- 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 unnecessary `bytes.Clone` calls for `opts.OriginalRequest` throughout executors.
- Introduced intermediate variable `originalPayloadSource` to simplify payload processing.
- Ensured better clarity and structure in request translation logic.
refactor(codex): remove codex instructions injection support
hkfires
f1597d6
fix(codex): avoid empty prompt_cache_key
Shady Khalifa
Unverified signature
b2f5f03
fix(openai): drop stream for responses/compact
Shady Khalifa
Unverified signature
9df2a02
feat(openai): add responses/compact support
Shady Khalifa
Unverified signature
642da09
feat(executor): add request_id to error logs
hkfires
c122a46
Extract error.message from JSON error responses when summarizing error bodies for debug logs
feat(executor): apply payload rules using requested model
hkfires
ba27e38
feat(registry): support provider-specific model info lookup
hkfires
a0b18a6
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(codex): enhance input transformation and remove unused `safety_identifier` field
- Added logic to transform `inputResults` into structured JSON for improved processing.
- Removed redundant `safety_identifier` field in executor payload to streamline requests.
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.
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
feat(cliproxy): implement model aliasing and hashing for Codex configurations, enhance request routing logic, and normalize Codex model entries
Expose thinking/effort normalization helpers from the executor package
so conversion tests use production code and stay aligned with runtime
validation behavior.
fix(executor): add `allowCompat` support for reasoning effort normalization
- 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.
fix(executor): increase buffer size for stream scanners to 50MB across multiple executors
sususu
d811e5f
**feat(registry): add GPT-5.1 Codex Max model definitions and support**
- Introduced `gpt-5.1-codex-max` variants to model definitions (`low`, `medium`, `high`, `xhigh`).
- Updated executor logic to map effort levels for Codex Max models.
- Added `lastCodexMaxPrompt` processing for `gpt-5.1-codex-max` prompts.
- Defined instructions for `gpt-5.1-codex-max` in a new file: `codex_instructions/gpt-5.1-codex-max_prompt.md`.
**fix(runtime): simplify scanner buffer allocation in executor implementations**
Extract reasoning effort mapping into a reusable function `setReasoningEffortByAlias` to reduce redundancy and improve maintainability. Introduce support for the "gpt-5.1-none" variant in the registry and runtime executor.
Stop advertising and mapping the unsupported gpt-5.1-minimal variant in the model registry and Codex executor, and align bare gpt-5.1 requests to use medium reasoning effort like Codex CLI while preserving minimal for gpt-5.
**feat(runtime): extend executor support for GPT-5.1 Codex and variants**
Expand executor logic to handle GPT-5.1 Codex family and its variants, including reasoning effort configurations for minimal, low, medium, and high levels. Ensure proper mapping of models to payload parameters.
**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.
feat(runtime): add support for GPT-5.1 models and variants
Introduce GPT-5.1 model family, including minimal, low, medium, high, Codex, and Codex Mini variants. Update tokenization and reasoning effort handling to accommodate new models in executor and registry.
feat(config): support HTTP headers across providers
hkfires
2881a1b
fix(executor): remove default reasoning effort for `gpt-5-codex-mini`
feat(registry): add GPT-5 Codex Mini model variants
Jeff Nash
a4aba82
Adds three new Codex Mini model variants (mini, mini-medium, mini-high)
that map to codex-mini-latest. Codex Mini supports medium and high
reasoning effort levels only (no low/minimal). Base model defaults to
medium reasoning effort.
fix(executor): add logging and prompt cache key handling for OpenAI responses
- Standardized User-Agent strings for Codex and Claude executors to improve request tracing and compatibility.
- Updated header insertion logic in both executors for consistency.
feat(translator): add token counting functionality for Gemini, Claude, and CLI
- Introduced `TokenCount` handling across various Codex translators (Gemini, Claude, CLI) with respective implementations.
- Added utility methods for token counting and formatting responses.
- Integrated `tiktoken-go/tokenizer` library for tokenization.
- Updated CodexExecutor with token counting logic to support multiple models including GPT-5 variants.
- Refined go.mod and go.sum to include new dependencies.
feat(runtime): add token counting functionality across executors
- Implemented token counting in OpenAICompatExecutor, QwenExecutor, and IFlowExecutor.
- Added utilities for token counting and response formatting using `tiktoken-go/tokenizer`.
- Integrated token counting into translators for Gemini, Claude, and Gemini CLI.
- Enhanced multiple model support, including GPT-5 variants, for token counting.
docs: update environment variable instructions for multi-model support
- Added details for sett…