| .. |
| helps | feat(session): enhance harness hierarchy recognition and deduplicate selector extraction | 2 months ago |
| aistudio_executor.go | fix(gemini): append trailing user turn for requests ending with model content | 2 months ago |
| aistudio_executor_test.go | fix(gemini): append trailing user turn for requests ending with model content | 2 months ago |
| antigravity_executor.go | perf(antigravity): batch functionResponse name repairs | 2 months ago |
| antigravity_executor_auth.go | fix(auth): preserve upstream status codes in antigravity auth errors | 2 months ago |
| antigravity_executor_buildrequest_test.go | fix(auth): preserve upstream status codes in antigravity auth errors | 2 months ago |
| antigravity_executor_compaction_test.go | feat(antigravity): add conversation compaction support and capsule encryption | 2 months ago |
| antigravity_executor_credits.go | fix(antigravity): bypass quota cooldowns and credit hints when cooling is disabled | 2 months ago |
| antigravity_executor_credits_test.go | fix(antigravity): remove cross-endpoint fallback (#5209) (#5228) | 2 months ago |
| antigravity_executor_disable_cooling_test.go | fix(antigravity): bypass quota cooldowns and credit hints when cooling is disabled | 2 months ago |
| antigravity_executor_execute.go | fix(antigravity): default to short connections and harden connection pool lifecycle (fixes #5494) | 2 months ago |
| antigravity_executor_finish_reason_test.go | fix(antigravity): safely synthesize terminal finish reasons (#5230) | 2 months ago |
| antigravity_executor_interactions_test.go | test(executor): update antigravity interactions test to use valid model | 2 months ago |
| antigravity_executor_keepalive_test.go | fix(antigravity): default to short connections and harden connection pool lifecycle (fixes #5494) | 2 months ago |
| antigravity_executor_request.go | fix(antigravity): remove cross-endpoint fallback (#5209) (#5228) | 2 months ago |
| antigravity_executor_signature_test.go | fix(gemini): append trailing user turn for requests ending with model content | 2 months ago |
| antigravity_executor_split_usage_test.go | fix(antigravity): safely synthesize terminal finish reasons (#5230) | 2 months ago |
| antigravity_executor_stream.go | fix(antigravity): default to short connections and harden connection pool lifecycle (fixes #5494) | 2 months ago |
| antigravity_executor_tokens.go | fix(antigravity): default to short connections and harden connection pool lifecycle (fixes #5494) | 2 months ago |
| antigravity_executor_transport_test.go | fix(antigravity): include resolved pool settings in transport cache key | 2 months ago |
| antigravity_home_model_capabilities_test.go | feat(auth): use home model capabilities for thinking | 2 months ago |
| antigravity_preupstream_rewrite_differential_test.go | perf(antigravity): batch functionResponse name repairs | 2 months ago |
| antigravity_preupstream_rewrite_legacy_oracle_test.go | fix(claude): preserve tool pairing across intervening system messages | 2 months ago |
| antigravity_reasoning_replay.go | perf(antigravity): batch reasoning replay mutations | 2 months ago |
| antigravity_reasoning_replay_clear_test.go | fix(antigravity): preserve complete reasoning replay (#4525) | 3 months ago |
| antigravity_reasoning_replay_index_test.go | perf(antigravity): batch reasoning replay mutations | 2 months ago |
| antigravity_reasoning_replay_legacy_oracle_test.go | refactor(antigravity): route replay merge through the request index | 3 months ago |
| antigravity_reasoning_replay_test.go | fix(antigravity): tighten replacement offset guard in tool provenance degradation | 2 months ago |
| antigravity_refresh_test.go | fix(auth): prefer errors from upstream attempts | 2 months ago |
| antigravity_schema_sanitize_test.go | fix(gemini): strip 'encrypted' metadata from tool parameters schemas (#5065) | 2 months ago |
| caching_verify_test.go | fix(claude): restore cloaked prompt-cache ownership and native shape | 3 months ago |
