt(
-            messages or [],
-            model=model,
-            tools=tools,
-            tool_choice=tool_choice,
-        )
-        # Normalise timeout: run_agent.py may pass an httpx.Timeout object
-        # (used natively by the OpenAI SDK) rather than a plain float.
-        if timeout is None:
-            _effective_timeout = _DEFAULT_TIMEOUT_SECONDS
-        elif isinstance(timeout, (int, float)):
-            _effective_timeout = float(timeout)
-        else:
-            # httpx.Timeout or similar — pick the largest component so the
-            # subprocess has enough wall-clock time for the full response.
-            _candidates = [
-                getattr(timeout, attr, None)
-                for attr in ("read", "write", "connect", "pool", "timeout")
-            ]
-            _numeric = [float(v) for v in _candidates if isinstance(v, (int, float))]
-            _effective_timeout = max(_numeric) if _numeric else _DEFAULT_TIMEOUT_SECONDS
-
-        response_text, reasoning_text = self._run_prompt(
-            prompt_text,
-            timeout_seconds=_effective_timeout,
-        )
-
-        tool_calls, cleaned_text = _extract_tool_calls_from_text(response_text)
-
-        usage = SimpleNamespace(
-            prompt_tokens=0,
-            completion_tokens=0,
-            total_tokens=0,
-            prompt_tokens_details=SimpleNamespace(cached_tokens=0),
-        )
-        assistant_message = SimpleNamespace(
-            content=cleaned_text,
-            tool_calls=tool_calls,
-            reasoning=reasoning_text or None,
-            reasoning_content=reasoning_text or None,
-            reasoning_details=None,
-        )
-        finish_reason = "tool_calls" if tool_calls else "stop"
-        choice = SimpleNamespace(message=assistant_message, finish_reason=finish_reason)
-        return SimpleNamespace(
-            choices=[choice],
-            usage=usage,
-            model=model or "copilot-acp",
-        )
-
-    def _run_prompt(self, prompt_text: str, *, timeout_seconds: float) -> tuple[str, str]:
-        try:
-            proc = subprocess.Popen(
-                [self._acp_command] + self._acp_args,
-                stdin=subprocess.PIPE,
-                stdout=subprocess.PIPE,
-                stderr=subprocess.PIPE,
-                text=True,
-                bufsize=1,
-                cwd=self._acp_cwd,
-                env=_build_subprocess_env(),
-            )
-        except FileNotFoundError as exc:
-            raise RuntimeError(
-                f"Could not start Copilot ACP command '{self._acp_command}'. "
-                "Install GitHub Copilot CLI or set HERMES_COPILOT_ACP_COMMAND/COPILOT_CLI_PATH."
-            ) from exc
-
-        if proc.stdin is None or proc.stdout is None:
-            proc.kill()
-            raise RuntimeError("Copilot ACP process did not expose stdin/stdout pipes.")
-
-        self.is_closed = False
-        with self._active_process_lock:
-            self._active_process = proc
-
-        inbox: queue.Queue[dict[str, Any]] = queue.Queue()
-        stderr_tail: deque[str] = deque(maxlen=40)
-
-        def _stdout_reader() -> None:
-            if proc.stdout is None:
-                return
-            for line in proc.stdout:
-                try:
-                    inbox.put(json.loads(line))
-                except Exception:
-                    inbox.put({"raw": line.rstrip("\n")})
-
-        def _stderr_reader() -> None:
-            if proc.stderr is None:
-                return
-            for line in proc.stderr:
-                stderr_tail.append(line.rstrip("\n"))
-
-        out_thread = threading.Thread(target=_stdout_reader, daemon=True)
-        err_thread = threading.Thread(target=_stderr_reader, daemon=True)
-        out_thread.start()
-        err_thread.start()
-
-        next_id = 0
-
-        def _request(method: str, params: dict[str, Any], *, text_parts: list[str] | None = None, reasoning_parts: list[str] | None = None) -> Any:
-            nonlocal next_id
-            next_id += 1
-            request_id = next_id
-            payload = {
-                "jsonrpc": "2.0",
-                "id": request_id,
-                "method": method,
-                "params": params,
-            }
-            proc.stdin.write(json.dumps(payload) + "\n")
-            proc.stdin.flush()
-
-            deadline = time.time() + timeout_seconds
-            while time.time() < deadline:
-                if proc.poll() is not None:
-                    break
-                try:
-                    msg = inbox.get(timeout=0.1)
-                except queue.Empty:
-                    continue
-
-                if self._handle_server_message(
-                    msg,
-                    process=proc,
-                    cwd=self._acp_cwd,
-                    text_parts=text_parts,
-                    reasoning_parts=reasoning_parts,
-                ):
-                    continue
-
-                if msg.get("id") != request_id:
-                    continue
-                if "error" in msg:
-                    err = msg.get("error") or {}
-                    raise RuntimeError(
-                        f"Copilot ACP {method} failed: {err.get('message') or err}"
-                    )
-                return msg.get("result")
-
-            stderr_text = "\n".join(stderr_tail).strip()
-            if proc.poll() is not None and stderr_text:
-                raise RuntimeError(f"Copilot ACP process exited early: {stderr_text}")
-            raise TimeoutError(f"Timed out waiting for Copilot ACP response to {method}.")
-
-        try:
-            _request(
-                "initialize",
-                {
-                    "protocolVersion": 1,
-                    "clientCapabilities": {
-                        "fs": {
-                            "readTextFile": True,
-                            "writeTextFile": True,
-                        }
-                    },
-                    "clientInfo": {
-                        "name": "hermes-agent",
-                        "title": "Hermes Agent",
-                        "version": "0.0.0",
-                    },
-                },
-            )
-            session = _request(
-                "session/new",
-                {
-                    "cwd": self._acp_cwd,
-                    "mcpServers": [],
-                },
-            ) or {}
-            session_id = str(session.get("sessionId") or "").strip()
-            if not session_id:
-                raise RuntimeError("Copilot ACP did not return a sessionId.")
-
-            text_parts: list[str] = []
-            reasoning_parts: list[str] = []
-            _request(
-                "session/prompt",
-                {
-                    "sessionId": session_id,
-                    "prompt": [
-                        {
-                            "type": "text",
-                            "text": prompt_text,
-                        }
-                    ],
-                },
-                text_parts=text_parts,
-                reasoning_parts=reasoning_parts,
-            )
-            return "".join(text_parts), "".join(reasoning_parts)
-        finally:
-            self.close()
-
-    def _handle_server_message(
-        self,
-        msg: dict[str, Any],
-        *,
-        process: subprocess.Popen[str],
-        cwd: str,
-        text_parts: list[str] | None,
-        reasoning_parts: list[str] | None,
-    ) -> bool:
-        method = msg.get("method")
-        if not isinstance(method, str):
-            return False
-
-        if method == "session/update":
-            params = msg.get("params") or {}
-            update = params.get("update") or {}
-            kind = str(update.get("sessionUpdate") or "").strip()
-            content = update.get("content") or {}
-            chunk_text = ""
-            if isinstance(content, dict):
-                chunk_text = str(content.get("text") or "")
-            if kind == "agent_message_chunk" and chunk_text and text_parts is not None:
-                text_parts.append(chunk_text)
-            elif kind == "agent_thought_chunk" and chunk_text and reasoning_parts is not None:
-                reasoning_parts.append(chunk_text)
-            return True
-
-        if process.stdin is None:
-            return True
-
-        message_id = msg.get("id")
-        params = msg.get("params") or {}
-
-        if method == "session/request_permission":
-            response = _permission_denied(message_id)
-        elif method == "fs/read_text_file":
-            try:
-                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
-                block_error = get_read_block_error(str(path))
-                if block_error:
-                    raise PermissionError(block_error)
-                content = path.read_text() if path.exists() else ""
-                line = params.get("line")
-                limit = params.get("limit")
-                if isinstance(line, int) and line > 1:
-                    lines = content.splitlines(keepends=True)
-                    start = line - 1
-                    end = start + limit if isinstance(limit, int) and limit > 0 else None
-                    content = "".join(lines[start:end])
-                if content:
-                    content = redact_sensitive_text(content)
-                response = {
-                    "jsonrpc": "2.0",
-                    "id": message_id,
-                    "result": {
-                        "content": content,
-                    },
-                }
-            except Exception as exc:
-                response = _jsonrpc_error(message_id, -32602, str(exc))
-        elif method == "fs/write_text_file":
-            try:
-                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
-                if is_write_denied(str(path)):
-                    raise PermissionError(
-                        f"Write denied: '{path}' is a protected system/credential file."
-                    )
-                path.parent.mkdir(parents=True, exist_ok=True)
-                path.write_text(str(params.get("content") or ""))
-                response = {
-                    "jsonrpc": "2.0",
-                    "id": message_id,
-                    "result": None,
-                }
-            except Exception as exc:
-                response = _jsonrpc_error(message_id, -32602, str(exc))
-        else:
-            response = _jsonrpc_error(
-                message_id,
-                -32601,
-                f"ACP client method '{method}' is not supported by Hermes yet.",
-            )
-
-        process.stdin.write(json.dumps(response) + "\n")
-        process.stdin.flush()
-        return True
+__all__ = ["CopilotACPClient"]

agent/model_metadata.py

@@ -313,6 +313,17 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "ollama.com": "ollama-cloud",
 }
 
+# Auto-extend with hostnames derived from provider profiles.
+# Any provider with a base_url not already in the map gets added automatically.
+try:
+    from providers import list_providers as _list_providers
+    for _pp in _list_providers():
+        _host = _pp.get_hostname()
+        if _host and _host not in _URL_TO_PROVIDER:
+            _URL_TO_PROVIDER[_host] = _pp.name
+except Exception:
+    pass
+
 
 def _infer_provider_from_url(base_url: str) -> Optional[str]:
     """Infer the models.dev provider name from a base URL.

agent/transports/__init__.py

@@ -6,9 +6,16 @@ Usage:
     result = transport.normalize_response(raw_response)
 """
 
-from agent.transports.types import NormalizedResponse, ToolCall, Usage, build_tool_call, map_finish_reason  # noqa: F401
+from agent.transports.types import (
+    NormalizedResponse,
+    ToolCall,
+    Usage,
+    build_tool_call,
+    map_finish_reason,
+)  # noqa: F401
 
 _REGISTRY: dict = {}
+_discovered: bool = False
 
 
 def register_transport(api_mode: str, transport_cls: type) -> None:
@@ -23,6 +30,9 @@ def get_transport(api_mode: str):
     This allows gradual migration — call sites can check for None
     and fall back to the legacy code path.
     """
+    global _discovered
+    if not _discovered:
+        _discover_transports()
     cls = _REGISTRY.get(api_mode)
     if cls is None:
         # The registry can be partially populated when a specific transport
@@ -38,6 +48,8 @@ def get_transport(api_mode: str):
 
 def _discover_transports() -> None:
     """Import all transport modules to trigger auto-registration."""
+    global _discovered
+    _discovered = True
     try:
         import agent.transports.anthropic  # noqa: F401
     except ImportError:

agent/transports/chat_completions.py

@@ -10,7 +10,7 @@ reasoning configuration, temperature handling, and extra_body assembly.
 """
 
 import copy
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 from agent.moonshot_schema import is_moonshot_model, sanitize_moonshot_tools
 from agent.prompt_builder import DEVELOPER_ROLE_MODELS
@@ -28,7 +28,9 @@ class ChatCompletionsTransport(ProviderTransport):
     def api_mode(self) -> str:
         return "chat_completions"
 
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> List[Dict[str, Any]]:
+    def convert_messages(
+        self, messages: list[dict[str, Any]], **kwargs
+    ) -> list[dict[str, Any]]:
         """Messages are already in OpenAI format — sanitize Codex leaks only.
 
         Strips Codex Responses API fields (``codex_reasoning_items`` /
@@ -45,7 +47,9 @@ class ChatCompletionsTransport(ProviderTransport):
             tool_calls = msg.get("tool_calls")
             if isinstance(tool_calls, list):
                 for tc in tool_calls:
-                    if isinstance(tc, dict) and ("call_id" in tc or "response_item_id" in tc):
+                    if isinstance(tc, dict) and (
+                        "call_id" in tc or "response_item_id" in tc
+                    ):
                         needs_sanitize = True
                         break
                 if needs_sanitize:
@@ -68,76 +72,52 @@ class ChatCompletionsTransport(ProviderTransport):
                         tc.pop("response_item_id", None)
         return sanitized
 
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    def convert_tools(self, tools: list[dict[str, Any]]) -> list[dict[str, Any]]:
         """Tools are already in OpenAI format — identity."""
         return tools
 
     def build_kwargs(
         self,
         model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
+        messages: list[dict[str, Any]],
+        tools: list[dict[str, Any]] | None = None,
         **params,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """Build chat.completions.create() kwargs.
 
-        This is the most complex transport method — it handles ~16 providers
-        via params rather than subclasses.
-
-        params:
+        params (all optional):
             timeout: float — API call timeout
             max_tokens: int | None — user-configured max tokens
-            ephemeral_max_output_tokens: int | None — one-shot override (error recovery)
+            ephemeral_max_output_tokens: int | None — one-shot override
             max_tokens_param_fn: callable — returns {max_tokens: N} or {max_completion_tokens: N}
             reasoning_config: dict | None
             request_overrides: dict | None
             session_id: str | None
-            qwen_session_metadata: dict | None — {sessionId, promptId} precomputed
             model_lower: str — lowercase model name for pattern matching
-            # Provider detection flags (all optional, default False)
-            is_openrouter: bool
-            is_nous: bool
-            is_qwen_portal: bool
-            is_github_models: bool
-            is_nvidia_nim: bool
-            is_kimi: bool
-            is_custom_provider: bool
-            ollama_num_ctx: int | None
-            # Provider routing
-            provider_preferences: dict | None
-            # Qwen-specific
-            qwen_prepare_fn: callable | None — runs AFTER codex sanitization
-            qwen_prepare_inplace_fn: callable | None — in-place variant for deepcopied lists
-            # Temperature
-            fixed_temperature: Any — from _fixed_temperature_for_model()
-            omit_temperature: bool
-            # Reasoning
+            # Provider profile path (all per-provider quirks live in providers/)
+            provider_profile: ProviderProfile | None — when present, delegates to
+                _build_kwargs_from_profile(); all flag params below are bypassed.
+            # Remaining flags — only used by the legacy fallback for unregistered
+            # providers (i.e. get_provider_profile() returned None).  Known
+            # providers all go through provider_profile.
+            qwen_session_metadata: dict | None
             supports_reasoning: bool
-            github_reasoning_extra: dict | None
-            # Claude on OpenRouter/Nous max output
             anthropic_max_output: int | None
-            # Extra
-            extra_body_additions: dict | None — pre-built extra_body entries
+            extra_body_additions: dict | None
         """
         # Codex sanitization: drop reasoning_items / call_id / response_item_id
         sanitized = self.convert_messages(messages)
 
-        # Qwen portal prep AFTER codex sanitization.  If sanitize already
-        # deepcopied, reuse that copy via the in-place variant to avoid a
-        # second deepcopy.
-        is_qwen = params.get("is_qwen_portal", False)
-        if is_qwen:
-            qwen_prep = params.get("qwen_prepare_fn")
-            qwen_prep_inplace = params.get("qwen_prepare_inplace_fn")
-            if sanitized is messages:
-                if qwen_prep is not None:
-                    sanitized = qwen_prep(sanitized)
-            else:
-                # Already deepcopied — transform in place
-                if qwen_prep_inplace is not None:
-                    qwen_prep_inplace(sanitized)
-                elif qwen_prep is not None:
-                    sanitized = qwen_prep(sanitized)
+        # ── Provider profile: single-path when present ──────────────────
+        _profile = params.get("provider_profile")
+        if _profile:
+            return self._build_kwargs_from_profile(
+                _profile, model, sanitized, tools, params
+            )
+
+        # ── Legacy fallback (unregistered / unknown provider) ───────────
+        # Reached only when get_provider_profile() returned None.
+        # Known providers always go through the profile path above.
 
         # Developer role swap for GPT-5/Codex models
         model_lower = params.get("model_lower", (model or "").lower())
@@ -150,7 +130,7 @@ class ChatCompletionsTransport(ProviderTransport):
             sanitized = list(sanitized)
             sanitized[0] = {**sanitized[0], "role": "developer"}
 
-        api_kwargs: Dict[str, Any] = {
+        api_kwargs: dict[str, Any] = {
             "model": model,
             "messages": sanitized,
         }
@@ -159,19 +139,6 @@ class ChatCompletionsTransport(ProviderTransport):
         if timeout is not None:
             api_kwargs["timeout"] = timeout
 
-        # Temperature
-        fixed_temp = params.get("fixed_temperature")
-        omit_temp = params.get("omit_temperature", False)
-        if omit_temp:
-            api_kwargs.pop("temperature", None)
-        elif fixed_temp is not None:
-            api_kwargs["temperature"] = fixed_temp
-
-        # Qwen metadata (caller precomputes {sessionId, promptId})
-        qwen_meta = params.get("qwen_session_metadata")
-        if qwen_meta and is_qwen:
-            api_kwargs["metadata"] = qwen_meta
-
         # Tools
         if tools:
             # Moonshot/Kimi uses a stricter flavored JSON Schema.  Rewriting
@@ -186,96 +153,24 @@ class ChatCompletionsTransport(ProviderTransport):
         ephemeral = params.get("ephemeral_max_output_tokens")
         max_tokens = params.get("max_tokens")
         anthropic_max_out = params.get("anthropic_max_output")
-        is_nvidia_nim = params.get("is_nvidia_nim", False)
-        is_kimi = params.get("is_kimi", False)
-        reasoning_config = params.get("reasoning_config")
 
         if ephemeral is not None and max_tokens_fn:
             api_kwargs.update(max_tokens_fn(ephemeral))
         elif max_tokens is not None and max_tokens_fn:
             api_kwargs.update(max_tokens_fn(max_tokens))
-        elif is_nvidia_nim and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(16384))
-        elif is_qwen and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(65536))
-        elif is_kimi and max_tokens_fn:
-            # Kimi/Moonshot: 32000 matches Kimi CLI's default
-            api_kwargs.update(max_tokens_fn(32000))
         elif anthropic_max_out is not None:
             api_kwargs["max_tokens"] = anthropic_max_out
 
-        # Kimi: top-level reasoning_effort (unless thinking disabled)
-        if is_kimi:
-            _kimi_thinking_off = bool(
-                reasoning_config
-                and isinstance(reasoning_config, dict)
-                and reasoning_config.get("enabled") is False
-            )
-            if not _kimi_thinking_off:
-                _kimi_effort = "medium"
-                if reasoning_config and isinstance(reasoning_config, dict):
-                    _e = (reasoning_config.get("effort") or "").strip().lower()
-                    if _e in ("low", "medium", "high"):
-                        _kimi_effort = _e
-                api_kwargs["reasoning_effort"] = _kimi_effort
-
         # extra_body assembly
-        extra_body: Dict[str, Any] = {}
+        extra_body: dict[str, Any] = {}
 
-        is_openrouter = params.get("is_openrouter", False)
-        is_nous = params.get("is_nous", False)
-        is_github_models = params.get("is_github_models", False)
-
-        provider_prefs = params.get("provider_preferences")
-        if provider_prefs and is_openrouter:
-            extra_body["provider"] = provider_prefs
-
-        # Kimi extra_body.thinking
-        if is_kimi:
-            _kimi_thinking_enabled = True
-            if reasoning_config and isinstance(reasoning_config, dict):
-                if reasoning_config.get("enabled") is False:
-                    _kimi_thinking_enabled = False
-            extra_body["thinking"] = {
-                "type": "enabled" if _kimi_thinking_enabled else "disabled",
-            }
-
-        # Reasoning
+        # Generic reasoning passthrough for unknown providers
         if params.get("supports_reasoning", False):
-            if is_github_models:
-                gh_reasoning = params.get("github_reasoning_extra")
-                if gh_reasoning is not None:
-                    extra_body["reasoning"] = gh_reasoning
+            reasoning_config = params.get("reasoning_config")
+            if reasoning_config is not None:
+                extra_body["reasoning"] = dict(reasoning_config)
             else:
-                if reasoning_config is not None:
-                    rc = dict(reasoning_config)
-                    if is_nous and rc.get("enabled") is False:
-                        pass  # omit for Nous when disabled
-                    else:
-                        extra_body["reasoning"] = rc
-                else:
-                    extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
-
-        if is_nous:
-            extra_body["tags"] = ["product=hermes-agent"]
-
-        # Ollama num_ctx
-        ollama_ctx = params.get("ollama_num_ctx")
-        if ollama_ctx:
-            options = extra_body.get("options", {})
-            options["num_ctx"] = ollama_ctx
-            extra_body["options"] = options
-
-        # Ollama/custom think=false
-        if params.get("is_custom_provider", False):
-            if reasoning_config and isinstance(reasoning_config, dict):
-                _effort = (reasoning_config.get("effort") or "").strip().lower()
-                _enabled = reasoning_config.get("enabled", True)
-                if _effort == "none" or _enabled is False:
-                    extra_body["think"] = False
-
-        if is_qwen:
-            extra_body["vl_high_resolution_images"] = True
+                extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
 
         # Merge any pre-built extra_body additions
         additions = params.get("extra_body_additions")
@@ -292,6 +187,117 @@ class ChatCompletionsTransport(ProviderTransport):
 
         return api_kwargs
 
+    def _build_kwargs_from_profile(self, profile, model, sanitized, tools, params):
+        """Build API kwargs using a ProviderProfile — single path, no legacy flags.
+
+        This method replaces the entire flag-based kwargs assembly when a
+        provider_profile is passed. Every quirk comes from the profile object.
+        """
+        from providers.base import OMIT_TEMPERATURE
+
+        # Message preprocessing
+        sanitized = profile.prepare_messages(sanitized)
+
+        # Developer role swap — model-name-based, applies to all providers
+        _model_lower = (model or "").lower()
+        if (
+            sanitized
+            and isinstance(sanitized[0], dict)
+            and sanitized[0].get("role") == "system"
+            and any(p in _model_lower for p in DEVELOPER_ROLE_MODELS)
+        ):
+            sanitized = list(sanitized)
+            sanitized[0] = {**sanitized[0], "role": "developer"}
+
+        api_kwargs: dict[str, Any] = {
+            "model": model,
+            "messages": sanitized,
+        }
+
+        # Temperature
+        if profile.fixed_temperature is OMIT_TEMPERATURE:
+            pass  # Don't include temperature at all
+        elif profile.fixed_temperature is not None:
+            api_kwargs["temperature"] = profile.fixed_temperature
+        else:
+            # Use caller's temperature if provided
+            temp = params.get("temperature")
+            if temp is not None:
+                api_kwargs["temperature"] = temp
+
+        # Timeout
+        timeout = params.get("timeout")
+        if timeout is not None:
+            api_kwargs["timeout"] = timeout
+
+        # Tools — apply Moonshot/Kimi schema sanitization regardless of path
+        if tools:
+            if is_moonshot_model(model):
+                tools = sanitize_moonshot_tools(tools)
+            api_kwargs["tools"] = tools
+
+        # max_tokens resolution — priority: ephemeral > user > profile default
+        max_tokens_fn = params.get("max_tokens_param_fn")
+        ephemeral = params.get("ephemeral_max_output_tokens")
+        user_max = params.get("max_tokens")
+        anthropic_max = params.get("anthropic_max_output")
+
+        if ephemeral is not None and max_tokens_fn:
+            api_kwargs.update(max_tokens_fn(ephemeral))
+        elif user_max is not None and max_tokens_fn:
+            api_kwargs.update(max_tokens_fn(user_max))
+        elif profile.default_max_tokens and max_tokens_fn:
+            api_kwargs.update(max_tokens_fn(profile.default_max_tokens))
+        elif anthropic_max is not None:
+            api_kwargs["max_tokens"] = anthropic_max
+
+        # Provider-specific api_kwargs extras (reasoning_effort, metadata, etc.)
+        reasoning_config = params.get("reasoning_config")
+        extra_body_from_profile, top_level_from_profile = (
+            profile.build_api_kwargs_extras(
+                reasoning_config=reasoning_config,
+                supports_reasoning=params.get("supports_reasoning", False),
+                qwen_session_metadata=params.get("qwen_session_metadata"),
+                model=model,
+                ollama_num_ctx=params.get("ollama_num_ctx"),
+            )
+        )
+        api_kwargs.update(top_level_from_profile)
+
+        # extra_body assembly
+        extra_body: dict[str, Any] = {}
+
+        # Profile's extra_body (tags, provider prefs, vl_high_resolution, etc.)
+        profile_body = profile.build_extra_body(
+            session_id=params.get("session_id"),
+            provider_preferences=params.get("provider_preferences"),
+        )
+        if profile_body:
+            extra_body.update(profile_body)
+
+        # Profile's reasoning/thinking extra_body entries
+        if extra_body_from_profile:
+            extra_body.update(extra_body_from_profile)
+
+        # Merge any pre-built extra_body additions from the caller
+        additions = params.get("extra_body_additions")
+        if additions:
+            extra_body.update(additions)
+
+        # Request overrides (user config)
+        overrides = params.get("request_overrides")
+        if overrides:
+            for k, v in overrides.items():
+                if k == "extra_body" and isinstance(v, dict):
+                    extra_body.update(v)
+                else:
+                    api_kwargs[k] = v
+
+        if extra_body:
+            api_kwargs["extra_body"] = extra_body
+
+        return api_kwargs
+
     def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
         """Normalize OpenAI ChatCompletion to NormalizedResponse.
 
