dostuff 0.2.2__tar.gz → 0.2.3__tar.gz

{dostuff-0.2.2 → dostuff-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dostuff
-Version: 0.2.2
+Version: 0.2.3
 Summary: DoStuff - a terminal coding agent for any LLM: TUI and headless mode, permissions, MCP, skills, web tools, sessions and git worktrees
 Author-email: Varun Kumawat <varunkumawatleap2@gmail.com>
 License-Expression: MIT
@@ -352,7 +352,7 @@ models:
 loop:
   max_iterations: 100
   subagent_max_iterations: 25
-  # context_window: 128000       # override when litellm doesn't know the model
+  # context_window: 128000       # override when dostuff/litellm don't know the model
   max_tool_output_chars: 30000   # longer tool results keep head + tail
   max_retries: 6                 # retries on rate limits, timeouts, 5xx (0 = none)
   retry_max_delay: 60            # cap on each wait, seconds; Retry-After is honored
@@ -416,6 +416,8 @@ or `/model` inside the TUI. Model lists come from litellm's catalog (chat models
 
 OpenCode models (`opencode/<id>` for Zen, `opencode-go/<id>` for a Go subscription) use the ids from the [OpenCode docs](https://opencode.ai/docs/zen/). litellm has no OpenCode provider, so DoStuff sends each model to the gateway endpoint for its family: Claude models (and a few Qwen / MiniMax models) to the Anthropic Messages endpoint, GPT / Grok / Muse models to the Responses endpoint, Gemini models to the Gemini endpoint, and all other models to chat completions. One console key in `OPENCODE_API_KEY` works for Zen and Go. OpenCode only allows its free models from its own app, so use paid models or Go.
 
+The gateways don't publish a model's context window in `/v1/models`, so `helpers/models/opencode.py` carries one per model, taken from [models.dev](https://models.dev)'s `opencode` and `opencode-go` entries (the same id can differ per gateway: `opencode/minimax-m3` is 512k, `opencode-go/minimax-m3` is 1M). `/context`, the status bar and auto-compaction size themselves from it; set `loop.context_window` to override.
+
 ---
 
 ## MCP servers

{dostuff-0.2.2 → dostuff-0.2.3}/README.md

@@ -304,7 +304,7 @@ models:
 loop:
   max_iterations: 100
   subagent_max_iterations: 25
-  # context_window: 128000       # override when litellm doesn't know the model
+  # context_window: 128000       # override when dostuff/litellm don't know the model
   max_tool_output_chars: 30000   # longer tool results keep head + tail
   max_retries: 6                 # retries on rate limits, timeouts, 5xx (0 = none)
   retry_max_delay: 60            # cap on each wait, seconds; Retry-After is honored
@@ -368,6 +368,8 @@ or `/model` inside the TUI. Model lists come from litellm's catalog (chat models
 
 OpenCode models (`opencode/<id>` for Zen, `opencode-go/<id>` for a Go subscription) use the ids from the [OpenCode docs](https://opencode.ai/docs/zen/). litellm has no OpenCode provider, so DoStuff sends each model to the gateway endpoint for its family: Claude models (and a few Qwen / MiniMax models) to the Anthropic Messages endpoint, GPT / Grok / Muse models to the Responses endpoint, Gemini models to the Gemini endpoint, and all other models to chat completions. One console key in `OPENCODE_API_KEY` works for Zen and Go. OpenCode only allows its free models from its own app, so use paid models or Go.
 