| claude_executor.go | fix(cliproxy): support base_URL-only config credentials and skip stale auth headers | 2 months ago |
| claude_executor_auth.go | fix(claude): support setup-tokens and gracefully handle 403 OAuth profile errors (#4983) (#5083) | 2 months ago |
| claude_executor_auth_race_test.go | fix(claude): replay measured OAuth wire, Fast and diagnostic profiles | 3 months ago |
| claude_executor_auth_test.go | fix(claude): support setup-tokens and gracefully handle 403 OAuth profile errors (#4983) (#5083) | 2 months ago |
| claude_executor_beta_policy_test.go | feat(claude): support advisor tool beta header | 2 months ago |
| claude_executor_cloaking.go | fix(claude): avoid mid-conversation system splicing for advisor calls or results | 2 months ago |
| claude_executor_diagnostics.go | feat(claude): implement 2.1.258 billing header fingerprint chain and upstream request continuity | 2 months ago |
| claude_executor_diagnostics_test.go | feat(claude): implement 2.1.258 billing header fingerprint chain and upstream request continuity | 2 months ago |
| claude_executor_execute.go | feat(claude): harden probe and helper request classification, diagnostics isolation, and late cloaking | 2 months ago |
| claude_executor_fable_ratelimit_test.go | fix(claude): treat allowed_warning as allowed in unified rate limit checks | 2 months ago |
| claude_executor_fast_error.go | fix(claude): add Anthropic unified rate-limit parsing helpers | 2 months ago |
| claude_executor_fast_error_test.go | fix(claude): harden request lifecycle | 3 months ago |
| claude_executor_native_helper_test.go | fix(claude): attach helper request IDs according to the upstream base | 2 months ago |
| claude_executor_ratelimit_test.go | fix(auth): prefer errors from upstream attempts | 2 months ago |
| claude_executor_request.go | fix(claude): attach helper request IDs according to the upstream base | 2 months ago |
| claude_executor_request_bench_test.go | perf(claude): batch OAuth tool name rewrites | 3 months ago |
| claude_executor_request_remap_test.go | fix(claude): restore tool_search_tool_result references and recognize advisor/agent server tools (#5044) (#5082) | 2 months ago |
| claude_executor_stream.go | feat(claude): harden probe and helper request classification, diagnostics isolation, and late cloaking | 2 months ago |
| claude_executor_test.go | fix(claude): align beta assembly and Haiku helper transport with the measured 2.1.258 | 2 months ago |
| claude_executor_thinking_signature_test.go | test(claude): preserve adaptive thinking signatures | 3 months ago |
| claude_executor_tokens.go | fix(claude): gate CCH signing by upstream origin and validate fingerprint-profile | 2 months ago |
| claude_executor_wire_casing_test.go | fix(claude): send Anthropic header names with the real client's casing | 3 months ago |
| claude_fingerprint_policy.go | refactor(claude): deduplicate CLI identity application and tidy helpers | 2 months ago |
| claude_fingerprint_policy_test.go | fix(claude): gate CCH signing by upstream origin and validate fingerprint-profile | 2 months ago |
| claude_mid_system_model_test.go | fix(claude): align beta assembly and Haiku helper transport with the measured 2.1.258 | 2 months ago |
| claude_signing.go | refactor(claude): deduplicate CLI identity application and tidy helpers | 2 months ago |
| claude_signing_test.go | fix(claude): gate CCH signing by upstream origin and validate fingerprint-profile | 2 months ago |
| claude_thinking_replay.go | fix(claude): add Claude-compatible thinking replay persistence for multi-turn sessions | 3 months ago |
| claude_thinking_replay_test.go | fix(claude): add Claude-compatible thinking replay persistence for multi-turn sessions | 3 months ago |
| codex_executor.go | chore(pluginhost): refactor and remove unused interceptors and executor methods | 3 months ago |
| codex_executor_auth.go | chore(pluginhost): refactor and remove unused interceptors and executor methods | 3 months ago |
| codex_executor_cache_test.go | fix(codex): normalize request session header to `Session-Id` and preload codex headers | 3 months ago |
