add: model gpt-5 #6599
add: model gpt-5 #6599
Conversation
WalkthroughSupport for GPT-5 models has been added by updating model recognition, vision model regexes, and request payload logic. The code now applies GPT-5-specific handling for temperature and token parameters in chat requests and extends the list of recognized OpenAI models and vision-capable models to include several GPT-5 variants. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant ChatClient
participant ChatGPTApi
participant OpenAI
User->>ChatClient: Sends chat request (selects model)
ChatClient->>ChatGPTApi: Calls chat() with model, temperature, max_tokens
ChatGPTApi->>ChatGPTApi: Detects model type (O1/O3/O4-mini/GPT-5/other)
ChatGPTApi->>ChatGPTApi: Adjusts temperature and token params based on model
ChatGPTApi->>OpenAI: Sends constructed payload
OpenAI-->>ChatGPTApi: Returns response
ChatGPTApi-->>ChatClient: Returns processed response
ChatClient-->>User: Displays result
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~15 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Poem
Note 🔌 MCP (Model Context Protocol) integration is now available in Early Access!Pro users can now connect to remote MCP servers under the Integrations page to get reviews and chat conversations that understand additional development context. ✨ Finishing Touches
🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (2)
app/constant.ts (1)
521-526: Add KnowledgeCutOffDate entries for GPT‑5 variantsWithout entries, the UI will fall back to the default 2021‑09 cutoff. Add mappings for:
- gpt-5, gpt-5-chat, gpt-5-chat-2025-01-01-preview, gpt-5-mini, gpt-5-nano.
Once you confirm the official cutoff dates, I can open a follow-up PR to add them. Do you want me to draft it?
app/client/platforms/openai.ts (1)
263-265: Reduce duplication by factoring a single guard for “completion tokens” familyYou repeat “!isO1OrO3 && !isGpt5”. Extract a helper boolean to avoid future drift and keep token logic consistent.
Within this block:
- if (visionModel && !isO1OrO3 && ! isGpt5) { + const usesMaxCompletionTokens = isO1OrO3 || isGpt5; + if (visionModel && !usesMaxCompletionTokens) { requestPayload["max_tokens"] = Math.max(modelConfig.max_tokens, 4000); }Add the helper near the other guards (isDalle3/isO1OrO3/isGpt5) to keep scope tight.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
app/client/platforms/openai.ts(3 hunks)app/constant.ts(2 hunks)
🧰 Additional context used
🧠 Learnings (2)
📚 Learning: 2025-07-31T09:13:27.479Z
Learnt from: Little-LittleProgrammer
PR: ChatGPTNextWeb/NextChat#6588
File: app/components/tts-config.tsx:90-90
Timestamp: 2025-07-31T09:13:27.479Z
Learning: In app/components/tts-config.tsx, the non-null assertion operator (!) on TTS_CONFIGS[props.ttsConfig.engine] is safe because: 1) TTSEngineType is a union type that exactly matches TTS_CONFIGS keys, 2) dropdown options are generated from Object.keys(TTS_CONFIGS) constraining user input, 3) TTS_CONFIGS is typed as Record<TTSEngineType, TTSConfigItem> guaranteeing key-value correspondence.
Applied to files:
app/client/platforms/openai.ts
📚 Learning: 2025-07-31T09:13:27.479Z
Learnt from: Little-LittleProgrammer
PR: ChatGPTNextWeb/NextChat#6588
File: app/components/tts-config.tsx:90-90
Timestamp: 2025-07-31T09:13:27.479Z
Learning: In app/components/tts-config.tsx, the non-null assertion operator (!) on TTS_CONFIGS[props.ttsConfig.engine] is safe because the engine values are constrained to keys that exist in TTS_CONFIGS through the dropdown generation (Object.keys(TTS_CONFIGS)) and validation (TTSConfigValidator.engine()).
Applied to files:
app/client/platforms/openai.ts
🔇 Additional comments (2)
app/client/platforms/openai.ts (2)
203-203: LGTM: Simple and robust GPT‑5 family detectionstartsWith("gpt-5") aligns with the new model IDs added in constants.