+The gateways don't publish a model's context window in `/v1/models`, so `helpers/models/opencode.py` carries one per model, taken from [models.dev](https://models.dev)'s `opencode` and `opencode-go` entries (the same id can differ per gateway: `opencode/minimax-m3` is 512k, `opencode-go/minimax-m3` is 1M). `/context`, the status bar and auto-compaction size themselves from it; set `loop.context_window` to override.
+
 ---
 
 ## MCP servers

dostuff-0.2.3/dostuff/helpers/agent/get_model_token_limit.py

@@ -0,0 +1,54 @@
+import litellm
+from dostuff.config import get_config
+from dostuff.helpers.models.opencode import context_window, is_opencode
+from dostuff.lib.model import get_litellm_model, get_model
+
+FALLBACK_CONTEXT_WINDOW = 128_000
+_warned_models: set[str] = set()
+
+
+def _litellm_limit(model: str) -> int | None:
+    """litellm's `max_input_tokens` for `model`, or None when it doesn't map it."""
+    try:
+        limit = litellm.get_model_info(model=model).get("max_input_tokens")
+    except Exception:
+        return None
+    return int(limit) if limit else None
+
+
+def get_model_token_limit() -> int:
+    """Context window for the active model: `loop.context_window`, else the OpenCode table, else
+    litellm's model info, else 128k.
+
+    OpenCode ids are checked against `helpers/models/opencode._CONTEXT_WINDOWS` first: litellm only
+    knows their upstream `openai/` / `anthropic/` route for a few of them, and the same id can have a
+    different window on each gateway.
+    """
+    configured = get_config().context_window
+    if configured > 0:
+        return configured
+    opencode = is_opencode(get_config().provider)
+    if opencode:
+        model_id = get_model().split("/", 1)[-1]
+        known = context_window(get_config().provider, model_id)
+        if known:
+            return known
+    model = get_litellm_model()
+    limit = _litellm_limit(model)
+    if limit:
+        return limit
+    if opencode:
+        # litellm keys some ids only without the route prefix, e.g. `deepseek-v4-pro` (1M) exists
+        # while `openai/deepseek-v4-pro` doesn't.
+        limit = _litellm_limit(get_model().split("/", 1)[-1])
+        if limit:
+            return limit
+    if model not in _warned_models:
+        _warned_models.add(model)
+        from dostuff.helpers.ui.emit import emit
+        emit(
+            f"Unknown context window for '{model}'; assuming {FALLBACK_CONTEXT_WINDOW:,} tokens. "
+            "Set loop.context_window in config.yaml to override.",
+            msg_type="system",
+        )
+    return FALLBACK_CONTEXT_WINDOW

