Luis Pater 20c9095cac fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never ...

- Allowlist the sdk-ts Agent SDK entrypoint and recognize its measured Haiku 5.5 helper requests so genuine Claude Code traffic passes through uncloaked.
- Preserve plausible newer Stainless SDK and runtime versions for confirmed clients and retain confirmed-shape caller headers when cloak_mode is never.
- Recognize the Agent SDK CLI identity prompt block alongside existing Claude Code identity strings.

Closes: #6812

2026-10-21 01:11:27 +08:00

..

helps

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

testdata/tool_search_disabled

feat(claude): honor upstream.claude.tool-search in executor, catalog and server

2026-10-11 14:08:49 +08:00

aistudio_executor_test.go

feat(gemini): treat MALFORMED_FUNCTION_CALL as retryable API error in Claude translation

2026-10-14 12:08:35 +08:00

aistudio_executor.go

feat(gemini): treat MALFORMED_FUNCTION_CALL as retryable API error in Claude translation

2026-10-14 12:08:35 +08:00

aistudio_issue6258_terminal_test.go

…

antigravity_caqs_replay_test.go

refactor(translator): update openai and interactions request converters to return errors

2026-10-08 03:00:04 +08:00

antigravity_connection_trace_test.go

fix(antigravity): align Hub requests and invalidate versioned model caches

2026-10-20 18:46:02 +08:00

antigravity_executor_auth.go

…

antigravity_executor_buildrequest_test.go

fix(antigravity): align Hub requests and invalidate versioned model caches

2026-10-20 18:46:02 +08:00

antigravity_executor_compaction_test.go

…

antigravity_executor_credits_test.go

fix(antigravity): align Hub requests and invalidate versioned model caches

2026-10-20 18:46:02 +08:00

antigravity_executor_credits.go

fix(antigravity): align Hub requests and invalidate versioned model caches

2026-10-20 18:46:02 +08:00

antigravity_executor_disable_cooling_test.go

…

antigravity_executor_execute.go

fix(translator): report unsendable user turn attachments in openai responses to interactions

2026-10-08 02:11:20 +08:00

antigravity_executor_finish_reason_test.go

…

antigravity_executor_interactions_test.go

feat(registry): add gemini-3.8 model variants and update test cases

2026-10-14 10:17:01 +08:00

antigravity_executor_keepalive_test.go

…

antigravity_executor_request.go

fix(antigravity): align Hub requests and invalidate versioned model caches

2026-10-20 18:46:02 +08:00

antigravity_executor_signature_test.go

fix(gemini): ensure trailing user turn for function response with media

2026-10-11 17:58:34 +08:00

antigravity_executor_split_usage_test.go

…

antigravity_executor_stream.go

fix(translator): report unsendable user turn attachments in openai responses to interactions

2026-10-08 02:11:20 +08:00

antigravity_executor_terminal_disconnect_test.go

…

antigravity_executor_tokens.go

fix(translator): report unsendable user turn attachments in openai responses to interactions

2026-10-08 02:11:20 +08:00

antigravity_executor_trailing_reasoning_test.go

fix(antigravity): drop trailing thought-only model turns

2026-10-11 20:45:18 +08:00

antigravity_executor_transport_test.go

…

antigravity_executor_unsupported_part_test.go

fix(translator): report unsendable user turn attachments in openai responses to interactions

2026-10-08 02:11:20 +08:00

antigravity_executor.go

feat(auth): enable expired antigravity AI credits negative hint recovery and retry logic

2026-10-19 02:35:21 +08:00

antigravity_home_model_capabilities_test.go

…

antigravity_preupstream_rewrite_differential_test.go

…

antigravity_preupstream_rewrite_legacy_oracle_test.go

…

antigravity_reasoning_replay_clear_test.go

…

antigravity_reasoning_replay_index_test.go

…

antigravity_reasoning_replay_legacy_oracle_test.go

…

antigravity_reasoning_replay_test.go

…

antigravity_reasoning_replay.go

…

antigravity_refresh_issue6199_test.go

fix(antigravity): align Hub requests and invalidate versioned model caches

2026-10-20 18:46:02 +08:00

antigravity_refresh_test.go

…

antigravity_schema_sanitize_test.go

feat(runtime): optimize antigravity schema sanitization to scale linearly with declarations