242-249: Confirmed GPT-5 usesmax_completion_tokensand omitsmax_tokens
The change to removemax_tokensand setmax_completion_tokensfor GPT-5 (mirroring o1/o3 models) aligns with the latest OpenAI API. No further adjustments are needed.
| temperature: (!isO1OrO3 && !isGpt5) ? modelConfig.temperature : 1, | ||
| presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0, | ||
| frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0, | ||
| top_p: !isO1OrO3 ? modelConfig.top_p : 1, | ||
| // max_tokens: Math.max(modelConfig.max_tokens, 1024), |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Confirm intent: forcing temperature=1 for GPT‑5
You’re forcing temperature=1 for GPT‑5 (similar to o1/o3/o4-mini) but leaving other sampling params (top_p, penalties) unchanged. Verify this matches GPT‑5 API semantics.
Optionally, extract a single guard to clarify intent:
- temperature: (!isO1OrO3 && !isGpt5) ? modelConfig.temperature : 1,
+ // If GPT‑5 requires fixed temperature, keep 1; otherwise pass-through.
+ temperature: (isO1OrO3 || isGpt5) ? 1 : modelConfig.temperature,🌐 Web query:
For OpenAI GPT-5 chat/completions, should temperature be fixed (e.g., 1 or 0) or is it supported like standard GPT models? Are presence_penalty, frequency_penalty, and top_p supported for GPT-5?
💡 Result:
Yes, OpenAI's GPT-5 model supports the temperature, top_p, presence_penalty, and frequency_penalty parameters in its chat/completions API, similar to previous GPT models. These parameters allow you to control various aspects of the model's output:
-
temperature: Controls the randomness of the model's responses. Lower values (e.g., 0.2) make the output more deterministic, while higher values (e.g., 0.8) increase randomness and creativity. (medium.com) -
top_p: Also known as nucleus sampling, this parameter determines the cumulative probability threshold for token selection. A value of 0.9 means the model considers the smallest set of tokens whose cumulative probability is at least 90%. (medium.com) -
presence_penalty: Encourages the model to introduce new topics by penalizing tokens that have already appeared in the text. Positive values increase the likelihood of discussing new topics. (notes.kodekloud.com) -
frequency_penalty: Reduces the model's tendency to repeat the same tokens by penalizing tokens based on their existing frequency in the text. Positive values decrease the likelihood of repetition. (notes.kodekloud.com)
These parameters are designed to be flexible and can be adjusted to suit your specific application needs. For example, setting temperature to 0.0 and top_p to 0.0 can produce deterministic outputs, while higher values can generate more diverse and creative responses. (notes.kodekloud.com)
It's important to note that while these parameters are supported in GPT-5, the optimal settings may vary depending on your specific use case and desired output characteristics.
Citations:
- 1: https://medium.com/nerd-for-tech/model-parameters-in-openai-api-161a5b1f8129?utm_source=openai
- 2: https://medium.com/nerd-for-tech/model-parameters-in-openai-api-161a5b1f8129?utm_source=openai
- 3: https://notes.kodekloud.com/docs/Mastering-Generative-AI-with-OpenAI/Understanding-Tokens-and-API-Parameters/Understanding-OpenAI-API-Parameters?utm_source=openai
- 4: https://notes.kodekloud.com/docs/Mastering-Generative-AI-with-OpenAI/Understanding-Tokens-and-API-Parameters/Understanding-OpenAI-API-Parameters?utm_source=openai
- 5: https://notes.kodekloud.com/docs/Mastering-Generative-AI-with-OpenAI/Understanding-Tokens-and-API-Parameters/Understanding-OpenAI-API-Parameters?utm_source=openai
Remove GPT-5 special-case for temperature
GPT-5 supports temperature, top_p, presence_penalty, and frequency_penalty just like other GPT models. We shouldn’t force temperature = 1 only for GPT-5—let it use modelConfig.temperature unless we have a clear reason to pin it. Please update in app/client/platforms/openai.ts around lines 234–238:
- temperature: (!isO1OrO3 && !isGpt5) ? modelConfig.temperature : 1,
+ // Only force temperature=1 for O1/O3; GPT-5 should respect the configured value.
