feat: Add GPT-5 series models to OpenAI metadata#9336
feat: Add GPT-5 series models to OpenAI metadata#9336edwinjosechittilappilly merged 4 commits intomainfrom
Conversation
Introduces metadata entries for the new GPT-5, GPT-5-mini, GPT-5-nano, and GPT-5-chat-latest models in the OPENAI_MODELS_DETAILED list. This update ensures these models are recognized and available for use in the application.
|
Important Review skippedAuto incremental reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the WalkthroughThis change adds four new GPT-5 Series model metadata entries to the Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Suggested labels
Suggested reviewers
✨ 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/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
github-actions
bot
added
enhancement
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
src/backend/base/langflow/base/models/openai_constants.py (1)
5-33: Validate GPT-5 metadata before exposing in productionThe four new GPT-5 entries in
src/backend/base/langflow/base/models/openai_constants.pyare currently marked asreasoning=True, so they will:
- Be grouped under
OPENAI_REASONING_MODEL_NAMES(hiding temperature & seed UI controls).- Route through reasoning-only branches in both component and agent logic.
- Retain
tool_calling=Truefor “gpt-5”, “gpt-5-mini” and “gpt-5-nano”, buttool_calling=Falsefor “gpt-5-chat-latest”.Action items:
- If GPT-5 is not yet GA, add
preview=Trueornot_supported=Trueto each metadata block to prevent premature exposure.- Confirm which GPT-5 variants support the standard chat API (and temperature/seed) versus reasoning-only.
- For chat-capable models, set
reasoning=False(and ensure they appear inOPENAI_CHAT_MODEL_NAMES).- Verify the
tool_callingflags align with OpenAI’s published capabilities.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/backend/base/langflow/base/models/openai_constants.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
{src/backend/**/*.py,tests/**/*.py,Makefile}
📄 CodeRabbit Inference Engine (.cursor/rules/backend_development.mdc)
{src/backend/**/*.py,tests/**/*.py,Makefile}: Run make format_backend to format Python code before linting or committing changes
Run make lint to perform linting checks on backend Python code
Files:
src/backend/base/langflow/base/models/openai_constants.py
🧠 Learnings (2)
📓 Common learnings
Learnt from: ogabrielluiz
PR: langflow-ai/langflow#9054
File: src/backend/tests/unit/components/agents/test_agent_component.py:104-133
Timestamp: 2025-07-15T14:37:19.189Z
Learning: The GPT-4.1 series models (GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano) are valid OpenAI models introduced on April 14, 2025, available exclusively through OpenAI's API with enhanced coding capabilities and 1 million token context support.
📚 Learning: 2025-07-15T14:37:19.189Z
Learnt from: ogabrielluiz
PR: langflow-ai/langflow#9054
File: src/backend/tests/unit/components/agents/test_agent_component.py:104-133
Timestamp: 2025-07-15T14:37:19.189Z
Learning: The GPT-4.1 series models (GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano) are valid OpenAI models introduced on April 14, 2025, available exclusively through OpenAI's API with enhanced coding capabilities and 1 million token context support.
Applied to files:
src/backend/base/langflow/base/models/openai_constants.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: Label PR
- GitHub Check: Run Ruff Check and Format
- GitHub Check: Update Starter Projects
- GitHub Check: Ruff Style Check (3.13)
🔇 Additional comments (1)
src/backend/base/langflow/base/models/openai_constants.py (1)
5-33: Reminder: run backend format & lint locally
Please ensure you’ve formatted and linted the Python backend code before merging. In your local environment, run:make format_backend && make lintThe sandbox doesn’t support
make, so verify these steps pass on your machine to keep the codebase consistent.
| # GPT-5 Series | ||
| create_model_metadata( | ||
| provider="OpenAI", | ||
| name="gpt-5", | ||
| icon="OpenAI", | ||
| tool_calling=True, | ||
| reasoning=True, | ||
| ), | ||
| create_model_metadata( | ||
| provider="OpenAI", | ||
| name="gpt-5-mini", | ||
| icon="OpenAI", | ||
| tool_calling=True, | ||
| reasoning=True, | ||
| ), | ||
| create_model_metadata( | ||
| provider="OpenAI", | ||
| name="gpt-5-nano", | ||
| icon="OpenAI", | ||
| tool_calling=True, | ||
| reasoning=True, | ||
| ), | ||
| create_model_metadata( | ||
| provider="OpenAI", | ||
| name="gpt-5-chat-latest", | ||
| icon="OpenAI", | ||
| tool_calling=False, | ||
| reasoning=True, | ||
| ), |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Critical: GPT-5 entries flagged as reasoning models will be excluded from chat model list (and may trigger reasoning-specific code paths).