@@ -313,7 +319,7 @@ class ChatCompletionsTransport(ProviderTransport):
                 # Gemini 3 thinking models attach extra_content with
                 # thought_signature — without replay on the next turn the API
                 # rejects the request with 400.
-                tc_provider_data: Dict[str, Any] = {}
+                tc_provider_data: dict[str, Any] = {}
                 extra = getattr(tc, "extra_content", None)
                 if extra is None and hasattr(tc, "model_extra"):
                     extra = (tc.model_extra or {}).get("extra_content")
@@ -324,12 +330,14 @@ class ChatCompletionsTransport(ProviderTransport):
                         except Exception:
                             pass
                     tc_provider_data["extra_content"] = extra
-                tool_calls.append(ToolCall(
-                    id=tc.id,
-                    name=tc.function.name,
-                    arguments=tc.function.arguments,
-                    provider_data=tc_provider_data or None,
-                ))
+                tool_calls.append(
+                    ToolCall(
+                        id=tc.id,
+                        name=tc.function.name,
+                        arguments=tc.function.arguments,
+                        provider_data=tc_provider_data or None,
+                    )
+                )
 
         usage = None
         if hasattr(response, "usage") and response.usage:
@@ -347,7 +355,7 @@ class ChatCompletionsTransport(ProviderTransport):
         reasoning = getattr(msg, "reasoning", None)
         reasoning_content = getattr(msg, "reasoning_content", None)
 
-        provider_data: Dict[str, Any] = {}
+        provider_data: dict[str, Any] = {}
         if reasoning_content:
             provider_data["reasoning_content"] = reasoning_content
         rd = getattr(msg, "reasoning_details", None)
@@ -373,7 +381,7 @@ class ChatCompletionsTransport(ProviderTransport):
             return False
         return True
 
-    def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
+    def extract_cache_stats(self, response: Any) -> dict[str, int] | None:
         """Extract OpenRouter/OpenAI cache stats from prompt_tokens_details."""
         usage = getattr(response, "usage", None)
         if usage is None:

agent/transports/types.py

@@ -12,7 +12,7 @@ from __future__ import annotations
 
 import json
 from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 
 @dataclass
@@ -32,10 +32,10 @@ class ToolCall:
     * Others: ``None``
     """
 
-    id: Optional[str]
+    id: str | None
     name: str
     arguments: str  # JSON string
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
+    provider_data: dict[str, Any] | None = field(default=None, repr=False)
 
     # ── Backward compatibility ──────────────────────────────────
     # The agent loop reads tc.function.name / tc.function.arguments
@@ -47,17 +47,17 @@ class ToolCall:
         return "function"
 
     @property
-    def function(self) -> "ToolCall":
+    def function(self) -> ToolCall:
         """Return self so tc.function.name / tc.function.arguments work."""
         return self
 
     @property
-    def call_id(self) -> Optional[str]:
+    def call_id(self) -> str | None:
         """Codex call_id from provider_data, accessed via getattr by _build_assistant_message."""
         return (self.provider_data or {}).get("call_id")
 
     @property
-    def response_item_id(self) -> Optional[str]:
+    def response_item_id(self) -> str | None:
         """Codex response_item_id from provider_data."""
         return (self.provider_data or {}).get("response_item_id")
 
@@ -101,18 +101,18 @@ class NormalizedResponse:
     * Others: ``None``
     """
 
-    content: Optional[str]
-    tool_calls: Optional[List[ToolCall]]
+    content: str | None
+    tool_calls: list[ToolCall] | None
     finish_reason: str  # "stop", "tool_calls", "length", "content_filter"
-    reasoning: Optional[str] = None
-    usage: Optional[Usage] = None
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
+    reasoning: str | None = None
+    usage: Usage | None = None
+    provider_data: dict[str, Any] | None = field(default=None, repr=False)
 
     # ── Backward compatibility ──────────────────────────────────
     # The shim _nr_to_assistant_message() mapped these from provider_data.
     # These properties let NormalizedResponse pass through directly.
     @property
-    def reasoning_content(self) -> Optional[str]:
+    def reasoning_content(self) -> str | None:
         pd = self.provider_data or {}
         return pd.get("reasoning_content")
 
@@ -136,8 +136,9 @@ class NormalizedResponse:
 # Factory helpers
 # ---------------------------------------------------------------------------
 
+
 def build_tool_call(
-    id: Optional[str],
+    id: str | None,
     name: str,
     arguments: Any,
     **provider_fields: Any,
@@ -151,7 +152,7 @@ def build_tool_call(
     return ToolCall(id=id, name=name, arguments=args_str, provider_data=pd)
 
 
-def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
+def map_finish_reason(reason: str | None, mapping: dict[str, str]) -> str:
     """Translate a provider-specific stop reason to the normalised set.
 
     Falls back to ``"stop"`` for unknown or ``None`` reasons.

hermes_cli/auth.py

@@ -374,6 +374,37 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
     ),
 }
 
+# Auto-extend PROVIDER_REGISTRY with any api-key provider registered in
+# providers/ that is not already declared above.  New providers only need a
+# providers/*.py file — no edits to this file required.
+try:
+    from providers import list_providers as _list_providers_for_registry
+    for _pp in _list_providers_for_registry():
+        if _pp.name in PROVIDER_REGISTRY:
+            continue
+        if _pp.auth_type != "api_key" or not _pp.env_vars:
+            continue
+        # Skip providers that need custom token resolution (copilot, kimi, zai)
+        # — those are already fully declared above.
+        if _pp.name in {"copilot", "kimi-coding", "kimi-coding-cn", "zai"}:
+            continue
+        _api_key_vars = tuple(v for v in _pp.env_vars if not v.endswith("_BASE_URL") and not v.endswith("_URL"))
+        _base_url_var = next((v for v in _pp.env_vars if v.endswith("_BASE_URL") or v.endswith("_URL")), None)
+        PROVIDER_REGISTRY[_pp.name] = ProviderConfig(
+            id=_pp.name,
+            name=_pp.display_name or _pp.name,
+            auth_type="api_key",
+            inference_base_url=_pp.base_url,
+            api_key_env_vars=_api_key_vars or _pp.env_vars,
+            base_url_env_var=_base_url_var or "",
+        )
+        # Also register aliases so resolve_provider() resolves them
+        for _alias in _pp.aliases:
+            if _alias not in PROVIDER_REGISTRY:
+                PROVIDER_REGISTRY[_alias] = PROVIDER_REGISTRY[_pp.name]
+except Exception:
+    pass
+
 
 # =============================================================================
 # Anthropic Key Helper
@@ -1150,6 +1181,17 @@ def resolve_provider(
         "vllm": "custom", "llamacpp": "custom",
         "llama.cpp": "custom", "llama-cpp": "custom",
     }
+    # Extend with aliases declared in providers/*.py that aren't already mapped.
+    # This keeps providers/ as the single source for new aliases while the
+    # hardcoded dict above remains authoritative for existing ones.
+    try:
+        from providers import list_providers as _lp
+        for _pp in _lp():
+            for _alias in _pp.aliases:
+                if _alias not in _PROVIDER_ALIASES:
+                    _PROVIDER_ALIASES[_alias] = _pp.name
+    except Exception:
+        pass
     normalized = _PROVIDER_ALIASES.get(normalized, normalized)
 
     if normalized == "openrouter":

hermes_cli/config.py

@@ -4252,3 +4252,45 @@ def config_command(args):
         print("  hermes config path      Show config file path")
         print("  hermes config env-path  Show .env file path")
         sys.exit(1)
+
+
+# ── Profile-driven env var injection ─────────────────────────────────────────
+# Any provider registered in providers/ with auth_type="api_key" automatically
+# gets its env_vars exposed in OPTIONAL_ENV_VARS without editing this file.
+# Runs once at import time.
+
+_profile_env_vars_injected = False
+
+
+def _inject_profile_env_vars() -> None:
+    """Populate OPTIONAL_ENV_VARS from provider profiles not already listed.
+
+    Called once at module load time. Idempotent — repeated calls are no-ops.
+    """
+    global _profile_env_vars_injected
+    if _profile_env_vars_injected:
+        return
+    _profile_env_vars_injected = True
+    try:
+        from providers import list_providers
+        for _pp in list_providers():
+            if _pp.auth_type not in ("api_key",):
+                continue
+            for _var in _pp.env_vars:
+                if _var in OPTIONAL_ENV_VARS:
+                    continue
+                _is_key = not _var.endswith("_BASE_URL") and not _var.endswith("_URL")
+                OPTIONAL_ENV_VARS[_var] = {
+                    "description": f"{_pp.display_name or _pp.name} {'API key' if _is_key else 'base URL override'}",
+                    "prompt": f"{_pp.display_name or _pp.name} {'API key' if _is_key else 'base URL (leave empty for default)'}",
+                    "url": _pp.signup_url or None,
+                    "password": _is_key,
+                    "category": "provider",
+                    "advanced": True,
+                }
+    except Exception:
+        pass
+
+
+# Eagerly inject so that OPTIONAL_ENV_VARS is fully populated at import time.
+_inject_profile_env_vars()

hermes_cli/doctor.py

@@ -164,6 +164,84 @@ def _check_gateway_service_linger(issues: list[str]) -> None:
         check_warn("Could not verify systemd linger", f"({linger_detail})")
 
 
+_APIKEY_PROVIDERS_CACHE: list | None = None
+
+
+def _build_apikey_providers_list() -> list:
+    """Build the API-key provider health-check list once and cache it.
+
+    Tuple format: (name, env_vars, default_url, base_env, supports_models_endpoint)
+    Base list augmented with any ProviderProfile with auth_type="api_key" not
+    already present — adding providers/*.py is sufficient to get into doctor.
+    """
+    _static = [
+        ("Z.AI / GLM",      ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"), "https://api.z.ai/api/paas/v4/models", "GLM_BASE_URL", True),
+        ("Kimi / Moonshot",  ("KIMI_API_KEY",),                              "https://api.moonshot.ai/v1/models",   "KIMI_BASE_URL", True),
+        ("StepFun Step Plan", ("STEPFUN_API_KEY",),                          "https://api.stepfun.ai/step_plan/v1/models", "STEPFUN_BASE_URL", True),
+        ("Kimi / Moonshot (China)", ("KIMI_CN_API_KEY",),                    "https://api.moonshot.cn/v1/models",   None, True),
+        ("Arcee AI",         ("ARCEEAI_API_KEY",),                           "https://api.arcee.ai/api/v1/models",  "ARCEE_BASE_URL", True),
+        ("GMI Cloud",        ("GMI_API_KEY",),                               "https://api.gmi-serving.com/v1/models", "GMI_BASE_URL", True),
+        ("DeepSeek",         ("DEEPSEEK_API_KEY",),                          "https://api.deepseek.com/v1/models",  "DEEPSEEK_BASE_URL", True),
+        ("Hugging Face",     ("HF_TOKEN",),                                  "https://router.huggingface.co/v1/models", "HF_BASE_URL", True),
+        ("NVIDIA NIM",       ("NVIDIA_API_KEY",),                            "https://integrate.api.nvidia.com/v1/models", "NVIDIA_BASE_URL", True),
+        ("Alibaba/DashScope", ("DASHSCOPE_API_KEY",),                        "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models", "DASHSCOPE_BASE_URL", True),
+        # MiniMax: the /anthropic endpoint doesn't support /models; use the /v1 surface.
+        ("MiniMax",          ("MINIMAX_API_KEY",),                           "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
+        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                        "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", True),
+        ("Vercel AI Gateway", ("AI_GATEWAY_API_KEY",),                       "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
+        ("Kilo Code",        ("KILOCODE_API_KEY",),                          "https://api.kilo.ai/api/gateway/models", "KILOCODE_BASE_URL", True),
+        ("OpenCode Zen",     ("OPENCODE_ZEN_API_KEY",),                      "https://opencode.ai/zen/v1/models",  "OPENCODE_ZEN_BASE_URL", True),
+        # OpenCode Go has no shared /models endpoint; skip the health check.
+        ("OpenCode Go",      ("OPENCODE_GO_API_KEY",),                       None,                                  "OPENCODE_GO_BASE_URL", False),
+    ]
+    _known_names = {t[0] for t in _static}
+    # Also index by profile canonical name so profiles without display_name
+    # don't create duplicate entries for providers already in the static list.
+    _known_canonical: set[str] = set()
+    _name_to_canonical = {
+        "Z.AI / GLM": "zai", "Kimi / Moonshot": "kimi-coding",
+        "StepFun Step Plan": "stepfun", "Kimi / Moonshot (China)": "kimi-coding-cn",
+        "Arcee AI": "arcee", "GMI Cloud": "gmi", "DeepSeek": "deepseek",
+        "Hugging Face": "huggingface", "NVIDIA NIM": "nvidia",
+        "Alibaba/DashScope": "alibaba", "MiniMax": "minimax",
+        "MiniMax (China)": "minimax-cn", "Vercel AI Gateway": "ai-gateway",
+        "Kilo Code": "kilocode", "OpenCode Zen": "opencode-zen",
+        "OpenCode Go": "opencode-go",
+    }
+    for _label, _canonical in _name_to_canonical.items():
+        _known_canonical.add(_canonical)
+    try:
+        from providers import list_providers
+        from providers.base import ProviderProfile as _PP
+        for _pp in list_providers():
+            if not isinstance(_pp, _PP) or _pp.auth_type != "api_key" or not _pp.env_vars:
+                continue
+            _label = _pp.display_name or _pp.name
+            if _label in _known_names or _pp.name in _known_canonical:
+                continue
+            # Separate API-key vars from base-URL override vars — the health-check
+            # loop sends the first found value as Authorization: Bearer, so a URL
+            # string must never be picked.
+            _key_vars = tuple(
+                v for v in _pp.env_vars
+                if not v.endswith("_BASE_URL") and not v.endswith("_URL")
+            )
+            _base_var = next(
+                (v for v in _pp.env_vars if v.endswith("_BASE_URL") or v.endswith("_URL")),
+                None,
+            )
+            if not _key_vars:
+                continue
+            _models_url = (
+                (_pp.models_url or (_pp.base_url.rstrip("/") + "/models"))
+                if _pp.base_url else None
+            )
+            _static.append((_label, _key_vars, _models_url, _base_var, True))
+    except Exception:
+        pass
+    return _static
+
+
 def run_doctor(args):
     """Run diagnostic checks."""
     should_fix = getattr(args, 'fix', False)
@@ -931,27 +1009,11 @@ def run_doctor(args):
 
     # -- API-key providers --
     # Tuple: (name, env_vars, default_url, base_env, supports_models_endpoint)
-    # If supports_models_endpoint is False, we skip the health check and just show "configured"
-    _apikey_providers = [
-        ("Z.AI / GLM",      ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"), "https://api.z.ai/api/paas/v4/models", "GLM_BASE_URL", True),
-        ("Kimi / Moonshot",  ("KIMI_API_KEY",),                              "https://api.moonshot.ai/v1/models",   "KIMI_BASE_URL", True),
-        ("StepFun Step Plan",   ("STEPFUN_API_KEY",),                           "https://api.stepfun.ai/step_plan/v1/models", "STEPFUN_BASE_URL", True),
-        ("Kimi / Moonshot (China)", ("KIMI_CN_API_KEY",),                    "https://api.moonshot.cn/v1/models",   None, True),
-        ("Arcee AI",         ("ARCEEAI_API_KEY",),                            "https://api.arcee.ai/api/v1/models",  "ARCEE_BASE_URL", True),
-        ("GMI Cloud",        ("GMI_API_KEY",),                                "https://api.gmi-serving.com/v1/models", "GMI_BASE_URL", True),
-        ("DeepSeek",         ("DEEPSEEK_API_KEY",),                           "https://api.deepseek.com/v1/models",  "DEEPSEEK_BASE_URL", True),
-        ("Hugging Face",     ("HF_TOKEN",),                                   "https://router.huggingface.co/v1/models", "HF_BASE_URL", True),
-        ("NVIDIA NIM",       ("NVIDIA_API_KEY",),                             "https://integrate.api.nvidia.com/v1/models", "NVIDIA_BASE_URL", True),
-        ("Alibaba/DashScope", ("DASHSCOPE_API_KEY",),                         "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models", "DASHSCOPE_BASE_URL", True),
-        # MiniMax: the /anthropic endpoint doesn't support /models, but the /v1 endpoint does.
-        ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
-        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", True),
-        ("Vercel AI Gateway",       ("AI_GATEWAY_API_KEY",),                          "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
-        ("Kilo Code",        ("KILOCODE_API_KEY",),                            "https://api.kilo.ai/api/gateway/models",  "KILOCODE_BASE_URL", True),
-        ("OpenCode Zen",     ("OPENCODE_ZEN_API_KEY",),                        "https://opencode.ai/zen/v1/models",  "OPENCODE_ZEN_BASE_URL", True),
-        # OpenCode Go has no shared /models endpoint; skip the health check.
-        ("OpenCode Go",      ("OPENCODE_GO_API_KEY",),                         None,                                  "OPENCODE_GO_BASE_URL", False),
-    ]
+    # Cached at module level after first build — profiles auto-extend it.
+    global _APIKEY_PROVIDERS_CACHE
+    if _APIKEY_PROVIDERS_CACHE is None:
+        _APIKEY_PROVIDERS_CACHE = _build_apikey_providers_list()
+    _apikey_providers = _APIKEY_PROVIDERS_CACHE
     for _pname, _env_vars, _default_url, _base_env, _supports_health_check in _apikey_providers:
         _key = ""
         for _ev in _env_vars:

hermes_cli/main.py

@@ -1528,6 +1528,21 @@ def cmd_model(args):
     select_provider_and_model(args=args)
 
 
+def _is_profile_api_key_provider(provider_id: str) -> bool:
+    """Return True when provider_id maps to a profile with auth_type='api_key'.
+
+    Used as a catch-all in select_provider_and_model() so that new providers
+    declared in providers/*.py automatically dispatch to _model_flow_api_key_provider
+    without requiring an explicit elif branch here.
+    """
+    try:
+        from providers import get_provider_profile
+        _p = get_provider_profile(provider_id)
+        return _p is not None and _p.auth_type == "api_key"
+    except Exception:
+        return False
+
+
 def select_provider_and_model(args=None):
     """Core provider selection + model picking logic.
 
@@ -1820,7 +1835,7 @@ def select_provider_and_model(args=None):
         "gmi",
         "nvidia",
         "ollama-cloud",
-    ):
+    ) or _is_profile_api_key_provider(selected_provider):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
     # ── Post-switch cleanup: clear stale OPENAI_BASE_URL ──────────────
@@ -7618,6 +7633,22 @@ def cmd_logs(args):
     )
 
 
+def _build_provider_choices() -> list[str]:
+    """Build the --provider choices list from CANONICAL_PROVIDERS + 'auto'."""
+    try:
+        from hermes_cli.models import CANONICAL_PROVIDERS as _cp
+        return ["auto"] + [p.slug for p in _cp]
+    except Exception:
+        # Fallback: static list guarantees the CLI always works
+        return [
+            "auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot",
+            "anthropic", "gemini", "google-gemini-cli", "xai", "bedrock", "azure-foundry",
+            "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn",
+            "stepfun", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee",
+            "nvidia", "deepseek", "alibaba", "qwen-oauth", "opencode-zen", "opencode-go",
+        ]
+
+
 def main():
     """Main entry point for hermes CLI."""
     parser = argparse.ArgumentParser(
@@ -7811,30 +7842,7 @@ For more help on a command:
     )
     chat_parser.add_argument(
         "--provider",
-        choices=[
-            "auto",
-            "openrouter",
-            "nous",
-            "openai-codex",
-            "copilot-acp",
-            "copilot",
-            "anthropic",
-            "gemini",
-            "xai",
-            "ollama-cloud",
-            "huggingface",
-            "zai",
-            "kimi-coding",
-            "kimi-coding-cn",
-            "stepfun",
-            "minimax",
-            "minimax-cn",
-            "kilocode",
-            "xiaomi",
-            "arcee",
-            "gmi",
-            "nvidia",
-        ],
+        choices=_build_provider_choices(),
         default=None,
         help="Inference provider (default: auto)",
     )

hermes_cli/models.py

@@ -750,6 +750,25 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
     ProviderEntry("azure-foundry",  "Azure Foundry",            "Azure Foundry (OpenAI-style or Anthropic-style endpoint — your Azure AI deployment)"),
 ]
 
+# Auto-extend CANONICAL_PROVIDERS with any provider registered in providers/
+# that is not already in the list above.  Adding providers/*.py is sufficient
+# to expose a new provider in the model picker, /model, and all downstream
+# consumers — no edits to this file needed.
+_canonical_slugs = {p.slug for p in CANONICAL_PROVIDERS}
+try:
+    from providers import list_providers as _list_providers_for_canonical
+    for _pp in _list_providers_for_canonical():
+        if _pp.name in _canonical_slugs:
+            continue
+        if _pp.auth_type in ("oauth_device_code", "oauth_external", "external_process", "aws_sdk", "copilot"):
+            continue  # non-api-key flows need bespoke picker UX; skip auto-inject
+        _label = _pp.display_name or _pp.name
+        _desc = _pp.description or f"{_label} (direct API)"
+        CANONICAL_PROVIDERS.append(ProviderEntry(_pp.name, _label, _desc))
+        _canonical_slugs.add(_pp.name)
+except Exception:
+    pass
+
 # Derived dicts — used throughout the codebase
 _PROVIDER_LABELS = {p.slug: p.label for p in CANONICAL_PROVIDERS}
 _PROVIDER_LABELS["custom"] = "Custom endpoint"  # special case: not a named provider
@@ -1884,6 +1903,34 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
             live = fetch_api_models(api_key, base_url)
             if live:
                 return live
+
+    # ── Profile-based generic live fetch (all simple api-key providers) ──
+    # Handles any provider registered in providers/ with auth_type="api_key".
+    # Replaces per-provider copy-paste blocks (stepfun, gmi, zai, etc.).
+    try:
+        from providers import get_provider_profile
+        from hermes_cli.auth import resolve_api_key_provider_credentials
+
+        _p = get_provider_profile(normalized)
+        if _p and _p.auth_type == "api_key" and _p.base_url:
+            try:
+                creds = resolve_api_key_provider_credentials(normalized)
+                api_key = str(creds.get("api_key") or "").strip()
+                base_url = str(creds.get("base_url") or "").strip()
+            except Exception:
+                api_key, base_url = "", _p.base_url
+            if not base_url:
+                base_url = _p.base_url
+            if api_key:
+                live = _p.fetch_models(api_key=api_key)
+                if live:
+                    return live
+            # Use profile's fallback_models if defined
+            if _p.fallback_models:
+                return list(_p.fallback_models)
+    except Exception:
+        pass
+
     curated_static = list(_PROVIDER_MODELS.get(normalized, []))
     if normalized in _MODELS_DEV_PREFERRED:
         return _merge_with_models_dev(normalized, curated_static)

hermes_cli/runtime_provider.py

@@ -214,10 +214,6 @@ def _resolve_runtime_from_pool_entry(
         base_url = cfg_base_url or base_url or "https://api.anthropic.com"
     elif provider == "openrouter":
         base_url = base_url or OPENROUTER_BASE_URL
-    elif provider == "xai":
-        api_mode = "codex_responses"
-    elif provider == "nous":
-        api_mode = "chat_completions"
     elif provider == "copilot":
         api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
         base_url = base_url or PROVIDER_REGISTRY["copilot"].inference_base_url
@@ -249,6 +245,14 @@ def _resolve_runtime_from_pool_entry(
             base_url = re.sub(r"/v1/?$", "", base_url)
     else:
         configured_provider = str(model_cfg.get("provider") or "").strip().lower()
+        # Use profile api_mode for all other known providers
+        try:
+            from providers import get_provider_profile
+            _p = get_provider_profile(provider)
+            if _p and _p.api_mode:
+                api_mode = _p.api_mode
+        except Exception:
+            pass
         # Honour model.base_url from config.yaml when the configured provider
         # matches this provider — same pattern as the Anthropic branch above.
         # Only override when the pool entry has no explicit base_url (i.e. it
@@ -266,12 +270,21 @@ def _resolve_runtime_from_pool_entry(
             from hermes_cli.models import opencode_model_api_mode
             api_mode = opencode_model_api_mode(provider, effective_model)
         else:
-            # Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
-            # Kimi /coding, api.openai.com → codex_responses, api.x.ai →
-            # codex_responses).
-            detected = _detect_api_mode_for_url(base_url)
-            if detected:
-                api_mode = detected
+            # Try profile api_mode first, then auto-detect from URL
+            try:
+                from providers import get_provider_profile
+                _p = get_provider_profile(provider)
+                if _p and _p.api_mode:
+                    api_mode = _p.api_mode
+            except Exception:
+                pass
+            if api_mode == "chat_completions":
+                # Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
+                # Kimi /coding, api.openai.com → codex_responses, api.x.ai →
+                # codex_responses).
+                detected = _detect_api_mode_for_url(base_url)
+                if detected:
+                    api_mode = detected
 
