fix: use correct AI model names and respect provider-specific env vars#77
fix: use correct AI model names and respect provider-specific env vars#77clneagu wants to merge 1 commit into
Conversation
- Update default models to actual current versions: - OpenAI: gpt-4o-mini (was gpt-5-mini) - Claude: claude-sonnet-4-5-20250929 (was claude-sonnet-4-5-20250930) - Gemini: gemini-1.5-flash (was gemini-3-flash) - xAI: grok-beta (was grok-4-mini-fast) - OpenRouter/Vercel: anthropic/claude-sonnet-4.5 - Only set provider env var from config api_key if env var is not already set This allows using -p flag to switch providers when env vars are configured - Update README with correct model names for all providers
📝 WalkthroughWalkthroughDocumentation and code updated to reflect new default AI models across multiple providers (OpenAI, Claude, Gemini, Groq, DeepSeek, xAI) and API key environment variable handling modified to prevent overwriting pre-existing provider-specific environment variables. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/provider/mod.rs (1)
80-82: Inconsistent environment variable handling for OpenRouter/Vercel.The native providers (lines 133-137) only set the environment variable if it's not already present, but OpenRouter and Vercel unconditionally overwrite the env var. This inconsistency prevents the
-pflag from working correctly when switching to these providers if their env vars are already set.🔎 Proposed fix to respect existing env vars
- if let Some(key) = api_key { - std::env::set_var(auth_env_key, key); + if let Some(key) = api_key { + if std::env::var(auth_env_key).is_err() { + std::env::set_var(auth_env_key, key); + } }
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
README.mdsrc/provider/mod.rs
🔇 Additional comments (2)
src/provider/mod.rs (1)
132-137: LGTM! Correctly respects existing environment variables.The logic properly checks that the env var is not already set before overwriting it. This enables the
-pflag to work correctly when switching providers even when provider-specific environment variables are configured.README.md (1)
204-204: LGTM! Documentation properly updated to reflect code changes.All model name references have been consistently updated throughout the README to match the new defaults in
src/provider/mod.rs. The changes are accurate and well-aligned with the code modifications.Also applies to: 209-209, 216-221, 247-247, 278-278
| _ => { | ||
| let (default_model, name, env_key) = match provider_type { | ||
| ProviderType::Openai => ("gpt-5-mini", "OpenAI", "OPENAI_API_KEY"), | ||
| ProviderType::Openai => ("gpt-4o-mini", "OpenAI", "OPENAI_API_KEY"), |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
OpenAI gpt-4o-mini model current API
💡 Result:
Here’s the current OpenAI API summary for the GPT-4o‑mini model (official docs/news):
- Model summary: fast, cost‑efficient small multimodal model (text + vision), optimized for focused tasks and fine‑tuning; 128k token context window; up to 16k output tokens per request. [1][2]
- Where to call: supported on Responses (v1/responses), Chat Completions (v1/chat/completions), Realtime, Assistants, Batch, and Fine-tuning endpoints. [1][4]
- Pricing (text tokens): input $0.15 / 1M tokens, output $0.60 / 1M tokens (per OpenAI announcement). [2][5]
- Features: streaming, function calling, structured outputs, fine‑tuning supported; snapshots available to pin versions. [1][5]
- Variants: also available as a TTS-specialized model (gpt-4o-mini-tts) with its own snapshots and rate limits. [4]
- Notes/updates: OpenAI has since released GPT‑4.1 series (incl. GPT‑4.1 mini) which supersedes GPT‑4o‑mini in some product flows; check model picker/docs if you need the latest recommended small model. [3][2]
Sources:
[1] OpenAI Platform — GPT-4o mini docs.
[2] OpenAI blog announcement — “GPT‑4o mini” (July 18, 2024).
[3] OpenAI release notes / Help Center (model updates; GPT‑4.1 mini replacement notice).
[4] OpenAI Platform — GPT‑4o mini TTS docs.
[5] OpenAI Platform — GPT-4o model pricing & features.
Would you like example API calls (Requests/JSON) for v1/responses or v1/chat/completions using gpt-4o-mini?
🌐 Web query:
Anthropic Claude claude-sonnet-4-5-20250929 model API
💡 Result:
Summary — what it is
- "claude-sonnet-4-5-20250929" is Anthropic’s Claude Sonnet 4.5 model release (versioned 2025‑09‑29), available via the Anthropic/Claude API and through partners (Amazon Bedrock, Google Vertex AI). [1][2][3][4]
Quick usage example (Anthropic / Claude API)
- Model identifier: "claude-sonnet-4-5-20250929".
- Minimal cURL POST to /v1/messages:
curl https://api.anthropic.com/v1/messages
-H "Content-Type: application/json"
-H "x-api-key: $ANTHROPIC_API_KEY"
-H "anthropic-version: 2023-06-01"
-d '{
"model":"claude-sonnet-4-5-20250929",
"max_tokens":1024,
"messages":[{"role":"user","content":"Hello, Claude"}]
}'
The /v1/messages docs show this request/response format. [5]
Partner endpoints / alternate names
- Amazon Bedrock example ID: anthropic.claude-sonnet-4-5-20250929-v1:0.
