- Raised `GEMINI_HEADER_RUNAWAY_THRESHOLD` from 10 to 24 to avoid false-positive interrupts on legitimate, complex reasoning blocks.
- Added a regression test verifying that 10 distinct, progressing headers do not trip the detector while 24 headers still trigger it.
- Migrated 288 lines of scattered error classification logic from `utils/error-id.ts` into a cohesive `packages/ai/src/error/` module with 13 specialized submodules covering flags, classes, OAuth, providers, rate-limiting, and finalization.
- Replaced 100+ generic `Error` throws across 60+ provider and registry files with semantic `AIError.*` classes (e.g., `AIError.MissingApiKeyError`, `AIError.OAuthError`, `AIError.ProviderResponseError`), improving error diagnostics and retry logic.
- Consolidated error utility imports from `pi-utils` and scattered classification functions into a single `AIError` namespace, reducing coupling and simplifying error handling across all packages.
- Introduce `resolveWithThinkingLoopCook` to manage automated retries for detected model thinking-loop stalls.
- Update `complete` and `completeSimple` to utilize the new retry orchestrator instead of direct stream resolution.
- Configure `pi-native-server` to respect the `loopGuard` option flag.
- Enable a final unguarded pass for persistent stalls after the retry budget is exhausted to ensure generation completion.
- Implemented a monitoring system to identify Gemini model runaway behavior during thinking steps using consecutive header detection.
- Introduced a configurable tool-call reminder prompt to inject corrective context when reasoning stalls.
- Added session-level logic to automatically interrupt and prune stalled assistant turns from the conversation history.
- Provided comprehensive test coverage for the detection logic and stream interruption scenarios.
- Integrated progress-lexicon analysis to identify and warn on low-information lexical stalls during reasoning.
- Enhanced loop stream processing to strip summarizer titles before performing analytical checks.
- Introduced CONCRETE_ANCHOR pattern and windowed state management to improve detection of novel reasoning references.
- Refactored the test suite to use a standardized feed function for chunked streams and added coverage for specific stall scenarios.
- Improved thinking loop detection logic by refining text normalization and treating stalls as retryable errors.
- Instrumented the agent session to recognize thinking loop markers within retryable error conditions.
- Automated the clearing of stale error banners upon successful auto-retry execution.
- Added comprehensive test coverage for chunked thinking loop errors and banner management.
- Integrated comprehensive loop guard support for DeepSeek and assistant prose patterns, including configurable stream checks.
- Implemented Moonshot Flavored JSON Schema (MFJS) normalization for improved tool compatibility and enum type inference.
- Added support for Ollama reasoning effort backfilling and Grok-specific service tier cost tracking across providers.
- Expanded model catalog with new entries and unified compatibility logic for improved OpenRouter API integration.
- Added Gemini thinking-loop detection helpers for near-duplicate and verbatim output checks.
- Wrapped `stream`, `streamPiNative`, and `streamSimple` dispatches with the loop guard.
- Emitted retryable empty-content loop errors and stopped completion events on loop hits.
- Added `enableGeminiThinkingLoopGuard` options for OpenAI compatibility with Gemini defaults and overrides.
can1357