ISSUE DESCRIPTION [Feature] Map thinkinglevel to DeepSeek thinking fields 🎯 The Goal /…
- User
ISSUE DESCRIPTION
[Feature] Map thinking_level to DeepSeek thinking fields
🎯 The Goal / Use Case
DeepSeek is currently treated as an OpenAI-compatible provider in PicoClaw, but its thinking-mode controls do not match the internal
thinking_levelabstraction 1:1.Please implement correct DeepSeek thinking mapping so that:
- explicit
thinking_level: "off"automatically disables DeepSeek thinking mode - thinking-enabled levels are translated to DeepSeek's documented OpenAI-compatible fields
- DeepSeek users can rely on the same
thinking_levelconfig without needing manualextra_bodyoverrides
💡 Proposed Solution
Add DeepSeek-specific request shaping on the OpenAI-compatible path.
Suggested mapping:
thinking_level: "off"->thinking: { "type": "disabled" }thinking_level: "high"->thinking: { "type": "enabled" }+reasoning_effort: "high"thinking_level: "xhigh"->thinking: { "type": "enabled" }+reasoning_effort: "max"
If
low/mediumare kept as valid internal levels, they can follow DeepSeek's documented compatibility behavior and map toreasoning_effort: "high".🛠 Potential Implementation (Optional)
PR #2898 already introduced explicit
thinking_level: "off"handling for several OpenAI-compatible providers and added provider-specific disable-field shaping.This issue is to extend that work for DeepSeek specifically:
- add DeepSeek request shaping on the OpenAI-compatible provider path
- map internal thinking levels to DeepSeek's
thinkingandreasoning_effortfields - ensure explicit
offis sent even when DeepSeek does not advertise generic thinking support viaSupportsThinking() - add tests covering both request shaping and fallback/rewrite paths if applicable
🚦 Impact & Roadmap Alignment
- This is a Core Feature
- This is a Nice-to-Have / Enhancement
- This aligns with the current Roadmap
🔄 Alternatives Considered
- Ask users to configure DeepSeek manually with
extra_body - Keep DeepSeek on the generic OpenAI-compatible path without provider-specific thinking mapping
Both alternatives are weaker because they make DeepSeek behavior inconsistent with the project-wide
thinking_levelabstraction.💬 Additional Context
https://api-docs.deepseek.com/zh-cn/guides/thinking_mode
DeepSeek's documented OpenAI-compatible thinking controls use:
thinking.typereasoning_effortreasoning_contentin responses
PR #2898 is closely related because it establishes the explicit-
offbehavior and provider-specific request shaping pattern. DeepSeek appears to still need its own mapping added on top of that work.Interface
Type: Function Name: SupportsThinking Path: pkg/providers/httpapi/http_provider.go Input: () Output: bool Description: Exposes the thinking capability of the underlying provider delegate over the HTTP API. Returns true if the delegate supports thinking; otherwise false.
ADDITIONAL ADVICE
Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use
git checkout <file>to restore the file to its original state. You can also reset all changes in the repository usinggit reset --hardcommand. Additionally, you can usegit stashandgit stash popto temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you callsubmit) usinggit statusorgit diffcommands. However you don't need to usegit addorgit commitbefore submitting your changes. In fact,submitonly submits currently unstaged changes because it usesgit diffto get the changes that need to be submitted.CHECKLIST
Before submitting your solution, please go over the following checklist and make sure you've done everything:
- If an error was reported in the issue description, I have successfully reproduced it.
- If an error was reported in the issue description, I have confirmed that my fix resolves the error.
- I have thought about edge cases and made sure my fix handles them as well.
- I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.
Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!
(Current directory: /picoclaw, current file: none) bash-$
- explicit
Assistant
Let me start by exploring the repository structure to understand what we're working with.
Assistant
Let me explore the structure moredeeply.
Assistant
Now let's look at the openai_compat package to understand how it currently works:
Assistant
Let me see the truncated part of the file:
Assistant
Now let me check the existing tests for understanding the test conventions:
Assistant
Now let me look at how the SupportsThinking capability is used:
Assistant
Now let me look at the
httpapi_facade.goto see if there's a SupportsThinking method already:Assistant
Now let me check more places where DeepSeek is handled and where SupportsThinking is being added:
Assistant
Let me check the openai_compat.Provider's existing methods:
Assistant
Let me see the recent git log:
Assistant
Let me look at how SupportsNativeSearch is implemented in openai_compat.Provider to follow the same pattern:
Assistant
Let me look at the existing tests for thinking-related features:
Assistant
Let me look at how the httpapi package handles SupportsThinking and other tests:
Assistant
Let me write a quick reproduce script to ensure my understanding of the current state:
Assistant
Let me make a proper test to confirm current state:
Assistant
Let me create a proper Go test file inside the openai_compat package to test current behavior:
Assistant
I've confirmed the current behavior: DeepSeek thinking levels are silently ignored. Now let me clean up the temp test and implement the changes.
Assistant
Now let me look at the full thinking.go to understand the agent flow:
Assistant
Let me look at the agent test patterns for understanding SupportsThinking integration:
Assistant
Let me look at
thinkingOptionRecordingProvider:Assistant
Now I have a complete picture. Let me implement the changes.
