Luis Pater 22392c537d fix(executor): restore hybrid passthrough mcp tool names in claude oauth ...

- Track declared passthrough MCP tools in `claudeMCPAliasResolver`
- Recover hybrid tool names when the model prepends a virtual server prefix or replaces the caller's server with the virtual server
- Ensure client-tool alias matches take precedence over passthrough recovery and reject ambiguous passthrough tool matches

Closes: #5949

2026-09-19 02:13:11 +08:00

..

helps

feat(executor): support use-max-completion-tokens for openai compatibility models

2026-09-19 01:54:05 +08:00

aistudio_executor_test.go

fix(gemini): append trailing user turn for requests ending with model content

2026-09-06 23:41:12 +08:00

aistudio_executor.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

antigravity_executor_auth.go

fix(auth): preserve upstream status codes in antigravity auth errors

2026-09-01 08:37:02 +08:00

antigravity_executor_buildrequest_test.go

feat(translator): enhance web search streaming and citation mapping in OpenAI Responses

2026-09-17 03:51:48 +08:00

antigravity_executor_compaction_test.go

feat(antigravity): add conversation compaction support and capsule encryption

2026-09-06 21:51:47 +08:00

antigravity_executor_credits_test.go

fix(antigravity): remove cross-endpoint fallback (#5209) (#5228)

2026-08-25 11:51:17 +08:00

antigravity_executor_credits.go

fix(antigravity): bypass quota cooldowns and credit hints when cooling is disabled

2026-09-02 22:01:55 +08:00

antigravity_executor_disable_cooling_test.go

fix(antigravity): bypass quota cooldowns and credit hints when cooling is disabled

2026-09-02 22:01:55 +08:00

antigravity_executor_execute.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

antigravity_executor_finish_reason_test.go

fix(antigravity): safely synthesize terminal finish reasons (#5230)

2026-08-25 15:13:04 +08:00

antigravity_executor_interactions_test.go

test(executor): update antigravity interactions test to use valid model

2026-09-01 18:00:04 +08:00

antigravity_executor_keepalive_test.go

fix(antigravity): default to short connections and harden connection pool lifecycle (fixes #5494)

2026-09-07 19:15:39 +08:00

antigravity_executor_request.go

fix(antigravity): remove cross-endpoint fallback (#5209) (#5228)

2026-08-25 11:51:17 +08:00

antigravity_executor_signature_test.go

fix(gemini): append trailing user turn for requests ending with model content

2026-09-06 23:41:12 +08:00

antigravity_executor_split_usage_test.go

fix(antigravity): safely synthesize terminal finish reasons (#5230)

2026-08-25 15:13:04 +08:00

antigravity_executor_stream.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

antigravity_executor_tokens.go

feat(translator): preserve model metadata in requests

2026-09-17 13:10:47 +08:00

antigravity_executor_transport_test.go

fix(antigravity): include resolved pool settings in transport cache key

2026-09-08 11:29:05 +08:00

antigravity_executor.go

feat(translator): enhance web search streaming and citation mapping in OpenAI Responses

2026-09-17 03:51:48 +08:00

antigravity_home_model_capabilities_test.go

feat(auth): use home model capabilities for thinking

2026-09-03 13:10:30 +08:00

antigravity_preupstream_rewrite_differential_test.go

perf(antigravity): batch functionResponse name repairs

2026-09-08 18:32:26 +08:00

antigravity_preupstream_rewrite_legacy_oracle_test.go

fix(claude): preserve tool pairing across intervening system messages

2026-08-31 19:27:20 +08:00

antigravity_reasoning_replay_clear_test.go

…

antigravity_reasoning_replay_index_test.go

perf(antigravity): batch reasoning replay mutations

2026-09-04 18:53:21 +08:00

antigravity_reasoning_replay_legacy_oracle_test.go

refactor(antigravity): route replay merge through the request index

2026-08-11 09:57:15 +08:00

antigravity_reasoning_replay_test.go

fix(gemini): preserve function call pairing for interrupted calls and replay failures

2026-09-10 20:01:39 +08:00

antigravity_reasoning_replay.go

fix(gemini): preserve function call pairing for interrupted calls and replay failures