     # OpenCode base URLs end with /v1 for OpenAI-compatible models, but the
     # Anthropic SDK prepends its own /v1/messages to the base_url.  Strip the

providers/README.md

@@ -0,0 +1,307 @@
+# providers/
+
+Single source of truth for every inference provider Hermes knows about.
+
+Each provider is declared once here as a `ProviderProfile`. Every other layer —
+auth resolution, transport kwargs, model listing, runtime routing — reads from
+these profiles instead of maintaining its own parallel data.
+
+---
+
+## Directory layout
+
+```
+providers/
+├── base.py           ProviderProfile dataclass + OMIT_TEMPERATURE sentinel
+├── __init__.py       Registry: register_provider(), get_provider_profile()
+├── README.md         This file
+│
+├── # Simple providers — just identity + auth + endpoint
+├── alibaba.py        Alibaba Cloud DashScope
+├── arcee.py          Arcee AI
+├── bedrock.py        AWS Bedrock  (api_mode=bedrock_converse)
+├── deepseek.py       DeepSeek
+├── huggingface.py    Hugging Face Inference API
+├── kilocode.py       Kilo Code
+├── minimax.py        MiniMax (international + CN)
+├── nvidia.py         NVIDIA NIM  (default_max_tokens=16384)
+├── ollama_cloud.py   Ollama Cloud
+├── stepfun.py        StepFun
+├── xiaomi.py         Xiaomi MiMo
+├── xai.py            xAI Grok  (api_mode=codex_responses)
+├── zai.py            Z.AI / GLM
+│
+├── # Medium — one or two quirks
+├── anthropic.py      Native Anthropic  (x-api-key header, api_mode=anthropic_messages)
+├── copilot.py        GitHub Copilot  (auth_type=copilot, reasoning per model)
+├── copilot_acp.py    Copilot ACP subprocess  (api_mode=copilot_acp)
+├── custom.py         Custom/Ollama local  (think=false, num_ctx)
+├── gemini.py         Google Gemini AI Studio + Cloud Code OAuth
+├── kimi.py           Kimi Coding  (OMIT_TEMPERATURE, thinking, dual endpoint)
+├── openai_codex.py   OpenAI Codex OAuth  (api_mode=codex_responses)
+├── opencode.py       OpenCode Zen + Go  (per-model api_mode routing)
+│
+├── # Complex — subclasses with multiple overrides
+├── nous.py           Nous Portal  (tags, attribution, reasoning omit-when-disabled)
+├── openrouter.py     OpenRouter  (provider preferences, public model fetch)
+├── qwen.py           Qwen OAuth  (message normalization, cache_control, vl_hires)
+└── vercel.py         Vercel AI Gateway  (attribution headers, reasoning passthrough)
+```
+
+---
+
+## ProviderProfile fields
+
+```python
+@dataclass
+class ProviderProfile:
+    # Identity
+    name: str                    # canonical ID — auto-registered as PROVIDER_REGISTRY key for new api-key providers
+    api_mode: str                # "chat_completions" | "anthropic_messages" |
+                                 # "codex_responses" | "bedrock_converse" | "copilot_acp"
+    aliases: tuple               # alternate names resolved by get_provider_profile()
+
+    # Auth & endpoints
+    env_vars: tuple              # env var names holding the API key, in priority order
+    base_url: str                # default inference endpoint
+    models_url: str              # explicit models endpoint; falls back to {base_url}/models
+                                 # set when the models catalog lives at a different URL
+                                 # (e.g. OpenRouter: public /api/v1/models vs /api/v1 inference)
+    auth_type: str               # "api_key" | "oauth_device_code" | "oauth_external" |
+                                 # "copilot" | "aws" | "external_process"
+
+    # Client-level quirks
+    default_headers: dict        # extra HTTP headers sent on every request
+
+    # Request-level quirks
+    fixed_temperature: Any       # None = use caller's default; OMIT_TEMPERATURE = don't send
+    default_max_tokens: int|None # inject max_tokens when caller omits it
+    default_aux_model: str       # cheap model for auxiliary tasks (compression, vision, etc.)
+                                 # empty string = use main model (default)
+```
+
+---
+
+## Hooks (override in a subclass)
+
+| Method | When to override |
+|--------|-----------------|
+| `prepare_messages(messages)` | Provider needs message pre-processing (Qwen: string → list-of-parts, cache_control) |
+| `build_extra_body(*, session_id, **ctx)` | Provider-specific `extra_body` fields (Nous: tags, OpenRouter: provider preferences) |
+| `build_api_kwargs_extras(*, reasoning_config, **ctx)` | Returns `(extra_body_additions, top_level_kwargs)` — use when some fields go to `extra_body` and some go top-level (Kimi: `reasoning_effort` top-level; OpenRouter: `reasoning` in extra_body) |
+| `fetch_models(*, api_key, timeout)` | Custom model listing (Anthropic: x-api-key header; OpenRouter: public endpoint, no auth; Bedrock/copilot-acp: return None) |
+
+All hooks have safe defaults — only override what differs from the base.
+
+---
+
+## How to add a new provider
+
+### 1. Simple (standard OpenAI-compatible endpoint)
+
+```python
+# providers/myprovider.py
+from providers import register_provider
+from providers.base import ProviderProfile
+
+myprovider = ProviderProfile(
+    name="myprovider",           # must match id in hermes_cli/auth.py PROVIDER_REGISTRY
+    aliases=("my-provider", "myp"),
+    api_mode="chat_completions",
+    env_vars=("MYPROVIDER_API_KEY",),
+    base_url="https://api.myprovider.com/v1",
+    auth_type="api_key",
+)
+
+register_provider(myprovider)
+```
+
+The default `fetch_models()` will call `GET https://api.myprovider.com/v1/models`
+with Bearer auth automatically. No override needed for standard `/v1/models`.
+
+### 2. With quirks (subclass)
+
+```python
+# providers/myprovider.py
+from typing import Any
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class MyProviderProfile(ProviderProfile):
+    """My provider — custom reasoning header."""
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        **ctx: Any,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        extra_body: dict[str, Any] = {}
+        if reasoning_config:
+            extra_body["my_reasoning"] = reasoning_config.get("effort", "medium")
+        return extra_body, {}
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        # Override only if your endpoint differs from standard /v1/models
+        return super().fetch_models(api_key=api_key, timeout=timeout)
+
+
+myprovider = MyProviderProfile(
+    name="myprovider",
+    aliases=("myp",),
+    env_vars=("MYPROVIDER_API_KEY",),
+    base_url="https://api.myprovider.com/v1",
+)
+
+register_provider(myprovider)
+```
+
+### 3. Wire it up
+
+After creating the file, add `name` to the `_PROFILE_ACTIVE_PROVIDERS` set in
+`run_agent.py` once you've verified parity against the legacy flag path. Start
+with a simple provider (no message prep, no reasoning quirks) and work up.
+
+---
+
+## fetch_models contract
+
+```python
+def fetch_models(
+    self,
+    *,
+    api_key: str | None = None,
+    timeout: float = 8.0,
+) -> list[str] | None:
+    ...
+```
+
+- Returns `list[str]`: model IDs from the provider's live endpoint.
+- Returns `None`: provider doesn't support REST model listing (Bedrock, copilot-acp),
+  or the request failed. Callers **must** fall back to `_PROVIDER_MODELS` on `None`.
+- Never raises — swallow exceptions and return `None`.
+- Default implementation: `GET {base_url}/models` with Bearer auth. Works for any
+  standard OpenAI-compatible provider.
+
+**Override when:**
+- Auth header is not `Bearer` (Anthropic: `x-api-key`)
+- Endpoint path differs from `/models` AND you can't just set `models_url` (OpenRouter: public endpoint, pass `api_key=None` explicitly)
+- Response format differs (extra wrapping, non-standard `id` field)
+- Provider has no REST endpoint (Bedrock, copilot-acp → return `None`)
+- Filtering needed post-fetch (only tool-capable models, etc.)
+
+Use `models_url` instead of overriding when the only difference is the URL:
+
+```python
+# No subclass needed — just set models_url
+myprovider = ProviderProfile(
+    name="myprovider",
+    base_url="https://api.myprovider.com/v1",
+    models_url="https://catalog.myprovider.com/models",  # different host
+)
+```
+
+---
+
+## Debugging
+
+### Check if a provider resolves
+
+```python
+from providers import get_provider_profile
+
+p = get_provider_profile("myprovider")
+print(p)           # ProviderProfile(name='myprovider', ...)
+print(p.base_url)
+print(p.api_mode)
+```
+
+### Check all registered providers
+
+```python
+from providers import _REGISTRY
+print(list(_REGISTRY.keys()))
+```
+
+### Test live model fetch
+
+```python
+import os
+from providers import get_provider_profile
+
+p = get_provider_profile("myprovider")
+key = os.getenv("MYPROVIDER_API_KEY")
+models = p.fetch_models(api_key=key, timeout=5.0)
+print(models)      # list of model IDs, or None on failure
+```
+
+### Test alias resolution
+
+```python
+from providers import get_provider_profile
+
+# All of these should return the same profile
+assert get_provider_profile("openrouter").name == "openrouter"
+assert get_provider_profile("or").name == "openrouter"
+```
+
+### Run the provider test suite
+
+```bash
+# From the repo root
+source venv/bin/activate
+python -m pytest tests/providers/ -v
+```
+
+### Check ruff + ty compliance
+
+```bash
+source venv/bin/activate
+ruff format providers/*.py
+ruff check providers/*.py --select UP,E,F,I,W
+ty check providers/*.py
+```
+
+---
+
+## Common mistakes
+
+**Wrong `name`** — must be the same string that appears as the key in
+`hermes_cli/auth.py` `PROVIDER_REGISTRY`. New api-key providers auto-register
+into `PROVIDER_REGISTRY` from the profile, so the name IS the key. For providers
+with a pre-existing `PROVIDER_REGISTRY` entry, use the exact `id` field value.
+
+**Wrong `env_vars`** — separate API-key vars from base-URL override vars in the
+tuple. Env vars that end with `_BASE_URL` or `_URL` are treated as URL overrides;
+everything else is treated as an API key. Getting this wrong causes the doctor
+health check to send a URL string as a Bearer token.
+
+**Wrong `base_url`** — several providers have non-obvious paths:
+`stepfun: /step_plan/v1`, `opencode-go: /zen/go/v1`. The profile's `base_url`
+is also used as the `inference_base_url` when auto-registering into `PROVIDER_REGISTRY`
+for new providers, so it must be correct for auth resolution to work.
+
+**Skipping `api_mode`** — defaults to `chat_completions`. Providers that use
+`anthropic_messages`, `codex_responses`, `bedrock_converse`, or `copilot_acp`
+must set it explicitly.
+
+**Forgetting `register_provider()`** — auto-discovery runs `pkgutil.iter_modules`
+over the package and imports each module, but only if `register_provider()` is
+called at module level. Without it the profile is never in `_REGISTRY`.
+
+**`fetch_models` returning the wrong shape** — must return `list[str]` (plain
+model IDs), not `list[tuple]` or `list[dict]`. Callers expect plain strings.
+
+**Wrong `build_api_kwargs_extras` return shape** — must return a 2-tuple
+`(extra_body_dict, top_level_dict)`. Returning a single dict causes a
+`ValueError: not enough values to unpack` in the transport.
+
+**`build_api_kwargs_extras` wrong tuple** — must return `(extra_body_dict,
+top_level_dict)`. Returning a flat dict or swapping the order silently sends
+fields to the wrong place.

providers/__init__.py

@@ -0,0 +1,76 @@
+"""Provider module registry.
+
+Auto-discovers ProviderProfile instances from providers/*.py modules.
+Each module should define a module-level PROVIDER or PROVIDERS list.
+
+Usage:
+    from providers import get_provider_profile
+    profile = get_provider_profile("nvidia")  # returns ProviderProfile or None
+    profile = get_provider_profile("kimi")    # checks name + aliases
+"""
+
+from __future__ import annotations
+
+from providers.base import OMIT_TEMPERATURE, ProviderProfile  # noqa: F401
+
+_REGISTRY: dict[str, ProviderProfile] = {}
+_ALIASES: dict[str, str] = {}
+_discovered = False
+
+
+def register_provider(profile: ProviderProfile) -> None:
+    """Register a provider profile by name and aliases."""
+    _REGISTRY[profile.name] = profile
+    for alias in profile.aliases:
+        _ALIASES[alias] = profile.name
+
+
+def get_provider_profile(name: str) -> ProviderProfile | None:
+    """Look up a provider profile by name or alias.
+
+    Returns None if the provider has no profile (falls back to generic).
+    """
+    if not _discovered:
+        _discover_providers()
+    canonical = _ALIASES.get(name, name)
+    return _REGISTRY.get(canonical)
+
+
+def list_providers() -> list[ProviderProfile]:
+    """Return all registered provider profiles (one per canonical name)."""
+    if not _discovered:
+        _discover_providers()
+    # Deduplicate: _REGISTRY has canonical names; _ALIASES points to same objects
+    seen: set[int] = set()
+    result: list[ProviderProfile] = []
+    for profile in _REGISTRY.values():
+        pid = id(profile)
+        if pid not in seen:
+            seen.add(pid)
+            result.append(profile)
+    return result
+
+
+def _discover_providers() -> None:
+    """Import all provider modules to trigger registration."""
+    global _discovered
+    if _discovered:
+        return
+    _discovered = True
+
+    import importlib
+    import pkgutil
+
+    import providers as _pkg
+
+    for _importer, modname, _ispkg in pkgutil.iter_modules(_pkg.__path__):
+        if modname.startswith("_") or modname == "base":
+            continue
+        try:
+            importlib.import_module(f"providers.{modname}")
+        except ImportError as e:
+            import logging
+
+            logging.getLogger(__name__).warning(
+                "Failed to import provider module %s: %s", modname, e
+            )

providers/alibaba.py

@@ -0,0 +1,13 @@
+"""Alibaba Cloud DashScope provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+alibaba = ProviderProfile(
+    name="alibaba",
+    aliases=("dashscope", "alibaba-cloud", "qwen-dashscope"),
+    env_vars=("DASHSCOPE_API_KEY",),
+    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
+)
+
+register_provider(alibaba)

providers/anthropic.py

@@ -0,0 +1,52 @@
+"""Native Anthropic provider profile."""
+
+import json
+import logging
+import urllib.request
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+logger = logging.getLogger(__name__)
+
+
+class AnthropicProfile(ProviderProfile):
+    """Native Anthropic — uses x-api-key header, not Bearer."""
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        """Anthropic uses x-api-key header and anthropic-version."""
+        if not api_key:
+            return None
+        try:
+            req = urllib.request.Request("https://api.anthropic.com/v1/models")
+            req.add_header("x-api-key", api_key)
+            req.add_header("anthropic-version", "2023-06-01")
+            req.add_header("Accept", "application/json")
+            with urllib.request.urlopen(req, timeout=timeout) as resp:
+                data = json.loads(resp.read().decode())
+            return [
+                m["id"]
+                for m in data.get("data", [])
+                if isinstance(m, dict) and "id" in m
+            ]
+        except Exception as exc:
+            logger.debug("fetch_models(anthropic): %s", exc)
+            return None
+
+
+anthropic = AnthropicProfile(
+    name="anthropic",
+    aliases=("claude", "claude-oauth", "claude-code"),
+    api_mode="anthropic_messages",
+    env_vars=("ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN", "CLAUDE_CODE_OAUTH_TOKEN"),
+    base_url="https://api.anthropic.com",
+    auth_type="api_key",
+    default_aux_model="claude-haiku-4-5-20251001",
+)
+
+register_provider(anthropic)

providers/arcee.py

@@ -0,0 +1,13 @@
+"""Arcee AI provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+arcee = ProviderProfile(
+    name="arcee",
+    aliases=("arcee-ai", "arceeai"),
+    env_vars=("ARCEEAI_API_KEY",),
+    base_url="https://api.arcee.ai/api/v1",
+)
+
+register_provider(arcee)

providers/base.py

@@ -0,0 +1,165 @@
+"""Provider profile base class.
+
+A ProviderProfile declares everything about an inference provider in one place:
+auth, endpoints, client quirks, request-time quirks. The transport reads this
+instead of receiving 20+ boolean flags.
+
+Provider profiles are DECLARATIVE — they describe the provider's behavior.
+They do NOT own client construction, credential rotation, or streaming.
+Those stay on AIAgent.
+"""
+
+from __future__ import annotations
+
+import logging
+from dataclasses import dataclass, field
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+# Sentinel for "omit temperature entirely" (Kimi: server manages it)
+OMIT_TEMPERATURE = object()
+
+
+@dataclass
+class ProviderProfile:
+    """Base provider profile — subclass or instantiate with overrides."""
+
+    # ── Identity ─────────────────────────────────────────────
+    name: str
+    api_mode: str = "chat_completions"
+    aliases: tuple = ()
+
+    # ── Human-readable metadata ───────────────────────────────
+    display_name: str = ""       # e.g. "GMI Cloud" — shown in picker/labels
+    description: str = ""        # e.g. "GMI Cloud (multi-model direct API)" — picker subtitle
+    signup_url: str = ""         # e.g. "https://www.gmicloud.ai/" — shown during setup
+
+    # ── Auth & endpoints ─────────────────────────────────────
+    env_vars: tuple = ()
+    base_url: str = ""
+    models_url: str = ""  # explicit models endpoint; falls back to {base_url}/models
+    auth_type: str = "api_key"   # api_key|oauth_device_code|oauth_external|copilot|aws_sdk
+
+    # ── Model catalog ─────────────────────────────────────────
+    # fallback_models: curated list shown in /model picker when live fetch fails.
+    # Only agentic models that support tool calling should appear here.
+    fallback_models: tuple = ()
+
+    # hostname: base hostname for URL→provider reverse-mapping in model_metadata.py
+    # e.g. "api.gmi-serving.com". Derived from base_url when empty.
+    hostname: str = ""
+
+    # ── Client-level quirks (set once at client construction) ─
+    default_headers: dict[str, str] = field(default_factory=dict)
+
+    # ── Request-level quirks ─────────────────────────────────
+    # Temperature: None = use caller's default, OMIT_TEMPERATURE = don't send
+    fixed_temperature: Any = None
+    default_max_tokens: int | None = None
+    default_aux_model: str = (
+        ""  # cheap model for auxiliary tasks (compression, vision, etc.)
+    )
+    # empty = use main model
+
+    # ── Hooks (override in subclass for complex providers) ───
+
+    def get_hostname(self) -> str:
+        """Return the provider's base hostname for URL-based detection.
+
+        Uses self.hostname if set explicitly, otherwise derives it from base_url.
+        e.g. 'https://api.gmi-serving.com/v1' → 'api.gmi-serving.com'
+        """
+        if self.hostname:
+            return self.hostname
+        if self.base_url:
+            from urllib.parse import urlparse
+            return urlparse(self.base_url).hostname or ""
+        return ""
+
+    def prepare_messages(self, messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        """Provider-specific message preprocessing.
+
+        Called AFTER codex field sanitization, BEFORE developer role swap.
+        Default: pass-through.
+        """
+        return messages
+
+    def build_extra_body(
+        self, *, session_id: str | None = None, **context: Any
+    ) -> dict[str, Any]:
+        """Provider-specific extra_body fields.
+
+        Merged into the API kwargs extra_body. Default: empty dict.
+        """
+        return {}
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        **context: Any,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """Provider-specific kwargs split between extra_body and top-level api_kwargs.
+
+        Returns (extra_body_additions, top_level_kwargs).
+        The transport merges extra_body_additions into extra_body, and
+        top_level_kwargs directly into api_kwargs.
+
+        This split exists because some providers put reasoning config in
+        extra_body (OpenRouter: extra_body.reasoning) while others put it
+        as top-level api_kwargs (Kimi: api_kwargs.reasoning_effort).
+
+        Default: ({}, {}).
+        """
+        return {}, {}
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        """Fetch the live model list from the provider's models endpoint.
+
+        Returns a list of model ID strings, or None if the fetch failed or
+        the provider does not support live model listing.
+
+        Resolution order for the endpoint URL:
+          1. self.models_url  (explicit override — use when the models
+             endpoint differs from the inference base URL, e.g. OpenRouter
+             exposes a public catalog at /api/v1/models while inference is
+             at /api/v1)
+          2. self.base_url + "/models"  (standard OpenAI-compat fallback)
+
+        The default implementation sends Bearer auth when api_key is given
+        and forwards self.default_headers. Override to customise auth, path,
+        response shape, or to return None for providers with no REST catalog.
+
+        Callers must always fall back to the static _PROVIDER_MODELS list
+        when this returns None.
+        """
+        url = (self.models_url or "").strip()
+        if not url:
+            if not self.base_url:
+                return None
+            url = self.base_url.rstrip("/") + "/models"
+
+        import json
+        import urllib.request
+
+        req = urllib.request.Request(url)
+        if api_key:
+            req.add_header("Authorization", f"Bearer {api_key}")
+        req.add_header("Accept", "application/json")
+        for k, v in self.default_headers.items():
+            req.add_header(k, v)
+
+        try:
+            with urllib.request.urlopen(req, timeout=timeout) as resp:
+                data = json.loads(resp.read().decode())
+            items = data if isinstance(data, list) else data.get("data", [])
+            return [m["id"] for m in items if isinstance(m, dict) and "id" in m]
+        except Exception as exc:
+            logger.debug("fetch_models(%s): %s", self.name, exc)
+            return None

providers/bedrock.py

@@ -0,0 +1,29 @@
+"""AWS Bedrock provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class BedrockProfile(ProviderProfile):
+    """AWS Bedrock — no REST /v1/models endpoint; uses AWS SDK."""
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        """Bedrock model listing requires AWS SDK, not a REST call."""
+        return None
+
+
+bedrock = BedrockProfile(
+    name="bedrock",
+    aliases=("aws", "aws-bedrock", "amazon-bedrock", "amazon"),
+    api_mode="bedrock_converse",
+    env_vars=(),  # AWS SDK credentials — not env vars
+    base_url="https://bedrock-runtime.us-east-1.amazonaws.com",
+    auth_type="aws_sdk",
+)
+
+register_provider(bedrock)

