- Replaced all instances of `bytes.Clone` with direct references to enhance efficiency.
- Simplified payload handling across executors and translators by eliminating unnecessary data duplication.
refactor(executor): optimize payload cloning and streamline SDK translator usage
- Replaced repetitive string operations with a centralized `escapeGJSONPathKey` function.
- Streamlined handling of JSON schema cleaning for Gemini and Antigravity requests.
- Improved payload management by transitioning from byte slices to strings for processing.
- Removed unnecessary cloning of byte slices in several places.
Merge pull request #1248 from shekohex/feat/responses-compact
Implement `request_retry` and `disable_cooling` metadata overrides for authentication management. Update retry and cooling logic accordingly across `Manager`, Antigravity executor, and file synthesizer. Add tests to validate new behaviors.
refactor(runtime): implement retry logic for Antigravity executor with improved error handling and capacity management
Fix Gemini function-calling INVALID_ARGUMENT by relaxing Gemini tool validation and cleaning schema
sowar1987
e4915f5
fix(gemini): preserve displayName and description in models list
XYenon
5ae9bf2
Previously GeminiModels handler unconditionally overwrote displayName
and description with the model name, losing the original values defined
in model definitions (e.g., 'Gemini 3 Pro Preview').
Now only set these fields as fallback when they are missing or empty.
fix(executor): only strip maxOutputTokens for non-claude models
hkfires
dfde8e4
Fix antigravity malformed_function_call
bexcodex
46083fd
feat(registry): support provider-specific model info lookup
hkfires
a0b18a6
fix(executor): stop rewriting thinkingLevel for gemini
hkfires
cf2ec46
feat(registry): expand antigravity model config
hkfires
15faa87
Remove static Name mapping and add entries for claude-sonnet-4-5,
tab_flash_lite_preview, and gpt-oss-120b-medium configs
refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation
hkfires
0d5d901
Update ApplyThinking signature to accept fromFormat and toFormat parameters
instead of a single provider string. This enables:
- Proper level-to-budget conversion when source is level-based (openai/codex)
and target is budget-based (gemini/claude)
- Strict budget range validation when source and target formats match
- Level clamping to nearest supported level for cross-format requests
- Format alias resolution in SDK translator registry for codex/openai-response
Also adds ErrBudgetOutOfRange error code and improves iflow config extraction
to fall back to openai format when iflow-specific config is not present.
feat(runtime): add model alias support and enhance payload rule matching
- Introduced `payloadModelAliases` and `payloadModelCandidates` functions to support model aliases for improved flexibility.
- Updated rule matching logic to handle multiple model candidates.
- Refactored variable naming in executor to improve code clarity and consistency.
feat(config): supplement missing default aliases during antigravity migration
hkfires
ed8924a
Merge pull request #1033 from router-for-me/reasoning
feat(auth): fetch and update Antigravity project ID from metadata during filestore operations
- Added support to retrieve and update `project_id` using the access token if missing in metadata.
- Integrated HTTP client to fetch project ID dynamically.
- Enhanced metadata persistence logic.
refactor(thinking): improve budget clamping and logging with provider/model context
hkfires
97554ba
fix(thinking): map reasoning_effort to thinkingConfig
hkfires
5304b2e
fix(thinking): improve model lookup and validation
hkfires
2637197
refactor(antigravity): remove hardcoded model aliases
fix(executor): update gemini model identifier to gemini-3-pro-preview
hkfires
22ee946
Update the model name check in `buildRequest` to target "gemini-3-pro-preview" instead of "gemini-3-pro" when applying specific system instruction handling.
feat(executor): update system instruction handling for Claude and Gemini-3-Pro models
Introduced `tokenRefreshTimeout` constant for token refresh operations and enhanced context propagation for `refreshToken` by embedding roundtrip information if available. Adjusted `refreshAuth` to ensure default context initialization and handle cancellation errors appropriately.
feat(executor): enhance payload translation with original request context
Refactored `applyPayloadConfig` to `applyPayloadConfigWithRoot`, adding support for default rule validation against the original payload when available. Updated all executors to use `applyPayloadConfigWithRoot` and incorporate an optional original request payload for translations.
fix(thinking): fallback to upstream model for thinking support when alias not in registry
hkfires
29db2b9
fix(thinking): use model alias for thinking config resolution in mapped models
hkfires
667d001
refactor(executor): resolve upstream model at conductor level before execution
hkfires
5a7ca8b
fix(executor): use upstream model for thinking config and payload translation
hkfires
3d1d6fa
fix(antigravity): parse retry-after delay from 429 response body
sususu
aab9e55
When receiving HTTP 429 (Too Many Requests) responses, parse the retry
delay from the response body using parseRetryDelay and populate the
statusErr.retryAfter field. This allows upstream callers to respect
the server's requested retry timing.
Applied to all error paths in Execute, executeClaudeNonStream,
ExecuteStream, CountTokens, and refreshToken functions.
feat(cliproxy): introduce global model name mappings for improved aliasing and routing