dostuff-0.2.3/dostuff/helpers/models/opencode.py

@@ -0,0 +1,200 @@
+"""OpenCode Zen (`opencode/<id>`) and OpenCode Go (`opencode-go/<id>`) models.
+
+litellm has no OpenCode provider. Each gateway serves a model family on the endpoint of its
+upstream API (https://opencode.ai/docs/zen/), so a model is sent through litellm's openai,
+anthropic or gemini route with the gateway as api_base.
+"""
+import os
+from typing import Any, Literal
+
+OPENCODE_PROVIDERS = {
+    "opencode": "https://opencode.ai/inference",
+    "opencode-go": "https://opencode.ai/inference/go",
+}
+OPENCODE_API_KEY_ENV = "OPENCODE_API_KEY"  # one console key works for Zen and Go
+# Served on the Anthropic Messages endpoint besides Claude; they differ between the gateways
+_ANTHROPIC_IDS = {
+    "opencode": {"qwen3.8-flash", "qwen3.6-plus", "qwen3.5-plus"},
+    "opencode-go": {"qwen3.8-max", "qwen3.8-flash", "qwen3.7-plus", "minimax-m3"},
+}
+# Input-token limit per model, from models.dev's `opencode` / `opencode-go` entries
+# (https://models.dev — the catalog OpenCode's own clients size their context with). The gateways
+# don't publish limits in /v1/models, litellm doesn't map their ids, and the same model can have a
+# different window on each gateway, so this table is the only reliable source. Refresh it when
+# `provider_models()` lists an id that is missing here (those fall back to litellm, then 128k).
+_CONTEXT_WINDOWS = {
+    "opencode": {
+        "beam-free": 1_048_576,
+        "big-pickle": 160_000,
+        "claude-fable-5": 1_000_000,
+        "claude-fable-5-1": 1_000_000,
+        "claude-haiku-4-5": 200_000,
+        "claude-haiku-5-5": 1_000_000,
+        "claude-opus-4-5": 200_000,
+        "claude-opus-4-6": 1_000_000,
+        "claude-opus-4-7": 1_000_000,
+        "claude-opus-4-8": 1_000_000,
+        "claude-opus-5": 1_000_000,
+        "claude-opus-5-5": 1_000_000,
+        "claude-sonnet-4-5": 1_000_000,
+        "claude-sonnet-4-6": 1_000_000,
+        "claude-sonnet-5": 1_000_000,
+        "claude-sonnet-5-5": 1_000_000,
+        "deepseek-v4-pro": 1_000_000,
+        "deepseek-v4.1-flash": 1_000_000,
+        "deepseek-v4.1-flash-free": 200_000,
+        "flint-40b-free": 262_144,
+        "gemini-3-flash": 1_048_576,
+        "gemini-3.1-pro": 1_048_576,
+        "gemini-3.5-flash": 1_048_576,
+        "gemini-3.5-flash-lite": 1_048_576,
+        "gemini-3.6-flash": 1_048_576,
+        "gemini-3.7-flash": 1_048_576,
+        "gemini-3.8-flash": 1_048_576,
+        "gemini-4-argon": 1_048_576,
+        "glm-5": 204_800,
+        "glm-5.1": 204_800,
+        "glm-5.2": 1_000_000,
+        "glm-5.3": 1_000_000,
+        "glm-5.3-flash": 1_000_000,
+        "glm-5.3-flash-free": 200_000,
+        "gpt-5": 272_000,
+        "gpt-5-codex": 272_000,
+        "gpt-5-nano": 272_000,
+        "gpt-5.1": 272_000,
+        "gpt-5.1-codex": 272_000,
+        "gpt-5.1-codex-max": 272_000,
+        "gpt-5.1-codex-mini": 272_000,
+        "gpt-5.2": 272_000,
+        "gpt-5.2-codex": 272_000,
+        "gpt-5.3-codex": 272_000,
+        "gpt-5.3-codex-spark": 128_000,
+        "gpt-5.4": 922_000,
+        "gpt-5.4-mini": 272_000,
+        "gpt-5.4-nano": 272_000,
+        "gpt-5.4-pro": 922_000,
+        "gpt-5.5": 922_000,
+        "gpt-5.5-pro": 922_000,
+        "gpt-5.6-luna": 922_000,
+        "gpt-5.6-sol": 922_000,
+        "gpt-5.6-terra": 922_000,
+        "gpt-6-astra": 922_000,
+        "gpt-6-luna": 922_000,
+        "gpt-6-sol": 922_000,
+        "gpt-6.1-sol": 922_000,
+        "grok-4.5": 500_000,
+        "grok-4.6": 500_000,
+        "grok-4.7": 500_000,
+        "grok-build-0.1": 256_000,
+        "kimi-k2.5": 262_144,
+        "kimi-k2.6": 262_144,
+        "kimi-k2.7-code": 262_144,
+        "kimi-k3": 1_048_576,
+        "mimo-v2.6-flash-free": 200_000,
+        "minimax-m2.5": 204_800,
+        "minimax-m2.7": 204_800,
+        "minimax-m3": 512_000,
+        "mistral-large-4": 524_288,
