Shinwayy / internal /runtime /executor /gemini_cli_executor.go

Commit History

  1. track binary files with git-lfs

    Shinway Deploy
    db492de

  1. refactor(translator, executor): remove redundant `bytes.Clone` calls for improved performance⁠

    Unverified signature
    7e8afbe
  2. refactor(executor): optimize payload cloning and streamline SDK translator usage⁠

    Unverified signature
    8953a28

  1. feat(openai): add responses/compact support

    Shady Khalifa
    Unverified signature
    642da09

  1. feat(executor): add request_id to error logs⁠

    hkfires
    c122a46

  1. feat(executor): apply payload rules using requested model

    hkfires
    ba27e38

  1. feat(registry): support provider-specific model info lookup

    hkfires
    a0b18a6

  1. refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation⁠

    hkfires
    0d5d901

  1. fix(executor): properly handle thinking application errors

    hkfires
    6e62482
  2. refactor: improve thinking logic

    hkfires
    c44624a

  1. feat(executor): add HttpRequest support across executors for better http request handling

    Unverified signature
    0268c3b

  1. feat(executor): enhance payload translation with original request context⁠

    Unverified signature
    b08e245

  1. fix(thinking): fallback to upstream model for thinking support when alias not in registry

    hkfires
    29db2b9
  2. fix(thinking): use model alias for thinking config resolution in mapped models

    hkfires
    667d001

  1. refactor(executor): resolve upstream model at conductor level before execution

    hkfires
    5a7ca8b
  2. fix(executor): use upstream model for thinking config and payload translation

    hkfires
    3d1d6fa

  1. fix: apply thinkingLevel from model suffix metadata for Gemini 3⁠

    Ben Vargas
    ba0d597

  1. Merge pull request #449 from sususu98/fix/gemini-cli-429-retry-delay-parsing⁠

    Unverified signature
    92f1d6c

  1. refactor(executor): clarify executor comments and oauth names

    hkfires
    5b3504c
  2. refactor(executor): clarify providers and streams⁠

    hkfires
    5fa4ee3

  1. fix(gemini-cli): enhance 429 retry delay parsing⁠

    sususu +1: Claude Opus 4.5
    9e72e87

  1. fix(executor): increase buffer size for stream scanners to 50MB across multiple executors

    sususu
    d811e5f

  1. fix(executor): centralize default thinking config

    hkfires
    51f4f88
  2. feat(executor): normalize thinking budget across all Gemini executors

    hkfires
    29b3fca

  1. Fixed: #414⁠

    Unverified signature
    c86627f

  1. refactor(executor): dedupe thinking metadata helpers across Gemini executors⁠

    auroraflux
    a3e833c

  1. **refactor(executor): simplify Gemini CLI execution and remove internal retry logic**⁠

    Unverified signature
    0e65031

  1. fix(executor): prevent streaming on failed response when no fallback⁠

    Ben Vargas
    31a0315
  2. fix(executor): prevent streaming from 429 response when fallback available⁠

    Ben Vargas
    98f4bdc
  3. feat(executor): add intelligent retry logic for 429 rate limits⁠

    Ben Vargas
    21841be

  1. **fix(runtime): simplify scanner buffer allocation in executor implementations**

    Unverified signature
    211886e

  1. **feat(runtime): add payload configuration support for executors**⁠

    Unverified signature
    3374794

  1. feat(gemini-cli): add multi-project support and enhance credential handling⁠

    Unverified signature
    11201d4

  1. fix(executor): remove outdated Gemini model previews from CLI fallback order

    Unverified signature
    271fb82

  1. fix(executor): remove `safetySettings` from payload for Gemini requests

    Unverified signature
    ff1947c

  1. refactor(executor): summarize API error bodies of html in debug logs

    hkfires
    4db8974

  1. chore(logging): clarify 429 rate-limit retries in Gemini executor

    hkfires
    9e51dcc
  2. fix(gemini-cli): correctly strip/normalize thinking config by model

    hkfires
    d3279a9
  3. fix(executor): only apply thinking config to supported models

    hkfires
    c833395

  1. fix(gemini): map responseModalities to uppercase IMAGE/TEXT

    hkfires
    3baf3c6

  1. feat(executor): add debug logs for rate-limiting retries in Gemini CLI executor

    Unverified signature
    6c7282b

  1. Refactor executor error handling and usage reporting⁠

    Unverified signature
    1d017d0

  1. Enhance logging for API requests and responses across executors⁠

    Unverified signature
    676719c
  2. Feature: #103⁠

    Unverified signature
    ec8aa00

  1. feat(registry, executor, util): add support for `gemini-2.5-flash-image-preview` and improve aspect ratio handling⁠

    Unverified signature
    db463dd
  2. feat(registry, executor): add support for `glm-4.6` model and enhance Gemini CLI token handling⁠

    Unverified signature
    46b90a5
  3. feat(registry, executor): add support for `gemini-2.5-flash-image` model⁠

    Unverified signature
    e35f1eb

  1. fix(gemini): Disable thinking config for incompatible models

    hkfires
    45ed610

  1. feat(registry/runtime): add Gemini 2.5 model and increase buffer sizes⁠

    Unverified signature
    2f0e897

  1. feat(runtime): introduce `newProxyAwareHTTPClient` for enhanced proxy handling⁠

    Unverified signature
    d704dad