OPENAI_CHAT_MODEL_NAMES (Lines 92-98) filters out entries with reasoning=True. With the current flags, none of the GPT-5 models will appear as selectable chat models, contradicting the PR goal “made available for use.” Also, some code paths may treat reasoning models differently (e.g., different API routes/options), which could mis-handle gpt-5 if it’s a general chat model.
Recommend treating GPT-5 series as chat models (reasoning=False). Also, gpt-5-chat-latest should have tool_calling=True for parity with other “chat” entries.
Apply this diff:
@@
- create_model_metadata(
- provider="OpenAI",
- name="gpt-5",
- icon="OpenAI",
- tool_calling=True,
- reasoning=True,
- ),
+ create_model_metadata(
+ provider="OpenAI",
+ name="gpt-5",
+ icon="OpenAI",
+ tool_calling=True,
+ reasoning=False,
+ ),
@@
- create_model_metadata(
- provider="OpenAI",
- name="gpt-5-mini",
- icon="OpenAI",
- tool_calling=True,
- reasoning=True,
- ),
+ create_model_metadata(
+ provider="OpenAI",
+ name="gpt-5-mini",
+ icon="OpenAI",
+ tool_calling=True,
+ reasoning=False,
+ ),
@@
- create_model_metadata(
- provider="OpenAI",
- name="gpt-5-nano",
- icon="OpenAI",
- tool_calling=True,
- reasoning=True,
- ),
+ create_model_metadata(
+ provider="OpenAI",
+ name="gpt-5-nano",
+ icon="OpenAI",
+ tool_calling=True,
+ reasoning=False,
+ ),
@@
- create_model_metadata(
- provider="OpenAI",
- name="gpt-5-chat-latest",
- icon="OpenAI",
- tool_calling=False,
- reasoning=True,
- ),
+ create_model_metadata(
+ provider="OpenAI",
+ name="gpt-5-chat-latest",
+ icon="OpenAI",
+ tool_calling=True,
+ reasoning=False,
+ ),📝 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.
| # GPT-5 Series | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=True, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-mini", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=True, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-nano", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=True, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-chat-latest", | |
| icon="OpenAI", | |
| tool_calling=False, | |
| reasoning=True, | |
| ), | |
| # GPT-5 Series | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-mini", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-nano", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-chat-latest", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), |
🤖 Prompt for AI Agents
In src/backend/base/langflow/base/models/openai_constants.py between lines 5 and
33, the GPT-5 models are incorrectly marked with reasoning=True, causing them to
be excluded from the chat model list and potentially triggering
reasoning-specific code paths. To fix this, set reasoning=False for all GPT-5
models and change tool_calling to True for the gpt-5-chat-latest model to align
it with other chat models.
There was a problem hiding this comment.
That is right, GPT5 act as a reasoning model
There was a problem hiding this comment.
@edwinjosechittilappilly Thank you for the clarification! I understand now that GPT-5 models are intended to function as reasoning models, similar to the o1/o3 series. The current implementation with reasoning=True is correct then.
✏️ Learnings added
Learnt from: edwinjosechittilappilly
PR: langflow-ai/langflow#9336
File: src/backend/base/langflow/base/models/openai_constants.py:5-33
Timestamp: 2025-08-11T16:52:17.859Z
Learning: In the Langflow codebase (src/backend/base/langflow/base/models/openai_constants.py), GPT-5 series models (gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat-latest) are reasoning models and should have the reasoning=True flag set, which places them in OPENAI_REASONING_MODEL_NAMES rather than OPENAI_CHAT_MODEL_NAMES.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
| name="gpt-5-chat-latest", | ||
| icon="OpenAI", | ||
| tool_calling=False, | ||
| reasoning=True, | ||
| ), |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Double-check intent for “gpt-5-chat-latest”: tool_calling should be True for a chat alias.
Every other chat-capable entry sets tool_calling=True. Setting it to False diminishes functionality unexpectedly.
If “chat-latest” is a general chat alias, switch tool_calling to True (and keep reasoning=False as suggested above).
🤖 Prompt for AI Agents
In src/backend/base/langflow/base/models/openai_constants.py around lines 29 to
33, the entry for "gpt-5-chat-latest" has tool_calling set to False, which is
inconsistent with other chat-capable entries. Change tool_calling to True to
enable full chat functionality, and also update reasoning to False as suggested.
This aligns the settings with the intended behavior for a general chat alias.
There was a problem hiding this comment.
gpt-5-chat-latest doesnt support tool calling
There was a problem hiding this comment.