2026-09-10 20:01:39 +08:00

antigravity_refresh_test.go

fix(auth): prefer errors from upstream attempts

2026-08-29 12:50:46 +08:00

antigravity_schema_sanitize_test.go

fix(gemini): strip 'encrypted' metadata from tool parameters schemas (#5065)

2026-08-19 19:13:56 +08:00

caching_verify_test.go

fix(claude): restore cloaked prompt-cache ownership and native shape

2026-08-11 19:33:40 +08:00

claude_cloaked_cache_repro_test.go

fix(claude): anchor billing fingerprint to initial turn for cloaked cache stability

2026-09-11 16:59:57 +08:00

claude_executor_auth_race_test.go

fix(claude): replay measured OAuth wire, Fast and diagnostic profiles

2026-08-03 14:47:26 +08:00

claude_executor_auth_test.go

fix(claude): support setup-tokens and gracefully handle 403 OAuth profile errors (#4983) (#5083)

2026-08-20 00:15:31 +08:00

claude_executor_auth.go

fix(claude): support setup-tokens and gracefully handle 403 OAuth profile errors (#4983) (#5083)

2026-08-20 00:15:31 +08:00

claude_executor_beta_passthrough_test.go

fix(claude): forward unmanaged caller betas on direct anthropic requests

2026-09-11 23:44:21 +08:00

claude_executor_beta_policy_test.go

feat(claude): support advisor tool beta header

2026-08-29 14:47:51 +08:00

claude_executor_cloaking.go

fix(executor): restrict claude advisor tool check to server tool use

2026-09-18 23:32:00 +08:00

claude_executor_diagnostics_test.go

feat(claude): implement 2.1.258 billing header fingerprint chain and upstream request continuity

2026-09-04 15:23:31 +08:00

claude_executor_diagnostics.go

feat(claude): implement 2.1.258 billing header fingerprint chain and upstream request continuity

2026-09-04 15:23:31 +08:00

claude_executor_execute.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

claude_executor_fable_ratelimit_test.go

fix(claude): skip retry-after header on overage-only rejections

2026-09-18 09:15:48 +08:00

claude_executor_fast_error_test.go

fix(claude): harden request lifecycle

2026-08-03 14:47:26 +08:00

claude_executor_fast_error.go

fix(claude): add Anthropic unified rate-limit parsing helpers

2026-08-15 14:08:16 +08:00

claude_executor_native_helper_test.go

fix(claude): attach helper request IDs according to the upstream base

2026-09-08 10:34:05 +08:00

claude_executor_ratelimit_test.go

fix(auth): prefer errors from upstream attempts

2026-08-29 12:50:46 +08:00

claude_executor_request_bench_test.go

perf(claude): batch OAuth tool name rewrites

2026-08-03 14:47:26 +08:00

claude_executor_request_remap_test.go

fix(executor): restore hybrid passthrough mcp tool names in claude oauth

2026-09-19 02:13:11 +08:00

claude_executor_request.go

fix(executor): restore hybrid passthrough mcp tool names in claude oauth

2026-09-19 02:13:11 +08:00

claude_executor_stream_terminal_test.go

fix(executor): prevent stream failure on client disconnect after claude completion

2026-09-16 20:00:27 +08:00

claude_executor_stream.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

claude_executor_subagent_ttl_regression_test.go

fix(claude): preserve 1h cache ttl and beta header for subagent requests

2026-09-10 10:58:34 +08:00

claude_executor_test.go

fix(executor): restrict claude advisor tool check to server tool use

2026-09-18 23:32:00 +08:00

claude_executor_thinking_signature_test.go

test(claude): preserve adaptive thinking signatures

2026-08-03 14:47:26 +08:00

claude_executor_tokens.go

feat(claude): support model-level cooling and scope overage rate limits

2026-09-18 01:55:36 +08:00

claude_executor_wire_casing_test.go

fix(claude): send Anthropic header names with the real client's casing

2026-08-03 14:47:26 +08:00

claude_executor.go

feat(claude): support model-level cooling and scope overage rate limits

2026-09-18 01:55:36 +08:00

claude_fingerprint_policy_test.go

fix(claude): gate CCH signing by upstream origin and validate fingerprint-profile

2026-08-18 18:06:40 +08:00

claude_fingerprint_policy.go

refactor(claude): deduplicate CLI identity application and tidy helpers

2026-08-18 18:21:33 +08:00

claude_mid_system_model_test.go

fix(claude): align beta assembly and Haiku helper transport with the measured 2.1.258