+        "muse-spark-1.2": 1_048_576,
+        "muse-spark-1.3": 1_048_576,
+        "muse-wonder-1.0": 1_048_576,
+        "nemotron-3.5-lightning-free": 262_144,
+        "nemotron-3.5-super-vl-free": 1_048_576,
+        "qwen3.5-plus": 262_144,
+        "qwen3.6-plus": 262_144,
+        "qwen3.8-flash": 1_000_000,
+        "qwen3.8-max": 262_144,
+    },
+    "opencode-go": {
+        "beam-free": 1_048_576,
+        "claude-haiku-5-5": 1_000_000,
+        "deepseek-v4-pro": 1_000_000,
+        "deepseek-v4.1-flash": 1_000_000,
+        "gemini-4-argon": 1_048_576,
+        "glm-5.2": 1_000_000,
+        "glm-5.3": 1_000_000,
+        "glm-5.3-flash": 1_000_000,
+        "gpt-5.6-luna": 922_000,
+        "gpt-6-luna": 922_000,
+        "grok-4.7": 500_000,
+        "hy3": 192_000,
+        "hy4-preview": 1_024_000,
+        "iceman-contributor-free": 262_144,
+        "kimi-k2.7-code": 262_144,
+        "kimi-k3": 1_048_576,
+        "kimi-k3.1-pro": 1_048_576,
+        "longcat-2.0": 1_000_000,
+        "mimo-v2.6-flash": 1_048_576,
+        "mimo-v2.6-pro": 1_048_576,
+        "minimax-m3": 1_000_000,
+        "minimax-m3.1-flash": 1_000_000,
+        "muse-spark-1.2-contributor": 1_048_576,
+        "muse-spark-1.3-contributor": 1_048_576,
+        "qwen3.7-plus": 1_000_000,
+        "qwen3.8-flash": 1_000_000,
+        "qwen3.8-max": 1_000_000,
+        "step-5-preview": 1_000_000,
+    },
+}
+# In /v1/models but not chat models
+_NOT_CHAT = ("jev-", "test")
+
+Endpoint = Literal["chat", "responses", "anthropic", "google"]
+
+
+def is_opencode(provider: str) -> bool:
+    return provider in OPENCODE_PROVIDERS
+
+
+def context_window(provider: str, model_id: str) -> int | None:
+    """Input-token limit for an OpenCode model id, or None if the table doesn't list it."""
+    return _CONTEXT_WINDOWS.get(provider, {}).get(model_id)
+
+
+def endpoint_for(provider: str, model_id: str) -> Endpoint:
+    """Which upstream API the gateway serves `model_id` on."""
+    if model_id.startswith("claude-") or model_id in _ANTHROPIC_IDS[provider]:
+        return "anthropic"
+    if model_id.startswith(("gpt-", "grok-", "muse-")):
+        return "responses"
+    if model_id.startswith("gemini-"):
+        return "google"
+    return "chat"
+
+
+def litellm_route(provider: str, model_id: str) -> tuple[str, str]:
+    """(litellm model, api_base) for an OpenCode model id."""
+    base = OPENCODE_PROVIDERS[provider]
+    endpoint = endpoint_for(provider, model_id)
+    if endpoint == "anthropic":
+        return f"anthropic/{model_id}", f"{base}/anthropic"  # litellm appends /v1/messages
+    if endpoint == "google":
+        return f"gemini/{model_id}", f"{base}/google/v1beta"
+    if endpoint == "responses":
+        return f"openai/responses/{model_id}", f"{base}/openai/v1"
+    return f"openai/{model_id}", f"{base}/openai/v1"
+
+
+def opencode_kwargs(provider: str, model_id: str, api_key: str | None, session_id: str, version: str) -> dict[str, Any]:
+    """litellm kwargs for an OpenCode model. Go asks clients to name themselves and send a
+    stable per-conversation id; Zen gets the same headers."""
+    model, api_base = litellm_route(provider, model_id)
+    return {
+        "model": model,
+        "api_base": api_base,
+        # Never fall back to OPENAI_API_KEY / ANTHROPIC_API_KEY: those would go to opencode.ai
+        "api_key": api_key or os.environ.get(OPENCODE_API_KEY_ENV) or "missing-opencode-key",
+        "extra_headers": {"User-Agent": f"dostuff/{version}", "x-opencode-session": session_id},
+    }
+
+
+def models_url(provider: str) -> str:
+    return f"{OPENCODE_PROVIDERS[provider]}/v1/models"
+
+
+def chat_model_ids(data: dict) -> list[str]:
+    """Model ids from a /v1/models response, without the non-chat ones."""
+    return [
+        m["id"] for m in data.get("data") or []
+        if isinstance(m, dict) and m.get("id") and not str(m["id"]).startswith(_NOT_CHAT)
+    ]