+ temperature: isO1OrO3 ? 1 : modelConfig.temperature,
presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0,
frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0,
top_p: !isO1OrO3 ? modelConfig.top_p : 1,This removes the isGpt5 check so GPT-5 calls remain configurable.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| temperature: (!isO1OrO3 && !isGpt5) ? modelConfig.temperature : 1, | |
| presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0, | |
| frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0, | |
| top_p: !isO1OrO3 ? modelConfig.top_p : 1, | |
| // max_tokens: Math.max(modelConfig.max_tokens, 1024), | |
| // Only force temperature=1 for O1/O3; GPT-5 should respect the configured value. | |
| temperature: isO1OrO3 ? 1 : modelConfig.temperature, | |
| presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0, | |
| frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0, | |
| top_p: !isO1OrO3 ? modelConfig.top_p : 1, | |
| // max_tokens: Math.max(modelConfig.max_tokens, 1024), |
🤖 Prompt for AI Agents
In app/client/platforms/openai.ts around lines 234 to 238, remove the
special-case check for GPT-5 in the temperature setting. Update the temperature
assignment to use modelConfig.temperature for all models, including GPT-5, by
eliminating the isGpt5 condition. Ensure presence_penalty, frequency_penalty,
and top_p remain conditional only on isO1OrO3 as before, without affecting GPT-5
handling.
| if (isGpt5) { | ||
| // Remove max_tokens if present | ||
| delete requestPayload.max_tokens; | ||
| // Add max_completion_tokens (or max_completion_tokens if that's what you meant) | ||
| requestPayload["max_completion_tokens"] = modelConfig.max_tokens; | ||
|
|
There was a problem hiding this comment.
🛠️ Refactor suggestion
TS safety and clarity: avoid deleting from a union-typed payload; set max_completion_tokens via a narrowed alias
delete on a union (RequestPayload | DalleRequestPayload) can trip TS checks. Also the comment repeats “max_completion_tokens”.
Apply:
- if (isGpt5) {
- // Remove max_tokens if present
- delete requestPayload.max_tokens;
- // Add max_completion_tokens (or max_completion_tokens if that's what you meant)
- requestPayload["max_completion_tokens"] = modelConfig.max_tokens;
- } else if (isO1OrO3) {
+ if (isGpt5) {
+ // GPT‑5 uses max_completion_tokens
+ const payload = requestPayload as RequestPayload;
+ payload.max_completion_tokens = modelConfig.max_tokens;
+ } else if (isO1OrO3) {This avoids delete on a union and fixes the comment.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| if (isGpt5) { | |
| // Remove max_tokens if present | |
| delete requestPayload.max_tokens; | |
| // Add max_completion_tokens (or max_completion_tokens if that's what you meant) | |
| requestPayload["max_completion_tokens"] = modelConfig.max_tokens; | |
| if (isGpt5) { | |
| // GPT-5 uses max_completion_tokens | |
| const payload = requestPayload as RequestPayload; | |
| payload.max_completion_tokens = modelConfig.max_tokens; | |
| } else if (isO1OrO3) { |
🤖 Prompt for AI Agents
In app/client/platforms/openai.ts around lines 242 to 247, avoid using delete on
a union-typed requestPayload as it causes TypeScript errors. Instead, create a
narrowed alias for the payload type that allows safe modification, then set
max_completion_tokens on that alias. Also, correct the comment to remove the
repeated phrase "max_completion_tokens" for clarity.
| /gpt-5/ | ||
| ]; |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Avoid blanket vision classification for all GPT‑5 variants
Using /gpt-5/ will flag nano/mini variants as vision-capable, which may cause image payloads to be sent to text-only models. Narrow the regex.
Apply:
- /grok-4/i,
- /gpt-5/
+ /grok-4/i,
+ /gpt-5(?!-(nano|mini))/If specific GPT‑5 vision SKUs differ, switch to an explicit allowlist instead of a broad regex. Please verify GPT‑5 nano/mini image-input support in current docs.
🌐 Web query:
Which OpenAI GPT-5 model variants support image inputs via the chat/completions API? Specifically, do "gpt-5-mini" and "gpt-5-nano" accept vision (image_url) content?
