Skip to content

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Rust

feat: add native Ollama provider support via OLLAMA_HOST env var

bellmanbe8112f5f55f
diff --git a/USAGE.md b/USAGE.md
index 25f8ca38..873dde91 100644
--- a/USAGE.md
+++ b/USAGE.md
@@ -245,6 +245,7 @@ export ANTHROPIC_AUTH_TOKEN="anthropic-oauth-or-proxy-bearer-token"
| `sk-ant-*` API key | `ANTHROPIC_API_KEY` | `x-api-key: sk-ant-...` | [console.anthropic.com](https://console.anthropic.com) |
| OAuth access token (opaque) | `ANTHROPIC_AUTH_TOKEN` | `Authorization: Bearer ...` | an Anthropic-compatible proxy or OAuth flow that mints bearer tokens |
| OpenRouter key (`sk-or-v1-*`) | `OPENAI_API_KEY` + `OPENAI_BASE_URL=https://openrouter.ai/api/v1` | `Authorization: Bearer ...` | [openrouter.ai/keys](https://openrouter.ai/keys) |
+| Ollama local instance | `OLLAMA_HOST` | no auth header (Ollama requires none) | local Ollama server at `http://127.0.0.1:11434` |
**Why this matters:** if you paste an `sk-ant-*` key into `ANTHROPIC_AUTH_TOKEN`, Anthropic's API will return `401 Invalid bearer token` because `sk-ant-*` keys are rejected over the Bearer header. The fix is a one-line env var swap — move the key to `ANTHROPIC_API_KEY`. Recent `claw` builds detect this exact shape (401 + `sk-ant-*` in the Bearer slot) and append a hint to the error message pointing at the fix.
@@ -305,18 +306,18 @@ cd rust
### Ollama
```bash
-export OPENAI_BASE_URL="http://127.0.0.1:11434/v1"
-unset OPENAI_API_KEY
+export OLLAMA_HOST="http://127.0.0.1:11434"
cd rust
./target/debug/claw --model "llama3.2" prompt "summarize this repository in one sentence"
```
-For Ollama tags with punctuation (for example `qwen2.5-coder:7b`), `OPENAI_BASE_URL` selects the local OpenAI-compatible route even when `OPENAI_API_KEY` is unset:
+`OLLAMA_HOST` is the preferred env var. Claw routes all models to the local Ollama endpoint automatically, and no API key is needed. The older `OPENAI_BASE_URL` + `OPENAI_API_KEY` workaround is also supported.
+
+For Ollama tags with punctuation (for example `qwen2.5-coder:7b`), both approaches work:
```bash
-export OPENAI_BASE_URL="http://127.0.0.1:11434/v1"
-unset OPENAI_API_KEY
+export OLLAMA_HOST="http://127.0.0.1:11434"
cd rust
./target/debug/claw --model "qwen2.5-coder:7b" prompt "reply with ready"
diff --git a/docs/local-openai-compatible-providers.md b/docs/local-openai-compatible-providers.md
index aabbe696..cf3766e0 100644
--- a/docs/local-openai-compatible-providers.md
+++ b/docs/local-openai-compatible-providers.md
@@ -57,11 +57,12 @@ ollama serve
In another shell:
```bash
-export OPENAI_BASE_URL="http://127.0.0.1:11434/v1"
-unset OPENAI_API_KEY
+export OLLAMA_HOST="http://127.0.0.1:11434"
claw --model "qwen3:latest" prompt "Reply exactly HELLO_WORLD_123"
```
+`OLLAMA_HOST` is the preferred env var for Ollama. Claw routes all models to the local OpenAI-compatible endpoint automatically when this is set, and no API key is needed. The older `OPENAI_BASE_URL` + `OPENAI_API_KEY` workaround is also supported for existing setups.
+
If Ollama is running without auth, `unset OPENAI_API_KEY` is acceptable. Use a placeholder token rather than a real cloud API key if your local server requires an Authorization header.
## llama.cpp server
diff --git a/rust/crates/api/src/client.rs b/rust/crates/api/src/client.rs
index 55d200c5..240559e8 100644
--- a/rust/crates/api/src/client.rs
+++ b/rust/crates/api/src/client.rs
@@ -32,16 +32,25 @@ impl ProviderClient {
OpenAiCompatConfig::xai(),
)?)),
ProviderKind::OpenAi => {
- // DashScope models (qwen-*) also return ProviderKind::OpenAi because they
- // speak the OpenAI wire format, but they need the DashScope config which
- // reads DASHSCOPE_API_KEY and points at dashscope.aliyuncs.com.
- let config = match providers::metadata_for_model(&resolved_model) {
- Some(meta) if meta.auth_env == "DASHSCOPE_API_KEY" => {
- OpenAiCompatConfig::dashscope()
- }
- _ => OpenAiCompatConfig::openai(),
- };
- Ok(Self::OpenAi(OpenAiCompatClient::from_env(config)?))
+ // OLLAMA_HOST takes priority: local Ollama needs no API key
+ // and ignores DashScope/OpenAI env-based dispatch.
+ if std::env::var_os("OLLAMA_HOST").is_some() {
+ Ok(Self::OpenAi(
+ openai_compat::OpenAiCompatClient::from_ollama_env()
+ .expect("from_ollama_env always returns Some"),
+ ))
+ } else {
+ // DashScope models (qwen-*) also return ProviderKind::OpenAi because they