{dostuff-0.2.2 → dostuff-0.2.3}/dostuff/templates/config.example.yaml

@@ -17,7 +17,7 @@ loop:
   max_iterations: 100  # max agent turns before forced exit; ESC cancels anytime
   subagent_max_iterations: 25  # iteration cap for delegate_to_subagent
   prompt_caching: true  # Claude models: cache the system prompt and history between calls (cheaper, faster)
-  # context_window: 128000     # override the model's context window (tokens) if litellm doesn't know it
+  # context_window: 128000     # override the model's context window (tokens) if dostuff/litellm can't tell
   max_tool_output_chars: 30000 # longer tool results keep head + tail with a truncation marker
   max_retries: 6               # retries on rate limits, timeouts and 5xx (0 = fail at once)
   retry_max_delay: 60          # longest wait between retries, seconds (backoff doubles from 1s; Retry-After is honored)

{dostuff-0.2.2 → dostuff-0.2.3}/dostuff.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dostuff
-Version: 0.2.2
+Version: 0.2.3
 Summary: DoStuff - a terminal coding agent for any LLM: TUI and headless mode, permissions, MCP, skills, web tools, sessions and git worktrees
 Author-email: Varun Kumawat <varunkumawatleap2@gmail.com>
 License-Expression: MIT
@@ -352,7 +352,7 @@ models:
 loop:
   max_iterations: 100
   subagent_max_iterations: 25
-  # context_window: 128000       # override when litellm doesn't know the model
+  # context_window: 128000       # override when dostuff/litellm don't know the model
   max_tool_output_chars: 30000   # longer tool results keep head + tail
   max_retries: 6                 # retries on rate limits, timeouts, 5xx (0 = none)
   retry_max_delay: 60            # cap on each wait, seconds; Retry-After is honored
@@ -416,6 +416,8 @@ or `/model` inside the TUI. Model lists come from litellm's catalog (chat models
 
 OpenCode models (`opencode/<id>` for Zen, `opencode-go/<id>` for a Go subscription) use the ids from the [OpenCode docs](https://opencode.ai/docs/zen/). litellm has no OpenCode provider, so DoStuff sends each model to the gateway endpoint for its family: Claude models (and a few Qwen / MiniMax models) to the Anthropic Messages endpoint, GPT / Grok / Muse models to the Responses endpoint, Gemini models to the Gemini endpoint, and all other models to chat completions. One console key in `OPENCODE_API_KEY` works for Zen and Go. OpenCode only allows its free models from its own app, so use paid models or Go.
 
+The gateways don't publish a model's context window in `/v1/models`, so `helpers/models/opencode.py` carries one per model, taken from [models.dev](https://models.dev)'s `opencode` and `opencode-go` entries (the same id can differ per gateway: `opencode/minimax-m3` is 512k, `opencode-go/minimax-m3` is 1M). `/context`, the status bar and auto-compaction size themselves from it; set `loop.context_window` to override.
+
 ---
 
 ## MCP servers

{dostuff-0.2.2 → dostuff-0.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dostuff"
-version = "0.2.2"
+version = "0.2.3"
 description = "DoStuff - a terminal coding agent for any LLM: TUI and headless mode, permissions, MCP, skills, web tools, sessions and git worktrees"
 readme = "README.md"
 license = "MIT"

{dostuff-0.2.2 → dostuff-0.2.3}/tests/test_opencode.py

@@ -1,6 +1,7 @@
 """OpenCode Zen / Go models: routing through litellm's openai / anthropic / gemini providers."""
 import pytest
 