providers/copilot.py

@@ -0,0 +1,58 @@
+"""Copilot / GitHub Models provider profile.
+
+Copilot uses per-model api_mode routing:
+  - GPT-5+ / Codex models → codex_responses
+  - Claude models → anthropic_messages
+  - Everything else → chat_completions (this profile covers that subset)
+
+Key quirks for the chat_completions subset:
+  - Editor attribution headers (via copilot_default_headers())
+  - GitHub Models reasoning extra_body (model-catalog gated)
+"""
+
+from typing import Any
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class CopilotProfile(ProviderProfile):
+    """GitHub Copilot / GitHub Models — editor headers + reasoning."""
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        model: str | None = None,
+        reasoning_config: dict | None = None,
+        supports_reasoning: bool = False,
+        **ctx,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        extra_body: dict[str, Any] = {}
+        if supports_reasoning and model:
+            try:
+                from hermes_cli.models import github_model_reasoning_efforts
+
+                supported_efforts = github_model_reasoning_efforts(model)
+                if supported_efforts and reasoning_config:
+                    effort = reasoning_config.get("effort", "medium")
+                    # Normalize non-standard effort levels to the nearest supported
+                    if effort == "xhigh":
+                        effort = "high"
+                    if effort in supported_efforts:
+                        extra_body["reasoning"] = {"effort": effort}
+                elif supported_efforts:
+                    extra_body["reasoning"] = {"effort": "medium"}
+            except Exception:
+                pass
+        return extra_body, {}
+
+
+copilot = CopilotProfile(
+    name="copilot",
+    aliases=("github-copilot", "github-models", "github-model", "github"),
+    env_vars=("COPILOT_GITHUB_TOKEN", "GH_TOKEN", "GITHUB_TOKEN"),
+    base_url="https://api.githubcopilot.com",
+    auth_type="copilot",
+)
+
+register_provider(copilot)

providers/copilot_acp.py

@@ -0,0 +1,34 @@
+"""GitHub Copilot ACP provider profile.
+
+copilot-acp uses an external ACP subprocess — NOT the standard
+transport. api_mode="copilot_acp" is handled separately in run_agent.py.
+The profile captures auth + endpoint metadata for registry migration.
+"""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class CopilotACPProfile(ProviderProfile):
+    """GitHub Copilot ACP — external process, no REST models endpoint."""
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        """Model listing is handled by the ACP subprocess."""
+        return None
+
+
+copilot_acp = CopilotACPProfile(
+    name="copilot-acp",
+    aliases=("github-copilot-acp", "copilot-acp-agent"),
+    api_mode="chat_completions",  # ACP subprocess uses chat_completions routing
+    env_vars=(),  # Managed by ACP subprocess
+    base_url="acp://copilot",  # ACP internal scheme
+    auth_type="external_process",
+)
+
+register_provider(copilot_acp)

providers/custom.py

@@ -0,0 +1,71 @@
+"""Custom / Ollama (local) provider profile.
+
+Covers any endpoint registered as provider="custom", including local
+Ollama instances. Key quirks:
+  - ollama_num_ctx → extra_body.options.num_ctx (local context window)
+  - reasoning_config disabled → extra_body.think = False
+"""
+
+from typing import Any
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class CustomProfile(ProviderProfile):
+    """Custom/Ollama local provider — think=false and num_ctx support."""
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        ollama_num_ctx: int | None = None,
+        **ctx: Any,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        extra_body: dict[str, Any] = {}
+
+        # Ollama context window
+        if ollama_num_ctx:
+            options = extra_body.get("options", {})
+            options["num_ctx"] = ollama_num_ctx
+            extra_body["options"] = options
+
+        # Disable thinking when reasoning is turned off
+        if reasoning_config and isinstance(reasoning_config, dict):
+            _effort = (reasoning_config.get("effort") or "").strip().lower()
+            _enabled = reasoning_config.get("enabled", True)
+            if _effort == "none" or _enabled is False:
+                extra_body["think"] = False
+
+        return extra_body, {}
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        """Custom/Ollama: base_url is user-configured; fetch if set."""
+        if not self.base_url:
+            return None
+        return super().fetch_models(api_key=api_key, timeout=timeout)
+
+
+custom = CustomProfile(
+    name="custom",
+    aliases=(
+        "ollama",
+        "local",
+        "lmstudio",
+        "lm-studio",
+        "lm_studio",
+        "vllm",
+        "llamacpp",
+        "llama.cpp",
+        "llama-cpp",
+    ),
+    env_vars=(),  # No fixed key — custom endpoint
+    base_url="",  # User-configured
+)
+
+register_provider(custom)

providers/deepseek.py

@@ -0,0 +1,20 @@
+"""DeepSeek provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+deepseek = ProviderProfile(
+    name="deepseek",
+    aliases=("deepseek-chat",),
+    env_vars=("DEEPSEEK_API_KEY",),
+    display_name="DeepSeek",
+    description="DeepSeek — native DeepSeek API",
+    signup_url="https://platform.deepseek.com/",
+    fallback_models=(
+        "deepseek-chat",
+        "deepseek-reasoner",
+    ),
+    base_url="https://api.deepseek.com/v1",
+)
+
+register_provider(deepseek)

providers/gemini.py

@@ -0,0 +1,34 @@
+"""Google Gemini provider profiles.
+
+gemini:            Google AI Studio (API key) — uses GeminiNativeClient
+google-gemini-cli: Google Cloud Code Assist (OAuth) — uses GeminiCloudCodeClient
+
+Both report api_mode="chat_completions" but use custom native clients
+that bypass the standard OpenAI transport. The profile captures auth
+and endpoint metadata for auth.py / runtime_provider.py migration.
+"""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+gemini = ProviderProfile(
+    name="gemini",
+    aliases=("google", "google-gemini", "google-ai-studio"),
+    api_mode="chat_completions",
+    env_vars=("GOOGLE_API_KEY", "GEMINI_API_KEY"),
+    base_url="https://generativelanguage.googleapis.com/v1beta",
+    auth_type="api_key",
+    default_aux_model="gemini-3-flash-preview",
+)
+
+google_gemini_cli = ProviderProfile(
+    name="google-gemini-cli",
+    aliases=("gemini-cli", "gemini-oauth"),
+    api_mode="chat_completions",
+    env_vars=(),  # OAuth — no API key
+    base_url="cloudcode-pa://google",  # Cloud Code Assist internal scheme
+    auth_type="oauth_external",
+)
+
+register_provider(gemini)
+register_provider(google_gemini_cli)

providers/gmi.py

@@ -0,0 +1,26 @@
+"""GMI Cloud provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+gmi = ProviderProfile(
+    name="gmi",
+    aliases=("gmi-cloud", "gmicloud"),
+    display_name="GMI Cloud",
+    description="GMI Cloud — multi-model direct API (slash-form model IDs)",
+    signup_url="https://www.gmicloud.ai/",
+    env_vars=("GMI_API_KEY", "GMI_BASE_URL"),
+    base_url="https://api.gmi-serving.com/v1",
+    auth_type="api_key",
+    default_aux_model="google/gemini-3.1-flash-lite-preview",
+    fallback_models=(
+        "zai-org/GLM-5.1-FP8",
+        "deepseek-ai/DeepSeek-V3.2",
+        "moonshotai/Kimi-K2.5",
+        "google/gemini-3.1-flash-lite-preview",
+        "anthropic/claude-sonnet-4.6",
+        "openai/gpt-5.4",
+    ),
+)
+
+register_provider(gmi)

providers/huggingface.py

@@ -0,0 +1,20 @@
+"""Hugging Face provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+huggingface = ProviderProfile(
+    name="huggingface",
+    aliases=("hf", "hugging-face", "huggingface-hub"),
+    env_vars=("HF_TOKEN",),
+    display_name="HuggingFace",
+    description="HuggingFace Inference API",
+    signup_url="https://huggingface.co/settings/tokens",
+    fallback_models=(
+        "Qwen/Qwen3.5-72B-Instruct",
+        "deepseek-ai/DeepSeek-V3.2",
+    ),
+    base_url="https://router.huggingface.co/v1",
+)
+
+register_provider(huggingface)

providers/kilocode.py

@@ -0,0 +1,14 @@
+"""Kilo Code provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+kilocode = ProviderProfile(
+    name="kilocode",
+    aliases=("kilo-code", "kilo", "kilo-gateway"),
+    env_vars=("KILOCODE_API_KEY",),
+    base_url="https://api.kilo.ai/api/gateway",
+    default_aux_model="google/gemini-3-flash-preview",
+)
+
+register_provider(kilocode)

providers/kimi.py

@@ -0,0 +1,71 @@
+"""Kimi / Moonshot provider profiles.
+
+Kimi has dual endpoints:
+  - sk-kimi-* keys → api.kimi.com/coding (Anthropic Messages API)
+  - legacy keys → api.moonshot.ai/v1 (OpenAI chat completions)
+
+This module covers the chat_completions path (/v1 endpoint).
+"""
+
+from typing import Any
+
+from providers import register_provider
+from providers.base import OMIT_TEMPERATURE, ProviderProfile
+
+
+class KimiProfile(ProviderProfile):
+    """Kimi/Moonshot — temperature omitted, thinking + reasoning_effort."""
+
+    def build_api_kwargs_extras(
+        self, *, reasoning_config: dict | None = None, **context
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """Kimi uses extra_body.thinking + top-level reasoning_effort."""
+        extra_body = {}
+        top_level = {}
+
+        if not reasoning_config or not isinstance(reasoning_config, dict):
+            # No config → thinking enabled, default effort
+            extra_body["thinking"] = {"type": "enabled"}
+            top_level["reasoning_effort"] = "medium"
+            return extra_body, top_level
+
+        enabled = reasoning_config.get("enabled", True)
+        if enabled is False:
+            extra_body["thinking"] = {"type": "disabled"}
+            return extra_body, top_level
+
+        # Enabled
+        extra_body["thinking"] = {"type": "enabled"}
+        effort = (reasoning_config.get("effort") or "").strip().lower()
+        if effort in ("low", "medium", "high"):
+            top_level["reasoning_effort"] = effort
+        else:
+            top_level["reasoning_effort"] = "medium"
+
+        return extra_body, top_level
+
+
+kimi = KimiProfile(
+    name="kimi-coding",
+    aliases=("kimi", "moonshot", "kimi-for-coding"),
+    env_vars=("KIMI_API_KEY", "KIMI_CODING_API_KEY"),
+    base_url="https://api.moonshot.ai/v1",
+    fixed_temperature=OMIT_TEMPERATURE,
+    default_max_tokens=32000,
+    default_headers={"User-Agent": "hermes-agent/1.0"},
+    default_aux_model="kimi-k2-turbo-preview",
+)
+
+kimi_cn = KimiProfile(
+    name="kimi-coding-cn",
+    aliases=("kimi-cn", "moonshot-cn"),
+    env_vars=("KIMI_CN_API_KEY",),
+    base_url="https://api.moonshot.cn/v1",
+    fixed_temperature=OMIT_TEMPERATURE,
+    default_max_tokens=32000,
+    default_headers={"User-Agent": "hermes-agent/1.0"},
+    default_aux_model="kimi-k2-turbo-preview",
+)
+
+register_provider(kimi)
+register_provider(kimi_cn)

providers/minimax.py

@@ -0,0 +1,31 @@
+"""MiniMax provider profiles (international + China).
+
+Both use anthropic_messages api_mode — their inference_base_url
+ends with /anthropic which triggers auto-detection to anthropic_messages.
+"""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+minimax = ProviderProfile(
+    name="minimax",
+    aliases=("mini-max",),
+    api_mode="anthropic_messages",
+    env_vars=("MINIMAX_API_KEY",),
+    base_url="https://api.minimax.io/anthropic",
+    auth_type="api_key",
+    default_aux_model="MiniMax-M2.7",
+)
+
+minimax_cn = ProviderProfile(
+    name="minimax-cn",
+    aliases=("minimax-china", "minimax_cn"),
+    api_mode="anthropic_messages",
+    env_vars=("MINIMAX_CN_API_KEY",),
+    base_url="https://api.minimaxi.com/anthropic",
+    auth_type="api_key",
+    default_aux_model="MiniMax-M2.7",
+)
+
+register_provider(minimax)
+register_provider(minimax_cn)

providers/nous.py

@@ -0,0 +1,53 @@
+"""Nous Portal provider profile."""
+
+from typing import Any
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class NousProfile(ProviderProfile):
+    """Nous Portal — product tags, reasoning with Nous-specific omission."""
+
+    def build_extra_body(
+        self, *, session_id: str | None = None, **context
+    ) -> dict[str, Any]:
+        return {"tags": ["product=hermes-agent"]}
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        supports_reasoning: bool = False,
+        **context,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """Nous: passes full reasoning_config, but OMITS when disabled."""
+        extra_body = {}
+        if supports_reasoning:
+            if reasoning_config is not None:
+                rc = dict(reasoning_config)
+                if rc.get("enabled") is False:
+                    pass  # Nous omits reasoning when disabled
+                else:
+                    extra_body["reasoning"] = rc
+            else:
+                extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
+        return extra_body, {}
+
+
+nous = NousProfile(
+    name="nous",
+    aliases=("nous-portal", "nousresearch"),
+    env_vars=("NOUS_API_KEY",),
+    display_name="Nous Research",
+    description="Nous Research — Hermes model family",
+    signup_url="https://nousresearch.com/",
+    fallback_models=(
+        "hermes-3-405b",
+        "hermes-3-70b",
+    ),
+    base_url="https://inference.nousresearch.com/v1",
+    auth_type="oauth_device_code",
+)
+
+register_provider(nous)

providers/nvidia.py

@@ -0,0 +1,21 @@
+"""NVIDIA NIM provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+nvidia = ProviderProfile(
+    name="nvidia",
+    aliases=("nvidia-nim",),
+    env_vars=("NVIDIA_API_KEY",),
+    display_name="NVIDIA NIM",
+    description="NVIDIA NIM — accelerated inference",
+    signup_url="https://build.nvidia.com/",
+    fallback_models=(
+        "nvidia/llama-3.1-nemotron-70b-instruct",
+        "nvidia/llama-3.3-70b-instruct",
+    ),
+    base_url="https://integrate.api.nvidia.com/v1",
+    default_max_tokens=16384,
+)
+
+register_provider(nvidia)

providers/ollama_cloud.py

@@ -0,0 +1,14 @@
+"""Ollama Cloud provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+ollama_cloud = ProviderProfile(
+    name="ollama-cloud",
+    aliases=("ollama_cloud",),
+    default_aux_model="nemotron-3-nano:30b",
+    env_vars=("OLLAMA_API_KEY",),
+    base_url="https://ollama.com/v1",
+)
+
+register_provider(ollama_cloud)

providers/openai_codex.py

@@ -0,0 +1,15 @@
+"""OpenAI Codex (Responses API) provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+openai_codex = ProviderProfile(
+    name="openai-codex",
+    aliases=("codex", "openai_codex"),
+    api_mode="codex_responses",
+    env_vars=(),  # OAuth external — no API key
+    base_url="https://chatgpt.com/backend-api/codex",
+    auth_type="oauth_external",
+)
+
+register_provider(openai_codex)

providers/opencode.py

@@ -0,0 +1,30 @@
+"""OpenCode provider profiles (Zen + Go).
+
+Both use per-model api_mode routing:
+  - OpenCode Zen: Claude → anthropic_messages, GPT-5/Codex → codex_responses,
+    everything else → chat_completions (this profile)
+  - OpenCode Go: MiniMax → anthropic_messages, GLM/Kimi → chat_completions
+    (this profile)
+"""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+opencode_zen = ProviderProfile(
+    name="opencode-zen",
+    aliases=("opencode", "opencode_zen", "zen"),
+    env_vars=("OPENCODE_ZEN_API_KEY",),
+    base_url="https://opencode.ai/zen/v1",
+    default_aux_model="gemini-3-flash",
+)
+
+opencode_go = ProviderProfile(
+    name="opencode-go",
+    aliases=("opencode_go", "go", "opencode-go-sub"),
+    env_vars=("OPENCODE_GO_API_KEY",),
+    base_url="https://opencode.ai/zen/go/v1",
+    default_aux_model="glm-5",
+)
+
+register_provider(opencode_zen)
+register_provider(opencode_go)

providers/openrouter.py

@@ -0,0 +1,86 @@
+"""OpenRouter provider profile."""
+
+import logging
+from typing import Any
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+logger = logging.getLogger(__name__)
+
+_CACHE: list[str] | None = None
+
+
+class OpenRouterProfile(ProviderProfile):
+    """OpenRouter aggregator — provider preferences, reasoning config passthrough."""
+
+    def fetch_models(
+        self,
+        *,
+        api_key: str | None = None,
+        timeout: float = 8.0,
+    ) -> list[str] | None:
+        """Fetch from public OpenRouter catalog — no auth required.
+
+        Note: Tool-call capability filtering is applied by hermes_cli/models.py
+        via fetch_openrouter_models() → _openrouter_model_supports_tools(), not
+        here. The picker early-returns via the dedicated openrouter path before
+        reaching this method, so filtering here would be unreachable.
+        """
+        global _CACHE  # noqa: PLW0603
+        if _CACHE is not None:
+            return _CACHE
+        try:
+            result = super().fetch_models(api_key=None, timeout=timeout)
+            if result is not None:
+                _CACHE = result
+            return result
+        except Exception as exc:
+            logger.debug("fetch_models(openrouter): %s", exc)
+            return None
+
+    def build_extra_body(
+        self, *, session_id: str | None = None, **context: Any
+    ) -> dict[str, Any]:
+        body: dict[str, Any] = {}
+        prefs = context.get("provider_preferences")
+        if prefs:
+            body["provider"] = prefs
+        return body
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        supports_reasoning: bool = False,
+        **context: Any,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """OpenRouter passes the full reasoning_config dict as extra_body.reasoning."""
+        extra_body: dict[str, Any] = {}
+        if supports_reasoning:
+            if reasoning_config is not None:
+                extra_body["reasoning"] = dict(reasoning_config)
+            else:
+                extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
+        return extra_body, {}
+
+
+openrouter = OpenRouterProfile(
+    name="openrouter",
+    aliases=("or",),
+    env_vars=("OPENROUTER_API_KEY",),
+    display_name="OpenRouter",
+    description="OpenRouter — unified API for 200+ models",
+    signup_url="https://openrouter.ai/keys",
+    base_url="https://openrouter.ai/api/v1",
+    models_url="https://openrouter.ai/api/v1/models",
+    fallback_models=(
+        "anthropic/claude-sonnet-4.6",
+        "openai/gpt-5.4",
+        "deepseek/deepseek-chat",
+        "google/gemini-3-flash-preview",
+        "qwen/qwen3-plus",
+    ),
+)
+
+register_provider(openrouter)

providers/qwen.py

@@ -0,0 +1,82 @@
+"""Qwen Portal provider profile."""
+
+import copy
+from typing import Any
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class QwenProfile(ProviderProfile):
+    """Qwen Portal — message normalization, vl_high_resolution, metadata top-level."""
+
+    def prepare_messages(self, messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        """Normalize content to list-of-dicts format.
+
+        Inject cache_control on system message.
+
+        Matches the behavior of run_agent.py:_qwen_prepare_chat_messages().
+        """
+        prepared = copy.deepcopy(messages)
+        if not prepared:
+            return prepared
+
+        for msg in prepared:
+            if not isinstance(msg, dict):
+                continue
+            content = msg.get("content")
+            if isinstance(content, str):
+                msg["content"] = [{"type": "text", "text": content}]
+            elif isinstance(content, list):
+                normalized_parts = []
+                for part in content:
+                    if isinstance(part, str):
+                        normalized_parts.append({"type": "text", "text": part})
+                    elif isinstance(part, dict):
+                        normalized_parts.append(part)
+                if normalized_parts:
+                    msg["content"] = normalized_parts
+
+        # Inject cache_control on the last part of the system message.
+        for msg in prepared:
+            if isinstance(msg, dict) and msg.get("role") == "system":
+                content = msg.get("content")
+                if (
+                    isinstance(content, list)
+                    and content
+                    and isinstance(content[-1], dict)
+                ):
+                    content[-1]["cache_control"] = {"type": "ephemeral"}
+                break
+
+        return prepared
+
+    def build_extra_body(
+        self, *, session_id: str | None = None, **context
+    ) -> dict[str, Any]:
+        return {"vl_high_resolution_images": True}
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        qwen_session_metadata: dict | None = None,
+        **context,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """Qwen metadata goes to top-level api_kwargs, not extra_body."""
+        top_level = {}
+        if qwen_session_metadata:
+            top_level["metadata"] = qwen_session_metadata
+        return {}, top_level
+
+
+qwen = QwenProfile(
+    name="qwen-oauth",
+    aliases=("qwen", "qwen-portal", "qwen-cli"),
+    env_vars=("QWEN_API_KEY",),
+    base_url="https://portal.qwen.ai/v1",
+    auth_type="oauth_external",
+    default_max_tokens=65536,
+)
+
+register_provider(qwen)

providers/stepfun.py

@@ -0,0 +1,14 @@
+"""StepFun provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+stepfun = ProviderProfile(
+    name="stepfun",
+    aliases=("step", "stepfun-coding-plan"),
+    default_aux_model="step-3.5-flash",
+    env_vars=("STEPFUN_API_KEY",),
+    base_url="https://api.stepfun.ai/step_plan/v1",
+)
+
+register_provider(stepfun)

providers/vercel.py

@@ -0,0 +1,43 @@
+"""Vercel AI Gateway provider profile.
+
+AI Gateway routes to multiple backends. Hermes sends attribution
+headers and full reasoning config passthrough.
+"""
+
+from typing import Any
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+
+class VercelAIGatewayProfile(ProviderProfile):
+    """Vercel AI Gateway — attribution headers + reasoning passthrough."""
+
+    def build_api_kwargs_extras(
+        self,
+        *,
+        reasoning_config: dict | None = None,
+        supports_reasoning: bool = True,
+        **ctx: Any,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        extra_body: dict[str, Any] = {}
+        if supports_reasoning and reasoning_config is not None:
+            extra_body["reasoning"] = dict(reasoning_config)
+        elif supports_reasoning:
+            extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
+        return extra_body, {}
+
+
+vercel = VercelAIGatewayProfile(
+    name="ai-gateway",
+    aliases=("vercel", "vercel-ai-gateway", "ai_gateway", "aigateway"),
+    env_vars=("AI_GATEWAY_API_KEY",),
+    base_url="https://ai-gateway.vercel.sh/v1",
+    default_headers={
+        "HTTP-Referer": "https://hermes-agent.nousresearch.com",
+        "X-Title": "Hermes Agent",
+    },
+    default_aux_model="google/gemini-3-flash",
+)
+
+register_provider(vercel)

providers/xai.py

@@ -0,0 +1,15 @@
+"""xAI (Grok) provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+xai = ProviderProfile(
+    name="xai",
+    aliases=("grok", "x-ai", "x.ai"),
+    api_mode="codex_responses",
+    env_vars=("XAI_API_KEY",),
+    base_url="https://api.x.ai/v1",
+    auth_type="api_key",
+)
+
+register_provider(xai)

providers/xiaomi.py

@@ -0,0 +1,13 @@
+"""Xiaomi MiMo provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+xiaomi = ProviderProfile(
+    name="xiaomi",
+    aliases=("mimo", "xiaomi-mimo"),
+    env_vars=("XIAOMI_API_KEY",),
+    base_url="https://api.xiaomimimo.com/v1",
+)
+
+register_provider(xiaomi)

providers/zai.py

@@ -0,0 +1,21 @@
+"""ZAI / GLM provider profile."""
+
+from providers import register_provider
+from providers.base import ProviderProfile
+
+zai = ProviderProfile(
+    name="zai",
+    aliases=("glm", "z-ai", "z.ai", "zhipu"),
+    env_vars=("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"),
+    display_name="Z.AI (GLM)",
+    description="Z.AI / GLM — Zhipu AI models",
+    signup_url="https://z.ai/",
+    fallback_models=(
+        "glm-5",
+        "glm-4-9b",
+    ),
+    base_url="https://api.z.ai/api/paas/v4",
+    default_aux_model="glm-4.5-flash",
+)
+
+register_provider(zai)

pyproject.toml

@@ -137,7 +137,7 @@ py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajector
 hermes_cli = ["web_dist/**/*"]
 