| codex_executor_compact_test.go | feat(executor, handlers): enhance websocket output restoration and compact compaction logic | 4 months ago |
| codex_executor_execute.go | fix(codex): simplify complex tool schema unions and detect empty incomplete responses | 2 months ago |
| codex_executor_grokbuild_keepalive_test.go | fix(codex): convert Grok client keepalive SSE frames to comments | 2 months ago |
| codex_executor_imagegen_test.go | feat(executor): add normalization for parallel tool calls in Codex executors | 3 months ago |
| codex_executor_input_ids_test.go | feature(codex): Normalize invalid sub2api message item IDs during Codex input sanitization | 3 months ago |
| codex_executor_instructions_test.go | chore: upgrade CLIProxyAPI dependency to v7 across the project | 6 months ago |
| codex_executor_parallel_tool_calls_test.go | feat(executor): add normalization for parallel tool calls in Codex executors | 3 months ago |
| codex_executor_reasoning.go | Merge PR #4546 into dev | 3 months ago |
| codex_executor_reasoning_replay_cache_test.go | perf(codex): make replay prefix fingerprints incremental | 3 months ago |
| codex_executor_request.go | chore(codex): update codex user-agent to 0.153.3 | 2 months ago |
| codex_executor_retry_test.go | fix(codex): scope usage limit errors to credentials and parse flexible quota resets | 2 months ago |
| codex_executor_signature_test.go | fix(executor): strip orphan reasoning ids when store is disabled (#4285) | 4 months ago |
| codex_executor_spawn_agent_test.go | fix(codex): restore dotted collaboration tool names in multi-agent v2 | 2 months ago |
| codex_executor_stream.go | fix(codex): simplify complex tool schema unions and detect empty incomplete responses | 2 months ago |
| codex_executor_stream_output_test.go | feat(codex): add opt-in stream bootstrap buffering and overload failover (#5115) | 2 months ago |
| codex_executor_terminal.go | fix(codex): recognize retryable server errors for bootstrap failover | 2 months ago |
| codex_executor_tokens.go | feat(compat): preserve compat-mode thinking/signature blocks for API-key models | 3 months ago |
| codex_executor_tool_schema_test.go | fix(codex): simplify complex tool schema unions and detect empty incomplete responses | 2 months ago |
| codex_executor_translate_test.go | refactor(executor): consolidate Codex request translation logic | 5 months ago |
| codex_openai_images.go | feat(executor): support `$`-based custom headers from downstream request headers | 2 months ago |
| codex_openai_images_extract_test.go | perf(codex): avoid rebuilding completed JSON when extracting generated images | 5 months ago |
| codex_openai_images_test.go | feat(codex): add `disable-codex-cloaking` config option and refine header management | 3 months ago |
| codex_stream_bootstrap_buffering_test.go | fix(codex): recognize retryable server errors for bootstrap failover | 2 months ago |
| codex_websockets_connection.go | fix(auth): prefer errors from upstream attempts | 2 months ago |
| codex_websockets_errors.go | fix(codex): scope usage limit errors to credentials and parse flexible quota resets | 2 months ago |
| codex_websockets_execute.go | fix(codex): simplify complex tool schema unions and detect empty incomplete responses | 2 months ago |
| codex_websockets_executor.go | chore(pluginhost): refactor and remove unused interceptors and executor methods | 3 months ago |
| codex_websockets_executor_store_test.go | feat: add Home credential concurrency support | 3 months ago |
| codex_websockets_executor_test.go | fix(codex): simplify complex tool schema unions and detect empty incomplete responses | 2 months ago |
| codex_websockets_request.go | fix(cliproxy): support base_URL-only config credentials and skip stale auth headers | 2 months ago |
| codex_websockets_session.go | fix(codex): clear multi-agent-v2 optimization state on namespace conflicts | 3 months ago |
| codex_websockets_spawn_agent_test.go | fix(codex): clear multi-agent-v2 optimization state on namespace conflicts | 3 months ago |
