Update docs for litellm removal

Author: Your Name

cecli/website/docs/config/adv-model-settings.md

@@ -41,7 +41,7 @@ The json file should be a dictionary with an entry for each model, as follows:
 
 ### Contribute model metadata
 
-Cecli relies on [litellm's model_prices_and_context_window.json file](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) for model metadata.
+Cecli ships its own bundled model metadata in `cecli/resources/model-metadata.json` (see the file in the [cecli repository](https://github.com/cecli-dev/cecli/blob/main/cecli/resources/model-metadata.json)). It is based on LiteLLM's configuration scheme [here](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json).
 
 Consider submitting a PR to that file to add missing models.
 
@@ -62,9 +62,9 @@ If the files above exist, they will be loaded in that order. Files loaded last w
 
 The YAML file should be a list of dictionary objects for each model.
 
-### Passing extra params to litellm.completion
+### Passing extra params to model requests
 
-The `extra_params` attribute of model settings is used to pass arbitrary extra parameters to the `litellm.completion()` call when sending data to the given model.
+The `extra_params` attribute of model settings is used to pass arbitrary extra parameters to cecli's completion dispatcher when sending data to the given model. These become request parameters sent to the provider API.
 
 For example:
 
@@ -76,7 +76,7 @@ For example:
     max_tokens: 8192
 ```
 
-You can use the special model name `cecli/extra_params` to define `extra_params` that will be passed to `litellm.completion()` for all models. Only the `extra_params` dict is used from this special model name.
+You can use the special model name `cecli/extra_params` to define `extra_params` that will be passed to cecli's completion dispatcher for all models. Only the `extra_params` dict is used from this special model name.
 
 For example:
 

cecli/website/docs/config/model-configuration.md

@@ -16,12 +16,12 @@ Cecli allows you to customize and override LLM configurations to fine-tune their
 
 For advanced configurations, you can organize override parameters into three logical groups: `api`, `llm`, and `agent`.
 ### 1. `api`
-Values under `api` are merged directly into the model's API request parameters (`headers`). This is useful for configuring provider-specific API options, temperature, or custom headers. For the full list of supported parameters, see the [LiteLLM completion input documentation](https://docs.litellm.ai/docs/completion/input).
+Values under `api` are request-level parameters that cecli passes to the provider API. This is useful for configuring provider-specific API options, temperature, or custom headers. For more details, see the [advanced model settings](../config/adv-model-settings.html) page.
 
 **Common parameters**: `temperature`, `top_p`, `max_tokens`, `parallel_tool_calls`, `extra_body` (e.g., `thinking: true` or `reasoning_effort: "high"`).
 
 ### 2. `llm`
-Values under `llm` are merged into the model's info dictionary (`self.info`). This allows you to override or augment model metadata and capabilities. For a comprehensive list of available model metadata fields, see the [LiteLLM model prices and context window reference](https://github.com/BerriAI/litellm/blob/litellm_internal_staging/model_prices_and_context_window.json).
+Values under `llm` are merged into the model's info dictionary (`self.info`). This allows you to override or augment model metadata and capabilities. For a comprehensive list of available model metadata fields, see cecli's bundled metadata in [cecli/resources/model-metadata.json](https://github.com/cecli-dev/cecli/blob/main/cecli/resources/model-metadata.json).
 
 **Common parameters**: `supports_vision`, `supports_function_calling`, token limits, or pricing information.
 

cecli/website/docs/llms/bedrock.md

@@ -17,7 +17,7 @@ Amazon Bedrock has added support for a new feature called [cross-region "inferen
 
 If you attempt to use a `Model ID` for a model that exclusively supports the Inference Profile feature, you will receive an error message like the following:
 
-> litellm.BadRequestError: BedrockException - b'{"message":"Invocation of model ID
+> BadRequestError: BedrockException - b'{"message":"Invocation of model ID
 anthropic.claude-3-7-sonnet-20250219-v1:0 with on-demand throughput isn\xe2\x80\x99t supported. Retry your request with the ID or ARN of an inference profile that contains this model."}'
 
 ## Installation and Configuration
@@ -94,22 +94,11 @@ cecli --list-models bedrock/
 
 Make sure you have access to these models in your AWS account before attempting to use them with cecli.
 
-## Install boto3
-You may need to install the `boto3` package.
+## AWS credentials
 
-```bash
-# If you installed with cecli-install or `uv tool`
-uv tool run --from cecli-dev pip install boto3
-
-# Or with pipx...
-pipx inject cecli-dev boto3
-
-# Or with pip
-pip install -U boto3
-```
+Cecli signs Bedrock requests itself (AWS SigV4) using the standard AWS credentials from your environment (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` and optionally `AWS_SESSION_TOKEN`), so the `boto3` package is not required.
 
 # More info
 
 For more information on Amazon Bedrock and its models, refer to the [official AWS documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html).
 
-Also, see the [litellm docs on Bedrock](https://litellm.vercel.app/docs/providers/bedrock).

cecli/website/docs/llms/gemini.md

@@ -36,15 +36,3 @@ cecli --model gemini-exp
 cecli --list-models gemini/
 ```
 