@edwinjosechittilappilly, thank you for the clarification! I understand that gpt-5-chat-latest doesn't support tool calling, so the current configuration with tool_calling=False is correct.
✏️ Learnings added
Learnt from: edwinjosechittilappilly
PR: langflow-ai/langflow#9336
File: src/backend/base/langflow/base/models/openai_constants.py:29-33
Timestamp: 2025-08-11T16:52:26.715Z
Learning: The "gpt-5-chat-latest" model in the OpenAI models configuration does not support tool calling, so tool_calling should be set to False for this model in src/backend/base/langflow/base/models/openai_constants.py.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
There was a problem hiding this comment.
Actionable comments posted: 3
🔭 Outside diff range comments (1)
src/backend/base/langflow/base/models/openai_constants.py (1)
92-104: Ensure GPT-5 series appears in default chat modelsThe new GPT-5 entries are currently tagged with
reasoning=True, so they’re filtered out ofOPENAI_CHAT_MODEL_NAMES(lines 92–98) and thus never make it intoMODEL_NAMES(line 121). If the intent is to “make [GPT-5] available for use” as chat models, we need to update the flags or the filter logic.• File: src/backend/base/langflow/base/models/openai_constants.py
– Lines 92–98:OPENAI_CHAT_MODEL_NAMESexcludes any model withreasoning=True.
– Line 121:MODEL_NAMESis set toOPENAI_CHAT_MODEL_NAMES.Recommendations:
- Remove or override the
reasoning=Trueflag on the GPT-5 entries if they should be in the chat list.- Or adjust the chat-model filter to include reasoning-capable models.
- Add a unit test asserting that
"gpt-5","gpt-5-mini", and"gpt-5-nano"appear inOPENAI_CHAT_MODEL_NAMES.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/backend/base/langflow/base/models/openai_constants.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
{src/backend/**/*.py,tests/**/*.py,Makefile}
📄 CodeRabbit Inference Engine (.cursor/rules/backend_development.mdc)
{src/backend/**/*.py,tests/**/*.py,Makefile}: Run make format_backend to format Python code before linting or committing changes
Run make lint to perform linting checks on backend Python code
Files:
src/backend/base/langflow/base/models/openai_constants.py
🧠 Learnings (2)
📓 Common learnings
Learnt from: ogabrielluiz
PR: langflow-ai/langflow#9054
File: src/backend/tests/unit/components/agents/test_agent_component.py:104-133
Timestamp: 2025-07-15T14:37:19.189Z
Learning: The GPT-4.1 series models (GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano) are valid OpenAI models introduced on April 14, 2025, available exclusively through OpenAI's API with enhanced coding capabilities and 1 million token context support.
📚 Learning: 2025-07-15T14:37:19.189Z
Learnt from: ogabrielluiz
PR: langflow-ai/langflow#9054
File: src/backend/tests/unit/components/agents/test_agent_component.py:104-133
Timestamp: 2025-07-15T14:37:19.189Z
Learning: The GPT-4.1 series models (GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano) are valid OpenAI models introduced on April 14, 2025, available exclusively through OpenAI's API with enhanced coding capabilities and 1 million token context support.
Applied to files:
src/backend/base/langflow/base/models/openai_constants.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Run Ruff Check and Format
- GitHub Check: Update Starter Projects
- GitHub Check: Ruff Style Check (3.13)
🔇 Additional comments (1)
src/backend/base/langflow/base/models/openai_constants.py (1)
5-5: Confirmed GPT-5 Series Model IDs and CapabilitiesI’ve verified against the official OpenAI documentation:
gpt-5, gpt-5-mini, gpt-5-nano
• Full/partial/minimal reasoning models
• Full tool-calling support (standard & custom tools)
• Ideal for agentic workflows, coding, research, automationgpt-5-chat-latest
• Chat-optimized only (no reasoning)
• Does not support tool calling
• Best for casual, conversational UIsNo changes to the existing constants are needed—the identifiers and comment in
openai_constants.pyare accurate.
| provider="OpenAI", | ||
| name="gpt-5", | ||
| icon="OpenAI", | ||
| tool_calling=True, | ||
| reasoning=True, | ||
| ), |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Reconsider reasoning=True for gpt-5 (will exclude it from chat models).
With reasoning=True, "gpt-5" will be filtered out of OPENAI_CHAT_MODEL_NAMES and only appear under OPENAI_REASONING_MODEL_NAMES. If GPT-5 is a general chat model, set reasoning=False so it’s surfaced in chat lists.