 [tool.setuptools.packages.find]
-include = ["agent", "agent.*", "tools", "tools.*", "hermes_cli", "gateway", "gateway.*", "tui_gateway", "tui_gateway.*", "cron", "acp_adapter", "plugins", "plugins.*"]
+include = ["agent", "agent.*", "tools", "tools.*", "hermes_cli", "gateway", "gateway.*", "tui_gateway", "tui_gateway.*", "cron", "acp_adapter", "plugins", "plugins.*", "providers", "providers.*"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

run_agent.py

@@ -1371,6 +1371,17 @@ class AIAgent:
                 elif base_url_host_matches(effective_base, "chatgpt.com"):
                     from agent.auxiliary_client import _codex_cloudflare_headers
                     client_kwargs["default_headers"] = _codex_cloudflare_headers(api_key)
+                elif "default_headers" not in client_kwargs:
+                    # Fall back to profile.default_headers for providers that
+                    # declare custom headers (e.g. Vercel AI Gateway attribution,
+                    # Kimi User-Agent on non-kimi.com endpoints).
+                    try:
+                        from providers import get_provider_profile as _gpf
+                        _ph = _gpf(self.provider)
+                        if _ph and _ph.default_headers:
+                            client_kwargs["default_headers"] = dict(_ph.default_headers)
+                    except Exception:
+                        pass
             else:
                 # No explicit creds — use the centralized provider router
                 from agent.auxiliary_client import resolve_provider_client
@@ -5037,7 +5048,7 @@ class AIAgent:
         _validate_proxy_env_urls()
         _validate_base_url(client_kwargs.get("base_url"))
         if self.provider == "copilot-acp" or str(client_kwargs.get("base_url", "")).startswith("acp://copilot"):
-            from agent.copilot_acp_client import CopilotACPClient
+            from acp_adapter.copilot_client import CopilotACPClient
 
             client = CopilotACPClient(**client_kwargs)
             logger.info(
@@ -5726,7 +5737,19 @@ class AIAgent:
                 self._client_kwargs.get("api_key", "")
             )
         else:
-            self._client_kwargs.pop("default_headers", None)
+            # No URL-specific headers — check profile.default_headers before clearing.
+            _ph_headers = None
+            try:
+                from providers import get_provider_profile as _gpf2
+                _ph2 = _gpf2(self.provider)
+                if _ph2 and _ph2.default_headers:
+                    _ph_headers = dict(_ph2.default_headers)
+            except Exception:
+                pass
+            if _ph_headers:
+                self._client_kwargs["default_headers"] = _ph_headers
+            else:
+                self._client_kwargs.pop("default_headers", None)
 
     def _swap_credential(self, entry) -> None:
         runtime_key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
@@ -7857,66 +7880,79 @@ class AIAgent:
         # ── chat_completions (default) ─────────────────────────────────────
         _ct = self._get_transport()
 
-        # Provider detection flags
-        _is_qwen = self._is_qwen_portal()
-        _is_or = self._is_openrouter_url()
-        _is_gh = (
-            base_url_host_matches(self._base_url_lower, "models.github.ai")
-            or base_url_host_matches(self._base_url_lower, "api.githubcopilot.com")
-        )
-        _is_nous = "nousresearch" in self._base_url_lower
-        _is_nvidia = "integrate.api.nvidia.com" in self._base_url_lower
-        _is_kimi = (
-            base_url_host_matches(self.base_url, "api.kimi.com")
-            or base_url_host_matches(self.base_url, "moonshot.ai")
-            or base_url_host_matches(self.base_url, "moonshot.cn")
-        )
-
-        # Temperature: _fixed_temperature_for_model may return OMIT_TEMPERATURE
-        # sentinel (temperature omitted entirely), a numeric override, or None.
+        # ── Provider profile path (all chat_completions providers) ─────────
+        # Profiles handle per-provider quirks via hooks. We compute the shared
+        # per-call context here and pass it through so hooks can use it.
         try:
-            from agent.auxiliary_client import _fixed_temperature_for_model, OMIT_TEMPERATURE
-            _ft = _fixed_temperature_for_model(self.model, self.base_url)
-            _omit_temp = _ft is OMIT_TEMPERATURE
-            _fixed_temp = _ft if not _omit_temp else None
+            from providers import get_provider_profile
+            _profile = get_provider_profile(self.provider)
         except Exception:
-            _omit_temp = False
-            _fixed_temp = None
+            _profile = None
 
-        # Provider preferences (OpenRouter-specific)
-        _prefs: Dict[str, Any] = {}
-        if self.providers_allowed:
-            _prefs["only"] = self.providers_allowed
-        if self.providers_ignored:
-            _prefs["ignore"] = self.providers_ignored
-        if self.providers_order:
-            _prefs["order"] = self.providers_order
-        if self.provider_sort:
-            _prefs["sort"] = self.provider_sort
-        if self.provider_require_parameters:
-            _prefs["require_parameters"] = True
-        if self.provider_data_collection:
-            _prefs["data_collection"] = self.provider_data_collection
+        if _profile:
+            _ephemeral_out = getattr(self, "_ephemeral_max_output_tokens", None)
+            if _ephemeral_out is not None:
+                self._ephemeral_max_output_tokens = None
 
-        # Anthropic max output for Claude on OpenRouter/Nous
-        _ant_max = None
-        if (_is_or or _is_nous) and "claude" in (self.model or "").lower():
-            try:
-                from agent.anthropic_adapter import _get_anthropic_max_output
-                _ant_max = _get_anthropic_max_output(self.model)
-            except Exception:
-                pass  # fail open — let the proxy pick its default
+            # Per-call context for profile hooks — mirrors the legacy flag block.
+            # Computed here so profiles receive live per-call values (not stale).
+            _prefs: Dict[str, Any] = {}
+            if self.providers_allowed:
+                _prefs["only"] = self.providers_allowed
+            if self.providers_ignored:
+                _prefs["ignore"] = self.providers_ignored
+            if self.providers_order:
+                _prefs["order"] = self.providers_order
+            if self.provider_sort:
+                _prefs["sort"] = self.provider_sort
+            if self.provider_require_parameters:
+                _prefs["require_parameters"] = True
+            if self.provider_data_collection:
+                _prefs["data_collection"] = self.provider_data_collection
 
-        # Qwen session metadata precomputed here (promptId is per-call random)
-        _qwen_meta = None
-        if _is_qwen:
-            _qwen_meta = {
-                "sessionId": self.session_id or "hermes",
-                "promptId": str(uuid.uuid4()),
-            }
+            _is_or = self._is_openrouter_url()
+            _is_nous = "nousresearch" in self._base_url_lower
+            _ant_max = None
+            if (_is_or or _is_nous) and "claude" in (self.model or "").lower():
+                try:
+                    from agent.anthropic_adapter import _get_anthropic_max_output
+                    _ant_max = _get_anthropic_max_output(self.model)
+                except Exception:
+                    pass
 
-        # Ephemeral max output override — consume immediately so the next
-        # turn doesn't inherit it.
+            _is_qwen = self._is_qwen_portal()
+            _qwen_meta = None
+            if _is_qwen:
+                _qwen_meta = {
+                    "sessionId": self.session_id or "hermes",
+                    "promptId": str(uuid.uuid4()),
+                }
+
+            return _ct.build_kwargs(
+                model=self.model,
+                messages=api_messages,
+                tools=self.tools,
+                timeout=self._resolved_api_call_timeout(),
+                max_tokens=self.max_tokens,
+                ephemeral_max_output_tokens=_ephemeral_out,
+                max_tokens_param_fn=self._max_tokens_param,
+                reasoning_config=self.reasoning_config,
+                request_overrides=self.request_overrides,
+                session_id=getattr(self, "session_id", None),
+                provider_profile=_profile,
+                ollama_num_ctx=self._ollama_num_ctx,
+                # Context forwarded to profile hooks:
+                provider_preferences=_prefs or None,
+                anthropic_max_output=_ant_max,
+                supports_reasoning=self._supports_reasoning_extra_body(),
+                qwen_session_metadata=_qwen_meta,
+            )
+
+        # ── Legacy flag path ────────────────────────────────────────────
+        # Reached only when get_provider_profile() returns None — i.e. a
+        # completely unknown provider not in providers/ registry.
+        # Best-effort: send a clean chat_completions request with no
+        # provider-specific quirks.
         _ephemeral_out = getattr(self, "_ephemeral_max_output_tokens", None)
         if _ephemeral_out is not None:
             self._ephemeral_max_output_tokens = None
@@ -7935,24 +7971,7 @@ class AIAgent:
             reasoning_config=self.reasoning_config,
             request_overrides=self.request_overrides,
             session_id=getattr(self, "session_id", None),
-            model_lower=(self.model or "").lower(),
-            is_openrouter=_is_or,
-            is_nous=_is_nous,
-            is_qwen_portal=_is_qwen,
-            is_github_models=_is_gh,
-            is_nvidia_nim=_is_nvidia,
-            is_kimi=_is_kimi,
-            is_custom_provider=self.provider == "custom",
             ollama_num_ctx=self._ollama_num_ctx,
-            provider_preferences=_prefs or None,
-            qwen_prepare_fn=self._qwen_prepare_chat_messages if _is_qwen else None,
-            qwen_prepare_inplace_fn=self._qwen_prepare_chat_messages_inplace if _is_qwen else None,
-            qwen_session_metadata=_qwen_meta,
-            fixed_temperature=_fixed_temp,
-            omit_temperature=_omit_temp,
-            supports_reasoning=self._supports_reasoning_extra_body(),
-            github_reasoning_extra=self._github_models_reasoning_extra_body() if _is_gh else None,
-            anthropic_max_output=_ant_max,
         )
 
     def _supports_reasoning_extra_body(self) -> bool:

tests/agent/test_copilot_acp_client.py

@@ -10,7 +10,7 @@ import unittest
 from pathlib import Path
 from unittest.mock import patch
 
-from agent.copilot_acp_client import CopilotACPClient
+from acp_adapter.copilot_client import CopilotACPClient
 
 
 class _FakeProcess:
@@ -100,7 +100,7 @@ class CopilotACPClientSafetyTests(unittest.TestCase):
             target = home / ".ssh" / "id_rsa"
             target.parent.mkdir(parents=True, exist_ok=True)
 
-            with patch("agent.copilot_acp_client.is_write_denied", return_value=True, create=True):
+            with patch("acp_adapter.copilot_client.is_write_denied", return_value=True, create=True):
                 response = self._dispatch(
                     {
                         "jsonrpc": "2.0",

tests/agent/test_minimax_provider.py

@@ -71,17 +71,17 @@ class TestMinimaxThinkingSupport:
 
 
 class TestMinimaxAuxModel:
-    """Verify auxiliary model is standard (not highspeed)."""
+    """Verify auxiliary model is standard (not highspeed) — now reads from profiles."""
 
     def test_minimax_aux_is_standard(self):
-        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
-        assert _API_KEY_PROVIDER_AUX_MODELS["minimax"] == "MiniMax-M2.7"
-        assert _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"] == "MiniMax-M2.7"
+        from agent.auxiliary_client import _get_aux_model_for_provider
+        assert _get_aux_model_for_provider("minimax") == "MiniMax-M2.7"
+        assert _get_aux_model_for_provider("minimax-cn") == "MiniMax-M2.7"
 
     def test_minimax_aux_not_highspeed(self):
-        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
-        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax"]
-        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"]
+        from agent.auxiliary_client import _get_aux_model_for_provider
+        assert "highspeed" not in _get_aux_model_for_provider("minimax")
+        assert "highspeed" not in _get_aux_model_for_provider("minimax-cn")
 
 
 class TestMinimaxBetaHeaders:

tests/agent/transports/test_chat_completions.py

@@ -73,17 +73,21 @@ class TestChatCompletionsBuildKwargs:
         assert kw["tools"] == tools
 
     def test_openrouter_provider_prefs(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("openrouter")
         msgs = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(
             model="gpt-4o", messages=msgs,
-            is_openrouter=True,
+            provider_profile=profile,
             provider_preferences={"only": ["openai"]},
         )
         assert kw["extra_body"]["provider"] == {"only": ["openai"]}
 
     def test_nous_tags(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("nous")
         msgs = [{"role": "user", "content": "Hi"}]
-        kw = transport.build_kwargs(model="gpt-4o", messages=msgs, is_nous=True)
+        kw = transport.build_kwargs(model="gpt-4o", messages=msgs, provider_profile=profile)
         assert kw["extra_body"]["tags"] == ["product=hermes-agent"]
 
     def test_reasoning_default(self, transport):
@@ -95,29 +99,36 @@ class TestChatCompletionsBuildKwargs:
         assert kw["extra_body"]["reasoning"] == {"enabled": True, "effort": "medium"}
 
     def test_nous_omits_disabled_reasoning(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("nous")
         msgs = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(
             model="gpt-4o", messages=msgs,
+            provider_profile=profile,
             supports_reasoning=True,
-            is_nous=True,
             reasoning_config={"enabled": False},
         )
         # Nous rejects enabled=false; reasoning omitted entirely
         assert "reasoning" not in kw.get("extra_body", {})
 
     def test_ollama_num_ctx(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("custom")
         msgs = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(
             model="llama3", messages=msgs,
+            provider_profile=profile,
             ollama_num_ctx=32768,
         )
         assert kw["extra_body"]["options"]["num_ctx"] == 32768
 
     def test_custom_think_false(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("custom")
         msgs = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(
             model="qwen3", messages=msgs,
-            is_custom_provider=True,
+            provider_profile=profile,
             reasoning_config={"effort": "none"},
         )
         assert kw["extra_body"]["think"] is False
@@ -142,23 +153,29 @@ class TestChatCompletionsBuildKwargs:
         assert kw["max_tokens"] == 2048
 
     def test_nvidia_default_max_tokens(self, transport):
+        """NVIDIA max_tokens=16384 is now set via ProviderProfile, not legacy flag."""
+        from providers import get_provider_profile
+
+        profile = get_provider_profile("nvidia")
         msgs = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(
-            model="glm-4.7", messages=msgs,
-            is_nvidia_nim=True,
+            model="nvidia/llama-3.1-405b-instruct",
+            messages=msgs,
             max_tokens_param_fn=lambda n: {"max_tokens": n},
+            provider_profile=profile,
         )
-        # NVIDIA default: 16384
         assert kw["max_tokens"] == 16384
 
     def test_qwen_default_max_tokens(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("qwen-oauth")
         msgs = [{"role": "user", "content": "Hi"}]
         kw = transport.build_kwargs(
             model="qwen3-coder-plus", messages=msgs,
-            is_qwen_portal=True,
+            provider_profile=profile,
             max_tokens_param_fn=lambda n: {"max_tokens": n},
         )
-        # Qwen default: 65536
+        # Qwen default: 65536 from profile.default_max_tokens
         assert kw["max_tokens"] == 65536
 
     def test_anthropic_max_output_for_claude_on_aggregator(self, transport):
@@ -181,14 +198,23 @@ class TestChatCompletionsBuildKwargs:
         assert kw["service_tier"] == "priority"
 
     def test_fixed_temperature(self, transport):
+        """Fixed temperature is now set via ProviderProfile.fixed_temperature."""
+        from providers.base import ProviderProfile
         msgs = [{"role": "user", "content": "Hi"}]
-        kw = transport.build_kwargs(model="gpt-4o", messages=msgs, fixed_temperature=0.6)
+        kw = transport.build_kwargs(
+            model="gpt-4o", messages=msgs,
+            provider_profile=ProviderProfile(name="_t", fixed_temperature=0.6),
+        )
         assert kw["temperature"] == 0.6
 
     def test_omit_temperature(self, transport):
+        """Omit temperature is set via ProviderProfile with OMIT_TEMPERATURE sentinel."""
+        from providers.base import ProviderProfile, OMIT_TEMPERATURE
         msgs = [{"role": "user", "content": "Hi"}]
-        kw = transport.build_kwargs(model="gpt-4o", messages=msgs, omit_temperature=True, fixed_temperature=0.5)
-        # omit wins
+        kw = transport.build_kwargs(
+            model="gpt-4o", messages=msgs,
+            provider_profile=ProviderProfile(name="_t", fixed_temperature=OMIT_TEMPERATURE),
+        )
         assert "temperature" not in kw
 
 
@@ -196,18 +222,22 @@ class TestChatCompletionsKimi:
     """Regression tests for the Kimi/Moonshot quirks migrated into the transport."""
 
     def test_kimi_max_tokens_default(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("kimi-coding")
         kw = transport.build_kwargs(
             model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
-            is_kimi=True,
+            provider_profile=profile,
             max_tokens_param_fn=lambda n: {"max_tokens": n},
         )
-        # Kimi CLI default: 32000
+        # Kimi CLI default: 32000 from KimiProfile.default_max_tokens
         assert kw["max_tokens"] == 32000
 
     def test_kimi_reasoning_effort_top_level(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("kimi-coding")
         kw = transport.build_kwargs(
             model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
-            is_kimi=True,
+            provider_profile=profile,
             reasoning_config={"effort": "high"},
             max_tokens_param_fn=lambda n: {"max_tokens": n},
         )
@@ -225,17 +255,21 @@ class TestChatCompletionsKimi:
         assert "reasoning_effort" not in kw
 
     def test_kimi_thinking_enabled_extra_body(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("kimi-coding")
         kw = transport.build_kwargs(
             model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
-            is_kimi=True,
+            provider_profile=profile,
             max_tokens_param_fn=lambda n: {"max_tokens": n},
         )
         assert kw["extra_body"]["thinking"] == {"type": "enabled"}
 
     def test_kimi_thinking_disabled_extra_body(self, transport):
+        from providers import get_provider_profile
+        profile = get_provider_profile("kimi-coding")
         kw = transport.build_kwargs(
             model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
-            is_kimi=True,
+            provider_profile=profile,
             reasoning_config={"enabled": False},
             max_tokens_param_fn=lambda n: {"max_tokens": n},
         )

tests/hermes_cli/test_gmi_provider.py

@@ -269,9 +269,9 @@ class TestGmiModelMetadata:
 
 class TestGmiAuxiliary:
     def test_aux_default_model(self):
-        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+        from agent.auxiliary_client import _get_aux_model_for_provider
 
-        assert _API_KEY_PROVIDER_AUX_MODELS["gmi"] == "google/gemini-3.1-flash-lite-preview"
+        assert _get_aux_model_for_provider("gmi") == "google/gemini-3.1-flash-lite-preview"
 
     def test_resolve_provider_client_uses_gmi_aux_default(self, monkeypatch):
         monkeypatch.setenv("GMI_API_KEY", "gmi-test-key")

tests/providers/test_e2e_wiring.py

@@ -0,0 +1,118 @@
+"""E2E tests: verify _build_kwargs_from_profile produces correct output.
+
+These tests call _build_kwargs_from_profile on the transport directly,
+without importing run_agent (which would cause xdist worker contamination).
+"""
+
+import pytest
+from agent.transports.chat_completions import ChatCompletionsTransport
+from providers import get_provider_profile
+
+
+@pytest.fixture
+def transport():
+    return ChatCompletionsTransport()
+
+
+def _msgs():
+    return [{"role": "user", "content": "hi"}]
+
+
+class TestNvidiaProfileWiring:
+    def test_nvidia_gets_default_max_tokens(self, transport):
+        profile = get_provider_profile("nvidia")
+        kwargs = transport.build_kwargs(
+            model="nvidia/llama-3.1-nemotron-70b-instruct",
+            messages=_msgs(),
+            tools=None,
+            provider_profile=profile,
+            max_tokens=None,
+            max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
+            timeout=300,
+            reasoning_config=None,
+            request_overrides=None,
+            session_id="test",
+            ollama_num_ctx=None,
+        )
+        # NVIDIA profile sets default_max_tokens=16384
+        assert kwargs.get("max_tokens") == 16384
+
+    def test_nvidia_nim_alias(self, transport):
+        profile = get_provider_profile("nvidia-nim")
+        assert profile is not None
+        assert profile.name == "nvidia"
+        assert profile.default_max_tokens == 16384
+
+    def test_nvidia_model_passed(self, transport):
+        profile = get_provider_profile("nvidia")
+        kwargs = transport.build_kwargs(
+            model="nvidia/test-model",
+            messages=_msgs(),
+            tools=None,
+            provider_profile=profile,
+            max_tokens=None,
+            max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
+            timeout=300,
+            reasoning_config=None,
+            request_overrides=None,
+            session_id="test",
+            ollama_num_ctx=None,
+        )
+        assert kwargs["model"] == "nvidia/test-model"
+
+    def test_nvidia_messages_passed(self, transport):
+        profile = get_provider_profile("nvidia")
+        msgs = _msgs()
+        kwargs = transport.build_kwargs(
+            model="nvidia/test",
+            messages=msgs,
+            tools=None,
+            provider_profile=profile,
+            max_tokens=None,
+            max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
+            timeout=300,
+            reasoning_config=None,
+            request_overrides=None,
+            session_id="test",
+            ollama_num_ctx=None,
+        )
+        assert kwargs["messages"] == msgs
+
+
+class TestDeepSeekProfileWiring:
+    def test_deepseek_no_forced_max_tokens(self, transport):
+        profile = get_provider_profile("deepseek")
+        kwargs = transport.build_kwargs(
+            model="deepseek-chat",
+            messages=_msgs(),
+            tools=None,
+            provider_profile=profile,
+            max_tokens=None,
+            max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
+            timeout=300,
+            reasoning_config=None,
+            request_overrides=None,
+            session_id="test",
+            ollama_num_ctx=None,
+        )
+        # DeepSeek has no default_max_tokens
+        assert kwargs["model"] == "deepseek-chat"
+        assert kwargs.get("max_tokens") is None or "max_tokens" not in kwargs
+
+    def test_deepseek_messages_passed(self, transport):
+        profile = get_provider_profile("deepseek")
+        msgs = _msgs()
+        kwargs = transport.build_kwargs(
+            model="deepseek-chat",
+            messages=msgs,
+            tools=None,
+            provider_profile=profile,
+            max_tokens=None,
+            max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
+            timeout=300,
+            reasoning_config=None,
+            request_overrides=None,
+            session_id="test",
+            ollama_num_ctx=None,
+        )
+        assert kwargs["messages"] == msgs

