docs: update the configuration example of the Deepseek model

[Snoopy1866]

The two model names deepseek-chat and deepseek-reasoner will be deprecated at 2026/07/24 23:59 Beijing time, and should be updated to the new model names: deepseek-v4-flash and deepseek-v4-pro. In addition, this PR also updates the link to obtain the API key.

https://api-docs.deepseek.com/

[qodo-free-for-open-source-projects]

PR Summary by Qodo

Docs: update DeepSeek model config example to v4 names and API key link
📝 Documentation 🕐 Less than 5 minutes

Description

• Update DeepSeek configuration example to use new v4 model identifiers.
• Switch fallback example from deprecated DeepSeek models to v4 replacements.
• Refresh the documentation link for obtaining a DeepSeek API key.

High-Level Assessment

The following are alternative approaches to this PR:

1. Add a deprecation note with both old and new model names

• ➕ Reduces confusion for users still on deprecated identifiers
• ➕ Makes the impending cutoff date explicit where users configure models
• ➖ Slightly longer docs section
• ➖ Requires keeping the note updated if timelines change

2. Use a small compatibility table (old → new) in the DeepSeek section

• ➕ Clear at-a-glance migration guidance
• ➕ Scales if additional model renames occur
• ➖ More formatting/maintenance than a simple example update

Recommendation: The PR’s approach (updating the example to the new v4 model names and correcting the API key link) is the right default. Consider additionally adding a one-line deprecation/migration note (or a tiny old→new mapping table) to help users who still have configs using deepseek-chat / deepseek-reasoner.

Files changed (1) +4 / -4

Documentation (1) +4 / -4

changing_a_model.mdRefresh DeepSeek config example to v4 model names and API key URL +4/-4

Refresh DeepSeek config example to v4 model names and API key URL

• Updates the DeepSeek usage snippet to use 'deepseek-v4-pro' as the primary model and 'deepseek-v4-flash' as the fallback instead of deprecated identifiers. Adjusts the referenced DeepSeek API key acquisition link to point to the API keys page.

docs/docs/usage-guide/changing_a_model.md

[qodo-free-for-open-source-projects]

Code Review by Qodo

🐞 Bugs (1) 📘 Rule violations (0) 📜 Skill insights (0)

1. DeepSeek v4 example breaks 🐞 Bug ≡ Correctness

Description

The docs now recommend model = "deepseek/deepseek-v4-pro", but this model ID is not present in
pr_agent.algo.MAX_TOKENS; with the default custom_model_max_tokens=-1, get_max_tokens() raises
and PR-Agent fails during diff/prompt preparation. Users following the example will likely crash
PR-Agent unless they also set config.custom_model_max_tokens or the code adds these model IDs to
MAX_TOKENS.

Code

docs/docs/usage-guide/changing_a_model.md[R330-335]

+To use deepseek-v4 model with DeepSeek, for example, set:

```toml
[config] # in configuration.toml
-model = "deepseek/deepseek-chat"
-fallback_models=["deepseek/deepseek-chat"]
+model = "deepseek/deepseek-v4-pro"
+fallback_models=["deepseek/deepseek-v4-flash"]

Evidence

The docs change introduces deepseek/deepseek-v4-pro and deepseek/deepseek-v4-flash, but
MAX_TOKENS currently only contains the older DeepSeek IDs. get_max_tokens() raises when a model is
missing and custom_model_max_tokens is not positive; defaults set custom_model_max_tokens=-1,
and PR processing calls get_max_tokens(model) during diff generation.

docs/docs/usage-guide/changing_a_model.md[328-336]
pr_agent/algo/init.py[66-71]
pr_agent/algo/utils.py[992-1010]
pr_agent/settings/configuration.toml[31-36]
pr_agent/algo/pr_processing.py[67-80]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
The DeepSeek docs example was updated to `deepseek/deepseek-v4-pro` / `deepseek/deepseek-v4-flash`, but these model IDs are not present in `pr_agent.algo.MAX_TOKENS`. With default settings (`custom_model_max_tokens=-1`), PR-Agent raises in `get_max_tokens()` and fails during PR diff processing.

## Issue Context
Users copy/paste this section to configure PR-Agent. The system calls `get_max_tokens(model)` early in PR processing; if the model is missing from `MAX_TOKENS` and `custom_model_max_tokens` is not set to a positive value, the run fails.

## Fix Focus Areas
- docs/docs/usage-guide/changing_a_model.md[330-336]
- pr_agent/algo/__init__.py[66-71]
- pr_agent/algo/utils.py[992-1010]
- pr_agent/settings/configuration.toml[31-36]
- pr_agent/algo/pr_processing.py[67-80]

## What to change
Implement one of:
1) Update `MAX_TOKENS` (and any related model lists if needed) to include `deepseek/deepseek-v4-pro` and `deepseek/deepseek-v4-flash` with appropriate context sizes.
2) If you intentionally don’t want to hardcode these model IDs, update the DeepSeek docs snippet to include `custom_model_max_tokens=...` (a positive value) so it won’t raise at runtime.

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

• Author self-review: I have reviewed the code review findings, and addressed the relevant ones.

[qodo-free-for-open-source-projects]

1. Deepseek v4 example breaks 🐞 Bug ≡ Correctness

The docs now recommend model = "deepseek/deepseek-v4-pro", but this model ID is not present in
pr_agent.algo.MAX_TOKENS; with the default custom_model_max_tokens=-1, get_max_tokens() raises
and PR-Agent fails during diff/prompt preparation. Users following the example will likely crash
PR-Agent unless they also set config.custom_model_max_tokens or the code adds these model IDs to
MAX_TOKENS.

Agent Prompt

## Issue description
The DeepSeek docs example was updated to `deepseek/deepseek-v4-pro` / `deepseek/deepseek-v4-flash`, but these model IDs are not present in `pr_agent.algo.MAX_TOKENS`. With default settings (`custom_model_max_tokens=-1`), PR-Agent raises in `get_max_tokens()` and fails during PR diff processing.

## Issue Context
Users copy/paste this section to configure PR-Agent. The system calls `get_max_tokens(model)` early in PR processing; if the model is missing from `MAX_TOKENS` and `custom_model_max_tokens` is not set to a positive value, the run fails.

## Fix Focus Areas
- docs/docs/usage-guide/changing_a_model.md[330-336]
- pr_agent/algo/__init__.py[66-71]
- pr_agent/algo/utils.py[992-1010]
- pr_agent/settings/configuration.toml[31-36]
- pr_agent/algo/pr_processing.py[67-80]

## What to change
Implement one of:
1) Update `MAX_TOKENS` (and any related model lists if needed) to include `deepseek/deepseek-v4-pro` and `deepseek/deepseek-v4-flash` with appropriate context sizes.
2) If you intentionally don’t want to hardcode these model IDs, update the DeepSeek docs snippet to include `custom_model_max_tokens=...` (a positive value) so it won’t raise at runtime.

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

[Snoopy1866]

The maximum context length supported by deepseek-v4-pro and deepseek-v4-flash is 1000000. Do I need to open a separate PR and modify MAX_TOKENS in pr_agent/algo/__init__.py?