Luis Pater cb110ad4fa perf(executor): improve token counting by introducing countXAIInputTokens ...

- Refactored token counting logic into a reusable `countXAIInputTokens` function for better readability and maintainability.
- Replaced direct encoder usage with structured input handling, including JSON parsing and segment collection.
- Switched tokenizer from `Cl100kBase` to `O200kBase` to support larger contexts.

Closes: #4492

2026-07-22 04:00:51 +08:00

..

helps

perf(util): introduce GetGJSONBytesNoCopy for efficient JSON parsing without data duplication

2026-07-20 15:37:55 +08:00

aistudio_executor_test.go

feat(executor): add TTFT tracking and reporting for enhanced performance metrics

2026-05-28 02:59:24 +08:00

aistudio_executor.go

feat(plugin, api): introduce host model callback support with Go example and API handlers

2026-06-12 02:22:23 +08:00

antigravity_executor_buildrequest_test.go

feat(schema): add removal of $comment and enumDescriptions in JSON schema processing

2026-06-20 00:22:08 +08:00

antigravity_executor_credits_test.go

Update Antigravity hub user agent (#4142)

2026-07-08 16:47:37 +08:00

antigravity_executor_interactions_test.go

feat(interactions): add support for Google Interactions

2026-07-07 02:39:13 +08:00

antigravity_executor_signature_test.go

feat: enhance fault tolerance for kv-based caching and introduce additional tests

2026-06-14 21:11:35 +08:00

antigravity_executor.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

antigravity_reasoning_replay_clear_test.go

test(antigravity): cover invalid-signature replay cache clear

2026-06-18 22:31:50 +08:00

antigravity_reasoning_replay_test.go

fix(translator): map OpenAI Responses reasoning to Gemini two-part signatures

2026-06-29 13:40:09 +08:00

antigravity_reasoning_replay.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

antigravity_refresh_test.go

feat(auth): deduplicate concurrent refresh token requests with singleflight

2026-06-10 03:19:26 +08:00

caching_verify_test.go

…

claude_executor_test.go

feat(executor): extend applyClaudeHeaders and Kimi executor with additional header support

2026-07-18 19:36:09 +08:00

claude_executor.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

claude_signing.go

feat(config): add support for rebuild_mid_system_message configuration

2026-06-20 12:15:06 +08:00

codex_executor_cache_test.go

feat(executor): implement agent-scoped cache key isolation and enhance replay handling

2026-07-18 02:18:09 +08:00

codex_executor_compact_test.go

feat(executor, handlers): enhance websocket output restoration and compact compaction logic

2026-07-11 11:42:51 +08:00

codex_executor_imagegen_test.go

feat(executor): add normalization for parallel tool calls in Codex executors

2026-07-18 03:58:03 +08:00

codex_executor_input_ids_test.go

feat(executor): sanitize and drop overlong encrypted reasoning IDs in Codex input processing

2026-07-20 02:02:17 +08:00

codex_executor_instructions_test.go

chore: upgrade CLIProxyAPI dependency to v7 across the project

2026-05-08 11:46:46 +08:00

codex_executor_parallel_tool_calls_test.go

feat(executor): add normalization for parallel tool calls in Codex executors

2026-07-18 03:58:03 +08:00

codex_executor_reasoning_replay_cache_test.go

feat(executor): implement agent-scoped cache key isolation and enhance replay handling

2026-07-18 02:18:09 +08:00

codex_executor_retry_test.go

feat(executor): handle usage limit errors and enhance retry logic

2026-06-17 07:19:02 +08:00

codex_executor_signature_test.go

fix(executor): strip orphan reasoning ids when store is disabled (#4285)

2026-07-14 00:35:48 +08:00

codex_executor_stream_output_test.go

feat(translator): improve error handling and response conversion for incomplete statuses

2026-07-16 04:38:19 +08:00

codex_executor_translate_test.go

refactor(executor): consolidate Codex request translation logic

2026-05-31 14:38:54 +08:00

codex_executor.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

codex_openai_images_extract_test.go

perf(codex): avoid rebuilding completed JSON when extracting generated images

2026-06-08 15:47:14 +00:00

codex_openai_images_test.go

fix(codex): sanitize downstream UA for direct image calls

2026-06-24 14:43:44 +08:00

codex_openai_images.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

codex_websockets_executor_store_test.go

chore: upgrade CLIProxyAPI dependency to v7 across the project

2026-05-08 11:46:46 +08:00

codex_websockets_executor_test.go

fix(websocket): propagate upstream 1009 without credential fallback (#4444)

2026-07-20 16:18:13 +08:00

codex_websockets_executor.go

fix(websocket): propagate upstream 1009 without credential fallback (#4444)

2026-07-20 16:18:13 +08:00

executor_payload_optimization_test.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

gemini_executor_test.go

feat(interactions): add support for Google Interactions

2026-07-07 02:39:13 +08:00

gemini_executor.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

gemini_vertex_executor.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

kimi_executor_test.go

Merge pull request #4419 from mikewong23571/fix/kimi-upstream-model-normalization

2026-07-18 23:29:16 +08:00

kimi_executor.go

perf(util): introduce GetGJSONBytesNoCopy for efficient JSON parsing without data duplication

2026-07-20 15:37:55 +08:00

openai_compat_executor_compact_test.go

feat(api): add OpenAI compatibility for image models

2026-05-19 10:13:26 +08:00

openai_compat_executor.go

perf(executor): replace sjson.SetBytes with optimized helpers for conditional payload updates

2026-07-20 13:57:14 +08:00

openai_responses_signature_test.go

fix(executor): strip orphan reasoning ids when store is disabled (#4285)

2026-07-14 00:35:48 +08:00

openai_responses_signature.go

fix(executor): strip orphan reasoning ids when store is disabled (#4285)

2026-07-14 00:35:48 +08:00

websocket_session_target_test.go

feat(websockets): implement active connection tracking for websocket sessions

2026-07-18 00:40:56 +08:00

xai_executor_test.go

perf(executor): improve token counting by introducing countXAIInputTokens

2026-07-22 04:00:51 +08:00

xai_executor.go

perf(executor): improve token counting by introducing countXAIInputTokens

2026-07-22 04:00:51 +08:00

xai_reasoning_replay.go

fix(xai): clear replay after compaction

2026-07-12 23:59:39 +08:00

xai_status_err_test.go

fix(xai): prevent Desktop hang on complex tool schemas and set free-usage Retry-After

2026-07-09 21:49:01 +05:30

xai_websockets_executor_test.go

fix(websocket): propagate upstream 1009 without credential fallback (#4444)

2026-07-20 16:18:13 +08:00

xai_websockets_executor.go

fix(websocket): propagate upstream 1009 without credential fallback (#4444)

2026-07-20 16:18:13 +08:00