+import dostuff.helpers.agent.get_model_token_limit as token_limit_module
 from dostuff import config as config_module
 from dostuff.config import reset_config
 from dostuff.helpers.models import list_models
@@ -79,3 +80,45 @@ def test_model_list(monkeypatch):
     assert chat_model_ids(data) == ["kimi-k3", "claude-haiku-5-5"]
     monkeypatch.setattr(list_models, "_get_json", lambda url, what: data if url.endswith("/go/v1/models") else {})
     assert list_models.provider_models("opencode-go") == ["opencode-go/claude-haiku-5-5", "opencode-go/kimi-k3"]
+
+
+def test_context_window_table(model):
+    """OpenCode gateways publish no context limit, so the table in helpers/models/opencode.py is used."""
+    t = token_limit_module
+    for name, window in [
+        ("opencode-go/deepseek-v4.1-flash", 1_000_000),  # the model that used to be assumed 128k
+        ("opencode/deepseek-v4.1-flash", 1_000_000),
+        ("opencode/minimax-m3", 512_000),  # same id, different window per gateway
+        ("opencode-go/minimax-m3", 1_000_000),
+        ("opencode/qwen3.8-max", 262_144),
+        ("opencode-go/qwen3.8-max", 1_000_000),
+    ]:
+        model(name)
+        assert t.get_model_token_limit() == window, name
+
+
+def test_context_window_bare_litellm_fallback(model, monkeypatch):
+    """An id missing from the table still resolves through litellm without the route prefix."""
+    t = token_limit_module
+    monkeypatch.setattr(t, "context_window", lambda provider, model_id: None)
+    model("opencode-go/deepseek-v4-pro")
+    assert t._litellm_limit("openai/deepseek-v4-pro") is None  # the routed name is unknown to litellm
+    assert t._litellm_limit("deepseek-v4-pro") == 1_000_000  # the bare id is not
+    assert t.get_model_token_limit() == 1_000_000
+
+
+def test_context_window_configured_wins(model, monkeypatch):
+    model("opencode-go/deepseek-v4.1-flash")
+    monkeypatch.setattr(token_limit_module.get_config(), "context_window", 32_000)
+    assert token_limit_module.get_model_token_limit() == 32_000
+
+
+def test_context_window_unknown_warns_once(model, monkeypatch):
+    t = token_limit_module
+    emitted = []
+    monkeypatch.setattr("dostuff.helpers.ui.emit.emit", lambda message, msg_type="system": emitted.append(message))
+    monkeypatch.setattr(t, "_warned_models", set())
+    model("opencode-go/not-a-real-model")
+    assert t.get_model_token_limit() == t.FALLBACK_CONTEXT_WINDOW
+    assert t.get_model_token_limit() == t.FALLBACK_CONTEXT_WINDOW
+    assert len(emitted) == 1 and "128,000" in emitted[0]

dostuff-0.2.2/dostuff/helpers/agent/get_model_token_limit.py

@@ -1,29 +0,0 @@
-import litellm
-from dostuff.config import get_config
-from dostuff.lib.model import get_litellm_model
-
-FALLBACK_CONTEXT_WINDOW = 128_000
-_warned_models: set[str] = set()
-
-
-def get_model_token_limit() -> int:
-    """Context window for the active model: `loop.context_window`, else litellm's model info, else 128k."""
-    configured = get_config().context_window
-    if configured > 0:
-        return configured
-    model = get_litellm_model()
-    try:
-        limit = litellm.get_model_info(model=model).get("max_input_tokens")
-        if limit:
-            return int(limit)
-    except Exception:
-        pass
-    if model not in _warned_models:
-        _warned_models.add(model)
-        from dostuff.helpers.ui.emit import emit
-        emit(
-            f"Unknown context window for '{model}'; assuming {FALLBACK_CONTEXT_WINDOW:,} tokens. "
-            "Set loop.context_window in config.yaml to override.",
-            msg_type="system",
-        )
-    return FALLBACK_CONTEXT_WINDOW