2026-10-18 02:50:03 +08:00

antigravity_transport_decorator_test.go

feat(httptransport): add request-scoped HTTP transport decorator

2026-10-13 13:01:12 +08:00

apply_patch_bridge_test.go

…

apply_patch_capability_test.go

…

apply_patch_identity_test.go

…

apply_patch_integration_test.go

…

apply_patch_repair_test.go

…

apply_patch_source_stop_test.go

…

caching_verify_test.go

…

claude_cloaked_cache_repro_test.go

…

claude_cloaked_date_pin_test.go

feat(claude): add session date pin retention to preserve continuity across credential switches

2026-10-16 22:53:30 +08:00

claude_effort_directive_test.go

fix(claude): preserve mid-conversation effort directives during system insertion

2026-10-09 17:43:09 +08:00

claude_executor_auth_race_test.go

…

claude_executor_auth_test.go

…

claude_executor_auth.go

…

claude_executor_beta_passthrough_test.go

…

claude_executor_beta_policy_test.go

feat(claude): add automatic thinking block binding and beta policy for preserved-thinking models

2026-10-17 02:56:09 +08:00

claude_executor_cloaking_display_test.go

…

claude_executor_cloaking.go

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

claude_executor_compaction_test.go

feat(claude): support responses compaction in claude executor

2026-10-09 03:24:45 +08:00

claude_executor_compaction.go

feat(executor): support Codex remote-compaction v2 on Kimi and Meta Responses routes

2026-10-19 22:07:14 +08:00

claude_executor_diagnostics_test.go

…

claude_executor_diagnostics.go

feat(runtime): detect upstream stream truncation across executors and proxy handlers

2026-10-17 20:42:18 +08:00

claude_executor_execute.go

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

claude_executor_fable_ratelimit_test.go

…

claude_executor_fast_error_test.go

…

claude_executor_fast_error.go

feat(runtime): narrow Claude per-minute rate-limit cooldown when short Retry-After is present

2026-10-18 10:50:40 +08:00

claude_executor_native_helper_test.go

…

claude_executor_ratelimit_test.go

…

claude_executor_request_bench_test.go

…

claude_executor_request_remap_test.go

fix(claude): restore passthrough MCP tools wrapped with their full mcp__ name

2026-10-12 11:53:16 +09:00

claude_executor_request.go

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

claude_executor_stop_reasons_test.go

fix(claude): map refusal, context window and pause_turn stop reasons; honor parallel_tool_calls

2026-10-20 23:42:36 +08:00

claude_executor_stream_terminal_test.go

…

claude_executor_stream_truncation_test.go

feat(runtime): detect upstream stream truncation across executors and proxy handlers

2026-10-17 20:42:18 +08:00

claude_executor_stream.go

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

claude_executor_subagent_ttl_regression_test.go

…

claude_executor_test.go

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

claude_executor_thinking_signature_test.go

…

claude_executor_tokens.go

fix(claude): treat sdk-ts as native Claude Code and preserve caller headers under cloak_mode never

2026-10-21 01:11:27 +08:00

claude_executor_tool_alias_scope_test.go

…

claude_executor_tool_search_disabled_test.go

test(claude): pin executor clock in tool_search disabled golden

2026-10-12 10:26:17 +02:00

claude_executor_tool_search_test.go

fix(claude): keep prompt cache when tool_search discovers the first deferred tool

2026-10-12 20:28:18 +02:00

claude_executor_tool_state.go

fix(claude): support plain-text and structured response bodies for missing thread errors

2026-10-07 23:32:21 +08:00

claude_executor_web_search_results_test.go

fix(claude): scope web search result cache by upstream credential

2026-10-21 00:23:55 +08:00

claude_executor_wire_casing_test.go

…

claude_executor.go

fix(claude): scope web search result cache by upstream credential

2026-10-21 00:23:55 +08:00

claude_fingerprint_policy_test.go

feat(claude): strip Claude Code identity on API keys with cloak mode never or uncloak

