feat: add Avian as an LLM provider#7561
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ae2fdc641e
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| pub const AVIAN_KNOWN_MODELS: &[&str] = &[ | ||
| "deepseek/deepseek-v3.2", | ||
| "moonshotai/kimi-k2.5", | ||
| "z-ai/glm-5", | ||
| "minimax/minimax-m2.5", |
There was a problem hiding this comment.
These Avian model IDs are registered as provider/model strings, but there are no corresponding canonical mappings for provider avian, so ModelConfig::with_canonical_limits falls back to defaults instead of model-specific limits. In practice this means Avian requests use the generic 128k context and 4096 output-token cap (via max_output_tokens()), which can truncate responses for models that are advertised with much larger limits (for example minimax/minimax-m2.5).
Useful? React with 👍 / 👎.
Add Avian (https://avian.io) as a built-in LLM provider. Avian offers a cost-effective OpenAI-compatible inference API with support for streaming and function calling. Available models: - deepseek/deepseek-v3.2 (164K context, $0.26/$0.38 per 1M tokens) - moonshotai/kimi-k2.5 (131K context, $0.45/$2.20 per 1M tokens) - z-ai/glm-5 (131K context, $0.30/$2.55 per 1M tokens) - minimax/minimax-m2.5 (1M context, $0.30/$1.10 per 1M tokens) Configuration: AVIAN_API_KEY (required), AVIAN_HOST (optional) Signed-off-by: Kyle D <[email protected]>
avianion
force-pushed
the
add-avian-provider
branch
from
ae2fdc6 to
28496fd
Compare
|
Hey @alexhancock, would love your review on this when you get a chance. Happy to address any feedback! |
|
Friendly follow-up — this PR is still active and ready for review. Would appreciate a look when you get a chance! cc @alexhancock |
|
Friendly follow-up — this PR is still active and ready for review. All feedback has been addressed. Would appreciate a look when you get a chance! cc @alexhancock |
|
Hey @zanesq @angiejones — friendly follow-up on this PR. Avian is an OpenAI-compatible inference provider that's already live and powering apps like ISEKAI ZERO. This is a lightweight integration (standard OpenAI-compatible endpoint) and we're happy to address any feedback or make adjustments. Would love to get this merged if you have a moment to review. Thanks! |
|
Thanks for the contribution! |
|
eh, sorry to have missed this, but can this not be a declarative provider? I do not think we want to have custom code for providers in our code base. If it is openai compatible, you should not need it. |
…deps * origin/main: (34 commits) fix: reduce server log verbosity — skip session in instrument, defaul… (#7729) fix: provider test infrastructure (#7738) fix: sanitize streamable HTTP extension names derived from URLs (#7740) refactor: derive GooseMode string conversions with strum (#7706) docs: Add Spraay Batch Payments MCP Extension Tutorial (#7525) fix: flake.nix (#7224) delete goose web (#7696) Add @angiejones as CODEOWNER for documentation (#7711) Add MLflow integration guide (#7563) docs: LM Studio availability (#7698) feat: add Avian as an LLM provider (#7561) Adds `linux-mcp-server` to the goose registry (#6979) fix: add #[serde(default)] to description field on 4 ExtensionConfig variants (#7708) feat: combine TUI UX from alexhancock/tui-goodness with publishing config from jackamadeo/package-tui (#7683) chore: cleanup old sandbox (#7700) Correct windows artifact (#7699) gh fall back (#7695) fix: restore smart-approve mode (#7690) fix: make TLS configurable in goosed agent via GOOSE_TLS env var (#7686) Update to rmcp 1.1.0 (#7619) ... # Conflicts: # Cargo.lock
* origin/main: (21 commits) fix(ui-desktop): unify path resolution around GOOSE_PATH_ROOT (#7335) fix: pass OAuth scopes to DCR and extract granted_scopes from token response (#7571) fix: write to real file if config.yaml is symlink (#7669) fix: preserve pairings when stopping gateway (#7733) fix: reduce server log verbosity — skip session in instrument, defaul… (#7729) fix: provider test infrastructure (#7738) fix: sanitize streamable HTTP extension names derived from URLs (#7740) refactor: derive GooseMode string conversions with strum (#7706) docs: Add Spraay Batch Payments MCP Extension Tutorial (#7525) fix: flake.nix (#7224) delete goose web (#7696) Add @angiejones as CODEOWNER for documentation (#7711) Add MLflow integration guide (#7563) docs: LM Studio availability (#7698) feat: add Avian as an LLM provider (#7561) Adds `linux-mcp-server` to the goose registry (#6979) fix: add #[serde(default)] to description field on 4 ExtensionConfig variants (#7708) feat: combine TUI UX from alexhancock/tui-goodness with publishing config from jackamadeo/package-tui (#7683) chore: cleanup old sandbox (#7700) Correct windows artifact (#7699) ...
