sususu98 4b2beb3da1 feat(executor): measure effective TTFT with protocol-aware token classification (#5313) ...

* feat(executor): measure effective TTFT with protocol-aware token classification

- Introduce protocol-aware streaming token classification under internal/runtime/executor/helps
- Implement responses_ttft_helpers.go for OpenAI Responses / Codex WebSocket & SSE streaming
- Filter out container metadata, rate limits, handshake headers, and tool execution outputs
- Implement dual-track firstPacketDuration fallback for abnormal / zero-token stream terminations
- Add TrackHTTPClientRoundTripOnly to bypass false TTFT triggers on first response body reads
- Optimize UsageReporter.ObserveTokenEvent hot path with fast-path RLock short-circuiting (0 B/op)
- Align terminal event completions across SSE, WebSocket streaming, and non-streaming executions
- Add EnsurePublished metric recording fallback for successful terminal turns lacking usage blocks
- Add stub helpers with comprehensive specifications for Chat, Claude, and Gemini protocols

* fix(executor): normalize SSE response.done and terminate incomplete WS streams

* fix(usage): capture first-packet fallback on initial body reads with TrackHTTPClientRoundTripOnly

2026-08-29 01:22:21 +08:00

..

helps

feat(executor): measure effective TTFT with protocol-aware token classification (#5313)

2026-08-29 01:22:21 +08:00

aistudio_executor_test.go

fix(executor): prepend empty user turn for model-first Gemini/Antigravity requests (#4959) (#5048)

2026-08-19 18:56:43 +08:00

aistudio_executor.go

fix(executor): prepend empty user turn for model-first Gemini/Antigravity requests (#4959) (#5048)

2026-08-19 18:56:43 +08:00

antigravity_executor_auth.go

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +08:00

antigravity_executor_buildrequest_test.go

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

2026-08-25 11:51:17 +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): remove cross-endpoint fallback (#5209) (#5228)

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

antigravity_executor_execute.go

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

2026-08-25 11:51:17 +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

…

antigravity_executor_keepalive_test.go

perf(antigravity): reuse native upstream connections

2026-08-11 18:33:50 +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(antigravity): safely synthesize terminal finish reasons (#5230)

2026-08-25 15:13:04 +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

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

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

antigravity_executor_tokens.go

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

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

antigravity_executor_transport_test.go

fix(antigravity): harden per-credential transport pooling

2026-08-11 18:33:50 +08:00

antigravity_executor.go

fix(gemini,antigravity): align parallel tool results with preceding tool calls

2026-08-25 14:57:46 +08:00

antigravity_preupstream_rewrite_differential_test.go

fix(gemini,antigravity): align parallel tool results with preceding tool calls

2026-08-25 14:57:46 +08:00

antigravity_preupstream_rewrite_legacy_oracle_test.go

perf(antigravity): batch pre-upstream JSON rewrites

2026-08-11 16:07:42 +08:00

antigravity_reasoning_replay_clear_test.go

fix(antigravity): preserve complete reasoning replay (#4525)

2026-07-25 14:07:31 +08:00

antigravity_reasoning_replay_index_test.go

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

2026-08-11 09:57:15 +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,antigravity): align parallel tool results with preceding tool calls

2026-08-25 14:57:46 +08:00

antigravity_reasoning_replay.go

perf(antigravity): batch pre-upstream JSON rewrites

2026-08-11 16:07:42 +08:00

antigravity_refresh_test.go

fix(antigravity): harden per-credential transport pooling

2026-08-11 18:33:50 +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_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_policy_test.go

feat(claude): add fingerprint-profile=claude-code-cli for API keys and delegated providers (#5047)

2026-08-18 17:29:26 +08:00

claude_executor_cloaking.go

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

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

claude_executor_diagnostics_test.go

fix(claude): pair diagnostics with cache beta

2026-08-03 15:44:44 +08:00

claude_executor_diagnostics.go

fix(claude): harden OAuth identity and native routing

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

claude_executor_execute.go

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

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

claude_executor_fable_ratelimit_test.go

fix(claude): treat allowed_warning as allowed in unified rate limit checks

2026-08-27 17:32:07 +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

feat(claude): add fingerprint-profile=claude-code-cli for API keys and delegated providers (#5047)

2026-08-18 17:29:26 +08:00

claude_executor_ratelimit_test.go

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

2026-08-15 14:08:16 +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(claude): restore tool_search_tool_result references and recognize advisor/agent server tools (#5044) (#5082)

2026-08-19 22:29:51 +08:00

claude_executor_request.go

fix(cliproxy): support base_URL-only config credentials and skip stale auth headers

2026-08-20 15:19:07 +08:00

claude_executor_stream.go

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

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

claude_executor_test.go

fix(test): improve cross-platform compatibility across unit tests

2026-08-28 05:01:42 +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

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

2026-08-18 18:06:40 +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

fix(cliproxy): support base_URL-only config credentials and skip stale auth headers

2026-08-20 15:19:07 +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

feat(claude): add fingerprint-profile=claude-code-cli for API keys and delegated providers (#5047)

2026-08-18 17:29:26 +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

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

2026-08-09 04:36:39 +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

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +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

feat(executor): support $-based custom headers from downstream request headers

2026-08-18 19:33:50 +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

perf(codex): make replay prefix fingerprints incremental

2026-07-24 11:10:58 -07:00

codex_executor_reasoning.go

Merge PR #4546 into dev

2026-07-26 19:11:32 +08:00

codex_executor_request.go

fix(cliproxy): support base_URL-only config credentials and skip stale auth headers