tests/providers/test_profile_wiring.py

@@ -0,0 +1,290 @@
+"""Profile-path parity tests: verify profile path produces identical output to legacy flags.
+
+Each test calls build_kwargs twice — once with legacy flags, once with provider_profile —
+and asserts the output is identical. This catches any behavioral drift between the two paths.
+"""
+
+import pytest
+from agent.transports.chat_completions import ChatCompletionsTransport
+from providers import get_provider_profile
+
+
+@pytest.fixture
+def transport():
+    return ChatCompletionsTransport()
+
+
+def _msgs():
+    return [{"role": "user", "content": "hello"}]
+
+
+def _max_tokens_fn(n):
+    return {"max_completion_tokens": n}
+
+
+class TestNvidiaProfileParity:
+    def test_max_tokens_match(self, transport):
+        """NVIDIA profile sets max_tokens=16384; legacy flag is removed."""
+        profile = transport.build_kwargs(
+            model="nvidia/nemotron", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("nvidia"),
+            max_tokens_param_fn=_max_tokens_fn,
+        )
+        assert profile["max_completion_tokens"] == 16384
+
+
+class TestKimiProfileParity:
+    def test_temperature_omitted(self, transport):
+        legacy = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi-coding"), omit_temperature=True,
+        )
+        profile = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi"),
+        )
+        assert "temperature" not in legacy
+        assert "temperature" not in profile
+
+    def test_max_tokens(self, transport):
+        legacy = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi-coding"), max_tokens_param_fn=_max_tokens_fn,
+        )
+        profile = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi"),
+            max_tokens_param_fn=_max_tokens_fn,
+        )
+        assert profile["max_completion_tokens"] == legacy["max_completion_tokens"] == 32000
+
+    def test_thinking_enabled(self, transport):
+        rc = {"enabled": True, "effort": "high"}
+        legacy = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi-coding"), reasoning_config=rc,
+        )
+        profile = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi"),
+            reasoning_config=rc,
+        )
+        assert profile["extra_body"]["thinking"] == legacy["extra_body"]["thinking"]
+        assert profile["reasoning_effort"] == legacy["reasoning_effort"] == "high"
+
+    def test_thinking_disabled(self, transport):
+        rc = {"enabled": False}
+        legacy = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi-coding"), reasoning_config=rc,
+        )
+        profile = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi"),
+            reasoning_config=rc,
+        )
+        assert profile["extra_body"]["thinking"] == legacy["extra_body"]["thinking"]
+        assert profile["extra_body"]["thinking"]["type"] == "disabled"
+        assert "reasoning_effort" not in profile
+        assert "reasoning_effort" not in legacy
+
+    def test_reasoning_effort_default(self, transport):
+        rc = {"enabled": True}
+        legacy = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi-coding"), reasoning_config=rc,
+        )
+        profile = transport.build_kwargs(
+            model="kimi-k2", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("kimi"),
+            reasoning_config=rc,
+        )
+        assert profile["reasoning_effort"] == legacy["reasoning_effort"] == "medium"
+
+
+class TestOpenRouterProfileParity:
+    def test_provider_preferences(self, transport):
+        prefs = {"allow": ["anthropic"]}
+        legacy = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"), provider_preferences=prefs,
+        )
+        profile = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            provider_preferences=prefs,
+        )
+        assert profile["extra_body"]["provider"] == legacy["extra_body"]["provider"]
+
+    def test_reasoning_full_config(self, transport):
+        rc = {"enabled": True, "effort": "high"}
+        legacy = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"), supports_reasoning=True, reasoning_config=rc,
+        )
+        profile = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            supports_reasoning=True, reasoning_config=rc,
+        )
+        assert profile["extra_body"]["reasoning"] == legacy["extra_body"]["reasoning"]
+
+    def test_default_reasoning(self, transport):
+        legacy = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"), supports_reasoning=True,
+        )
+        profile = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            supports_reasoning=True,
+        )
+        assert profile["extra_body"]["reasoning"] == legacy["extra_body"]["reasoning"]
+
+
+class TestNousProfileParity:
+    def test_tags(self, transport):
+        legacy = transport.build_kwargs(
+            model="hermes-3", messages=_msgs(), tools=None, provider_profile=get_provider_profile("nous"),
+        )
+        profile = transport.build_kwargs(
+            model="hermes-3", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("nous"),
+        )
+        assert profile["extra_body"]["tags"] == legacy["extra_body"]["tags"]
+
+    def test_reasoning_omitted_when_disabled(self, transport):
+        rc = {"enabled": False}
+        legacy = transport.build_kwargs(
+            model="hermes-3", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("nous"), supports_reasoning=True, reasoning_config=rc,
+        )
+        profile = transport.build_kwargs(
+            model="hermes-3", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("nous"),
+            supports_reasoning=True, reasoning_config=rc,
+        )
+        assert "reasoning" not in legacy.get("extra_body", {})
+        assert "reasoning" not in profile.get("extra_body", {})
+
+
+class TestQwenProfileParity:
+    def test_max_tokens(self, transport):
+        legacy = transport.build_kwargs(
+            model="qwen3.5", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("qwen-oauth"), max_tokens_param_fn=_max_tokens_fn,
+        )
+        profile = transport.build_kwargs(
+            model="qwen3.5", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("qwen"),
+            max_tokens_param_fn=_max_tokens_fn,
+        )
+        assert profile["max_completion_tokens"] == legacy["max_completion_tokens"] == 65536
+
+    def test_vl_high_resolution(self, transport):
+        legacy = transport.build_kwargs(
+            model="qwen3.5", messages=_msgs(), tools=None, provider_profile=get_provider_profile("qwen-oauth"),
+        )
+        profile = transport.build_kwargs(
+            model="qwen3.5", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("qwen"),
+        )
+        assert profile["extra_body"]["vl_high_resolution_images"] == legacy["extra_body"]["vl_high_resolution_images"]
+
+    def test_metadata_top_level(self, transport):
+        meta = {"sessionId": "s123", "promptId": "p456"}
+        legacy = transport.build_kwargs(
+            model="qwen3.5", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("qwen-oauth"), qwen_session_metadata=meta,
+        )
+        profile = transport.build_kwargs(
+            model="qwen3.5", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("qwen"),
+            qwen_session_metadata=meta,
+        )
+        assert profile["metadata"] == legacy["metadata"] == meta
+        assert "metadata" not in profile.get("extra_body", {})
+
+    def test_message_preprocessing(self, transport):
+        """Qwen profile normalizes string content to list-of-parts."""
+        msgs = [
+            {"role": "system", "content": "You are helpful."},
+            {"role": "user", "content": "hello"},
+        ]
+        profile = transport.build_kwargs(
+            model="qwen3.5", messages=msgs, tools=None,
+            provider_profile=get_provider_profile("qwen"),
+        )
+        out_msgs = profile["messages"]
+        # System message content normalized + cache_control injected
+        assert isinstance(out_msgs[0]["content"], list)
+        assert out_msgs[0]["content"][0]["type"] == "text"
+        assert "cache_control" in out_msgs[0]["content"][-1]
+        # User message content normalized
+        assert isinstance(out_msgs[1]["content"], list)
+        assert out_msgs[1]["content"][0] == {"type": "text", "text": "hello"}
+
+
+class TestDeveloperRoleParity:
+    """Developer role swap must work on BOTH legacy and profile paths."""
+
+    def test_legacy_path_swaps_for_gpt5(self, transport):
+        msgs = [{"role": "system", "content": "Be helpful"}, {"role": "user", "content": "hi"}]
+        kw = transport.build_kwargs(
+            model="gpt-5.4", messages=msgs, tools=None,
+        )
+        assert kw["messages"][0]["role"] == "developer"
+
+    def test_profile_path_swaps_for_gpt5(self, transport):
+        msgs = [{"role": "system", "content": "Be helpful"}, {"role": "user", "content": "hi"}]
+        kw = transport.build_kwargs(
+            model="gpt-5.4", messages=msgs, tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+        )
+        assert kw["messages"][0]["role"] == "developer"
+
+    def test_profile_path_no_swap_for_claude(self, transport):
+        msgs = [{"role": "system", "content": "Be helpful"}, {"role": "user", "content": "hi"}]
+        kw = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6", messages=msgs, tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+        )
+        assert kw["messages"][0]["role"] == "system"
+
+
+class TestRequestOverridesParity:
+    """request_overrides with extra_body must merge identically on both paths."""
+
+    def test_extra_body_override_legacy(self, transport):
+        kw = transport.build_kwargs(
+            model="gpt-5.4", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            request_overrides={"extra_body": {"custom_key": "custom_val"}},
+        )
+        assert kw["extra_body"]["custom_key"] == "custom_val"
+
+    def test_extra_body_override_profile(self, transport):
+        kw = transport.build_kwargs(
+            model="gpt-5.4", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            request_overrides={"extra_body": {"custom_key": "custom_val"}},
+        )
+        assert kw["extra_body"]["custom_key"] == "custom_val"
+
+    def test_extra_body_override_merges_with_provider_body(self, transport):
+        """Override extra_body merges WITH provider extra_body, not replaces."""
+        kw = transport.build_kwargs(
+            model="hermes-3", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("nous"),
+            request_overrides={"extra_body": {"custom": True}},
+        )
+        assert kw["extra_body"]["tags"] == ["product=hermes-agent"]  # from profile
+        assert kw["extra_body"]["custom"] is True  # from override
+
+    def test_top_level_override(self, transport):
+        kw = transport.build_kwargs(
+            model="gpt-5.4", messages=_msgs(), tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            request_overrides={"top_p": 0.9},
+        )
+        assert kw["top_p"] == 0.9

tests/providers/test_provider_profiles.py

@@ -0,0 +1,203 @@
+"""Tests for the provider module registry and profiles."""
+
+import pytest
+from providers import get_provider_profile, _REGISTRY
+from providers.base import ProviderProfile, OMIT_TEMPERATURE
+
+
+class TestRegistry:
+    def test_discovery_populates_registry(self):
+        p = get_provider_profile("nvidia")
+        assert p is not None
+        assert p.name == "nvidia"
+
+    def test_alias_lookup(self):
+        assert get_provider_profile("kimi").name == "kimi-coding"
+        assert get_provider_profile("moonshot").name == "kimi-coding"
+        assert get_provider_profile("kimi-coding-cn").name == "kimi-coding-cn"
+        assert get_provider_profile("or").name == "openrouter"
+        assert get_provider_profile("nous-portal").name == "nous"
+        assert get_provider_profile("qwen").name == "qwen-oauth"
+        assert get_provider_profile("qwen-portal").name == "qwen-oauth"
+
+    def test_unknown_provider_returns_none(self):
+        assert get_provider_profile("nonexistent-provider") is None
+
+    def test_all_providers_have_name(self):
+        get_provider_profile("nvidia")  # trigger discovery
+        for name, profile in _REGISTRY.items():
+            assert profile.name == name
+
+
+class TestNvidiaProfile:
+    def test_max_tokens(self):
+        p = get_provider_profile("nvidia")
+        assert p.default_max_tokens == 16384
+
+    def test_no_special_temperature(self):
+        p = get_provider_profile("nvidia")
+        assert p.fixed_temperature is None
+
+    def test_base_url(self):
+        p = get_provider_profile("nvidia")
+        assert "nvidia.com" in p.base_url
+
+
+class TestKimiProfile:
+    def test_temperature_omit(self):
+        p = get_provider_profile("kimi")
+        assert p.fixed_temperature is OMIT_TEMPERATURE
+
+    def test_max_tokens(self):
+        p = get_provider_profile("kimi")
+        assert p.default_max_tokens == 32000
+
+    def test_cn_separate_profile(self):
+        p = get_provider_profile("kimi-coding-cn")
+        assert p.name == "kimi-coding-cn"
+        assert p.env_vars == ("KIMI_CN_API_KEY",)
+        assert "moonshot.cn" in p.base_url
+
+    def test_cn_not_alias_of_kimi(self):
+        kimi = get_provider_profile("kimi-coding")
+        cn = get_provider_profile("kimi-coding-cn")
+        assert kimi is not cn
+        assert kimi.base_url != cn.base_url
+
+    def test_thinking_enabled(self):
+        p = get_provider_profile("kimi")
+        eb, tl = p.build_api_kwargs_extras(reasoning_config={"enabled": True, "effort": "high"})
+        assert eb["thinking"] == {"type": "enabled"}
+        assert tl["reasoning_effort"] == "high"
+
+    def test_thinking_disabled(self):
+        p = get_provider_profile("kimi")
+        eb, tl = p.build_api_kwargs_extras(reasoning_config={"enabled": False})
+        assert eb["thinking"] == {"type": "disabled"}
+        assert "reasoning_effort" not in tl
+
+    def test_reasoning_effort_default(self):
+        p = get_provider_profile("kimi")
+        eb, tl = p.build_api_kwargs_extras(reasoning_config={"enabled": True})
+        assert tl["reasoning_effort"] == "medium"
+
+    def test_no_config_defaults(self):
+        p = get_provider_profile("kimi")
+        eb, tl = p.build_api_kwargs_extras(reasoning_config=None)
+        assert eb["thinking"] == {"type": "enabled"}
+        assert tl["reasoning_effort"] == "medium"
+
+
+class TestOpenRouterProfile:
+    def test_extra_body_with_prefs(self):
+        p = get_provider_profile("openrouter")
+        body = p.build_extra_body(provider_preferences={"allow": ["anthropic"]})
+        assert body["provider"] == {"allow": ["anthropic"]}
+
+    def test_extra_body_no_prefs(self):
+        p = get_provider_profile("openrouter")
+        body = p.build_extra_body()
+        assert body == {}
+
+    def test_reasoning_full_config(self):
+        p = get_provider_profile("openrouter")
+        eb, _ = p.build_api_kwargs_extras(
+            reasoning_config={"enabled": True, "effort": "high"},
+            supports_reasoning=True,
+        )
+        assert eb["reasoning"] == {"enabled": True, "effort": "high"}
+
+    def test_reasoning_disabled_still_passes(self):
+        """OpenRouter passes disabled reasoning through (unlike Nous)."""
+        p = get_provider_profile("openrouter")
+        eb, _ = p.build_api_kwargs_extras(
+            reasoning_config={"enabled": False},
+            supports_reasoning=True,
+        )
+        assert eb["reasoning"] == {"enabled": False}
+
+    def test_default_reasoning(self):
+        p = get_provider_profile("openrouter")
+        eb, _ = p.build_api_kwargs_extras(supports_reasoning=True)
+        assert eb["reasoning"] == {"enabled": True, "effort": "medium"}
+
+
+class TestNousProfile:
+    def test_tags(self):
+        p = get_provider_profile("nous")
+        body = p.build_extra_body()
+        assert body["tags"] == ["product=hermes-agent"]
+
+    def test_auth_type(self):
+        p = get_provider_profile("nous")
+        assert p.auth_type == "oauth_device_code"
+
+    def test_reasoning_enabled(self):
+        p = get_provider_profile("nous")
+        eb, _ = p.build_api_kwargs_extras(
+            reasoning_config={"enabled": True, "effort": "medium"},
+            supports_reasoning=True,
+        )
+        assert eb["reasoning"] == {"enabled": True, "effort": "medium"}
+
+    def test_reasoning_omitted_when_disabled(self):
+        p = get_provider_profile("nous")
+        eb, _ = p.build_api_kwargs_extras(
+            reasoning_config={"enabled": False},
+            supports_reasoning=True,
+        )
+        assert "reasoning" not in eb
+
+
+class TestQwenProfile:
+    def test_max_tokens(self):
+        p = get_provider_profile("qwen-oauth")
+        assert p.default_max_tokens == 65536
+
+    def test_auth_type(self):
+        p = get_provider_profile("qwen-oauth")
+        assert p.auth_type == "oauth_external"
+
+    def test_extra_body_vl(self):
+        p = get_provider_profile("qwen-oauth")
+        body = p.build_extra_body()
+        assert body["vl_high_resolution_images"] is True
+
+    def test_prepare_messages_normalizes_content(self):
+        p = get_provider_profile("qwen-oauth")
+        msgs = [
+            {"role": "system", "content": "Be helpful"},
+            {"role": "user", "content": "hello"},
+        ]
+        result = p.prepare_messages(msgs)
+        # System message: content normalized to list, cache_control on last part
+        assert isinstance(result[0]["content"], list)
+        assert result[0]["content"][-1].get("cache_control") == {"type": "ephemeral"}
+        assert result[0]["content"][-1]["text"] == "Be helpful"
+        # User message: content normalized to list
+        assert isinstance(result[1]["content"], list)
+        assert result[1]["content"][0]["text"] == "hello"
+
+    def test_metadata_top_level(self):
+        p = get_provider_profile("qwen-oauth")
+        meta = {"sessionId": "s123", "promptId": "p456"}
+        eb, tl = p.build_api_kwargs_extras(qwen_session_metadata=meta)
+        assert tl["metadata"] == meta
+        assert "metadata" not in eb
+
+
+class TestBaseProfile:
+    def test_prepare_messages_passthrough(self):
+        p = ProviderProfile(name="test")
+        msgs = [{"role": "user", "content": "hi"}]
+        assert p.prepare_messages(msgs) is msgs
+
+    def test_build_extra_body_empty(self):
+        p = ProviderProfile(name="test")
+        assert p.build_extra_body() == {}
+
+    def test_build_api_kwargs_extras_empty(self):
+        p = ProviderProfile(name="test")
+        eb, tl = p.build_api_kwargs_extras()
+        assert eb == {}
+        assert tl == {}

tests/providers/test_transport_parity.py

@@ -0,0 +1,258 @@
+"""Parity tests: pin the exact current transport behavior per provider.
+
+These tests document the flag-based contract between run_agent.py and
+ChatCompletionsTransport.build_kwargs(). When the next PR wires profiles
+to replace flags, every assertion here must still pass — any failure is
+a behavioral regression.
+"""
+
+import pytest
+from agent.transports.chat_completions import ChatCompletionsTransport
+from providers import get_provider_profile
+
+
+@pytest.fixture
+def transport():
+    return ChatCompletionsTransport()
+
+
+def _simple_messages():
+    return [{"role": "user", "content": "hello"}]
+
+
+def _max_tokens_fn(n):
+    return {"max_completion_tokens": n}
+
+
+class TestNvidiaParity:
+    """NVIDIA NIM: default max_tokens=16384."""
+
+    def test_default_max_tokens(self, transport):
+        """NVIDIA default max_tokens=16384 comes from profile, not legacy is_nvidia_nim flag."""
+        from providers import get_provider_profile
+
+        profile = get_provider_profile("nvidia")
+        kw = transport.build_kwargs(
+            model="nvidia/llama-3.1-nemotron-70b-instruct",
+            messages=_simple_messages(),
+            tools=None,
+            max_tokens_param_fn=_max_tokens_fn,
+            provider_profile=profile,
+        )
+        assert kw["max_completion_tokens"] == 16384
+
+    def test_user_max_tokens_overrides(self, transport):
+        from providers import get_provider_profile
+
+        profile = get_provider_profile("nvidia")
+        kw = transport.build_kwargs(
+            model="nvidia/llama-3.1-nemotron-70b-instruct",
+            messages=_simple_messages(),
+            tools=None,
+            max_tokens=4096,
+            max_tokens_param_fn=_max_tokens_fn,
+            provider_profile=profile,
+        )
+        assert kw["max_completion_tokens"] == 4096  # user overrides default
+
+
+class TestKimiParity:
+    """Kimi: OMIT temperature, max_tokens=32000, thinking + reasoning_effort."""
+
+    def test_temperature_omitted(self, transport):
+        kw = transport.build_kwargs(
+            model="kimi-k2",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("kimi-coding"),
+            omit_temperature=True,
+        )
+        assert "temperature" not in kw
+
+    def test_default_max_tokens(self, transport):
+        kw = transport.build_kwargs(
+            model="kimi-k2",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("kimi-coding"),
+            max_tokens_param_fn=_max_tokens_fn,
+        )
+        assert kw["max_completion_tokens"] == 32000
+
+    def test_thinking_enabled(self, transport):
+        kw = transport.build_kwargs(
+            model="kimi-k2",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("kimi-coding"),
+            reasoning_config={"enabled": True, "effort": "high"},
+        )
+        assert kw["extra_body"]["thinking"] == {"type": "enabled"}
+
+    def test_thinking_disabled(self, transport):
+        kw = transport.build_kwargs(
+            model="kimi-k2",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("kimi-coding"),
+            reasoning_config={"enabled": False},
+        )
+        assert kw["extra_body"]["thinking"] == {"type": "disabled"}
+
+    def test_reasoning_effort_top_level(self, transport):
+        """Kimi reasoning_effort is a TOP-LEVEL api_kwargs key, NOT in extra_body."""
+        kw = transport.build_kwargs(
+            model="kimi-k2",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("kimi-coding"),
+            reasoning_config={"enabled": True, "effort": "high"},
+        )
+        assert kw.get("reasoning_effort") == "high"
+        assert "reasoning_effort" not in kw.get("extra_body", {})
+
+    def test_reasoning_effort_default_medium(self, transport):
+        kw = transport.build_kwargs(
+            model="kimi-k2",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("kimi-coding"),
+            reasoning_config={"enabled": True},
+        )
+        assert kw.get("reasoning_effort") == "medium"
+
+
+class TestOpenRouterParity:
+    """OpenRouter: provider preferences, reasoning in extra_body."""
+
+    def test_provider_preferences(self, transport):
+        prefs = {"allow": ["anthropic"], "sort": "price"}
+        kw = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            provider_preferences=prefs,
+        )
+        assert kw["extra_body"]["provider"] == prefs
+
+    def test_reasoning_passes_full_config(self, transport):
+        """OpenRouter passes the FULL reasoning_config dict, not just effort."""
+        rc = {"enabled": True, "effort": "high"}
+        kw = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            supports_reasoning=True,
+            reasoning_config=rc,
+        )
+        assert kw["extra_body"]["reasoning"] == rc
+
+    def test_default_reasoning_when_no_config(self, transport):
+        """When supports_reasoning=True but no config, adds default."""
+        kw = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("openrouter"),
+            supports_reasoning=True,
+        )
+        assert kw["extra_body"]["reasoning"] == {"enabled": True, "effort": "medium"}
+
+
+class TestNousParity:
+    """Nous: product tags, reasoning, omit when disabled."""
+
+    def test_tags(self, transport):
+        kw = transport.build_kwargs(
+            model="hermes-3-llama-3.1-405b",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("nous"),
+        )
+        assert kw["extra_body"]["tags"] == ["product=hermes-agent"]
+
+    def test_reasoning_omitted_when_disabled(self, transport):
+        """Nous special case: reasoning omitted entirely when disabled."""
+        kw = transport.build_kwargs(
+            model="hermes-3-llama-3.1-405b",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("nous"),
+            supports_reasoning=True,
+            reasoning_config={"enabled": False},
+        )
+        assert "reasoning" not in kw.get("extra_body", {})
+
+    def test_reasoning_enabled(self, transport):
+        rc = {"enabled": True, "effort": "high"}
+        kw = transport.build_kwargs(
+            model="hermes-3-llama-3.1-405b",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("nous"),
+            supports_reasoning=True,
+            reasoning_config=rc,
+        )
+        assert kw["extra_body"]["reasoning"] == rc
+
+
+class TestQwenParity:
+    """Qwen: max_tokens=65536, vl_high_resolution, metadata top-level."""
+
+    def test_default_max_tokens(self, transport):
+        kw = transport.build_kwargs(
+            model="qwen3.5-plus",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("qwen-oauth"),
+            max_tokens_param_fn=_max_tokens_fn,
+        )
+        assert kw["max_completion_tokens"] == 65536
+
+    def test_vl_high_resolution(self, transport):
+        kw = transport.build_kwargs(
+            model="qwen3.5-plus",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("qwen-oauth"),
+        )
+        assert kw["extra_body"]["vl_high_resolution_images"] is True
+
+    def test_metadata_top_level(self, transport):
+        """Qwen metadata goes to top-level api_kwargs, NOT extra_body."""
+        meta = {"sessionId": "s123", "promptId": "p456"}
+        kw = transport.build_kwargs(
+            model="qwen3.5-plus",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("qwen-oauth"),
+            qwen_session_metadata=meta,
+        )
+        assert kw["metadata"] == meta
+        assert "metadata" not in kw.get("extra_body", {})
+
+
+class TestCustomOllamaParity:
+    """Custom/Ollama: num_ctx, think=false — now tested via profile."""
+
+    def test_ollama_num_ctx(self, transport):
+        kw = transport.build_kwargs(
+            model="llama3.1",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("custom"),
+            ollama_num_ctx=131072,
+        )
+        assert kw["extra_body"]["options"]["num_ctx"] == 131072
+
+    def test_think_false_when_disabled(self, transport):
+        kw = transport.build_kwargs(
+            model="qwen3:72b",
+            messages=_simple_messages(),
+            tools=None,
+            provider_profile=get_provider_profile("custom"),
+            reasoning_config={"enabled": False, "effort": "none"},
+        )
+        assert kw["extra_body"]["think"] is False

tests/run_agent/test_run_agent.py

@@ -1097,6 +1097,7 @@ class TestBuildApiKwargs:
         assert "temperature" not in kwargs
 
     def test_kimi_coding_endpoint_omits_temperature(self, agent):
+        agent.provider = "kimi-coding"
         agent.base_url = "https://api.kimi.com/coding/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-k2.5"
@@ -1109,6 +1110,7 @@ class TestBuildApiKwargs:
     def test_kimi_coding_endpoint_sends_max_tokens_and_reasoning(self, agent):
         """Kimi endpoint should send max_tokens=32000 and reasoning_effort as
         top-level params, matching Kimi CLI's default behavior."""
+        agent.provider = "kimi-coding"
         agent.base_url = "https://api.kimi.com/coding/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-for-coding"
@@ -1121,6 +1123,7 @@ class TestBuildApiKwargs:
 
     def test_kimi_coding_endpoint_respects_custom_effort(self, agent):
         """reasoning_effort should reflect reasoning_config.effort when set."""
+        agent.provider = "kimi-coding"
         agent.base_url = "https://api.kimi.com/coding/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-for-coding"
@@ -1134,6 +1137,7 @@ class TestBuildApiKwargs:
     def test_kimi_coding_endpoint_sends_thinking_extra_body(self, agent):
         """Kimi endpoint should send extra_body.thinking={"type":"enabled"}
         to activate reasoning mode, mirroring Kimi CLI's with_thinking()."""
+        agent.provider = "kimi-coding"
         agent.base_url = "https://api.kimi.com/coding/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-for-coding"
@@ -1147,6 +1151,7 @@ class TestBuildApiKwargs:
         """When reasoning_config.enabled=False, thinking should be disabled
         and reasoning_effort should be omitted entirely — mirroring Kimi
         CLI's with_thinking("off") which maps to reasoning_effort=None."""
+        agent.provider = "kimi-coding"
         agent.base_url = "https://api.kimi.com/coding/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-for-coding"
@@ -1160,6 +1165,7 @@ class TestBuildApiKwargs:
 
     def test_moonshot_endpoint_sends_max_tokens_and_reasoning(self, agent):
         """api.moonshot.ai should get the same Kimi-compatible params."""
+        agent.provider = "kimi-coding"
         agent.base_url = "https://api.moonshot.ai/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-k2.5"
@@ -1173,6 +1179,7 @@ class TestBuildApiKwargs:
 
