Luis Pater 690f4f3116 feat(executor): support use-max-completion-tokens for openai compatibility models ...

- Add `use-max-completion-tokens` setting to OpenAI compatibility model configuration
- Provide token normalization between `max_tokens` and `max_completion_tokens` based on model preference

Closes: #5939

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

..

antigravity_compaction_test.go

…

antigravity_compaction.go

…

antigravity_grounding_urls_test.go

…

antigravity_grounding_urls.go

…

cache_helpers_test.go

…

cache_helpers.go

…

chat_ttft_helpers.go

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

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

claude_bip39_words.txt

…

claude_builtin_tools_test.go

…

claude_builtin_tools.go

…

claude_cli_identity_seed_test.go

…

claude_cli_identity_seed.go

…

claude_client_detection_test.go

…

claude_client_detection.go

…

claude_code_session_test.go

…

claude_code_session.go

…

claude_credential_identity_race_test.go

…

claude_credential_identity_test.go

…

claude_credential_identity.go

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

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

claude_device_profile_test.go

…

claude_device_profile.go

…

claude_diagnostics_test.go

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

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

claude_diagnostics.go

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

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

claude_input_tokens_test.go

…

claude_input_tokens.go

…

claude_mcp_alias_test.go

…

claude_mcp_alias_wordlist.go

…

claude_mcp_alias.go

…

claude_ratelimit_test.go

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

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

claude_ratelimit.go

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

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

claude_ttft_helpers.go

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

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

claude_upstream_test.go

…

claude_upstream.go

…

cloak_obfuscate.go

fix(devin): strip system prompt lines matching configured sensitive words to evade unicode normalization bypass

2026-09-13 23:34:43 +08:00

cloak_utils.go

…

codex_input_ids_test.go

…

codex_input_ids.go

…

codex_multi_agent_v2_test.go

fix(openai): align tool call messages and preserve ordering on ambiguous outputs

2026-09-18 12:32:21 +08:00

codex_multi_agent_v2.go

fix(openai): align tool call messages and preserve ordering on ambiguous outputs

2026-09-18 12:32:21 +08:00

codex_native.go

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

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

codex_quota_test.go

…

codex_quota.go

…

codex_terminal_incomplete_test.go

…

codex_terminal_incomplete.go

…

codex_tool_schema_test.go

fix(schema): inspect patternProperties keys and avoid Unicode escape fast-path bypass

2026-09-09 18:03:39 +08:00

codex_tool_schema.go

fix(schema): inspect patternProperties keys and avoid Unicode escape fast-path bypass

2026-09-09 18:03:39 +08:00

cpa_session.go

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

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

derived_session_test.go

…

derived_session.go

…

devin_models_test.go

fix(devin): support swe-1-6-slow model variant

2026-09-16 16:49:49 +08:00

devin_models.go

fix(devin): support swe-1-6-slow model variant

2026-09-16 16:49:49 +08:00

devin_wire_test.go

fix(devin): aggregate tool calls by id and track cache write tokens

2026-09-18 01:04:43 +08:00

devin_wire.go

fix(devin): handle orphaned tool results and normalize function result payloads

2026-09-18 01:34:38 +08:00

gemini_content_turns_test.go

…

gemini_content_turns.go

…

gemini_ttft_helpers.go

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

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

home_refresh_test.go

…

home_refresh.go

…

json_retry_helpers.go

…

kimi_responses_test.go

feat(kimi): support openai responses api

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

kimi_responses.go

feat(kimi): support openai responses api

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

logging_helpers_test.go

…

logging_helpers.go

…

model_capabilities_test.go

…

model_capabilities.go

…

openai_compat_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_max_tokens.go

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

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

openai_compat_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_tool_results.go

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

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

payload_helpers_disable_image_generation_test.go

…

payload_helpers.go

…

payload_mutations_test.go

docs(config): document payload filter examples for codex tools

2026-09-13 22:12:28 +08:00

payload_mutations.go

…

plugin_executor_usage.go

…

proxy_helpers_test.go

fix(devin): transport reuse, interleaved stream steps, strings.Builder panic, and updater URL

2026-09-13 23:34:43 +08:00

proxy_helpers.go

fix(devin): transport reuse, interleaved stream steps, strings.Builder panic, and updater URL

2026-09-13 23:34:43 +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

response_model_test.go

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

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

response_model.go

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

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

responses_ttft_helpers_test.go

…

responses_ttft_helpers.go

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

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

responses_usage_helpers_test.go

…

responses_usage_helpers.go

…

session_id_cache_test.go

…

session_id_cache.go

…

stream_response_model_observer_test.go

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

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

stream_response_model_observer.go

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

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

thinking_providers.go

…

thinking_test.go

…

thinking.go

…

token_helpers.go

…

transport_cache_test.go

…

transport_cache.go

…

usage_helpers_test.go

fix(thinking): extract configuration_update reasoning effort in codex usage reporting

2026-09-11 12:15:57 +08:00

usage_helpers.go

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

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

usage_stream_benchmark_test.go

…

user_id_cache_test.go

…

user_id_cache.go

…

utls_client_resumption_test.go

…

utls_client_test.go

…

utls_client.go

…

vertex_payload_helpers_test.go

…

vertex_payload_helpers.go

…

websocket_observer_helpers_test.go

…

websocket_observer_helpers.go

…