2026-10-19 12:59:13 +08:00

claude_fingerprint_policy.go

feat(config): add operator overrides for Claude header defaults and client request ID modes

2026-10-15 00:57:02 +08:00

claude_header_overrides_issue5093_test.go

feat(config): add operator overrides for Claude header defaults and client request ID modes

2026-10-15 00:57:18 +08:00

claude_issue_6120_test.go

…

claude_issue_6193_test.go

…

claude_issue_6698_test.go

feat(claude): support between_tools thinking disable type and adaptive fallbacks

2026-10-17 13:56:34 +08:00

claude_messages_passthrough_test.go

…

claude_mid_system_model_test.go

…

claude_prompt_cache_options_test.go

fix(claude): relocate caller system prompt to messages for OAuth requests

2026-10-07 20:52:17 +08:00

claude_request_rate_test.go

feat(runtime): narrow Claude per-minute rate-limit cooldown when short Retry-After is present

2026-10-18 10:50:40 +08:00

claude_signing_test.go

…

claude_signing.go

…

claude_thinking_replay_test.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

claude_thinking_replay.go

…

claude_tls_handshake_retry_test.go

refactor(config): move tls-handshake-timeout-seconds to root request configuration

2026-10-14 20:59:02 +08:00

codex_executor_auth_test.go

feat(codex): support Sign in with ChatGPT

2026-10-12 11:45:25 +08:00

codex_executor_auth.go

feat(auth): increase Codex proactive refresh lead to 96 hours and improve rejected token handling

2026-10-19 01:41:19 +08:00

codex_executor_cache_test.go

…

codex_executor_compact_test.go

fix(codex): reconcile replayed web_search_call history with tool declarations

2026-10-19 19:00:41 +08:00

codex_executor_execute_usage_test.go

…

codex_executor_execute.go

fix(codex): reconcile replayed web_search_call history with tool declarations

2026-10-19 19:00:41 +08:00

codex_executor_grokbuild_keepalive_test.go

…

codex_executor_imagegen_test.go

…

codex_executor_input_ids_test.go

…

codex_executor_instructions_test.go

…

codex_executor_parallel_tool_calls_test.go

…

codex_executor_reasoning_replay_cache_test.go

…

codex_executor_reasoning.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

codex_executor_request.go

fix(codex): reconcile replayed web_search_call history with tool declarations

2026-10-19 19:00:41 +08:00

codex_executor_retry_test.go

…

codex_executor_routing_hint_test.go

…

codex_executor_signature_test.go

…

codex_executor_siwc_configuration_update_test.go

feat(pluginhost): add content-addressed shadow copies for dynamic library loading

2026-10-16 12:04:22 +08:00

codex_executor_spawn_agent_test.go

…

codex_executor_sse_events_test.go

feat(sse): implement CodexSSEScanner for improved event data handling

2026-10-14 02:54:02 +08:00

codex_executor_stream_alloc_test.go

…

codex_executor_stream_output_test.go

…

codex_executor_stream.go

fix(codex): reconcile replayed web_search_call history with tool declarations

2026-10-19 19:00:41 +08:00

codex_executor_terminal.go

fix(executor): count completed reasoning items toward TTFT

2026-10-20 17:17:41 +08:00

codex_executor_tokens_test.go

…

codex_executor_tokens.go

fix(translator): stop dropping attachments and empty turns

2026-10-07 19:21:32 +09:00

codex_executor_tool_schema_test.go

…

codex_executor_translate_test.go

refactor(translator): update openai and interactions request converters to return errors