-You may need to install the `google-generativeai` package. 
-
-```bash
-# If you installed with cecli-install or `uv tool`
-uv tool run --from cecli-dev pip install google-generativeai
-
-# Or with pipx...
-pipx inject cecli-dev google-generativeai
-
-# Or with pip
-pip install -U google-generativeai
-```

cecli/website/docs/llms/github.md

@@ -19,4 +19,4 @@ uv tool install cecli-dev
 
 ---
 
-When you specify a github copilot model on start up (e.g. `github_copilot/gpt-5-mini`), [litellm](https://github.com/BerriAI/litellm) will enter a github auth workflow wherein you will connect to your github account with the provided auth code to grant the system access. Further details can be found [here](https://docs.litellm.ai/docs/providers/github_copilot).
+When you specify a GitHub Copilot model on start up (e.g. `github_copilot/gpt-5-mini`), cecli will enter a GitHub auth workflow natively, wherein you will connect to your GitHub account with the provided auth code to grant the system access.

cecli/website/docs/llms/other.md

@@ -5,7 +5,7 @@ nav_order: 800
 
 # Other LLMs
 
-Cecli uses the [litellm](https://docs.litellm.ai/docs/providers) package to connect to hundreds of other models. You can use `cecli --model <model-name>` to use any supported model.
+Cecli connects directly to hundreds of models through their providers' APIs, so there is no extra model-routing package to install. You can use `cecli --model <model-name>` to use any supported model.
 
 To explore the list of supported models you can run `cecli --list-models <model-name>` with a partial model name. If the supplied name is not an exact match for a known model, cecli will return a list of possible matching models. For example:
 
@@ -23,70 +23,24 @@ Models which match "turbo":
 
 See the [model warnings](warnings.html) section for information on warnings which will occur when working with models that cecli is not familiar with.
 
-## LiteLLM
+## Connecting to other providers
 
-Cecli uses the LiteLLM package to connect to LLM providers. The [LiteLLM provider docs](https://docs.litellm.ai/docs/providers) contain more detail on all the supported providers, their models and any required environment variables.
+Cecli connects to each provider through its own request dispatcher (`cecli/helpers/llms/`): when you specify a model, cecli resolves the provider's base URL, API-key environment variable and API family (OpenAI-compatible chat, Anthropic Messages, Responses, Gemini, or Bedrock) and handles authentication and headers itself.
 
 ## Other API key variables
 
-Here are the API key environment variables that are supported by litellm. See their docs for more info.
+The authoritative list of provider base URLs and API-key environment variables is cecli's own provider configuration (`cecli/resources/providers.json`, which covers 61 providers) plus built-in defaults for the major providers. Each provider page in this section lists the variables you need to set, and `cecli --list-models <partial-name>` shows the model names cecli knows about.
 
