04e039f687
Follow-up to the cherry-picked PR #13897 fix. Three issues found: 1. CRITICAL: The thinking block synthesised from reasoning_content was immediately stripped by the third-party signature management code (Kimi is classified as _is_third_party_anthropic_endpoint). Added a Kimi-specific carve-out that preserves unsigned thinking blocks while still stripping Anthropic-signed blocks Kimi can't validate. 2. Empty-string reasoning_content was silently dropped because the truthiness check ('if reasoning_content and ...') evaluates to False for ''. Changed to 'isinstance(reasoning_content, str)' so the tier-3 fallback from _copy_reasoning_content_for_api (which injects '' for Kimi tool-call messages with no reasoning) actually produces a thinking block. 3. The thinking block was appended AFTER tool_use blocks. Anthropic protocol requires thinking -> text -> tool_use ordering. Changed to blocks.insert(0, ...) to prepend. |
||
|---|---|---|
| .. | ||
| transports | ||
| __init__.py | ||
| account_usage.py | ||
| anthropic_adapter.py | ||
| auxiliary_client.py | ||
| bedrock_adapter.py | ||
| codex_responses_adapter.py | ||
| context_compressor.py | ||
| context_engine.py | ||
| context_references.py | ||
| copilot_acp_client.py | ||
| credential_pool.py | ||
| credential_sources.py | ||
| display.py | ||
| error_classifier.py | ||
| file_safety.py | ||
| gemini_cloudcode_adapter.py | ||
| gemini_native_adapter.py | ||
| gemini_schema.py | ||
| google_code_assist.py | ||
| google_oauth.py | ||
| image_gen_provider.py | ||
| image_gen_registry.py | ||
| insights.py | ||
| manual_compression_feedback.py | ||
| memory_manager.py | ||
| memory_provider.py | ||
| model_metadata.py | ||
| models_dev.py | ||
| nous_rate_guard.py | ||
| prompt_builder.py | ||
| prompt_caching.py | ||
| rate_limit_tracker.py | ||
| redact.py | ||
| retry_utils.py | ||
| shell_hooks.py | ||
| skill_commands.py | ||
| skill_utils.py | ||
| subdirectory_hints.py | ||
| title_generator.py | ||
| trajectory.py | ||
| usage_pricing.py | ||