2026-10-08 03:00:04 +08:00

codex_executor.go

…

codex_native_fidelity_test.go

…

codex_openai_images_extract_test.go

…

codex_openai_images_test.go

fix(codex): preserve resolved upstream model in direct openai image requests

2026-10-09 10:10:50 +08:00

codex_openai_images.go

feat(codex): support Sign in with ChatGPT

2026-10-12 11:45:25 +08:00

codex_per_credential_cloaking_issue6034_test.go

…

codex_response_model_test.go

…

codex_stream_bootstrap_buffering_test.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

codex_websockets_connection.go

…

codex_websockets_duplex_bootstrap_input_test.go

…

codex_websockets_duplex_credential_failure_test.go

…

codex_websockets_duplex_health_test.go

…

codex_websockets_duplex_initial_failure_test.go

…

codex_websockets_duplex_rejection_test.go

…

codex_websockets_duplex_successor_metadata_test.go

…

codex_websockets_duplex_test.go

feat(pluginhost): add content-addressed shadow copies for dynamic library loading

2026-10-16 12:04:22 +08:00

codex_websockets_duplex.go

feat(pluginhost): add content-addressed shadow copies for dynamic library loading

2026-10-16 12:04:22 +08:00

codex_websockets_errors.go

…

codex_websockets_execute.go

fix(codex): reconcile replayed web_search_call history with tool declarations

2026-10-19 19:00:41 +08:00

codex_websockets_executor_store_test.go

fix(executor): preserve websocket sessions across reload and auth removal

2026-10-12 19:42:54 +08:00

codex_websockets_executor_test.go

…

codex_websockets_executor.go

fix(executor): preserve websocket sessions across reload and auth removal

2026-10-12 19:42:54 +08:00

codex_websockets_interrupt_test.go

feat(openai): support response.interrupt in responses websocket handling

2026-10-08 21:32:26 +08:00

codex_websockets_late_interrupt_test.go

fix(codex): handle late response interrupts on websocket sessions

2026-10-09 21:35:40 +08:00

codex_websockets_request.go

feat(codex): support Sign in with ChatGPT

2026-10-12 11:45:25 +08:00

codex_websockets_routing_hint_test.go

…

codex_websockets_session.go

fix(executor): preserve websocket sessions across reload and auth removal

2026-10-12 19:42:54 +08:00

codex_websockets_spawn_agent_test.go

…

codex_websockets_stream.go

fix(codex): reconcile replayed web_search_call history with tool declarations

2026-10-19 19:00:41 +08:00

custom_magic_headers_test.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00

devin_executor_test.go

fix(devin): do not seed input token estimates for claude streams

2026-10-10 21:48:20 +08:00

devin_executor.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

devin_quota_cooldown_regression_test.go

feat(devin): add account-wide quota exhaustion tracking and credential cooldown refresh

2026-10-17 02:18:41 +08:00

devin_stream_content_test.go

…

devin_user_turn_test.go

fix(translator): report unsendable user turn attachments in openai responses to interactions

2026-10-08 02:11:20 +08:00

executor_payload_optimization_test.go

…

gemini_executor_signature_test.go

…

gemini_executor_test.go

feat(gemini): treat MALFORMED_FUNCTION_CALL as retryable API error in Claude translation

2026-10-14 12:08:35 +08:00

gemini_executor.go

feat(runtime): detect upstream stream truncation across executors and proxy handlers

2026-10-17 20:42:18 +08:00

gemini_interactions_continuation_test.go

…

gemini_interactions_tool_names_test.go

…

gemini_interactions_translate_test.go

refactor(translator): update openai and interactions request converters to return errors

2026-10-08 03:00:04 +08:00

gemini_vertex_executor_interactions_test.go

feat(vertex): add support for native gemini interactions api

2026-10-08 12:39:31 +08:00

gemini_vertex_executor_openapi_test.go

fix(translator): preserve gemini thought signatures across openai chat translations