Step 1: Modify openai_compat/provider.go
First, let me look at the existing applyThinkingControl code:
Assistant
Now let me make the modifications to openai_compat/provider.go:
Assistant
Let me directly edit the file:
Assistant
Now let me update the applyThinkingControl function:
Assistant
Now let me add the deepseek case in the provider name switch and the SupportsThinking method. Let me add the deepseek case in the switch:
Assistant
Now let me add the SupportsThinking method to the openai_compat Provider. Let me first see where SupportsNativeSearch is defined:
Assistant
Now let me add the SupportsThinking method:
Assistant
I noticed I missed a blank line. Let me fix that:
Assistant
I see a duplicated line. Let me fix it:
Assistant
There are duplicate SupportsThinking definitions. Let me clean it up:
Assistant
There are still duplicate SupportsNativeSearch definitions. Let me checkwhat's happening:
Assistant
I see the duplication. Let me look at the file structure:
Assistant
Let me view the file from line 825 to make sure there are no duplicates:
Assistant
The file looks good. Let me fix the missing blank lines for proper formatting:
Assistant
Let me reset the file and start fresh:
Assistant
Good, the file is reset. Now let me apply the changes more carefully using Python:
Assistant
Now let me run the tests to ensure my changes compile:
Assistant
The code compiles. Now let me update HTTPProvider to add SupportsThinking:
Assistant
Let me reset the openai_compat file and start fresh:
Assistant
The file was reset. Let me re-apply changes and properly open the right file:
Assistant
Now let me open the httpapi/http_provider.go file:
Assistant
I need to preserve the original
SupportsNativeSearch(). Let me restore that:Assistant
Let me revert the unnecessary change to
SupportsNativeSearch():Assistant
Now let me verify the diff:
Assistant
Now let me build to ensure both files compile:
Assistant
Now let me write a quick test to validate the behavior:
Assistant
There's an import cycle issue. I can't import httpapi from openai_compat tests. Let me update the test to only check the openai_compat level:
Assistant
The behavior works as expected:
off:thinking: {type: "disabled"}low:thinking: {type: "enabled"}+reasoning_effort: "high"medium:thinking: {type: "enabled"}+reasoning_effort: "high"high:thinking: {type: "enabled"}+reasoning_effort: "high"xhigh:thinking: {type: "enabled"}+reasoning_effort: "max"adaptive: ignored (no mapping)
And SupportsThinking returns true for DeepSeek host or provider name.
Now let me clean up the temp test and add proper tests:
Assistant
Now let me also test the HTTPProvider:
Assistant
HTTPProvider.SupportsThinking works as expected. Let me clean up:
Assistant
Now let me add proper tests. First let me look at the test patterns:
Assistant
Now let me add the DeepSeek tests. I'll add them right after the existing thinking tests:
Assistant
Let me check the current file:
Assistant
Wait, the file shown by
headis openai_compat but the displayed file is http_provider.go. That's odd. Let me check both:Assistant
Hmm, the http_provider.go is now 229 lines (was 107). Let me look at it:
Assistant
Let me revert the wrong file:
Assistant
OK, the http_provider.go was reverted but the provider_test.go was also reverted (still2056 lines). Let me also check provider_test.go:
Assistant
Good, the provider_test.go was also reverted. Now I'll use Python to apply changes:
Assistant
Now let me also add a test for HTTPProvider.SupportsThinking:
Assistant
There's no http_provider_test.go yet. Let me create one with tests for SupportsThinking:
Assistant
Now let me run all the tests to verify everything works:
Assistant
All new tests pass. Let me also run the httpapi tests:
Assistant
The http_provider.go was reverted. Let me re-apply the SupportsThinking method:
Assistant
Now let me run the tests:
Assistant
All tests pass. Now let me run all the tests in the providers directory to ensure I haven't broken anything:
Assistant
All tests pass! Now let me also check the agent tests that are related to thinking:
Assistant
All agent tests pass. Let me also check the full diff to make sure I haven't missed anything:
Assistant
Let me check the edge case of extra_body interacting with thinking control:
Assistant
Let me verify my implementation matches the interface specification in the issue:
Assistant
The implementation matches the interface spec. Let me run the full test suite once more to confirm nothing is broken:
Assistant
All tests pass. Let me also run the cmd tests just to be safe:
Assistant
Let me check if this is a pre-existing issue:
Assistant
The error is pre-existing. Let me restore my changes:
Assistant
This is a CGO-related issue with the matrix crypto library, unrelated to my changes. Let me only build the providers package:
Assistant
Everything builds and passes vet. Let me also look at the final diff to verify:
Assistant
Let me check that streaming also benefits from the thinking control:
Assistant
Good. Both Chat and ChatStream use buildRequestBody, so the thinking control applies to both.
Let me also look at the buildRequestBody carefullyto ensure the thinking control is applied before extra_body is merged:
Assistant
Let me also check if there are any other places where DeepSeek thinking handling might be relevant:
Assistant
Let me run all the tests one more time to ensure everything works:
Assistant
All tests pass. Let me also do one final review by viewing the full diff:
Assistant
Let me verify all tests pass one final time:
Assistant
All tests pass. Let me also make a final check that the linting is OK:
Assistant
Let me create a final reproduction script to verify the behavior end-to-end:
Assistant
All mappings work as expected. Let me clean up:
Assistant
Let me also check the diff one more time to ensure everything is good:
Assistant
Let me run the entire test suite once more for final confirmation:
Assistant
All tests pass. Let me also check the documentation/comments are good:
Assistant
Let me also look at the http_provider.go to ensure it's correct:
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
claude-sonnet-5Compare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-35B-A3BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →