Jason 63aa310576 feat(copilot): strip thinking blocks before forwarding to save premium quota ...

Copilot routes through OpenAI-compatible endpoints that reject Anthropic's
thinking and redacted_thinking blocks. Previously the request would fail
upstream, burning one premium interaction, and only then trigger
thinking_rectifier to retry. This adds a proactive strip_thinking_blocks
pass in the Copilot optimization pipeline (step 3.5, after tool_result
merging). Signature fields and top-level thinking are left alone — those
are the reactive rectifier's job on the error path.

Also fixes a default-value inconsistency where CopilotOptimizerConfig's
Default impl used "gpt-4o-mini" while the serde default function returned
"gpt-5-mini" (aligned to gpt-5-mini, matching the reference implementation).

Aligned with yuegongzi/copilot-api's /v1/messages handler behavior.

2026-04-21 11:57:06 +08:00

..

capabilities

…

icons

…

src

feat(copilot): strip thinking blocks before forwarding to save premium quota

2026-04-21 11:57:06 +08:00

tests

…

wix

…

.gitignore

…

build.rs

…

Cargo.lock

…

Cargo.toml

…

common-controls.manifest

…

Info.plist

…

tauri.conf.json

…

tauri.windows.conf.json

…