Luis Pater a59b1764e7 fix(claude): emit trailing usage chunk and aggregate stream usage ...

- Emit an OpenAI-compatible trailing usage chunk with an empty choices array on `message_stop`.
- Include `cache_write_tokens` in prompt token details for OpenAI response translations.
- Parse usage from `message.usage` and buffer Claude stream usage across chunks to merge input and output token counts.
- Ensure observed streaming usage details are published on completion or stream failure.

Closes: #5617

2026-09-09 10:48:05 +08:00

..

helps

fix(claude): emit trailing usage chunk and aggregate stream usage

2026-09-09 10:48:05 +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

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

2026-09-06 23:41:12 +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

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

2026-09-01 08:37:02 +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

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

2026-09-07 19:15:39 +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

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

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

antigravity_executor_tokens.go

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

2026-09-07 19:15:39 +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

perf(antigravity): batch functionResponse name repairs

2026-09-08 18:32:26 +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

…

antigravity_reasoning_replay_test.go

fix(antigravity): tighten replacement offset guard in tool provenance degradation

2026-09-04 09:45:49 +08:00

antigravity_reasoning_replay.go

perf(antigravity): batch reasoning replay mutations

2026-09-04 18:53:21 +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

…

claude_executor_auth_race_test.go

…

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): support advisor tool beta header

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

claude_executor_cloaking.go

fix(claude): avoid mid-conversation system splicing for advisor calls or results

2026-09-06 05:55:42 +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(claude): emit trailing usage chunk and aggregate stream usage

2026-09-09 10:48:05 +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

…

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

…

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

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

claude_executor_stream.go

fix(claude): emit trailing usage chunk and aggregate stream usage

2026-09-09 10:48:05 +08:00

claude_executor_test.go

fix(claude): emit trailing usage chunk and aggregate stream usage

2026-09-09 10:48:05 +08:00

claude_executor_thinking_signature_test.go

…

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

…

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

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

…

claude_thinking_replay.go

…

codex_executor_auth.go

…

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

2026-09-07 20:09:29 +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

…

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

chore(codex): update codex user-agent to 0.153.3

2026-09-06 15:27:15 +08:00

codex_executor_retry_test.go

fix(codex): scope usage limit errors to credentials and parse flexible quota resets

2026-09-06 06:20:20 +08:00

codex_executor_signature_test.go

…

codex_executor_spawn_agent_test.go

fix(codex): restore dotted collaboration tool names in multi-agent v2

2026-09-07 19:12:46 +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

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

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

codex_executor_terminal.go

fix(codex): recognize retryable server errors for bootstrap failover

2026-09-08 03:49:10 +08:00

codex_executor_tokens.go

…

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

…

codex_openai_images_extract_test.go

…

codex_openai_images_test.go

…

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

fix(codex): recognize retryable server errors for bootstrap failover

2026-09-08 03:49:10 +08:00

codex_websockets_connection.go

fix(auth): prefer errors from upstream attempts

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

codex_websockets_errors.go

fix(codex): scope usage limit errors to credentials and parse flexible quota resets

2026-09-06 06:20:20 +08:00

codex_websockets_execute.go

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

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

codex_websockets_executor_store_test.go

…

codex_websockets_executor_test.go

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

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

codex_websockets_executor.go

…

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

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

2026-09-07 20:09:29 +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(auth): prefer errors from upstream attempts

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

gemini_executor_test.go

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

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

gemini_executor.go

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

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

gemini_vertex_executor.go

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

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

home_codex_terminal_test.go

…

kimi_executor_test.go

feat(kimi): support openai responses api

2026-09-08 10:52:27 +08:00

kimi_executor.go

feat(kimi): support openai responses api

2026-09-08 10:52:27 +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

…

kimi_thinking_replay.go

…

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

…

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

…

openai_compat_executor.go

fix(codex): scope usage limit errors to credentials and parse flexible quota resets

2026-09-06 06:20:20 +08:00

openai_responses_signature_test.go

…

openai_responses_signature.go

…

websocket_lifecycle_bind_test.go

…

websocket_session_target_test.go

…

xai_executor_auth.go

…

xai_executor_execute.go

fix(xai): support compaction fallback from payload input or previous response id

2026-09-06 22:16:06 +08:00

xai_executor_media.go

fix(xai): use chat base url resolution for image and video requests

2026-08-30 14:01:18 +08:00

xai_executor_request.go

fix(xai): use chat base url resolution for image and video requests

2026-08-30 14:01:18 +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): use chat base url resolution for image and video requests

2026-08-30 14:01:18 +08:00

xai_executor_tokens.go

…

xai_executor.go

fix(xai): use chat base url resolution for image and video requests

2026-08-30 14:01:18 +08:00

xai_reasoning_replay.go

…

xai_status_err_test.go

…

xai_websockets_executor_test.go

fix(xai): support compaction fallback from payload input or previous response id

2026-09-06 22:16:06 +08:00

xai_websockets_executor.go

fix(xai): support compaction fallback from payload input or previous response id

2026-09-06 22:16:06 +08:00