2026-10-21 00:29:47 +08:00

gemini_vertex_executor_terminal_disconnect_test.go

…

gemini_vertex_executor_test.go

feat(vertex): honor full /publishers/ prefix in API-key base-url

2026-10-15 18:36:57 +08:00

gemini_vertex_executor_trailing_reasoning_test.go

feat(executor): drop trailing thought-only model turns in Gemini Vertex requests

2026-10-15 08:05:58 +08:00

gemini_vertex_executor.go

feat(vertex): support partner and open models via endpoints/openapi route

2026-10-19 12:56:25 +08:00

home_codex_terminal_test.go

…

issue6258_terminal_test.go

…

issue6381_responses_eof_test.go

…

issue6478_tool_ids_edges_test.go

fix(executor): normalize and restore non-portable tool call IDs

2026-10-09 19:44:24 +08:00

issue6478_tool_ids_test.go

fix(executor): normalize and restore non-portable tool call IDs

2026-10-09 19:44:24 +08:00

kimi_executor_test.go

feat(executor): support Codex remote-compaction v2 on Kimi and Meta Responses routes

2026-10-19 22:07:14 +08:00

kimi_executor.go

feat(executor): support Codex remote-compaction v2 on Kimi and Meta Responses routes

2026-10-19 22:07:14 +08:00

kimi_home_model_capabilities_test.go

…

kimi_thinking_replay_test.go

…

kimi_thinking_replay.go

…

meta_executor_execute.go

feat(executor): support Codex remote-compaction v2 on Kimi and Meta Responses routes

2026-10-19 22:07:14 +08:00

meta_executor_stream.go

fix(meta): measure streaming TTFT on effective token frames

2026-10-20 16:57:14 +08:00

meta_executor_terminal_disconnect_test.go

test(meta): handle client disconnect gracefully after terminal stream events

2026-10-16 23:23:33 +08:00

meta_executor_test.go

feat(executor): support Codex remote-compaction v2 on Kimi and Meta Responses routes

2026-10-19 22:07:14 +08:00

meta_executor_ttft_test.go

fix(executor): count completed reasoning items toward TTFT

2026-10-20 17:17:41 +08:00

meta_executor.go

…

oauth_scope_executor.go

…

oauth_scope_test.go

…

openai_compat_executor_compact_test.go

…

openai_compat_executor_images_test.go

…

openai_compat_executor_max_tokens_test.go

…

openai_compat_executor_reasoning_test.go

…

openai_compat_executor_retry_test.go

…

openai_compat_executor_tool_results_test.go

…

openai_compat_executor_ttft_test.go

fix(openai-compat): measure streaming TTFT on effective token frames

2026-10-09 19:00:58 +08:00

openai_compat_executor_video_test.go

…

openai_compat_executor.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00

openai_compat_home_options_test.go

…

openai_responses_signature_test.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

openai_responses_signature.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

payload_barrier_test.go

…

payload_review_test.go

…

request_proxy_priority_test.go

…

response_model_multiprovider_test.go

…

unsupported_part_executor_test.go

fix(translator): report unsendable user turn attachments in openai responses to interactions

2026-10-08 02:11:20 +08:00

vertex_proxy_token_test.go

…

websocket_lifecycle_bind_test.go

…

websocket_proxy_reuse_test.go

…

websocket_session_target_test.go

…

websocket_upstream_disconnect_test.go

…

xai_client_version_test.go

fix(xai): add proxy support and semver validation to Grok CLI updater

2026-10-08 02:39:32 +08:00

xai_configuration_update_plugin_test.go

…

xai_configuration_update_test.go

…

xai_executor_auth.go

…

xai_executor_execute.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

xai_executor_media.go

…

xai_executor_request.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00

xai_executor_response.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

xai_executor_speech_test.go

fix(routing): restrict speech-only models to speech endpoints and refine xAI error scoping

2026-10-07 13:46:58 +08:00

xai_executor_speech.go

fix(routing): restrict speech-only models to speech endpoints and refine xAI error scoping

2026-10-07 13:46:58 +08:00

xai_executor_stream.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

xai_executor_test.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00

xai_executor_tokens.go

…

xai_executor.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00

xai_reasoning_replay.go

fix(signature): strip OpenRouter private RouterSuffix on official and non-OpenRouter upstreams

2026-10-18 20:57:01 +08:00

xai_status_err_test.go

…

xai_websockets_executor_test.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00

xai_websockets_executor.go

feat(executor): pass through downstream User-Agent and set default xAI User-Agent

2026-10-20 17:05:03 +08:00