- Remove redundant definedness, null, and type checks across test suites in multiple packages.
- Clean up unused assertions, metadata tests, and obsolete test cases.
- Add good versus bad test filter guidelines and requirements to project documentation.
- 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.
- Default reasoning.summary to auto in openai-codex requests to ensure summaries are emitted by the backend.
- Gate stream_options reasoning_summary_delivery behind the PI_CODEX_CONCURRENT_SUMMARIES environment variable opt-in.
- Update tests in openai-codex-responses-lite to verify default summary behavior and opt-in concurrent delivery controls.
- Updated the OpenAI Codex provider to unroll native computer calls and tool outputs into standard function calls.
- Added support for the `PI_CODEX_RESPONSES_LITE` environment variable override via the request transformer.
- Updated documentation and tests to cover lite response resolution and native computer response unrolling.
- Credential-shaped token redaction now requires explicit opt-in via `configureCredentialRedaction` and is disabled by default, so user-supplied credential-like strings reach providers unmodified unless the host enables redaction.
- Wired the `secrets.enabled` ("Hide Secrets") setting to `configureCredentialRedaction` in the coding-agent so the pattern redaction follows the existing secret-obfuscation toggle.
- Added explicit existence checks for objects prior to property access across various test suites.
- Replaced optional chaining with non-null assertions to satisfy TypeScript strictness requirements in test assertions.
- Force `reasoning.context` to `all_turns` in OpenAI Codex requests when `responsesLite` is enabled.
- Include `reasoning.encrypted_content` in the `include` header for lite responses.
- Update request transformation logic to ensure these fields are populated even when reasoning effort is not explicitly set.
- Introduced `SequentialCutoffSummaryState` to track reasoning summaries globally across all response items.
- Updated `CodexStreamRuntime` to maintain cumulative summary state instead of per-item snapshots.
- Modified `applyReasoningSummaryDone` and `finalizeReasoningThinking` to emit only append-only text deltas, suppressing replayed content from previous items.
- Added comprehensive test coverage to verify correct incremental thinking output across multiple sequential reasoning items.
- Enabled Codex Responses Lite for GPT-5.6 models by integrating model discovery flags and wire contract updates.
- Implemented request transformations for streaming and remote compaction, including header injection and image detail stripping.
- Introduced sequential-cutoff logic and atomic reasoning summary events for concurrent stream processing.
- Added comprehensive test suites to validate remote compaction, image handling, and reasoning summary delivery.
- Preserved Codex developer instructions while adding a user continuation when the request would otherwise contain only hidden guidance.
- Covered fresh plan execution request shaping and verified existing Codex lite tests.
Fixes#4714
- Added a check to omit the `reasoning.summary` parameter on OpenAI Codex models older than version 5.4.
- Introduced `supportsCodexReasoningSummary` in the catalog package to identify compatible model versions.
- Added comprehensive unit tests validating correct parameter inclusion and suppression across models.
- Guarded the `all_turns` reasoning context value to OpenAI models version 5.4 or greater.
- Suppressed `reasoning.context` defaults and explicit overrides when `all_turns` is requested on unsupported models to prevent server rejection.
- Introduced `supportsAllTurnsReasoningContext` helper in `@oh-my-pi/pi-catalog/identity` using semver classification.
- Updated request-transformer and response-options logic to conditionalize the request payload shaping.
- Expanded test coverage to verify correct fallback behavior and explicit overrides across gpt-5.x versions.
- Standardized reasoning context to default to all_turns across all Codex requests to mirror codex-rs behavior.
- Updated request transformer logic to explicitly set reasoning context rather than omitting it when unset.
- Updated API documentation to reflect consistent all_turns default behavior and corrected internal references.
- Adjusted unit tests to verify the enforced all_turns default reasoning context expectation.
Codex Responses Lite only accepts text input, so GPT image prompts with input_image failed before reaching the full multimodal transport.
The request transformer and Codex headers now fall back to full Responses whenever a request body contains input_image, with regression coverage for the lite header.
Fixes#3421
Added the missing models.yml schema field for compat.supportsImageDetailOriginal so custom Responses-compatible proxies can opt out of snapcompact's native-resolution image hint.
Covered the CC Switch-style custom provider override and the Codex Responses wire clamp from original to auto.
Fixes#3092
- Added `responsesLite`, `reasoningContext`, `clientMetadata`, and `onModerationMetadata` options.
- Changed Lite request transformation to default `reasoning.context` to `all_turns`.
- Changed request shaping to strip image `detail` fields and force `parallel_tool_calls` off in Lite mode.
- Fixed streaming behavior by excluding `client_metadata` from websocket append diffs and swallowing moderation metadata errors.
can1357