feat(harness): give pi adaptive thinking for a fair A/B - #44
Merged
Conversation
…ity) #43 disabled pi's thinking (reasoning:false) to dodge the 400 from pi-ai's deprecated `thinking:{type:'enabled',budget_tokens}`. That unblocked pi but left it running without extended thinking while the anthropic control uses adaptive — an unfair A/B on that axis. pi-ai supports the modern format via a model `compat` flag: set `compat:{forceAdaptiveThinking:true}` so it sends `thinking:{type:'adaptive'}` + output_config.effort (what Opus 4.8 / Sonnet 5 require), turn reasoning back on, and pass thinkingLevel:'medium' to match the control's medium effort. Also set supportsTemperature:false (Opus 4.7+ rejects a non-default temperature) — both mirror how pi-ai's own built-in anthropic-messages models are configured. Needs a real `SEAM_WIZARD_HARNESS=pi npm run eval` to confirm (adaptive isn't exercised in CI).
itelo
force-pushed
the
itelo/pi-thinking-parity
branch
from
August 21, 2026 17:04
36a94ec to
79dba03
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Thinking parity for the pi harness. #43 disabled pi's thinking (
reasoning:false) to dodge the 400 from pi-ai's deprecatedthinking:{type:'enabled',budget_tokens}— that unblocked pi but left it running without extended thinking while the anthropic control uses adaptive, an unfair A/B on that axis.pi-ai supports the modern format via a model
compatflag:compat: { forceAdaptiveThinking: true }→ pi sendsthinking:{type:'adaptive'}+output_config.effort(what Opus 4.8 / Sonnet 5 require, and what the Claude Agent SDK control sends).reasoning: true(back on) +thinkingLevel: 'medium'→ matches the control'seffort: 'medium'.supportsTemperature: false→ Opus 4.7+ rejects a non-default temperature.All three mirror how pi-ai's own built-in anthropic-messages models are configured.
Needs a real run — adaptive isn't exercised in CI:
SEAM_WIZARD_HARNESS=pi SEAM_API_KEY=… npm run evalExpect pi to still run (tool calls, non-empty diff) — now with thinking. If the proxy/model rejects the adaptive shape, it'd regress to the 400, so this shouldn't merge until a run confirms it. (The anthropic control already sends adaptive through the same proxy successfully, so confidence is high.)
Testing
Security & Compliance