| codex_websockets_stream.go | fix(codex): simplify complex tool schema unions and detect empty incomplete responses | 2 months ago |
| custom_magic_headers_test.go | feat(executor): support `$`-based custom headers from downstream request headers | 2 months ago |
| executor_payload_optimization_test.go | perf(executor): replace `sjson.SetBytes` with optimized helpers for conditional payload updates | 3 months ago |
| gemini_executor.go | fix(gemini): append trailing user turn for requests ending with model content | 2 months ago |
| gemini_executor_signature_test.go | fix(auth): prefer errors from upstream attempts | 2 months ago |
| gemini_executor_test.go | fix(gemini): append trailing user turn for requests ending with model content | 2 months ago |
| gemini_vertex_executor.go | fix(gemini): append trailing user turn for requests ending with model content | 2 months ago |
| home_codex_terminal_test.go | feat: add Home credential concurrency support | 3 months ago |
| kimi_executor.go | feat(kimi): support openai responses api | 2 months ago |
| kimi_executor_test.go | feat(kimi): support openai responses api | 2 months ago |
| kimi_home_model_capabilities_test.go | refactor(kimi): use request thinking helper | 2 months ago |
| kimi_thinking_replay.go | fix(claude): add Claude-compatible thinking replay persistence for multi-turn sessions | 3 months ago |
| kimi_thinking_replay_test.go | fix(kimi): canonicalize K2.7 Code model aliases to official Kimi-For-Coding IDs | 3 months ago |
| openai_compat_executor.go | fix(codex): scope usage limit errors to credentials and parse flexible quota resets | 2 months ago |
| openai_compat_executor_compact_test.go | fix(openai): handle premature SSE stream termination with terminal error emission | 3 months ago |
| openai_compat_executor_reasoning_test.go | feat(compat): preserve Claude thinking/tool-call content for is-compat OpenAI compatibility models | 3 months ago |
| openai_compat_executor_retry_test.go | fix(openai-compat): honor bounded rate-limit waits | 2 months ago |
| openai_compat_executor_tool_results_test.go | feat(executor): normalize OpenAI tool results for text-only compatibility models | 3 months ago |
| openai_responses_signature.go | Reduce Codex request amplification for large payloads | 3 months ago |
| openai_responses_signature_test.go | Reduce Codex request amplification for large payloads | 3 months ago |
| websocket_lifecycle_bind_test.go | feat: add Home credential concurrency support | 3 months ago |
| websocket_session_target_test.go | feat: add Home credential concurrency support | 3 months ago |
| xai_executor.go | fix(xai): use chat base url resolution for image and video requests | 2 months ago |
| xai_executor_auth.go | chore(pluginhost): refactor and remove unused interceptors and executor methods | 3 months ago |
| xai_executor_execute.go | fix(xai): support compaction fallback from payload input or previous response id | 2 months ago |
| xai_executor_media.go | fix(xai): use chat base url resolution for image and video requests | 2 months ago |
| xai_executor_request.go | fix(xai): use chat base url resolution for image and video requests | 2 months ago |
| xai_executor_response.go | fix(xai): fold namespace tools and restore dispatcher tool calls | 2 months ago |
| xai_executor_stream.go | fix(xai): fold namespace tools and restore dispatcher tool calls | 2 months ago |
| xai_executor_test.go | fix(xai): use chat base url resolution for image and video requests | 2 months ago |
| xai_executor_tokens.go | chore(pluginhost): refactor and remove unused interceptors and executor methods | 3 months ago |
| xai_reasoning_replay.go | fix(xai): clear replay after compaction | 4 months ago |
| xai_status_err_test.go | fix(xai): remap bad-credentials 403s to unauthorized | 3 months ago |
| xai_websockets_executor.go | fix(xai): support compaction fallback from payload input or previous response id | 2 months ago |
| xai_websockets_executor_test.go | fix(xai): support compaction fallback from payload input or previous response id | 2 months ago |