9 Commits

• refactor(thinking): use parentheses for metadata suffix
  hkfires · 2025-12-11 18:39:07 +08:00
  e79f65fd8e
• refactor(thinking): use bracket tags for thinking meta

  Align thinking suffix handling on a single bracket-style marker.
  
  NormalizeThinkingModel strips a terminal `[value]` segment from
  model identifiers and turns it into either a thinking budget (for
  numeric values) or a reasoning effort hint (for strings). Emission
  of `ThinkingIncludeThoughtsMetadataKey` is removed.
  
  Executor helpers and the example config are updated so their
  comments reference the new `[value]` suffix format instead of the
  legacy dash variants.
  
  BREAKING CHANGE: dash-based thinking suffixes (`-thinking`,
  `-thinking-N`, `-reasoning`, `-nothinking`) are no longer parsed
  for thinking metadata; only `[value]` annotations are recognized.

  hkfires · 2025-12-11 18:17:28 +08:00
  facfe7c518
• docs(runtime): document reasoning effort precedence
  hkfires · 2025-12-11 16:35:36 +08:00
  21bbceca0c
• fix(runtime): unify reasoning effort metadata overrides
  hkfires · 2025-12-11 14:35:05 +08:00
  3a81ab22fd
• fix(runtime): validate reasoning effort levels
  hkfires · 2025-12-11 12:36:54 +08:00
  519da2e042
• feat(runtime): add thinking config normalization
  hkfires · 2025-12-11 11:51:33 +08:00
  3ffd120ae9
• feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic

  - Added support for parsing and normalizing dynamic thinking model suffixes.
  - Centralized budget resolution across executors and payload helpers.
  - Retired legacy Gemini-specific thinking handlers in favor of unified logic.
  - Updated executors to use metadata-based thinking configuration.
  - Added `ResolveOriginalModel` utility for resolving normalized upstream models using request metadata.
  - Updated executors (Gemini, Codex, iFlow, OpenAI, Qwen) to incorporate upstream model resolution and substitute model values in payloads and request URLs.
  - Ensured fallbacks handle cases with missing or malformed metadata to derive models robustly.
  - Refactored upstream model resolution to dynamically incorporate metadata for selecting and normalizing models.
  - Improved handling of thinking configurations and model overrides in executors.
  - Removed hardcoded thinking model entries and migrated logic to metadata-based resolution.
  - Updated payload mutations to always include the resolved model.

  Luis Pater · 2025-12-11 03:10:50 +08:00
  423ce97665
• refactor(executor): dedupe thinking metadata helpers across Gemini executors

  Extract applyThinkingMetadata and applyThinkingMetadataCLI helpers to
  payload_helpers.go and use them across all four Gemini-based executors:
  - gemini_executor.go (Execute, ExecuteStream, CountTokens)
  - gemini_cli_executor.go (Execute, ExecuteStream, CountTokens)
  - aistudio_executor.go (translateRequest)
  - antigravity_executor.go (Execute, ExecuteStream)
  
  This eliminates code duplication introduced in the -reasoning suffix PR
  and centralizes the thinking config application logic.
  
  Net reduction: 28 lines of code.

  auroraflux · 2025-11-30 15:20:15 -08:00
  1c6f4be8ae
• **feat(runtime): add payload configuration support for executors**

  Introduce `PayloadConfig` in the configuration to define default and override rules for modifying payload parameters. Implement `applyPayloadConfig` and `applyPayloadConfigWithRoot` to apply these rules across various executors, ensuring consistent parameter handling for different models and protocols. Update all relevant executors to utilize this functionality.

  Luis Pater · 2025-11-13 23:27:40 +08:00
  fcd98f4f9b