     def test_moonshot_cn_endpoint_sends_max_tokens_and_reasoning(self, agent):
         """api.moonshot.cn (China endpoint) should get the same params."""
+        agent.provider = "kimi-coding-cn"
         agent.base_url = "https://api.moonshot.cn/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.model = "kimi-k2.5"
@@ -1185,6 +1192,7 @@ class TestBuildApiKwargs:
         assert kwargs["extra_body"]["thinking"] == {"type": "enabled"}
 
     def test_provider_preferences_injected(self, agent):
+        agent.provider = "openrouter"
         agent.base_url = "https://openrouter.ai/api/v1"
         agent.providers_allowed = ["Anthropic"]
         messages = [{"role": "user", "content": "hi"}]
@@ -1193,6 +1201,7 @@ class TestBuildApiKwargs:
 
     def test_reasoning_config_default_openrouter(self, agent):
         """Default reasoning config for OpenRouter should be medium."""
+        agent.provider = "openrouter"
         agent.base_url = "https://openrouter.ai/api/v1"
         agent.model = "anthropic/claude-sonnet-4-20250514"
         messages = [{"role": "user", "content": "hi"}]
@@ -1202,6 +1211,7 @@ class TestBuildApiKwargs:
         assert reasoning["effort"] == "medium"
 
     def test_reasoning_config_custom(self, agent):
+        agent.provider = "openrouter"
         agent.base_url = "https://openrouter.ai/api/v1"
         agent.model = "anthropic/claude-sonnet-4-20250514"
         agent.reasoning_config = {"enabled": False}
@@ -1217,6 +1227,7 @@ class TestBuildApiKwargs:
         assert "reasoning" not in kwargs.get("extra_body", {})
 
     def test_reasoning_sent_for_supported_openrouter_model(self, agent):
+        agent.provider = "openrouter"
         agent.base_url = "https://openrouter.ai/api/v1"
         agent.model = "qwen/qwen3.5-plus-02-15"
         messages = [{"role": "user", "content": "hi"}]
@@ -1224,6 +1235,7 @@ class TestBuildApiKwargs:
         assert kwargs["extra_body"]["reasoning"]["effort"] == "medium"
 
     def test_reasoning_sent_for_nous_route(self, agent):
+        agent.provider = "nous"
         agent.base_url = "https://inference-api.nousresearch.com/v1"
         agent.model = "minimax/minimax-m2.5"
         messages = [{"role": "user", "content": "hi"}]
@@ -1231,18 +1243,38 @@ class TestBuildApiKwargs:
         assert kwargs["extra_body"]["reasoning"]["effort"] == "medium"
 
     def test_reasoning_sent_for_copilot_gpt5(self, agent):
-        agent.base_url = "https://api.githubcopilot.com"
-        agent.model = "gpt-5.4"
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
+        """Copilot/GitHub Models: GPT-5 reasoning goes in extra_body.reasoning."""
+        from agent.transports import get_transport
+        from providers import get_provider_profile
+
+        transport = get_transport("chat_completions")
+        profile = get_provider_profile("copilot")
+        msgs = [{"role": "user", "content": "hi"}]
+        kwargs = transport.build_kwargs(
+            model="gpt-5.4",
+            messages=msgs,
+            tools=None,
+            supports_reasoning=True,
+            provider_profile=profile,
+        )
         assert kwargs["extra_body"]["reasoning"] == {"effort": "medium"}
 
     def test_reasoning_xhigh_normalized_for_copilot(self, agent):
-        agent.base_url = "https://api.githubcopilot.com"
-        agent.model = "gpt-5.4"
-        agent.reasoning_config = {"enabled": True, "effort": "xhigh"}
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
+        """xhigh effort should normalize to high for Copilot GitHub Models."""
+        from agent.transports import get_transport
+        from providers import get_provider_profile
+
+        transport = get_transport("chat_completions")
+        profile = get_provider_profile("copilot")
+        msgs = [{"role": "user", "content": "hi"}]
+        kwargs = transport.build_kwargs(
+            model="gpt-5.4",
+            messages=msgs,
+            tools=None,
+            supports_reasoning=True,
+            reasoning_config={"enabled": True, "effort": "xhigh"},
+            provider_profile=profile,
+        )
         assert kwargs["extra_body"]["reasoning"] == {"effort": "high"}
 
     def test_reasoning_omitted_for_non_reasoning_copilot_model(self, agent):
@@ -1260,6 +1292,7 @@ class TestBuildApiKwargs:
 
 
     def test_qwen_portal_formats_messages_and_metadata(self, agent):
+        agent.provider = "qwen-oauth"
         agent.base_url = "https://portal.qwen.ai/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.session_id = "sess-123"
@@ -1276,6 +1309,7 @@ class TestBuildApiKwargs:
         assert kwargs["messages"][2]["content"][0]["text"] == "hi"
 
     def test_qwen_portal_normalizes_bare_string_content_parts(self, agent):
+        agent.provider = "qwen-oauth"
         agent.base_url = "https://portal.qwen.ai/v1"
         agent._base_url_lower = agent.base_url.lower()
         messages = [
@@ -1288,6 +1322,7 @@ class TestBuildApiKwargs:
         assert user_content[1] == {"type": "text", "text": "world"}
 
     def test_qwen_portal_no_system_message(self, agent):
+        agent.provider = "qwen-oauth"
         agent.base_url = "https://portal.qwen.ai/v1"
         agent._base_url_lower = agent.base_url.lower()
         messages = [{"role": "user", "content": "hi"}]
@@ -1308,6 +1343,7 @@ class TestBuildApiKwargs:
     def test_qwen_portal_default_max_tokens(self, agent):
         """When max_tokens is None, Qwen Portal gets a default of 65536
         to prevent reasoning models from exhausting their output budget."""
+        agent.provider = "qwen-oauth"
         agent.base_url = "https://portal.qwen.ai/v1"
         agent._base_url_lower = agent.base_url.lower()
         agent.max_tokens = None
@@ -3843,7 +3879,7 @@ def test_aiagent_uses_copilot_acp_client():
         patch("run_agent.get_tool_definitions", return_value=_make_tool_defs("web_search")),
         patch("run_agent.check_toolset_requirements", return_value={}),
         patch("run_agent.OpenAI") as mock_openai,
-        patch("agent.copilot_acp_client.CopilotACPClient") as mock_acp_client,
+        patch("acp_adapter.copilot_client.CopilotACPClient") as mock_acp_client,
     ):
         acp_client = MagicMock()
         mock_acp_client.return_value = acp_client

uv.lock

@@ -9,7 +9,7 @@ resolution-markers = [
 ]
 
 [options]
-exclude-newer = "2026-04-17T16:49:45.944715922Z"
+exclude-newer = "2026-04-19T17:00:07.266826Z"
 exclude-newer-span = "P7D"
 
 [[package]]
@@ -564,30 +564,30 @@ wheels = [
 
 [[package]]
 name = "boto3"
-version = "1.42.89"
+version = "1.42.91"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "botocore" },
     { name = "jmespath" },
     { name = "s3transfer" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/bb/0c/f7bccb22b245cabf392816baba20f9e95f78ace7dbc580fd40136e80e732/boto3-1.42.89.tar.gz", hash = "sha256:3e43aacc0801bba9bcd23a8c271c089af297a69565f783fcdd357ae0e330bf1e", size = 113165, upload-time = "2026-04-13T19:36:17.516Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a7/c0/98b8cec7ca22dde776df48c58940ae1abc425593959b7226e270760d726f/boto3-1.42.91.tar.gz", hash = "sha256:03d70532b17f7f84df37ca7e8c21553280454dea53ae12b15d1cfef9b16fcb8a", size = 113181, upload-time = "2026-04-17T19:31:06.251Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b9/33/55103ba5ef9975ea54b8d39e69b76eb6e9fded3beae5f01065e26951a3a1/boto3-1.42.89-py3-none-any.whl", hash = "sha256:6204b189f4d0c655535f43d7eaa57ff4e8d965b8463c97e45952291211162932", size = 140556, upload-time = "2026-04-13T19:36:13.894Z" },
+    { url = "https://files.pythonhosted.org/packages/02/29/faba6521257c34085cc9b439ef98235b581772580f417fa3629728007270/boto3-1.42.91-py3-none-any.whl", hash = "sha256:04e72071cde022951ce7f81bd9933c90095ab8923e8ced61c8dacfe9edac0f5c", size = 140553, upload-time = "2026-04-17T19:31:02.57Z" },
 ]
 
 [[package]]
 name = "botocore"
-version = "1.42.89"
+version = "1.42.91"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jmespath" },
     { name = "python-dateutil" },
     { name = "urllib3" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0f/cc/e6be943efa9051bd15c2ee14077c2b10d6e27c9e9385fc43a03a5c4ed8b5/botocore-1.42.89.tar.gz", hash = "sha256:95ac52f472dad29942f3088b278ab493044516c16dbf9133c975af16527baa99", size = 15206290, upload-time = "2026-04-13T19:36:02.321Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/21/bc/a4b7c46471c2e789ad8c4c7acfd7f302fdb481d93ff870f441249b924ae6/botocore-1.42.91.tar.gz", hash = "sha256:d252e27bc454afdbf5ed3dc617aa423f2c855c081e98b7963093399483ecc698", size = 15213010, upload-time = "2026-04-17T19:30:50.793Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/91/f1/90a7b8eda38b7c3a65ca7ee0075bdf310b6b471cb1b95fab6e8994323a50/botocore-1.42.89-py3-none-any.whl", hash = "sha256:d9b786c8d9db6473063b4cc5be0ba7e6a381082307bd6afb69d4216f9fa95f35", size = 14887287, upload-time = "2026-04-13T19:35:56.677Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/fc/24cc0a47c824f13933e210e9ad034b4fba22f7185b8d904c0fbf5a3b2be8/botocore-1.42.91-py3-none-any.whl", hash = "sha256:7a28c3cc6bfab5724ad18899d52402b776a0de7d87fa20c3c5270bcaaf199ce8", size = 14897344, upload-time = "2026-04-17T19:30:44.245Z" },
 ]
 
 [[package]]
@@ -1759,6 +1759,77 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/6a/09/e21df6aef1e1ffc0c816f0522ddc3f6dcded766c3261813131c78a704470/gitpython-3.1.46-py3-none-any.whl", hash = "sha256:79812ed143d9d25b6d176a10bb511de0f9c67b1fa641d82097b0ab90398a2058", size = 208620, upload-time = "2026-01-01T15:37:30.574Z" },
 ]
 
+[[package]]
+name = "google-api-core"
+version = "2.30.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-auth" },
+    { name = "googleapis-common-protos" },
+    { name = "proto-plus" },
+    { name = "protobuf" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/16/ce/502a57fb0ec752026d24df1280b162294b22a0afb98a326084f9a979138b/google_api_core-2.30.3.tar.gz", hash = "sha256:e601a37f148585319b26db36e219df68c5d07b6382cff2d580e83404e44d641b", size = 177001, upload-time = "2026-04-10T00:41:28.035Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/03/15/e56f351cf6ef1cfea58e6ac226a7318ed1deb2218c4b3cc9bd9e4b786c5a/google_api_core-2.30.3-py3-none-any.whl", hash = "sha256:a85761ba72c444dad5d611c2220633480b2b6be2521eca69cca2dbb3ffd6bfe8", size = 173274, upload-time = "2026-04-09T22:57:16.198Z" },
+]
+
+[[package]]
+name = "google-api-python-client"
+version = "2.194.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-api-core" },
+    { name = "google-auth" },
+    { name = "google-auth-httplib2" },
+    { name = "httplib2" },
+    { name = "uritemplate" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/60/ab/e83af0eb043e4ccc49571ca7a6a49984e9d00f4e9e6e6f1238d60bc84dce/google_api_python_client-2.194.0.tar.gz", hash = "sha256:db92647bd1a90f40b79c9618461553c2b20b6a43ce7395fa6de07132dc14f023", size = 14443469, upload-time = "2026-04-08T23:07:35.757Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b0/34/5a624e49f179aa5b0cb87b2ce8093960299030ff40423bfbde09360eb908/google_api_python_client-2.194.0-py3-none-any.whl", hash = "sha256:61eaaac3b8fc8fdf11c08af87abc3d1342d1b37319cc1b57405f86ef7697e717", size = 15016514, upload-time = "2026-04-08T23:07:33.093Z" },
+]
+
+[[package]]
+name = "google-auth"
+version = "2.49.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cryptography" },
+    { name = "pyasn1-modules" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c6/fc/e925290a1ad95c975c459e2df070fac2b90954e13a0370ac505dff78cb99/google_auth-2.49.2.tar.gz", hash = "sha256:c1ae38500e73065dcae57355adb6278cf8b5c8e391994ae9cbadbcb9631ab409", size = 333958, upload-time = "2026-04-10T00:41:21.888Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/73/76/d241a5c927433420507215df6cac1b1fa4ac0ba7a794df42a84326c68da8/google_auth-2.49.2-py3-none-any.whl", hash = "sha256:c2720924dfc82dedb962c9f52cabb2ab16714fd0a6a707e40561d217574ed6d5", size = 240638, upload-time = "2026-04-10T00:41:14.501Z" },
+]
+
+[[package]]
+name = "google-auth-httplib2"
+version = "0.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-auth" },
+    { name = "httplib2" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ed/99/107612bef8d24b298bb5a7c8466f908ecda791d43f9466f5c3978f5b24c1/google_auth_httplib2-0.3.1.tar.gz", hash = "sha256:0af542e815784cb64159b4469aa5d71dd41069ba93effa006e1916b1dcd88e55", size = 11152, upload-time = "2026-03-30T22:50:26.766Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/97/e9/93afb14d23a949acaa3f4e7cc51a0024671174e116e35f42850764b99634/google_auth_httplib2-0.3.1-py3-none-any.whl", hash = "sha256:682356a90ef4ba3d06548c37e9112eea6fc00395a11b0303a644c1a86abc275c", size = 9534, upload-time = "2026-03-30T22:49:03.384Z" },
+]
+
+[[package]]
+name = "google-auth-oauthlib"
+version = "1.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-auth" },
+    { name = "requests-oauthlib" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a6/82/62482931dcbe5266a2680d0da17096f2aab983ecb320277d9556700ce00e/google_auth_oauthlib-1.3.1.tar.gz", hash = "sha256:14c22c7b3dd3d06dbe44264144409039465effdd1eef94f7ce3710e486cc4bfa", size = 21663, upload-time = "2026-03-30T22:49:56.408Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/e0/cb454a95f460903e39f101e950038ec24a072ca69d0a294a6df625cc1627/google_auth_oauthlib-1.3.1-py3-none-any.whl", hash = "sha256:1a139ef23f1318756805b0e95f655c238bffd29655329a2978218248da4ee7f8", size = 19247, upload-time = "2026-03-30T20:02:23.894Z" },
+]
+
 [[package]]
 name = "googleapis-common-protos"
 version = "1.73.0"
@@ -1912,6 +1983,9 @@ all = [
     { name = "elevenlabs" },
     { name = "fastapi" },
     { name = "faster-whisper" },
+    { name = "google-api-python-client" },
+    { name = "google-auth-httplib2" },
+    { name = "google-auth-oauthlib" },
     { name = "honcho-ai" },
     { name = "lark-oapi" },
     { name = "markdown", marker = "sys_platform == 'linux'" },
@@ -1965,6 +2039,11 @@ feishu = [
     { name = "lark-oapi" },
     { name = "qrcode" },
 ]
+google = [
+    { name = "google-api-python-client" },
+    { name = "google-auth-httplib2" },
+    { name = "google-auth-oauthlib" },
+]
 homeassistant = [
     { name = "aiohttp" },
 ]
@@ -2064,6 +2143,9 @@ requires-dist = [
     { name = "faster-whisper", marker = "extra == 'voice'", specifier = ">=1.0.0,<2" },
     { name = "fire", specifier = ">=0.7.1,<1" },
     { name = "firecrawl-py", specifier = ">=4.16.0,<5" },
+    { name = "google-api-python-client", marker = "extra == 'google'", specifier = ">=2.100,<3" },
+    { name = "google-auth-httplib2", marker = "extra == 'google'", specifier = ">=0.2,<1" },
+    { name = "google-auth-oauthlib", marker = "extra == 'google'", specifier = ">=1.0,<2" },
     { name = "hermes-agent", extras = ["acp"], marker = "extra == 'all'" },
     { name = "hermes-agent", extras = ["acp"], marker = "extra == 'termux'" },
     { name = "hermes-agent", extras = ["bedrock"], marker = "extra == 'all'" },
@@ -2075,6 +2157,7 @@ requires-dist = [
     { name = "hermes-agent", extras = ["dev"], marker = "extra == 'all'" },
     { name = "hermes-agent", extras = ["dingtalk"], marker = "extra == 'all'" },
     { name = "hermes-agent", extras = ["feishu"], marker = "extra == 'all'" },
+    { name = "hermes-agent", extras = ["google"], marker = "extra == 'all'" },
     { name = "hermes-agent", extras = ["homeassistant"], marker = "extra == 'all'" },
     { name = "hermes-agent", extras = ["honcho"], marker = "extra == 'all'" },
     { name = "hermes-agent", extras = ["honcho"], marker = "extra == 'termux'" },
@@ -2136,7 +2219,7 @@ requires-dist = [
     { name = "wandb", marker = "extra == 'rl'", specifier = ">=0.15.0,<1" },
     { name = "yc-bench", marker = "python_full_version >= '3.12' and extra == 'yc-bench'", git = "https://github.com/collinear-ai/yc-bench.git?rev=bfb0c88062450f46341bd9a5298903fc2e952a5c" },
 ]
-provides-extras = ["modal", "daytona", "dev", "messaging", "cron", "slack", "matrix", "cli", "tts-premium", "voice", "pty", "honcho", "mcp", "homeassistant", "sms", "acp", "mistral", "bedrock", "termux", "dingtalk", "feishu", "web", "rl", "yc-bench", "all"]
+provides-extras = ["modal", "daytona", "dev", "messaging", "cron", "slack", "matrix", "cli", "tts-premium", "voice", "pty", "honcho", "mcp", "homeassistant", "sms", "acp", "mistral", "bedrock", "termux", "dingtalk", "feishu", "google", "web", "rl", "yc-bench", "all"]
 
 [[package]]
 name = "hf-transfer"
@@ -2238,6 +2321,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784, upload-time = "2025-04-24T22:06:20.566Z" },
 ]
 
+[[package]]
+name = "httplib2"
+version = "0.31.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pyparsing" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c1/1f/e86365613582c027dda5ddb64e1010e57a3d53e99ab8a72093fa13d565ec/httplib2-0.31.2.tar.gz", hash = "sha256:385e0869d7397484f4eab426197a4c020b606edd43372492337c0b4010ae5d24", size = 250800, upload-time = "2026-01-23T11:04:44.165Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2f/90/fd509079dfcab01102c0fdd87f3a9506894bc70afcf9e9785ef6b2b3aff6/httplib2-0.31.2-py3-none-any.whl", hash = "sha256:dbf0c2fa3862acf3c55c078ea9c0bc4481d7dc5117cae71be9514912cf9f8349", size = 91099, upload-time = "2026-01-23T11:04:42.78Z" },
+]
+
 [[package]]
 name = "httptools"
 version = "0.7.1"
@@ -3277,6 +3372,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/57/a7/b35835e278c18b85206834b3aa3abe68e77a98769c59233d1f6300284781/numpy-2.4.3-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:4b42639cdde6d24e732ff823a3fa5b701d8acad89c4142bc1d0bd6dc85200ba5", size = 12504685, upload-time = "2026-03-09T07:58:50.525Z" },
 ]
 
+[[package]]
+name = "oauthlib"
+version = "3.3.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/0b/5f/19930f824ffeb0ad4372da4812c50edbd1434f678c90c2733e1188edfc63/oauthlib-3.3.1.tar.gz", hash = "sha256:0f0f8aa759826a193cf66c12ea1af1637f87b9b4622d46e866952bb022e538c9", size = 185918, upload-time = "2025-06-19T22:48:08.269Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/be/9c/92789c596b8df838baa98fa71844d84283302f7604ed565dafe5a6b5041a/oauthlib-3.3.1-py3-none-any.whl", hash = "sha256:88119c938d2b8fb88561af5f6ee0eec8cc8d552b7bb1f712743136eb7523b7a1", size = 160065, upload-time = "2025-06-19T22:48:06.508Z" },
+]
+
 [[package]]
 name = "obstore"
 version = "0.8.2"
@@ -3855,6 +3959,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/5b/5a/bc7b4a4ef808fa59a816c17b20c4bef6884daebbdf627ff2a161da67da19/propcache-0.4.1-py3-none-any.whl", hash = "sha256:af2a6052aeb6cf17d3e46ee169099044fd8224cbaf75c76a2ef596e8163e2237", size = 13305, upload-time = "2025-10-08T19:49:00.792Z" },
 ]
 
+[[package]]
+name = "proto-plus"
+version = "1.27.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/81/0d/94dfe80193e79d55258345901acd2917523d56e8381bc4dee7fd38e3868a/proto_plus-1.27.2.tar.gz", hash = "sha256:b2adde53adadf75737c44d3dcb0104fde65250dfc83ad59168b4aa3e574b6a24", size = 57204, upload-time = "2026-03-26T22:18:57.174Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/84/f3/1fba73eeffafc998a25d59703b63f8be4fe8a5cb12eaff7386a0ba0f7125/proto_plus-1.27.2-py3-none-any.whl", hash = "sha256:6432f75893d3b9e70b9c412f1d2f03f65b11fb164b793d14ae2ca01821d22718", size = 50450, upload-time = "2026-03-26T22:13:42.927Z" },
+]
+
 [[package]]
 name = "protobuf"
 version = "6.33.5"
@@ -3929,6 +4045,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/50/f2/c0e76a0b451ffdf0cf788932e182758eb7558953f4f27f1aff8e2518b653/pyarrow-23.0.1-cp314-cp314t-win_amd64.whl", hash = "sha256:527e8d899f14bd15b740cd5a54ad56b7f98044955373a17179d5956ddb93d9ce", size = 28365807, upload-time = "2026-02-16T10:14:03.892Z" },
 ]
 
+[[package]]
+name = "pyasn1"
+version = "0.6.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5c/5f/6583902b6f79b399c9c40674ac384fd9cd77805f9e6205075f828ef11fb2/pyasn1-0.6.3.tar.gz", hash = "sha256:697a8ecd6d98891189184ca1fa05d1bb00e2f84b5977c481452050549c8a72cf", size = 148685, upload-time = "2026-03-17T01:06:53.382Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5d/a0/7d793dce3fa811fe047d6ae2431c672364b462850c6235ae306c0efd025f/pyasn1-0.6.3-py3-none-any.whl", hash = "sha256:a80184d120f0864a52a073acc6fc642847d0be408e7c7252f31390c0f4eadcde", size = 83997, upload-time = "2026-03-17T01:06:52.036Z" },
+]
+
+[[package]]
+name = "pyasn1-modules"
+version = "0.4.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pyasn1" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e9/e6/78ebbb10a8c8e4b61a59249394a4a594c1a7af95593dc933a349c8d00964/pyasn1_modules-0.4.2.tar.gz", hash = "sha256:677091de870a80aae844b1ca6134f54652fa2c8c5a52aa396440ac3106e941e6", size = 307892, upload-time = "2025-03-28T02:41:22.17Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/47/8d/d529b5d697919ba8c11ad626e835d4039be708a35b0d22de83a269a6682c/pyasn1_modules-0.4.2-py3-none-any.whl", hash = "sha256:29253a9207ce32b64c3ac6600edc75368f98473906e8fd1043bd6b5b1de2c14a", size = 181259, upload-time = "2025-03-28T02:41:19.028Z" },
+]
+
 [[package]]
 name = "pycparser"
 version = "3.0"
@@ -4529,6 +4666,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/56/5d/c814546c2333ceea4ba42262d8c4d55763003e767fa169adc693bd524478/requests-2.33.0-py3-none-any.whl", hash = "sha256:3324635456fa185245e24865e810cecec7b4caf933d7eb133dcde67d48cee69b", size = 65017, upload-time = "2026-03-25T15:10:40.382Z" },
 ]
 
+[[package]]
+name = "requests-oauthlib"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "oauthlib" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/42/f2/05f29bc3913aea15eb670be136045bf5c5bbf4b99ecb839da9b422bb2c85/requests-oauthlib-2.0.0.tar.gz", hash = "sha256:b3dffaebd884d8cd778494369603a9e7b58d29111bf6b41bdc2dcd87203af4e9", size = 55650, upload-time = "2024-03-22T20:32:29.939Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3b/5d/63d4ae3b9daea098d5d6f5da83984853c1bbacd5dc826764b249fe119d24/requests_oauthlib-2.0.0-py2.py3-none-any.whl", hash = "sha256:7dd8a5c40426b779b0868c404bdef9768deccf22749cde15852df527e6269b36", size = 24179, upload-time = "2024-03-22T20:32:28.055Z" },
+]
+
 [[package]]
 name = "requests-toolbelt"
 version = "1.0.0"
@@ -4664,27 +4814,27 @@ wheels = [
 
