- Added a curated think gallery fixture; the generic fallback carries no
thoughts field, so the streaming state rendered zero lines.
- Seeded the shared test registry with a runtime openai key: the prompt
preflight validates through the registry, not the per-request getApiKey
override, so keyless CI runners threw before reaching the mock server.
- Expected reasoning effort "none" — the only disable level the Responses
wire accepts; "off" is not a wire value.
- Added support for external thinking and forced reasoning disablement across AI provider options and request transformers.
- Implemented the private scratchpad think tool along with its renderer, system prompt rules, and schema configuration.
- Updated agent session management and SDK tools to support dynamic runtime activation of the think tool via the externalThinking setting.
- Added comprehensive unit tests covering reasoning fallbacks, tool activation, and rendering behavior.
- Extracted version verification logic into a reusable function accepting an explicit binary path.
- Updated shim takeover to verify the newly placed executable path directly instead of re-resolving via PATH.
- Added `resolveReleaseDist` and `shouldForceBinaryUpdate` to parse package manifests and gate major updates to binary releases.
- Implemented `updateViaShimTakeover` in `update-cli.ts` to seamlessly replace Windows script launchers with standalone binaries.
- Added comprehensive unit tests covering release distribution parsing, binary force updates, and script-shim takeover behavior.
After a prewalk hand-off plus mid-run compaction, the openai-responses input
builder re-encoded replayed assistant turns via convertResponsesAssistantMessage,
demoting their reasoning to <think> output_text and emitting no reasoning item.
DeepSeek (opencode-go) then rejected the thinking-mode continuation with
400 "The reasoning_text in the thinking mode must be passed back to the API"
and OMP looped on the unchanged request.
The encoder now synthesizes a reasoning_text reasoning item for every replayed
assistant turn when the target requires reasoning replay in thinking mode
(requiresReasoningContentForAllAssistantTurns / requiresReasoningContentForToolCalls),
carrying surviving thinking text when present, mirroring the chat-completions
reasoning_content safety net. Gated on reasoning being active for the request,
so non-DeepSeek Responses targets and reasoning-disabled turns are unaffected.
Fixes#8248
- Define a centralized `USER_AGENT` constant in `@oh-my-pi/pi-utils` formatted as `omp/<version>`.
- Replace hardcoded and platform-specific user agent strings across AI providers, catalog scrapers, tools, and search providers with the unified `USER_AGENT`.
- Add unit tests for update-cli binary release distribution gating.
- Updated user agent and openrouter titles in packages/ai from Oh-My-Pi to omp.
- Integrated getOpenRouterHeaders into image generation tool requests in packages/coding-agent.
- Updated provider documentation and test assertions to reflect the rebrand.
showHookCustom hardcoded the overlay geometry and never read
overlayOptions/onHandle, which regressed the v0.45.6 API (PR
badlogic/pi-mono#667). Forward overlayOptions to showOverlay (keeping the
full-cover defaults as fallback), invoke onHandle with the returned
OverlayHandle, widen the options type via a shared ExtensionCustomOptions,
and re-export OverlayHandle/OverlayOptions from the extension API.
Daniel Anderson-Little