- Google Vertex AI example ID: claude-sonnet-4-5@20250929. [3][4]
Notes
- Check Anthropic/Claude docs for exact API headers, rate limits, and any model-specific migration notes (Sonnet 4.5 migration guide / release notes). [1][3]
Sources
[1] Anthropic model docs (Get a Model).
[2] Anthropic product page (Claude Sonnet 4.5).
[3] Claude docs — "What's new" / availability (lists claude-sonnet-4-5-20250929).
[4] Google Cloud Vertex AI — Claude Sonnet 4.5 partner model page.
[5] Claude API / Messages endpoint example.
🌐 Web query:
Google Gemini gemini-1.5-flash model API
💡 Result:
Summary — gemini-1.5-flash (Google Gemini)
- Model ID: gemini-1.5-flash. It’s a multimodal text-generation model (text outputs; accepts text, code, images, audio, video, PDFs). [1]
- Token / context limits: up to 1,048,576 input tokens; default max output ~8,192 tokens. [1]
- Lifecycle / status: documented as a legacy/deprecated model (Google recommends using Gemini 2.0 Flash or newer) and specific model versions (e.g., gemini-1.5-flash-002) have deprecation/discontinuation dates. Check the model page for exact dates for any version you plan to use. [1]
- Where to call it:
- Vertex AI / Google Cloud (Model Garden / Generative AI on Vertex AI). Use Vertex AI REST/SDKs or gcloud for deployment and inference. [1][3]
- Google announced Gemini access via the OpenAI-compatible Library / REST surface — you can call model="gemini-1.5-flash" through that API (example snippet in the Google developers post). Confirm which endpoint and credentials you must use for your project. [2]
- Features: multimodal inputs, grounding with Google Search (for supported models/features), tuning (fine-tuning) options were available for 1.5 Flash versions when supported. [1][3]
If you want a short example (OpenAI-compatible) or Vertex AI code snippet for calling gemini-1.5-flash, tell me which environment you’ll use (Vertex AI Python SDK, REST/gcloud, or OpenAI-compatible client) and I’ll paste the minimal working example with the correct endpoint and parameters plus notes about authentication and region.
Sources: Google Cloud model page and release notes; Google Developers post about OpenAI Library access. [1][3][2]
🌐 Web query:
xAI Grok grok-beta model API
💡 Result:
Short summary — xAI "grok-beta" model API
- Endpoint/base URL: HTTPS REST API at https://api.x.ai/v1. Use your xAI API key from console.x.ai. [1][3]
- Model name to request: "grok-beta" (early preview model). [1][2]
- Key capabilities: text-only grok-beta supports system prompts and function-calling; xAI announced a multimodal/vision variant (grok-vision-beta) coming. Context window ~128,000 tokens (announced for grok-beta). [1][2]
- Compatibility: REST interface designed to be compatible with OpenAI-style SDKs (you can often switch base_url + key). Example: change OpenAI Python SDK base_url to https://api.x.ai/v1. [1]
- Status/pricing: grok-beta was a public‑beta/early model (xAI later released newer grok-2 family and other models); pricing slabs and newer recommended models (grok-2 series, grok-4, etc.) are listed on xAI’s API/docs pages. Check docs.x.ai or console.x.ai for current availability, deprecation, and exact pricing. [2][3]
If you want, I can:
- show a minimal curl or Python example calling "grok-beta", or
- look up the current status/pricing for grok-beta right now. Which would you like?
Consider using more current model versions for Gemini and xAI.
The model names are valid and callable, but note:
- Google Gemini:
gemini-1.5-flashis documented as legacy/deprecated; Google recommends using Gemini 2.0 Flash or newer. - xAI:
grok-betais a public-beta early model; xAI has since released newer versions (grok-2 and later). Check docs.x.ai for current recommended models and pricing. - OpenAI
gpt-4o-miniand Anthropicclaude-sonnet-4-5-20250929are current and supported.
Also applies to: 115-115, 122-123
🤖 Prompt for AI Agents
In src/provider/mod.rs around lines 113, 115 and 122-123, the hardcoded model
identifiers for Google Gemini and xAI are set to legacy/beta names; update those
entries to use the current recommended model versions (e.g., Gemini 2.0 Flash or
the latest Gemini release and xAI grok-2 or the current stable grok model) by
replacing the deprecated model strings with the up-to-date names from the
providers' docs, and ensure any related provider display name or env key remains
correct; verify compilation and update tests or comments to reference the
provider docs/versions used.
1 participant
Update default models to actual current versions:
Only set provider env var from config api_key if env var is not already set This allows using -p flag to switch providers when env vars are configured
Update README with correct model names for all providers
Summary by CodeRabbit
Documentation
Changes
✏️ Tip: You can customize this high-level summary in your review settings.