Add OpenAI's GPT-5.5 model support

[PeterDaveHello]

Reference:

• https://platform.openai.com/docs/models/gpt-5.5
• https://developers.openai.com/api/docs/models/gpt-5.5

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

Review Summary by Qodo

Add OpenAI GPT-5.5 model support with token configuration

✨ Enhancement

Walkthroughs

Description

• Add GPT-5.5 model variants with 1.05M token context window
• Register model identifiers in token limit configuration
• Add unit tests for GPT-5.5 max token retrieval
• Include GPT-5.5 in reasoning effort detection logic

Diagram

flowchart LR
  A["GPT-5.5 Models<br/>gpt-5.5<br/>gpt-5.5-2026-04-23"] -->|"1.05M tokens"| B["Token Config<br/>pr_agent/algo/__init__.py"]
  A -->|"Model Detection"| C["Reasoning Effort<br/>test_litellm_reasoning_effort.py"]
  B -->|"Validation"| D["Unit Tests<br/>test_get_max_tokens.py"]

Loading

File Changes

1. pr_agent/algo/__init__.py ⚙️ Configuration changes +2/-0

Register GPT-5.5 models with token limits

• Added two GPT-5.5 model variants to the model token limits dictionary
• Configured both gpt-5.5 and gpt-5.5-2026-04-23 with 1050000 token context window
• Included comments noting the 1.05M token limit with potential config restrictions

pr_agent/algo/init.py

---

2. tests/unittest/test_get_max_tokens.py 🧪 Tests +13/-0

Add GPT-5.5 max token unit tests

• Added new test method test_gpt55_model_max_tokens with parametrized models
• Tests both gpt-5.5 and gpt-5.5-2026-04-23 model identifiers
• Validates that get_max_tokens() returns 1050000 for GPT-5.5 variants
• Uses mock settings with zero custom and max model token overrides

tests/unittest/test_get_max_tokens.py

---

3. tests/unittest/test_litellm_reasoning_effort.py 🧪 Tests +2/-0

Include GPT-5.5 in model detection tests

• Added gpt-5.5 and gpt-5.5-2026-04-23 to the GPT-5 model detection test list
• Ensures both model variants are recognized for reasoning effort logic
• Maintains comprehensive coverage of GPT-5 model version strings

tests/unittest/test_litellm_reasoning_effort.py

---

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

Code Review by Qodo

🐞 Bugs (1) 📘 Rule violations (0)

1. _thinking model token crash 🐞 Bug ☼ Reliability

Description

If the configured model is set to a GPT-5.5 “_thinking” variant (e.g., "gpt-5.5_thinking"),
get_max_tokens() will raise because MAX_TOKENS only contains the base names added in this PR and
lookup is exact-match. This blocks get_pr_diff() (and thus all tools) before LiteLLMAIHandler can
strip the “_thinking” suffix.

Code

pr_agent/algo/init.py[R52-53]

+    'gpt-5.5': 1050000,  # 1.05M, but may be limited by config.max_model_tokens
+    'gpt-5.5-2026-04-23': 1050000,  # 1.05M, but may be limited by config.max_model_tokens

Evidence

This PR adds only the base GPT-5.5 keys to MAX_TOKENS. get_max_tokens() requires the model string to
match a MAX_TOKENS key exactly and raises otherwise; get_pr_diff() calls get_max_tokens(model)
early, so a “*_thinking” model string will crash before the AI handler runs. Separately,
LiteLLMAIHandler explicitly supports “_thinking” model names by stripping the suffix, and unit tests
assert that behavior—showing “_thinking” is an expected variant that should also work with token
budgeting.

pr_agent/algo/init.py[46-54]
pr_agent/algo/utils.py[991-1012]
pr_agent/algo/pr_processing.py[68-80]
pr_agent/algo/ai_handlers/litellm_ai_handler.py[296-317]
tests/unittest/test_litellm_reasoning_effort.py[365-384]

Agent prompt

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

### Issue description
`get_max_tokens(model)` performs an exact key lookup in `MAX_TOKENS`. The codebase supports GPT-5 “_thinking” model names in `LiteLLMAIHandler` (it strips `_thinking` before calling the provider), but `get_pr_diff()` calls `get_max_tokens(model)` before the AI handler runs. As a result, configuring `config.model = "gpt-5.5_thinking"` (or any `gpt-5.*_thinking`) will raise an exception and prevent PR processing.

### Issue Context
- This PR adds `gpt-5.5` entries to `MAX_TOKENS`, but does not address `_thinking` variants.
- There are existing tests asserting `_thinking` suffix handling for GPT-5 models.

### Fix Focus Areas
- pr_agent/algo/utils.py[991-1012]
- pr_agent/algo/pr_processing.py[68-80]
- pr_agent/algo/ai_handlers/litellm_ai_handler.py[296-317]
- tests/unittest/test_get_max_tokens.py[64-76]

### Implementation direction
- Normalize `model` inside `get_max_tokens()` before lookup by stripping a trailing `_thinking` suffix (and optionally any internal provider prefixes if applicable in your config patterns).
- Add a unit test ensuring `get_max_tokens("gpt-5.5_thinking")` returns the same value as `get_max_tokens("gpt-5.5")` (and similarly for the dated variant, if you want full coverage).

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

---

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

1. _thinking model token crash 🐞 Bug ☼ Reliability

If the configured model is set to a GPT-5.5 “_thinking” variant (e.g., "gpt-5.5_thinking"),
get_max_tokens() will raise because MAX_TOKENS only contains the base names added in this PR and
lookup is exact-match. This blocks get_pr_diff() (and thus all tools) before LiteLLMAIHandler can
strip the “_thinking” suffix.

Agent Prompt

### Issue description
`get_max_tokens(model)` performs an exact key lookup in `MAX_TOKENS`. The codebase supports GPT-5 “_thinking” model names in `LiteLLMAIHandler` (it strips `_thinking` before calling the provider), but `get_pr_diff()` calls `get_max_tokens(model)` before the AI handler runs. As a result, configuring `config.model = "gpt-5.5_thinking"` (or any `gpt-5.*_thinking`) will raise an exception and prevent PR processing.

### Issue Context
- This PR adds `gpt-5.5` entries to `MAX_TOKENS`, but does not address `_thinking` variants.
- There are existing tests asserting `_thinking` suffix handling for GPT-5 models.

### Fix Focus Areas
- pr_agent/algo/utils.py[991-1012]
- pr_agent/algo/pr_processing.py[68-80]
- pr_agent/algo/ai_handlers/litellm_ai_handler.py[296-317]
- tests/unittest/test_get_max_tokens.py[64-76]

### Implementation direction
- Normalize `model` inside `get_max_tokens()` before lookup by stripping a trailing `_thinking` suffix (and optionally any internal provider prefixes if applicable in your config patterns).
- Add a unit test ensuring `get_max_tokens("gpt-5.5_thinking")` returns the same value as `get_max_tokens("gpt-5.5")` (and similarly for the dated variant, if you want full coverage).

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