+ // speak the OpenAI wire format, but they need the DashScope config which
+ // reads DASHSCOPE_API_KEY and points at dashscope.aliyuncs.com.
+ let config = match providers::metadata_for_model(&resolved_model) {
+ Some(meta) if meta.auth_env == "DASHSCOPE_API_KEY" => {
+ OpenAiCompatConfig::dashscope()
+ }
+ _ => OpenAiCompatConfig::openai(),
+ };
+ Ok(Self::OpenAi(OpenAiCompatClient::from_env(config)?))
+ }
}
}
}
diff --git a/rust/crates/api/src/providers/mod.rs b/rust/crates/api/src/providers/mod.rs
index f8fe6244..57dce27e 100644
--- a/rust/crates/api/src/providers/mod.rs
+++ b/rust/crates/api/src/providers/mod.rs
@@ -351,6 +351,11 @@ fn looks_like_local_openai_model(model: &str) -> bool {
#[must_use]
pub fn detect_provider_kind(model: &str) -> ProviderKind {
+ // OLLAMA_HOST takes priority: if set, route all models through the local
+ // OpenAI-compatible endpoint regardless of model name or other env vars.
+ if std::env::var_os("OLLAMA_HOST").is_some() {
+ return ProviderKind::OpenAi;
+ }
let resolved_model = resolve_model_alias(model);
if let Some(metadata) = metadata_for_model(&resolved_model) {
return metadata.provider;
diff --git a/rust/crates/api/src/providers/openai_compat.rs b/rust/crates/api/src/providers/openai_compat.rs
index a1a82b88..7f82d00c 100644
--- a/rust/crates/api/src/providers/openai_compat.rs
+++ b/rust/crates/api/src/providers/openai_compat.rs
@@ -49,6 +49,14 @@ const XAI_MAX_REQUEST_BODY_BYTES: usize = 52_428_800; // 50MB
const OPENAI_MAX_REQUEST_BODY_BYTES: usize = 104_857_600; // 100MB
const DASHSCOPE_MAX_REQUEST_BODY_BYTES: usize = 6_291_456; // 6MB (observed limit in dogfood)
+pub const OLLAMA_CONFIG: OpenAiCompatConfig = OpenAiCompatConfig {
+ provider_name: "Ollama",
+ api_key_env: "OLLAMA_HOST",
+ base_url_env: "OLLAMA_HOST",
+ default_base_url: "http://127.0.0.1:11434/v1",
+ max_request_body_bytes: 104_857_600,
+};
+
impl OpenAiCompatConfig {
#[must_use]
pub const fn xai() -> Self {
@@ -149,6 +157,22 @@ impl OpenAiCompatClient {
};
Ok(Self::new(api_key, config).with_base_url(base_url))
}
+ /// Create an Ollama client from `OLLAMA_HOST` env var.
+ /// Ollama requires no API key; a placeholder is used for the Authorization header.
+ pub fn from_ollama_env() -> Option<Self> {
+ let host =
+ std::env::var("OLLAMA_HOST").unwrap_or_else(|_| "http://127.0.0.1:11434".to_string());
+ let base_url = format!("{}/v1", host.trim_end_matches('/'));
+ Some(Self {
+ http: build_http_client_or_default(),
+ api_key: "ollama".to_string(),
+ config: OLLAMA_CONFIG,
+ base_url,
+ max_retries: DEFAULT_MAX_RETRIES,
+ initial_backoff: DEFAULT_INITIAL_BACKOFF,
+ max_backoff: DEFAULT_MAX_BACKOFF,
+ })
+ }
#[must_use]
pub fn with_base_url(mut self, base_url: impl Into<String>) -> Self {
diff --git a/rust/crates/rusty-claude-cli/src/main.rs b/rust/crates/rusty-claude-cli/src/main.rs
index 9b1d8a74..38974eb5 100644
--- a/rust/crates/rusty-claude-cli/src/main.rs
+++ b/rust/crates/rusty-claude-cli/src/main.rs
@@ -2903,6 +2903,14 @@ fn resolve_model_alias_with_config(model: &str) -> String {
/// Rejects: empty, whitespace-only, strings with spaces, or invalid chars.
fn validate_model_syntax(model: &str) -> Result<(), String> {
let trimmed = model.trim();
+ // Ollama models use names like "qwen3:8b" that don't match provider/model
+ // syntax. Skip strict validation when OLLAMA_HOST is configured.
+ if std::env::var_os("OLLAMA_HOST").is_some() {
+ if trimmed.is_empty() {
+ return Err("invalid model syntax: model string cannot be empty.\nUsage: --model <model-name> e.g. --model qwen3:8b".to_string());
+ }
+ return Ok(());
+ }
if trimmed.is_empty() {
return Err("invalid model syntax: model string cannot be empty.\nUsage: --model <provider/model> e.g. --model anthropic/claude-opus-4-7".to_string());
}
@@ -19689,4 +19697,16 @@ mod alias_resolution_tests {
assert_eq!(resolve_model_alias_with_config(model), model);
assert!(validate_model_syntax(model).is_ok());
}
+ #[test]
+ fn test_ollama_host_bypasses_model_validation() {
+ // Safety: test sets and clears env var within the test.
+ std::env::set_var("OLLAMA_HOST", "http://127.0.0.1:11434");
+ // Ollama model names with colons pass
+ assert!(validate_model_syntax("qwen3:8b").is_ok());
+ assert!(validate_model_syntax("gemma4:e2b").is_ok());
+ assert!(validate_model_syntax("qwen3.6:27b-nvfp4").is_ok());
+ // Empty model still rejected
+ assert!(validate_model_syntax("").is_err());
+ std::env::remove_var("OLLAMA_HOST");
+ }
}