2026-08-20 15:19:07 +08:00

codex_executor_retry_test.go

…

codex_executor_signature_test.go

…

codex_executor_spawn_agent_test.go

feat(codex): add model-level is-compat flag to rewrite MultiAgentV2 agent_message for Responses-compatible endpoints

2026-08-06 04:49:28 +08:00

codex_executor_stream_output_test.go

feat(codex): add opt-in stream bootstrap buffering and overload failover (#5115)

2026-08-20 21:31:53 +08:00

codex_executor_stream.go

feat(executor): measure effective TTFT with protocol-aware token classification (#5313)

2026-08-29 01:22:21 +08:00

codex_executor_terminal.go

feat(executor): measure effective TTFT with protocol-aware token classification (#5313)

2026-08-29 01:22:21 +08:00

codex_executor_tokens.go

feat(compat): preserve compat-mode thinking/signature blocks for API-key models

2026-08-06 17:19:24 +08:00

codex_executor_translate_test.go

…

codex_executor.go

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +08:00

codex_openai_images_extract_test.go

…

codex_openai_images_test.go

feat(codex): add disable-codex-cloaking config option and refine header management

2026-07-30 16:37:40 +08:00

codex_openai_images.go

feat(executor): support $-based custom headers from downstream request headers

2026-08-18 19:33:50 +08:00

codex_stream_bootstrap_buffering_test.go

feat(codex): add opt-in stream bootstrap buffering and overload failover (#5115)

2026-08-20 21:31:53 +08:00

codex_websockets_connection.go

Reduce Codex request amplification for large payloads

2026-08-07 19:16:06 +08:00

codex_websockets_errors.go

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +08:00

codex_websockets_execute.go

feat(executor): measure effective TTFT with protocol-aware token classification (#5313)

2026-08-29 01:22:21 +08:00

codex_websockets_executor_store_test.go

feat: add Home credential concurrency support

2026-07-23 13:42:08 +08:00

codex_websockets_executor_test.go

fix(codex): use codex status error for websocket handshake rejections

2026-08-27 17:09:28 +08:00

codex_websockets_executor.go

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +08:00

codex_websockets_request.go

fix(cliproxy): support base_URL-only config credentials and skip stale auth headers

2026-08-20 15:19:07 +08:00

codex_websockets_session.go

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

2026-08-12 18:20:13 +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

feat(executor): measure effective TTFT with protocol-aware token classification (#5313)

2026-08-29 01:22:21 +08:00

custom_magic_headers_test.go

feat(executor): support $-based custom headers from downstream request headers

2026-08-18 19:33:50 +08:00

executor_payload_optimization_test.go

…

gemini_executor_signature_test.go

fix(executor): sanitize thought signatures in Gemini and Gemini Vertex executors (#5110)

2026-08-21 10:57:03 +08:00

gemini_executor_test.go

fix(cliproxy): support base_URL-only config credentials and skip stale auth headers

2026-08-20 15:19:07 +08:00

gemini_executor.go

fix(executor): sanitize thought signatures in Gemini and Gemini Vertex executors (#5110)

2026-08-21 10:57:03 +08:00

gemini_vertex_executor.go

fix(executor): sanitize thought signatures in Gemini and Gemini Vertex executors (#5110)

2026-08-21 10:57:03 +08:00

home_codex_terminal_test.go

feat: add Home credential concurrency support

2026-07-23 13:42:08 +08:00

kimi_executor_test.go

feat(claude): add fingerprint-profile=claude-code-cli for API keys and delegated providers (#5047)

2026-08-18 17:29:26 +08:00

kimi_executor.go

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

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

kimi_thinking_replay_test.go

fix(kimi): canonicalize K2.7 Code model aliases to official Kimi-For-Coding IDs

2026-08-08 05:08:42 +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

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_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_tool_results_test.go

feat(executor): normalize OpenAI tool results for text-only compatibility models

2026-08-03 03:37:24 +08:00

openai_compat_executor.go

feat(executor): support $-based custom headers from downstream request headers

2026-08-18 19:33:50 +08:00

openai_responses_signature_test.go

Reduce Codex request amplification for large payloads

2026-08-07 19:16:06 +08:00

openai_responses_signature.go

Reduce Codex request amplification for large payloads

2026-08-07 19:16:06 +08:00

websocket_lifecycle_bind_test.go

feat: add Home credential concurrency support

2026-07-23 13:42:08 +08:00

websocket_session_target_test.go

feat: add Home credential concurrency support

2026-07-23 13:42:08 +08:00

xai_executor_auth.go

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +08:00

xai_executor_execute.go

fix(xai): fold namespace tools and restore dispatcher tool calls

2026-08-27 01:08:35 +08:00

xai_executor_media.go

feat(executor): support $-based custom headers from downstream request headers

2026-08-18 19:33:50 +08:00

xai_executor_request.go

fix(xai): fold namespace tools and restore dispatcher tool calls

2026-08-27 01:08:35 +08:00

xai_executor_response.go

fix(xai): fold namespace tools and restore dispatcher tool calls

2026-08-27 01:08:35 +08:00

xai_executor_stream.go

fix(xai): fold namespace tools and restore dispatcher tool calls

2026-08-27 01:08:35 +08:00

xai_executor_test.go

fix(xai): fold namespace tools and restore dispatcher tool calls

2026-08-27 01:08:35 +08:00

xai_executor_tokens.go

chore(pluginhost): refactor and remove unused interceptors and executor methods

2026-07-26 14:31:45 +08:00

xai_executor.go

fix(xai): fold namespace tools and restore dispatcher tool calls

2026-08-27 01:08:35 +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): remap bad-credentials 403s to unauthorized

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

xai_websockets_executor.go

feat(plugin): support observing upstream websocket response events

2026-08-27 05:30:19 +08:00