💡 Result:
GPT-5 Full supports image (vision) inputs via the chat/completions API, but gpt-5-mini and gpt-5-nano are either limited or do not have native support for image (image_url) content as input.
Details and evidence:
-
GPT-5 Full is clearly described in official model documentation and API guides as accepting both text and image inputs for chat/completions, with a 400,000 token context window[3][5]. Multiple sources confirm that the flagship GPT-5 is a multimodal model designed to handle simultaneous text and vision inputs directly in the chat/completions endpoint[3][5][8][9].
-
GPT-5 Mini offers a downsized model for cost and speed, but public technical docs and third-party guides do not confirm vision input support via the chat/completions API. The most detailed API specification and model overview for gpt-5-mini emphasize text processing, large context windows, and quick response times, but do not state it accepts image_url or vision content as input[2][4]. This is also consistent with third-party documentation and community reports[6][10].
-
GPT-5 Nano is even further optimized for edge and real-time text tasks. Official model guides state it processes single images, but only for constrained use cases such as mobile inference—not for general multimodal chat/completions (e.g., not by passing "image_url" in the typical API structure)[2]. This suggests the Nano variant's image handling is not equivalent to the flagship's fully supported multimodal input[2][6].
-
Table summary (based on official and developer sources):
| Model Variant | Text Input | Image Input via Chat/Completions API |
|---|---|---|
| gpt-5 (Full) | Yes | Yes |
| gpt-5-mini | Yes | No (not supported or very limited) |
| gpt-5-nano | Yes | No (not supported or very limited) |
- Additional Clarification:
Official OpenAI documentation and reputable blog reviews clarify that GPT-5 supports both text and image (vision) input, but audio and image generation remain covered by specialized models like GPT-4o Audio and GPT Image 1[8]. There is no public evidence that gpt-5-mini and gpt-5-nano offer full multimodal chat/completions support for vision input (image_url)[2][6][8].
Conclusion:
You can use image inputs with GPT-5 Full via the chat/completions API. gpt-5-mini and gpt-5-nano do not natively accept vision (image_url) content as input in the chat/completions endpoint; they are text-specialized models, with only minimal or separate image processing capabilities[2][6][8].
Citations:
- 1: https://platform.openai.com/docs/guides/tools-image-generation
- 2: https://www.cursor-ide.com/blog/gpt-5-api-guide
- 3: https://platform.openai.com/docs/models/gpt-5-chat-latest
- 4: https://openrouter.ai/openai/gpt-5-mini
- 5: https://openrouter.ai/openai/gpt-5
- 6: https://docs.litellm.ai/docs/providers/openai
- 7: https://platform.openai.com/docs/guides/images-vision
- 8: https://simonwillison.net/2025/Aug/7/gpt-5/
- 9: https://openai.com/index/introducing-gpt-5/
- 10: https://community.openai.com/t/gpt-5-gpt-5-mini-and-gpt-5-nano-now-available-in-the-api/1337048
Narrow GPT-5 Regex to Exclude Non-Vision Variants
GPT-5 Full accepts image inputs via the chat/completions API, but gpt-5-mini and gpt-5-nano do not. Using a blanket /gpt-5/ will mistakenly flag those text-only variants as vision-capable.
Please update the regex in app/constant.ts (around lines 496–497):
- /grok-4/i,
- /gpt-5/
+ /grok-4/i,
+ /gpt-5(?!-(nano|mini))/If OpenAI introduces new GPT-5 SKUs with vision support in the future, switch to an explicit allowlist for better precision.
🤖 Prompt for AI Agents
In app/constant.ts around lines 496 to 497, the regex /gpt-5/ is too broad and
incorrectly matches GPT-5 variants without vision capabilities like gpt-5-mini
and gpt-5-nano. Update the regex to explicitly match only the GPT-5 variants
that support vision inputs, excluding the non-vision ones. Consider using an
explicit allowlist pattern for the known vision-capable GPT-5 SKUs to ensure
precise matching and easier future updates.
|
when will the azure gpt-5 and gpt-image-1 will support |
3 participants
💻 变更类型 | Change Type
🔀 变更说明 | Description of Change
New Feature:
Summary by CodeRabbit
New Features
Bug Fixes