2026-09-08 10:34:05 +08:00

claude_signing_test.go

fix(claude): gate CCH signing by upstream origin and validate fingerprint-profile

2026-08-18 18:06:40 +08:00

claude_signing.go

refactor(claude): deduplicate CLI identity application and tidy helpers

2026-08-18 18:21:33 +08:00

claude_thinking_replay_test.go

feat(api-call): support $TOKEN$ replacement in request body data

2026-09-14 09:20:03 +08:00

claude_thinking_replay.go

fix(claude): add Claude-compatible thinking replay persistence for multi-turn sessions

2026-08-09 04:36:39 +08:00

codex_executor_auth.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

codex_executor_cache_test.go

fix(codex): normalize request session header to Session-Id and preload codex headers

2026-08-12 18:28:40 +08:00

codex_executor_compact_test.go

…

codex_executor_execute.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

codex_executor_grokbuild_keepalive_test.go

fix(codex): convert Grok client keepalive SSE frames to comments

2026-08-22 20:58:35 +08:00

codex_executor_imagegen_test.go

…

codex_executor_input_ids_test.go

feature(codex): Normalize invalid sub2api message item IDs during Codex input sanitization

2026-08-03 02:45:49 +08:00

codex_executor_instructions_test.go

…

codex_executor_parallel_tool_calls_test.go

…

codex_executor_reasoning_replay_cache_test.go

…

codex_executor_reasoning.go

…

codex_executor_request.go

feat(codex): preserve native fidelity for responses-lite requests

2026-09-13 15:05:03 +08:00

codex_executor_retry_test.go

feat(codex): support model-level quota cooling

2026-09-09 11:57:58 +08:00

codex_executor_signature_test.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

codex_executor_spawn_agent_test.go

chore(codex): update codex user-agent to 0.154.0

2026-09-11 00:30:24 +08:00

codex_executor_stream_output_test.go

fix(auth): enable model cooldown and rotation for model not found errors

2026-09-10 12:35:07 +08:00

codex_executor_stream.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

codex_executor_terminal.go

feat(codex): record upstream response model and warn on silent model substitution

2026-09-18 12:31:52 +08:00

codex_executor_tokens.go

feat(codex): preserve native fidelity for responses-lite requests

2026-09-13 15:05:03 +08:00

codex_executor_tool_schema_test.go

fix(codex): simplify complex tool schema unions and detect empty incomplete responses

2026-09-07 20:09:29 +08:00

codex_executor_translate_test.go

…

codex_executor.go

feat(codex): support model-level quota cooling

2026-09-09 11:57:58 +08:00

codex_native_fidelity_test.go

feat(codex): preserve native fidelity for responses-lite requests

2026-09-13 15:05:03 +08:00

codex_openai_images_extract_test.go

…

codex_openai_images_test.go

feat(codex): add support for gpt-image-2.5 models

2026-09-10 10:40:53 +08:00

codex_openai_images.go

feat(codex): record upstream response model and warn on silent model substitution

2026-09-18 12:31:52 +08:00

codex_response_model_test.go

feat(codex): record upstream response model and warn on silent model substitution

2026-09-18 12:31:52 +08:00

codex_stream_bootstrap_buffering_test.go

feat(codex): add optional time ceiling for stream bootstrap buffering

2026-09-14 14:25:45 +08:00

codex_websockets_connection.go

feat(codex): preserve native fidelity for responses-lite requests

2026-09-13 15:05:03 +08:00

codex_websockets_errors.go

feat(codex): support model-level quota cooling

2026-09-09 11:57:58 +08:00

codex_websockets_execute.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

codex_websockets_executor_store_test.go

…

codex_websockets_executor_test.go

feat(codex): preserve native fidelity for responses-lite requests

2026-09-13 15:05:03 +08:00

codex_websockets_executor.go

…

codex_websockets_request.go

feat(codex): preserve native fidelity for responses-lite requests

2026-09-13 15:05:03 +08:00

codex_websockets_session.go

fix(websockets): prevent keepalive pong starvation during large payload writes

2026-09-11 19:53:45 +08:00

codex_websockets_spawn_agent_test.go

fix(codex): clear multi-agent-v2 optimization state on namespace conflicts

2026-08-12 18:20:13 +08:00

codex_websockets_stream.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

custom_magic_headers_test.go

feat(auth): propagate canonical session id for custom header expansion

2026-09-10 01:43:37 +08:00

devin_executor_test.go

fix(executor): record expected Devin upstream model and bound stream observer memory