Proposed change:
- tool_calling=True,
- reasoning=True,
+ tool_calling=True,
+ reasoning=False,🏁 Script executed:
#!/bin/bash
# Display the relevant portion of openai_constants.py to verify reasoning logic
FILE="src/backend/base/langflow/base/models/openai_constants.py"
if [ -f "$FILE" ]; then
sed -n '1,200p' "$FILE"
else
echo "File not found: $FILE"
fiLength of output: 4962
Disable reasoning for gpt-5 to include it in chat models
With reasoning=True, “gpt-5” is excluded from OPENAI_CHAT_MODEL_NAMES and only surfaces under reasoning models. If it’s intended as a general chat model, set reasoning=False so it appears in chat lists.
• File: src/backend/base/langflow/base/models/openai_constants.py
• Lines: 7–12
Suggested diff:
--- a/src/backend/base/langflow/base/models/openai_constants.py
+++ b/src/backend/base/langflow/base/models/openai_constants.py
@@ create_model_metadata(
- tool_calling=True,
- reasoning=True,
+ tool_calling=True,
+ reasoning=False,📝 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.
| provider="OpenAI", | |
| name="gpt-5", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=True, | |
| ), | |
| provider="OpenAI", | |
| name="gpt-5", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), |
🤖 Prompt for AI Agents
In src/backend/base/langflow/base/models/openai_constants.py between lines 7 and
12, the "gpt-5" model has reasoning set to True, which excludes it from the
general chat models list. To fix this, change the reasoning attribute for
"gpt-5" from True to False so it is included in OPENAI_CHAT_MODEL_NAMES and
treated as a general chat model.
| provider="OpenAI", | ||
| name="gpt-5-mini", | ||
| icon="OpenAI", | ||
| tool_calling=True, | ||
| reasoning=True, | ||
| ), | ||
| create_model_metadata( | ||
| provider="OpenAI", | ||
| name="gpt-5-nano", | ||
| icon="OpenAI", | ||
| tool_calling=True, | ||
| reasoning=True, | ||
| ), |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Align flags for gpt-5-mini and gpt-5-nano with intended category.
Both entries have reasoning=True, which removes them from chat lists. If these are standard chat models, flip reasoning to False so they appear in OPENAI_CHAT_MODEL_NAMES.
name="gpt-5-mini",
icon="OpenAI",
- tool_calling=True,
- reasoning=True,
+ tool_calling=True,
+ reasoning=False,
),
create_model_metadata(
provider="OpenAI",
name="gpt-5-nano",
icon="OpenAI",
- tool_calling=True,
- reasoning=True,
+ tool_calling=True,
+ reasoning=False,
),I’ll pull all model metadata entries and locate the chat‐model list to confirm the intended flags.
🏁 Script executed:
#!/bin/bash
# List all create_model_metadata calls in the OpenAI constants file
rg -n "create_model_metadata" src/backend/base/langflow/base/models/openai_constants.py
echo
echo "### OPENAI_CHAT_MODEL_NAMES definition and usage ###"
rg -n "OPENAI_CHAT_MODEL_NAMES" -n .Length of output: 197792
Align gpt-5-mini and gpt-5-nano flags with chat models
Both entries are currently marked reasoning=True, which excludes them from OPENAI_CHAT_MODEL_NAMES (the dropdown of chat models). Since these act as standard chat + tool-calling models, flip reasoning to False so they appear in the chat list.
In src/backend/base/langflow/base/models/openai_constants.py:
create_model_metadata(
provider="OpenAI",
name="gpt-5-mini",
icon="OpenAI",
tool_calling=True,
- reasoning=True,
+ reasoning=False,
),
create_model_metadata(
provider="OpenAI",
name="gpt-5-nano",
icon="OpenAI",
tool_calling=True,
- reasoning=True,
+ reasoning=False,
),📝 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.
| provider="OpenAI", | |
| name="gpt-5-mini", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=True, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-nano", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=True, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-mini", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-nano", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), |
🤖 Prompt for AI Agents
In src/backend/base/langflow/base/models/openai_constants.py around lines 14 to
26, the models "gpt-5-mini" and "gpt-5-nano" have the flag reasoning=True, which
excludes them from the chat model dropdown. Change the reasoning flag to False
for both models to align them with standard chat models and ensure they appear
in the OPENAI_CHAT_MODEL_NAMES list.
| provider="OpenAI", | ||
| name="gpt-5-chat-latest", | ||
| icon="OpenAI", | ||
| tool_calling=False, | ||
| reasoning=True, | ||
| ), |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
gpt-5-chat-latest flags look inverted for a chat alias.
