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
I'll start by exploring the repository structure to understand the codebase.
Assistant
Let me explore the providers directory structure, particularly looking at httpapi and openai-related providers.
Assistant
Let me see the middle part of the file that was truncated, particularly the
thinkingControlKindfunction and helper functions.Assistant
Let me see the full
thinkingControlKindfunction and the helper functions likeisVolcengineHost,isDashScopeHost, etc.Assistant
Now let me look at the http_provider.go to understand the
SupportsThinkinginterface.Assistant
There's no
SupportsThinkingmethod in http_provider.go. The issue's interface mentions:- 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.
So I need to add a
SupportsThinking()method onHTTPProvider. Let me check if there's already aSupportsThinkingmethod on the openai_compat Provider.Assistant
Let me look at the gemini_provider.go
SupportsThinkingfor reference and the provider_test.go.Assistant
Let me check the httpapi tests directory for any existing tests, and check how the factory creates DeepSeek providers.
Assistant
Let me look at how the HTTPProvider is used and whether there's a facade that wraps it.
Assistant
Let me look at the
finalizeProviderFromConfigand thetoolSchemaTransformProviderwrapper.Assistant
Let me check existing tests for DeepSeek thinking and look at the gemini thinking test patterns.
Assistant
Let me check if there's an http_provider test file in httpapi.
Assistant
No http_provider test file. Only gemini_provider_test.go. Let me look at how the agent test uses SupportsThinking to understand the expected behavior.
Assistant
Now let me check the legacy_provider and any other places that might need SupportsThinking.
Assistant
Now I have a complete understanding. Let me implement the changes. First, let me modify
openai_compat/provider.go.Assistant
Now let me edit the
applyThinkingControlfunction and add the DeepSeek mapping:Assistant
Now let me replace the
applyThinkingControlfunction with the DeepSeek-aware version:Assistant
Now let me add the
isDeepSeekProviderhelper andSupportsThinkingmethod. Let me find theisDeepSeekHostfunction:Assistant
Now let me add the
isDeepSeekProvidermethod afterisDeepSeekHost, and addSupportsThinkingafterSupportsNativeSearch:Assistant
I see a duplicate was created. Let me fix lines 355-379 to have a single clean
isDeepSeekHostplus the newisDeepSeekProvider:Assistant
Now let me add the
SupportsThinkingmethod on the openai_compatProvider, right afterSupportsNativeSearch:Assistant
There's an extra closing brace at line 861. Let me remove it:
Assistant
Let me add a blank line after the
SupportsThinkingfunction:Assistant
Now let me add the
SupportsThinkingmethod to theHTTPProviderinhttp_provider.go:Assistant
Now let me build to check for compilation errors:
Assistant
The only error is a pre-existing embed pattern issue unrelated to my change. Let me build the specific packages I changed:
Assistant
Build passes. Let me run the existing tests for the relevant packages:
Assistant
All tests pass. Now let me write a temporary test script to verify the DeepSeek thinking mapping behavior end-to-end:
Assistant
All my temporary tests pass. Let me also test that the HTTPProvider
SupportsThinkingis properly delegated through the wrapper, and that doubao still preserves behavior:Assistant
Let me write an integration-style test verifying the full request shaping through the HTTPProvider with a mock server:
Assistant
Excellent! The full path works. Now let me remove the temporary test files and run the full relevant test suite:
Assistant
All tests pass. Let me verify the temporary test files are gone and review my final diff:
Assistant
The diff is clean. Let me verify the pre-existing embed error is unrelated to my change by checking it on a clean tree:
Assistant
Confirmed: the
pattern workspaceembed error is pre-existing on the clean tree and unrelated to my changes. My affected packages build and test cleanly.Let me do a final review of the complete changed sections to ensure correctness:
Assistant
Everything looks correct. Let me run the broader test suite one final time to be thorough, including any tests that might touch the factory:
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 →