2026-09-18 22:08:35 +08:00

devin_executor.go

fix(executor): record expected Devin upstream model and bound stream observer memory

2026-09-18 22:08:35 +08:00

executor_payload_optimization_test.go

…

gemini_executor_signature_test.go

fix(auth): prefer errors from upstream attempts

2026-08-29 12:50:46 +08:00

gemini_executor_test.go

fix(interactions): strip invalid id from function_result and redundant call_id from function_call

2026-09-16 00:31:31 +08:00

gemini_executor.go

fix(executor): record authentic Devin and Gemini Interactions response models

2026-09-18 21:32:59 +08:00

gemini_vertex_executor.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

home_codex_terminal_test.go

…

kimi_executor_test.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

kimi_executor.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

kimi_home_model_capabilities_test.go

refactor(kimi): use request thinking helper

2026-09-03 13:10:30 +08:00

kimi_thinking_replay_test.go

feat(kimi): add Kimi K2.8 model definitions, normalization, and temperature guard

2026-09-11 17:01:00 +08:00

kimi_thinking_replay.go

fix(claude): add Claude-compatible thinking replay persistence for multi-turn sessions

2026-08-09 04:36:39 +08:00

meta_executor_execute.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

meta_executor_stream.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

meta_executor_test.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

meta_executor.go

feat(executor): add native Meta (Muse Code) provider integration

2026-09-15 18:12:49 +08:00

openai_compat_executor_compact_test.go

fix(openai): handle premature SSE stream termination with terminal error emission

2026-08-12 13:05:06 +08:00

openai_compat_executor_images_test.go

fix(executor): robust response model observability across meta, kimi, and openai-compat streams

2026-09-18 21:53:19 +08:00

openai_compat_executor_max_tokens_test.go

feat(executor): support use-max-completion-tokens for openai compatibility models

2026-09-19 01:54:05 +08:00

openai_compat_executor_reasoning_test.go

feat(compat): preserve Claude thinking/tool-call content for is-compat OpenAI compatibility models

2026-08-07 06:26:33 +08:00

openai_compat_executor_retry_test.go

fix(openai-compat): honor bounded rate-limit waits

2026-09-03 11:12:09 +08:00

openai_compat_executor_tool_results_test.go

fix(executor): strip relayed tool result images for text-only models

2026-09-17 09:57:13 +08:00

openai_compat_executor.go

feat(executor): support use-max-completion-tokens for openai compatibility models

2026-09-19 01:54:05 +08:00

openai_responses_signature_test.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

openai_responses_signature.go

fix(codex): preserve reasoning content and IDs for compat models in responses

2026-09-18 23:02:54 +08:00

response_model_multiprovider_test.go

fix(executor): record authentic Devin and Gemini Interactions response models

2026-09-18 21:32:59 +08:00

websocket_lifecycle_bind_test.go

…

websocket_session_target_test.go

…

xai_executor_auth.go

…

xai_executor_execute.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

xai_executor_media.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

xai_executor_request.go

fix(xai): restore aliased client web search tool name in responses

2026-09-18 09:57:06 +08:00

xai_executor_response.go

fix(xai): restore aliased client web search tool name in responses

2026-09-18 09:57:06 +08:00

xai_executor_stream.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00

xai_executor_test.go

fix(xai): restore aliased client web search tool name in responses

2026-09-18 09:57:06 +08:00

xai_executor_tokens.go

…

xai_executor.go

fix(xai): restore aliased client web search tool name in responses

2026-09-18 09:57:06 +08:00

xai_reasoning_replay.go

…

xai_status_err_test.go

fix(xai): remap bad-credentials 403s to unauthorized

2026-08-07 06:48:09 +08:00

xai_websockets_executor_test.go

fix(xai): restore aliased client web search tool name in responses

2026-09-18 09:57:06 +08:00

xai_websockets_executor.go

feat(executor): extend response model recording and substitution warnings to all providers

2026-09-18 21:22:43 +08:00