 [[package]]
 name = "ruff"
-version = "0.15.10"
+version = "0.15.11"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/e7/d9/aa3f7d59a10ef6b14fe3431706f854dbf03c5976be614a9796d36326810c/ruff-0.15.10.tar.gz", hash = "sha256:d1f86e67ebfdef88e00faefa1552b5e510e1d35f3be7d423dc7e84e63788c94e", size = 4631728, upload-time = "2026-04-09T14:06:09.884Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e4/8d/192f3d7103816158dfd5ea50d098ef2aec19194e6cbccd4b3485bdb2eb2d/ruff-0.15.11.tar.gz", hash = "sha256:f092b21708bf0e7437ce9ada249dfe688ff9a0954fc94abab05dcea7dcd29c33", size = 4637264, upload-time = "2026-04-16T18:46:26.58Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/eb/00/a1c2fdc9939b2c03691edbda290afcd297f1f389196172826b03d6b6a595/ruff-0.15.10-py3-none-linux_armv6l.whl", hash = "sha256:0744e31482f8f7d0d10a11fcbf897af272fefdfcb10f5af907b18c2813ff4d5f", size = 10563362, upload-time = "2026-04-09T14:06:21.189Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/15/006990029aea0bebe9d33c73c3e28c80c391ebdba408d1b08496f00d422d/ruff-0.15.10-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:b1e7c16ea0ff5a53b7c2df52d947e685973049be1cdfe2b59a9c43601897b22e", size = 10951122, upload-time = "2026-04-09T14:06:02.236Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/c0/4ac978fe874d0618c7da647862afe697b281c2806f13ce904ad652fa87e4/ruff-0.15.10-py3-none-macosx_11_0_arm64.whl", hash = "sha256:93cc06a19e5155b4441dd72808fdf84290d84ad8a39ca3b0f994363ade4cebb1", size = 10314005, upload-time = "2026-04-09T14:06:00.026Z" },
-    { url = "https://files.pythonhosted.org/packages/da/73/c209138a5c98c0d321266372fc4e33ad43d506d7e5dd817dd89b60a8548f/ruff-0.15.10-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83e1dd04312997c99ea6965df66a14fb4f03ba978564574ffc68b0d61fd3989e", size = 10643450, upload-time = "2026-04-09T14:05:42.137Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/76/0deec355d8ec10709653635b1f90856735302cb8e149acfdf6f82a5feb70/ruff-0.15.10-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8154d43684e4333360fedd11aaa40b1b08a4e37d8ffa9d95fee6fa5b37b6fab1", size = 10379597, upload-time = "2026-04-09T14:05:49.984Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/be/86bba8fc8798c081e28a4b3bb6d143ccad3fd5f6f024f02002b8f08a9fa3/ruff-0.15.10-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ab88715f3a6deb6bde6c227f3a123410bec7b855c3ae331b4c006189e895cef", size = 11146645, upload-time = "2026-04-09T14:06:12.246Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/89/140025e65911b281c57be1d385ba1d932c2366ca88ae6663685aed8d4881/ruff-0.15.10-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a768ff5969b4f44c349d48edf4ab4f91eddb27fd9d77799598e130fb628aa158", size = 12030289, upload-time = "2026-04-09T14:06:04.776Z" },
-    { url = "https://files.pythonhosted.org/packages/88/de/ddacca9545a5e01332567db01d44bd8cf725f2db3b3d61a80550b48308ea/ruff-0.15.10-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ee3ef42dab7078bda5ff6a1bcba8539e9857deb447132ad5566a038674540d0", size = 11496266, upload-time = "2026-04-09T14:05:55.485Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/bb/7ddb00a83760ff4a83c4e2fc231fd63937cc7317c10c82f583302e0f6586/ruff-0.15.10-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:51cb8cc943e891ba99989dd92d61e29b1d231e14811db9be6440ecf25d5c1609", size = 11256418, upload-time = "2026-04-09T14:05:57.69Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/8d/55de0d35aacf6cd50b6ee91ee0f291672080021896543776f4170fc5c454/ruff-0.15.10-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:e59c9bdc056a320fb9ea1700a8d591718b8faf78af065484e801258d3a76bc3f", size = 11288416, upload-time = "2026-04-09T14:05:44.695Z" },
-    { url = "https://files.pythonhosted.org/packages/68/cf/9438b1a27426ec46a80e0a718093c7f958ef72f43eb3111862949ead3cc1/ruff-0.15.10-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:136c00ca2f47b0018b073f28cb5c1506642a830ea941a60354b0e8bc8076b151", size = 10621053, upload-time = "2026-04-09T14:05:52.782Z" },
-    { url = "https://files.pythonhosted.org/packages/4c/50/e29be6e2c135e9cd4cb15fbade49d6a2717e009dff3766dd080fcb82e251/ruff-0.15.10-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:8b80a2f3c9c8a950d6237f2ca12b206bccff626139be9fa005f14feb881a1ae8", size = 10378302, upload-time = "2026-04-09T14:06:14.361Z" },
-    { url = "https://files.pythonhosted.org/packages/18/2f/e0b36a6f99c51bb89f3a30239bc7bf97e87a37ae80aa2d6542d6e5150364/ruff-0.15.10-py3-none-musllinux_1_2_i686.whl", hash = "sha256:e3e53c588164dc025b671c9df2462429d60357ea91af7e92e9d56c565a9f1b07", size = 10850074, upload-time = "2026-04-09T14:06:16.581Z" },
-    { url = "https://files.pythonhosted.org/packages/11/08/874da392558ce087a0f9b709dc6ec0d60cbc694c1c772dab8d5f31efe8cb/ruff-0.15.10-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:b0c52744cf9f143a393e284125d2576140b68264a93c6716464e129a3e9adb48", size = 11358051, upload-time = "2026-04-09T14:06:18.948Z" },
-    { url = "https://files.pythonhosted.org/packages/e4/46/602938f030adfa043e67112b73821024dc79f3ab4df5474c25fa4c1d2d14/ruff-0.15.10-py3-none-win32.whl", hash = "sha256:d4272e87e801e9a27a2e8df7b21011c909d9ddd82f4f3281d269b6ba19789ca5", size = 10588964, upload-time = "2026-04-09T14:06:07.14Z" },
-    { url = "https://files.pythonhosted.org/packages/25/b6/261225b875d7a13b33a6d02508c39c28450b2041bb01d0f7f1a83d569512/ruff-0.15.10-py3-none-win_amd64.whl", hash = "sha256:28cb32d53203242d403d819fd6983152489b12e4a3ae44993543d6fe62ab42ed", size = 11745044, upload-time = "2026-04-09T14:05:39.473Z" },
-    { url = "https://files.pythonhosted.org/packages/58/ed/dea90a65b7d9e69888890fb14c90d7f51bf0c1e82ad800aeb0160e4bacfd/ruff-0.15.10-py3-none-win_arm64.whl", hash = "sha256:601d1610a9e1f1c2165a4f561eeaa2e2ea1e97f3287c5aa258d3dab8b57c6188", size = 11035607, upload-time = "2026-04-09T14:05:47.593Z" },
+    { url = "https://files.pythonhosted.org/packages/02/1e/6aca3427f751295ab011828e15e9bf452200ac74484f1db4be0197b8170b/ruff-0.15.11-py3-none-linux_armv6l.whl", hash = "sha256:e927cfff503135c558eb581a0c9792264aae9507904eb27809cdcff2f2c847b7", size = 10607943, upload-time = "2026-04-16T18:46:05.967Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/26/1341c262e74f36d4e84f3d6f4df0ac68cd53331a66bfc5080daa17c84c0b/ruff-0.15.11-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:7a1b5b2938d8f890b76084d4fa843604d787a912541eae85fd7e233398bbb73e", size = 10988592, upload-time = "2026-04-16T18:46:00.742Z" },
+    { url = "https://files.pythonhosted.org/packages/03/71/850b1d6ffa9564fbb6740429bad53df1094082fe515c8c1e74b6d8d05f18/ruff-0.15.11-py3-none-macosx_11_0_arm64.whl", hash = "sha256:d4176f3d194afbdaee6e41b9ccb1a2c287dba8700047df474abfbe773825d1cb", size = 10338501, upload-time = "2026-04-16T18:46:03.723Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/11/cc1284d3e298c45a817a6aadb6c3e1d70b45c9b36d8d9cce3387b495a03a/ruff-0.15.11-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3b17c886fb88203ced3afe7f14e8d5ae96e9d2f4ccc0ee66aa19f2c2675a27e4", size = 10670693, upload-time = "2026-04-16T18:46:41.941Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/9e/f8288b034ab72b371513c13f9a41d9ba3effac54e24bfb467b007daee2ca/ruff-0.15.11-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:49fafa220220afe7758a487b048de4c8f9f767f37dfefad46b9dd06759d003eb", size = 10416177, upload-time = "2026-04-16T18:46:21.717Z" },
+    { url = "https://files.pythonhosted.org/packages/85/71/504d79abfd3d92532ba6bbe3d1c19fada03e494332a59e37c7c2dabae427/ruff-0.15.11-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2ab8427e74a00d93b8bda1307b1e60970d40f304af38bccb218e056c220120d", size = 11221886, upload-time = "2026-04-16T18:46:15.086Z" },
+    { url = "https://files.pythonhosted.org/packages/43/5a/947e6ab7a5ad603d65b474be15a4cbc6d29832db5d762cd142e4e3a74164/ruff-0.15.11-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:195072c0c8e1fc8f940652073df082e37a5d9cb43b4ab1e4d0566ab8977a13b7", size = 12075183, upload-time = "2026-04-16T18:46:07.944Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/a1/0b7bb6268775fdd3a0818aee8efd8f5b4e231d24dd4d528ced2534023182/ruff-0.15.11-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a3a0996d486af3920dec930a2e7daed4847dfc12649b537a9335585ada163e9e", size = 11516575, upload-time = "2026-04-16T18:46:31.687Z" },
+    { url = "https://files.pythonhosted.org/packages/30/c3/bb5168fc4d233cc06e95f482770d0f3c87945a0cd9f614b90ea8dc2f2833/ruff-0.15.11-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1bef2cb556d509259f1fe440bb9cd33c756222cf0a7afe90d15edf0866702431", size = 11306537, upload-time = "2026-04-16T18:46:36.988Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/92/4cfae6441f3967317946f3b788136eecf093729b94d6561f963ed810c82e/ruff-0.15.11-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:030d921a836d7d4a12cf6e8d984a88b66094ccb0e0f17ddd55067c331191bf19", size = 11296813, upload-time = "2026-04-16T18:46:24.182Z" },
+    { url = "https://files.pythonhosted.org/packages/43/26/972784c5dde8313acde8ac71ba8ac65475b85db4a2352a76c9934361f9bc/ruff-0.15.11-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:0e783b599b4577788dbbb66b9addcef87e9a8832f4ce0c19e34bf55543a2f890", size = 10633136, upload-time = "2026-04-16T18:46:39.802Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/53/3985a4f185020c2f367f2e08a103032e12564829742a1b417980ce1514a0/ruff-0.15.11-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:ae90592246625ba4a34349d68ec28d4400d75182b71baa196ddb9f82db025ef5", size = 10424701, upload-time = "2026-04-16T18:46:10.381Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/57/bf0dfb32241b56c83bb663a826133da4bf17f682ba8c096973065f6e6a68/ruff-0.15.11-py3-none-musllinux_1_2_i686.whl", hash = "sha256:1f111d62e3c983ed20e0ca2e800f8d77433a5b1161947df99a5c2a3fb60514f0", size = 10873887, upload-time = "2026-04-16T18:46:29.157Z" },
+    { url = "https://files.pythonhosted.org/packages/02/05/e48076b2a57dc33ee8c7a957296f97c744ca891a8ffb4ffb1aaa3b3f517d/ruff-0.15.11-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:06f483d6646f59eaffba9ae30956370d3a886625f511a3108994000480621d1c", size = 11404316, upload-time = "2026-04-16T18:46:19.462Z" },
+    { url = "https://files.pythonhosted.org/packages/88/27/0195d15fe7a897cbcba0904792c4b7c9fdd958456c3a17d2ea6093716a9a/ruff-0.15.11-py3-none-win32.whl", hash = "sha256:476a2aa56b7da0b73a3ee80b6b2f0e19cce544245479adde7baa65466664d5f3", size = 10655535, upload-time = "2026-04-16T18:46:12.47Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/5e/c927b325bd4c1d3620211a4b96f47864633199feed60fa936025ab27e090/ruff-0.15.11-py3-none-win_amd64.whl", hash = "sha256:8b6756d88d7e234fb0c98c91511aae3cd519d5e3ed271cae31b20f39cb2a12a3", size = 11779692, upload-time = "2026-04-16T18:46:17.268Z" },
+    { url = "https://files.pythonhosted.org/packages/63/b6/aeadee5443e49baa2facd51131159fd6301cc4ccfc1541e4df7b021c37dd/ruff-0.15.11-py3-none-win_arm64.whl", hash = "sha256:063fed18cc1bbe0ee7393957284a6fe8b588c6a406a285af3ee3f46da2391ee4", size = 11032614, upload-time = "2026-04-16T18:46:34.487Z" },
 ]
 
 [[package]]
@@ -5268,6 +5418,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4c/a7/563b2d8fb7edc07320bf69ac6a7eedcd7a1a9d663a6bb90a4d9bd2eda5f7/unpaddedbase64-2.1.0-py3-none-any.whl", hash = "sha256:485eff129c30175d2cd6f0cd8d2310dff51e666f7f36175f738d75dfdbd0b1c6", size = 6083, upload-time = "2021-03-09T11:35:46.7Z" },
 ]
 
+[[package]]
+name = "uritemplate"
+version = "4.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/98/60/f174043244c5306c9988380d2cb10009f91563fc4b31293d27e17201af56/uritemplate-4.2.0.tar.gz", hash = "sha256:480c2ed180878955863323eea31b0ede668795de182617fef9c6ca09e6ec9d0e", size = 33267, upload-time = "2025-06-02T15:12:06.318Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a9/99/3ae339466c9183ea5b8ae87b34c0b897eda475d2aec2307cae60e5cd4f29/uritemplate-4.2.0-py3-none-any.whl", hash = "sha256:962201ba1c4edcab02e60f9a0d3821e82dfc5d2d6662a21abd533879bdb8a686", size = 11488, upload-time = "2025-06-02T15:12:03.405Z" },
+]
+
 [[package]]
 name = "urllib3"
 version = "2.6.3"

website/docs/developer-guide/adding-providers.md

@@ -93,6 +93,42 @@ This path includes everything from Path A plus:
 11. `run_agent.py`
 12. `pyproject.toml` if a provider SDK is required
 
+## Fast path: Simple API-key providers
+
+If your provider is just an OpenAI-compatible endpoint that authenticates with a single API key, you do not need to touch `auth.py`, `runtime_provider.py`, `main.py`, or any of the other files in the full checklist below.
+
+All you need is:
+
+1. A file in `providers/` (e.g. `providers/myprovider.py`) that calls `register_provider()` with the provider config.
+2. That's it. `auth.py` auto-registers every file in `providers/` at startup via a module-level import sweep.
+
+When you add a `providers/*.py` file and call `register_provider()`, the following wire up automatically:
+
+1. `PROVIDER_REGISTRY` entry in `auth.py` (credential resolution, env-var lookup)
+2. `api_mode` set to `chat_completions`
+3. `base_url` sourced from the config or the declared env var
+4. `env_vars` checked in priority order for the API key
+5. `fallback_models` list registered for the provider
+6. `--provider` CLI flag accepts the provider id
+7. `hermes model` menu includes the provider
+8. `hermes setup` wizard delegates to `main.py` automatically
+9. `provider:model` alias syntax works
+10. Runtime resolver returns the correct `base_url` and `api_key`
+11. `HERMES_INFERENCE_PROVIDER` env-var override accepts the provider id
+12. Fallback model activation can switch into the provider cleanly
+
+See `providers/nvidia.py` or `providers/gmi.py` as a template.
+
+## Full path: OAuth and complex providers
+
+Use the full checklist below when your provider needs any of the following:
+
+- OAuth or token refresh (Nous Portal, Codex, Google Gemini, Qwen Portal, Copilot)
+- A non-OpenAI API shape that requires a new adapter (Anthropic Messages, Codex Responses)
+- Custom endpoint detection or multi-region probing (z.ai, Kimi)
+- A curated static model catalog or live `/models` fetch
+- Provider-specific `hermes model` menu entries with bespoke auth flows
+
 ## Step 1: Pick one canonical provider id
 
 Choose a single provider id and use it everywhere.

website/docs/developer-guide/provider-runtime.md

@@ -20,6 +20,9 @@ Primary implementation:
 - `hermes_cli/auth.py` — provider registry, `resolve_provider()`
 - `hermes_cli/model_switch.py` — shared `/model` switch pipeline (CLI + gateway)
 - `agent/auxiliary_client.py` — auxiliary model routing
+- `providers/` — declarative source for `api_mode`, `base_url`, `env_vars`, `fallback_models` (auto-registered into `auth.py` `PROVIDER_REGISTRY` at startup)
+
+`get_provider_profile()` in `providers/` returns a typed dict for a given provider id. `runtime_provider.py` calls this at resolution time to get the canonical `base_url`, `env_vars` priority list, `api_mode`, and `fallback_models` without needing to duplicate that data in multiple files. Adding a new `providers/*.py` file that calls `register_provider()` is enough for `runtime_provider.py` to pick it up — no branch needed in the resolver itself.
 
 If you are trying to add a new first-class inference provider, read [Adding Providers](./adding-providers.md) alongside this page.
 

website/docs/integrations/providers.md

@@ -423,6 +423,44 @@ model:
 For on-prem deployments (DGX Spark, local GPU), set `NVIDIA_BASE_URL=http://localhost:8000/v1`. NIM exposes the same OpenAI-compatible chat completions API as build.nvidia.com, so switching between cloud and local is a one-line env-var change.
 :::
 
+### GMI Cloud
+
+Open and reasoning models via [GMI Cloud](https://inference.gmi.ai) — OpenAI-compatible API, API key authentication.
+
+```bash
+# GMI Cloud
+hermes chat --provider gmi --model deepseek-ai/DeepSeek-R1
+# Requires: GMI_API_KEY in ~/.hermes/.env
+```
+
+Or set it permanently in `config.yaml`:
+```yaml
+model:
+  provider: "gmi"
+  default: "deepseek-ai/DeepSeek-R1"
+```
+
+The base URL can be overridden with `GMI_BASE_URL` (default: `https://api.gmi.ai/v1`).
+
+### StepFun
+
+Step-series models via [StepFun](https://platform.stepfun.com) — OpenAI-compatible API, API key authentication.
+
+```bash
+# StepFun
+hermes chat --provider stepfun --model step-3-mini
+# Requires: STEPFUN_API_KEY in ~/.hermes/.env
+```
+
+Or set it permanently in `config.yaml`:
+```yaml
+model:
+  provider: "stepfun"
+  default: "step-3-mini"
+```
+
+The base URL can be overridden with `STEPFUN_BASE_URL` (default: `https://api.stepfun.com/v1`).
+
 ### Hugging Face Inference Providers
 
 [Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers) routes to 20+ open models through a unified OpenAI-compatible endpoint (`router.huggingface.co/v1`). Requests are automatically routed to the fastest available backend (Groq, Together, SambaNova, etc.) with automatic failover.
@@ -1178,7 +1216,7 @@ fallback_model:
 
 When activated, the fallback swaps the model and provider mid-session without losing your conversation. It fires **at most once** per session.
 
-Supported providers: `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `google-gemini-cli`, `qwen-oauth`, `huggingface`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `deepseek`, `nvidia`, `xai`, `ollama-cloud`, `bedrock`, `ai-gateway`, `opencode-zen`, `opencode-go`, `kilocode`, `xiaomi`, `arcee`, `gmi`, `alibaba`, `custom`.
+Supported providers: `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `google-gemini-cli`, `qwen-oauth`, `huggingface`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `deepseek`, `nvidia`, `gmi`, `stepfun`, `xai`, `ollama-cloud`, `bedrock`, `ai-gateway`, `opencode-zen`, `opencode-go`, `kilocode`, `xiaomi`, `arcee`, `alibaba`, `custom`.
 
 :::tip
 Fallback is configured exclusively through `config.yaml` — there are no environment variables for it. For full details on when it triggers, supported providers, and how it interacts with auxiliary tasks and delegation, see [Fallback Providers](/docs/user-guide/features/fallback-providers).

website/docs/reference/environment-variables.md

@@ -65,6 +65,10 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `DEEPSEEK_BASE_URL` | Custom DeepSeek API base URL |
 | `NVIDIA_API_KEY` | NVIDIA NIM API key — Nemotron and open models ([build.nvidia.com](https://build.nvidia.com)) |
 | `NVIDIA_BASE_URL` | Override NVIDIA base URL (default: `https://integrate.api.nvidia.com/v1`; set to `http://localhost:8000/v1` for a local NIM endpoint) |
+| `GMI_API_KEY` | GMI Cloud API key — open and reasoning models ([inference.gmi.ai](https://inference.gmi.ai)) |
+| `GMI_BASE_URL` | Override GMI Cloud base URL (default: `https://api.gmi.ai/v1`) |
+| `STEPFUN_API_KEY` | StepFun API key — Step-series models ([platform.stepfun.com](https://platform.stepfun.com)) |
+| `STEPFUN_BASE_URL` | Override StepFun base URL (default: `https://api.stepfun.com/v1`) |
 | `OLLAMA_API_KEY` | Ollama Cloud API key — managed Ollama catalog without local GPU ([ollama.com/settings/keys](https://ollama.com/settings/keys)) |
 | `OLLAMA_BASE_URL` | Override Ollama Cloud base URL (default: `https://ollama.com/v1`) |
 | `XAI_API_KEY` | xAI (Grok) API key for chat + TTS ([console.x.ai](https://console.x.ai/)) |
@@ -91,7 +95,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 
 | Variable | Description |
 |----------|-------------|
-| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `custom`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `gemini`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `kilocode`, `xiaomi`, `arcee`, `gmi`, `alibaba`, `deepseek`, `nvidia`, `ollama-cloud`, `xai` (alias `grok`), `google-gemini-cli`, `qwen-oauth`, `bedrock`, `opencode-zen`, `opencode-go`, `ai-gateway` (default: `auto`) |
+| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `custom`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `gemini`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `kilocode`, `xiaomi`, `arcee`, `gmi`, `stepfun`, `alibaba`, `deepseek`, `nvidia`, `ollama-cloud`, `xai` (alias `grok`), `google-gemini-cli`, `qwen-oauth`, `bedrock`, `opencode-zen`, `opencode-go`, `ai-gateway` (default: `auto`) |
 | `HERMES_PORTAL_BASE_URL` | Override Nous Portal URL (for development/testing) |
 | `NOUS_INFERENCE_BASE_URL` | Override Nous inference API URL |
 | `HERMES_NOUS_MIN_KEY_TTL_SECONDS` | Min agent key TTL before re-mint (default: 1800 = 30min) |

website/docs/user-guide/features/fallback-providers.md

@@ -48,6 +48,8 @@ Both `provider` and `model` are **required**. If either is missing, the fallback
 | MiniMax (China) | `minimax-cn` | `MINIMAX_CN_API_KEY` |
 | DeepSeek | `deepseek` | `DEEPSEEK_API_KEY` |
 | NVIDIA NIM | `nvidia` | `NVIDIA_API_KEY` (optional: `NVIDIA_BASE_URL`) |
+| GMI Cloud | `gmi` | `GMI_API_KEY` (optional: `GMI_BASE_URL`) |
+| StepFun | `stepfun` | `STEPFUN_API_KEY` (optional: `STEPFUN_BASE_URL`) |
 | Ollama Cloud | `ollama-cloud` | `OLLAMA_API_KEY` |
 | Google Gemini (OAuth) | `google-gemini-cli` | `hermes model` (Google OAuth; optional: `HERMES_GEMINI_PROJECT_ID`) |
 | Google AI Studio | `gemini` | `GOOGLE_API_KEY` (alias: `GEMINI_API_KEY`) |