dostuff-0.2.2/dostuff/helpers/models/opencode.py

@@ -1,76 +0,0 @@
-"""OpenCode Zen (`opencode/<id>`) and OpenCode Go (`opencode-go/<id>`) models.
-
-litellm has no OpenCode provider. Each gateway serves a model family on the endpoint of its
-upstream API (https://opencode.ai/docs/zen/), so a model is sent through litellm's openai,
-anthropic or gemini route with the gateway as api_base.
-"""
-import os
-from typing import Any, Literal
-
-OPENCODE_PROVIDERS = {
-    "opencode": "https://opencode.ai/inference",
-    "opencode-go": "https://opencode.ai/inference/go",
-}
-OPENCODE_API_KEY_ENV = "OPENCODE_API_KEY"  # one console key works for Zen and Go
-# Served on the Anthropic Messages endpoint besides Claude; they differ between the gateways
-_ANTHROPIC_IDS = {
-    "opencode": {"qwen3.8-flash", "qwen3.6-plus", "qwen3.5-plus"},
-    "opencode-go": {"qwen3.8-max", "qwen3.8-flash", "qwen3.7-plus", "minimax-m3"},
-}
-# In /v1/models but not chat models
-_NOT_CHAT = ("jev-", "test")
-
-Endpoint = Literal["chat", "responses", "anthropic", "google"]
-
-
-def is_opencode(provider: str) -> bool:
-    return provider in OPENCODE_PROVIDERS
-
-
-def endpoint_for(provider: str, model_id: str) -> Endpoint:
-    """Which upstream API the gateway serves `model_id` on."""
-    if model_id.startswith("claude-") or model_id in _ANTHROPIC_IDS[provider]:
-        return "anthropic"
-    if model_id.startswith(("gpt-", "grok-", "muse-")):
-        return "responses"
-    if model_id.startswith("gemini-"):
-        return "google"
-    return "chat"
-
-
-def litellm_route(provider: str, model_id: str) -> tuple[str, str]:
-    """(litellm model, api_base) for an OpenCode model id."""
-    base = OPENCODE_PROVIDERS[provider]
-    endpoint = endpoint_for(provider, model_id)
-    if endpoint == "anthropic":
-        return f"anthropic/{model_id}", f"{base}/anthropic"  # litellm appends /v1/messages
-    if endpoint == "google":
-        return f"gemini/{model_id}", f"{base}/google/v1beta"
-    if endpoint == "responses":
-        return f"openai/responses/{model_id}", f"{base}/openai/v1"
-    return f"openai/{model_id}", f"{base}/openai/v1"
-
-
-def opencode_kwargs(provider: str, model_id: str, api_key: str | None, session_id: str, version: str) -> dict[str, Any]:
-    """litellm kwargs for an OpenCode model. Go asks clients to name themselves and send a
-    stable per-conversation id; Zen gets the same headers."""
-    model, api_base = litellm_route(provider, model_id)
-    return {
-        "model": model,
-        "api_base": api_base,
-        # Never fall back to OPENAI_API_KEY / ANTHROPIC_API_KEY: those would go to opencode.ai
-        "api_key": api_key or os.environ.get(OPENCODE_API_KEY_ENV) or "missing-opencode-key",
-        "extra_headers": {"User-Agent": f"dostuff/{version}", "x-opencode-session": session_id},
-    }
-
-
-def models_url(provider: str) -> str:
-    return f"{OPENCODE_PROVIDERS[provider]}/v1/models"
-
-
-def chat_model_ids(data: dict) -> list[str]:
-    """Model ids from a /v1/models response, without the non-chat ones."""
-    return [
-        m["id"] for m in data.get("data") or []
-        if isinstance(m, dict) and m.get("id") and not str(m["id"]).startswith(_NOT_CHAT)
-    ]