hi: configurable reasoning_effort for OpenAI-compatible endpoints#87
Merged
Conversation
Threads a ReasoningEffort level (minimal/low/medium/high/xhigh) through ChatRequest and emits it as `reasoning_effort` only on the OpenAI-compatible path; the Anthropic adapter keeps using thinking_budget. Previously hi sent no reasoning control at all on the OpenAI path, so models like pipenetwork's ipop/coder-balanced ran at the endpoint default (which is off, not medium). Configurable three ways: - CLI: --reasoning-effort <level> - profile TOML: reasoning_effort = "..." (CLI overrides profile) - runtime: /config reasoning <level|off>, plus /config temp <v|off> Only the main turn takes the configured effort; housekeeping turns (compaction/memory/recap) stay off. Surfaced in --show-config. Verified live: the flag reaches the wire, the model reasons (completion-token jump) while only the final answer renders, and unset omits the field entirely. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Threads a ReasoningEffort level (minimal/low/medium/high/xhigh) through ChatRequest and emits it as
reasoning_effortonly on the OpenAI-compatible path; the Anthropic adapter keeps using thinking_budget. Previously hi sent no reasoning control at all on the OpenAI path, so models like pipenetwork's ipop/coder-balanced ran at the endpoint default (which is off, not medium).Configurable three ways:
Only the main turn takes the configured effort; housekeeping turns (compaction/memory/recap) stay off. Surfaced in --show-config.
Verified live: the flag reaches the wire, the model reasons (completion-token jump) while only the final answer renders, and unset omits the field entirely.