-- ALEPH_ALPHA_API_KEY
-- ALEPHALPHA_API_KEY
+Here are some of the most commonly used API key environment variables:
+
+- OPENAI_API_KEY
 - ANTHROPIC_API_KEY
-- ANYSCALE_API_KEY
-- ARK_API_KEY
-- AZURE_AI_API_KEY
-- AZURE_API_KEY
-- AZURE_OPENAI_API_KEY
-- BASETEN_API_KEY
-- BYTEZ_API_KEY
-- CEREBRAS_API_KEY
-- CLARIFAI_API_KEY
-- CLOUDFLARE_API_KEY
-- CO_API_KEY
-- CODESTRAL_API_KEY
-- COHERE_API_KEY
-- COMPACTIFAI_API_KEY
-- DASHSCOPE_API_KEY
-- DATABRICKS_API_KEY
-- DEEPINFRA_API_KEY
 - DEEPSEEK_API_KEY
-- FEATHERLESS_AI_API_KEY
-- FIREWORKS_AI_API_KEY
-- FIREWORKS_API_KEY
-- FIREWORKSAI_API_KEY
+- OPENROUTER_API_KEY
 - GEMINI_API_KEY
-- GOOGLE_API_KEY
+- META_API_KEY
 - GROQ_API_KEY
-- HUGGINGFACE_API_KEY
-- INFINITY_API_KEY
-- MARITALK_API_KEY
+- XAI_API_KEY
 - MISTRAL_API_KEY
-- MOONSHOT_API_KEY
-- NEBIUS_API_KEY
-- NLP_CLOUD_API_KEY
-- NOVITA_API_KEY
-- NVIDIA_NIM_API_KEY
 - OLLAMA_API_KEY
-- OPENAI_API_KEY
-- OPENAI_LIKE_API_KEY
-- OPENROUTER_API_KEY
-- OR_API_KEY
-- OVHCLOUD_API_KEY
-- PALM_API_KEY
-- PERPLEXITYAI_API_KEY
-- PREDIBASE_API_KEY
-- PROVIDER_API_KEY
-- REPLICATE_API_KEY
-- SAMBANOVA_API_KEY
-- TOGETHERAI_API_KEY
-- USER_API_KEY
-- VERCEL_AI_GATEWAY_API_KEY
-- VOLCENGINE_API_KEY
-- VOYAGE_API_KEY
-- WANDB_API_KEY
-- WATSONX_API_KEY
-- WX_API_KEY
-- XAI_API_KEY
-- XINFERENCE_API_KEY
+- AZURE_API_KEY

cecli/website/docs/llms/warnings.md

@@ -67,5 +67,5 @@ If required variables are missing,
 you may get errors when you attempt to chat with the model.
 You can look in the [cecli's LLM documentation](../llms.html)
 or the
-[litellm documentation](https://docs.litellm.ai/docs/providers)
+provider pages in this section
 to see if the required variables are listed there.

cecli/website/docs/troubleshooting/imports.md

@@ -35,4 +35,3 @@ Cecli pins its dependencies and is tested to work with those specific versions.
 
 In particular, be careful with the packages with pinned versions noted at the end of [cecli's requirements.in file](https://github.com/cecli-dev/cecli/blob/main/requirements/requirements.in). These versions are pinned because cecli is known not to work with the latest versions of these libraries.
 
-Also be wary of upgrading `litellm`, as it changes versions frequently and sometimes introduces bugs or backwards incompatible changes.

cecli/website/docs/troubleshooting/support.md

@@ -45,9 +45,9 @@ Yes, you can use local LLMs with cecli. Here's a summary of the options:
 
 2. OpenAI-compatible API: cecli can access local models that provide an OpenAI-compatible API.
 
-3. Other local models: cecli uses the LiteLLM package to connect to various LLM providers, which may include options for running models locally.
+3. Other local models: cecli connects directly to many LLM providers, including local and OpenAI-compatible endpoints (Ollama, LM Studio, etc.).
 
-However, it's important to note that cecli works best with more capable models. Less capable models may have difficulty properly returning "code edits," which could result in cecli not being able to edit your files and commit changes effectively.
+However, it's important to note that cecli works best with more capable models. Less capable models may have difficulty properly returning code edits, which could result in cecli not being able to edit your files and commit changes effectively.
 
 For more detailed information on using local LLMs and connecting to various models, you might want to check out these relevant documentation pages:
 

cecli/website/docs/troubleshooting/warnings.md

@@ -66,8 +66,7 @@ which variables are required for the model.
 If required variables are missing,
 you may get errors when you attempt to chat with the model.
 You can look in the [cecli's LLM documentation](../llms.html)
-or the
-[litellm documentation](https://docs.litellm.ai/docs/providers)
+or the provider-specific pages (e.g. [OpenAI-compatible endpoints](../llms/openai-compat.html))
 to see if the required variables are listed there.
 
 ## More help