Setting tool_calling=False and reasoning=True will exclude this from chat lists; a “chat-latest” alias typically should be a chat model with tool calling enabled. Recommend tool_calling=True and reasoning=False (unless OpenAI docs specify otherwise).
- tool_calling=False,
- reasoning=True,
+ tool_calling=True,
+ reasoning=False,If OpenAI’s latest docs specify different capabilities for this alias, please align with those and consider adding preview=True if it’s an alias that can move.
🏁 Script executed:
#!/bin/bash
# Show context around the gpt-5-chat-latest entry
grep -R -n -C20 "gpt-5-chat-latest" src/backend/base/langflow/base/models/openai_constants.py
# List all model definitions with "chat" in their name for comparison
grep -R -n 'name=".*chat' src/backend/base/langflow/base/models/openai_constants.py
# Find all references to the tool_calling flag to understand how it’s used
grep -R -n "tool_calling" srcLength of output: 292887
🏁 Script executed:
#!/bin/bash
# Find all references to the reasoning flag to understand its usage
grep -R -n "reasoning=" srcLength of output: 1720
🏁 Script executed:
#!/bin/bash
# Locate the "Reasoning Models" section in openai_constants.py
grep -R -n "# Reasoning Models" src/backend/base/langflow/base/models/openai_constants.pyLength of output: 117
🏁 Script executed:
#!/bin/bash
# Print the first 60 lines to see grouping/context
sed -n '1,60p' src/backend/base/langflow/base/models/openai_constants.pyLength of output: 2849
Update GPT-5 chat alias metadata flags
The gpt-5-chat-latest entry in openai_constants.py should be marked as a chat model (tool_calling=True) and not as a reasoning-only variant (reasoning=False), so it appears alongside the other chat models. Please update lines 29–33 as follows:
- create_model_metadata(
- provider="OpenAI",
- name="gpt-5-chat-latest",
- icon="OpenAI",
- tool_calling=False,
- reasoning=True,
- ),
+ create_model_metadata(
+ provider="OpenAI",
+ name="gpt-5-chat-latest",
+ icon="OpenAI",
+ tool_calling=True,
+ reasoning=False,
+ ),📝 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.
| provider="OpenAI", | |
| name="gpt-5-chat-latest", | |
| icon="OpenAI", | |
| tool_calling=False, | |
| reasoning=True, | |
| ), | |
| create_model_metadata( | |
| provider="OpenAI", | |
| name="gpt-5-chat-latest", | |
| icon="OpenAI", | |
| tool_calling=True, | |
| reasoning=False, | |
| ), |
🤖 Prompt for AI Agents
In src/backend/base/langflow/base/models/openai_constants.py between lines 28
and 33, update the metadata for the "gpt-5-chat-latest" model by setting
tool_calling to True and reasoning to False. This change correctly marks it as a
chat model rather than a reasoning-only variant, ensuring it is grouped with
other chat models.
|
FYI I think some of the old OpenAI model (I'm not sure) are now deprecated and the API endpoint not longer exist. Might be interesting to check it at the same time Reply from openai.com/api/v1/models : |
|
@ErwanLorteau Thats interesting, If possible can you share the related docs or create a new PR wrt to it. |
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
github-actions
bot
added
enhancement
|
Codecov Report✅ All modified and coverable lines are covered by tests. ❌ Your project status has failed because the head coverage (2.69%) is below the target coverage (10.00%). You can increase the head coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## main #9336 +/- ##
==========================================
- Coverage 33.51% 33.46% -0.05%
==========================================
Files 1194 1194
Lines 56104 56126 +22
Branches 5279 5279
==========================================
- Hits 18804 18785 -19
- Misses 37240 37281 +41
Partials 60 60
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
Add GPT-5 series models to OpenAI metadata Introduces metadata entries for the new GPT-5, GPT-5-mini, GPT-5-nano, and GPT-5-chat-latest models in the OPENAI_MODELS_DETAILED list. This update ensures these models are recognized and available for use in the application.
Add GPT-5 series models to OpenAI metadata Introduces metadata entries for the new GPT-5, GPT-5-mini, GPT-5-nano, and GPT-5-chat-latest models in the OPENAI_MODELS_DETAILED list. This update ensures these models are recognized and available for use in the application.
|
Thank you so much for adding this @edwinjosechittilappilly . When can we expect this to be released or is it in already? I installed langflow (1.5.1) but could not see gpt-5 in UI. |
4 participants
Introduces metadata entries for the new GPT-5, GPT-5-mini, GPT-5-nano, and GPT-5-chat-latest models in the OPENAI_MODELS_DETAILED list. This update ensures these models are recognized and available for use in the application.
Summary by CodeRabbit