-
Notifications
You must be signed in to change notification settings - Fork 4.5k
Preserve thinking content for providers that require it #8857
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
jh-block
wants to merge
5
commits into
main
Choose a base branch
from
jhugo/investigate-issue-7363
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
a02a417
Add declarative Anthropic thinking preservation and Z.AI provider
jh-block c4eb8cb
Restrict OpenAI request params to supported fields
jh-block 81da1fb
Add opt-in thinking replay for OpenAI-compatible providers
jh-block fd13ad1
Preserve thinking for reasoning providers
jh-block 95a5fac
Merge streamed reasoning suffixes for OpenAI-compatible tools
jh-block File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| { | ||
| "name": "zai", | ||
| "engine": "anthropic", | ||
| "display_name": "Z.AI", | ||
| "description": "Z.AI GLM models via Anthropic-compatible API.", | ||
| "api_key_env": "ZHIPU_API_KEY", | ||
| "base_url": "${ZAI_BASE_URL}", | ||
| "env_vars": [ | ||
| { | ||
| "name": "ZAI_BASE_URL", | ||
| "required": false, | ||
| "secret": false, | ||
| "default": "https://api.z.ai/api/anthropic", | ||
| "description": "Z.AI Anthropic-compatible API base URL." | ||
| } | ||
| ], | ||
| "catalog_provider_id": "zai", | ||
| "model_doc_link": "https://docs.z.ai/devpack/tool/goose", | ||
| "fast_model": "glm-4.5-air", | ||
| "preserves_thinking": true, | ||
| "models": [ | ||
| {"name": "glm-5.1", "context_limit": 200000}, | ||
| {"name": "glm-5", "context_limit": 204800}, | ||
| {"name": "glm-5-turbo", "context_limit": 200000}, | ||
| {"name": "glm-4.7", "context_limit": 204800}, | ||
| {"name": "glm-4.7-flash", "context_limit": 200000}, | ||
| {"name": "glm-4.7-flashx", "context_limit": 200000}, | ||
| {"name": "glm-4.6", "context_limit": 204800}, | ||
| {"name": "glm-4.5", "context_limit": 131072}, | ||
| {"name": "glm-4.5-air", "context_limit": 131072}, | ||
| {"name": "glm-4.5-flash", "context_limit": 131072} | ||
| ], | ||
| "supports_streaming": true | ||
| } |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fresh evidence after the earlier
custom_deepseekconcern: this commit marks built-in JSONs aspreserves_thinking: true, but newly created custom providers are now hardcoded topreserves_thinking: falsehere, and the create/update request types still expose no way to set it. Sinceformat_messages_with_optionsinproviders/formats/openai.rsnow sendsreasoning_contentonly when that flag is enabled, custom OpenAI-compatible providers that depend on reasoning replay can silently lose tool-call continuation context unless users manually edit provider JSON.Useful? React with 👍 / 👎.