* origin/main: (21 commits) fix(ui-desktop): unify path resolution around GOOSE_PATH_ROOT (#7335) fix: pass OAuth scopes to DCR and extract granted_scopes from token response (#7571) fix: write to real file if config.yaml is symlink (#7669) fix: preserve pairings when stopping gateway (#7733) fix: reduce server log verbosity — skip session in instrument, defaul… (#7729) fix: provider test infrastructure (#7738) fix: sanitize streamable HTTP extension names derived from URLs (#7740) refactor: derive GooseMode string conversions with strum (#7706) docs: Add Spraay Batch Payments MCP Extension Tutorial (#7525) fix: flake.nix (#7224) delete goose web (#7696) Add @angiejones as CODEOWNER for documentation (#7711) Add MLflow integration guide (#7563) docs: LM Studio availability (#7698) feat: add Avian as an LLM provider (#7561) Adds `linux-mcp-server` to the goose registry (#6979) fix: add #[serde(default)] to description field on 4 ExtensionConfig variants (#7708) feat: combine TUI UX from alexhancock/tui-goodness with publishing config from jackamadeo/package-tui (#7683) chore: cleanup old sandbox (#7700) Correct windows artifact (#7699) ...
…e-issue * origin/main: fix(ui-desktop): unify path resolution around GOOSE_PATH_ROOT (#7335) fix: pass OAuth scopes to DCR and extract granted_scopes from token response (#7571) fix: write to real file if config.yaml is symlink (#7669) fix: preserve pairings when stopping gateway (#7733) fix: reduce server log verbosity — skip session in instrument, defaul… (#7729) fix: provider test infrastructure (#7738) fix: sanitize streamable HTTP extension names derived from URLs (#7740) refactor: derive GooseMode string conversions with strum (#7706) docs: Add Spraay Batch Payments MCP Extension Tutorial (#7525) fix: flake.nix (#7224) delete goose web (#7696) Add @angiejones as CODEOWNER for documentation (#7711) Add MLflow integration guide (#7563) docs: LM Studio availability (#7698) feat: add Avian as an LLM provider (#7561) Adds `linux-mcp-server` to the goose registry (#6979) fix: add #[serde(default)] to description field on 4 ExtensionConfig variants (#7708)
3 participants
Summary
Adds Avian as a built-in LLM provider for Goose. Avian provides a cost-effective, OpenAI-compatible inference API with streaming and function calling support.
Available Models
deepseek/deepseek-v3.2moonshotai/kimi-k2.5z-ai/glm-5minimax/minimax-m2.5Configuration
AVIAN_API_KEY(required) - API key from avian.ioAVIAN_HOST(optional) - defaults tohttps://api.avian.io/v1Changes
crates/goose/src/providers/avian.rs- New provider usingOpenAiCompatibleProvider(follows xAI pattern)crates/goose/src/providers/mod.rs- Module declarationcrates/goose/src/providers/init.rs- Provider registrationdocumentation/docs/getting-started/providers.md- Documentation entryImplementation
Uses the
OpenAiCompatibleProviderbase, identical pattern to the xAI provider. Bearer token auth, standard/chat/completionsand/modelsendpoints.cc @baxen @michaelneale