Adolanium 7caee2898b perf(agent): stop rebuilding the streamed reply text on every delta ...

`_record_streamed_assistant_text` grew the turn's visible text with `+=`
on an attribute. Python only grows a string in place when the target is a
local variable, so this copied the whole text on every delta.

The loop runs once per streamed token, so a reply of length N costs about
N squared in copying. A 200 KB answer arriving in 4-character deltas
moves several billion characters and burns seconds of CPU in the loop the
file itself calls the hottest one in the agent.

The text is now kept as a list of pieces and joined when read. Reading
happens at turn end and on interrupt, not per delta, so the whole turn is
linear in the length of the reply. `_fire_stream_delta` used to join on
every token just to ask if the text was empty. That check now looks at
the parts list.

`_current_streamed_assistant_text` becomes a property over that list, so
the seven readers and the call sites that clear it between turns keep
working unchanged. Reading does not collapse the pieces, because a delta
landing between the join and the write back would be lost.

Measured with 8-character deltas: adding 20k deltas to an already long
text took 3.1 times as long as the first 20k before, and 0.9 times after.

2026-09-03 04:46:41 +05:30

..

__init__.py

…

conftest.py

…

repro_48013_image_shrink_brick.py

fix(agent): accept pixel-correct image downscale when bytes grow (#48013)

2026-06-19 11:37:51 -07:00

test_413_compression.py

fix(agent): long-context tier recovery also rechecks the rebuilt request

2026-09-01 21:36:09 -07:00

test_860_dedup.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_1630_context_overflow_loop.py

Merge remote-tracking branch 'origin/main' into tests/prune-low-value

2026-07-29 15:24:14 -07:00

test_18028_content_policy_blocked.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_24996_fallback_exhaustion_cooldown.py

fix(backoff): keep 60s first-hit cooldown, escalate only on consecutive rate-limits

2026-08-03 22:54:54 +05:30

test_28161_anthropic_stream_pool_cleanup.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_31273_402_not_retried.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_32646_fallback_429_after_timeout.py

fix(agent): reopen fallback chain after primary recovery

2026-06-28 00:57:42 -07:00

test_63425_credential_pool_auto_detect.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_66267_multimodal_interim.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_69078_image_corrupt_recovery.py

fix(agent): classify xAI's downloaded-response wording as a corrupt image

2026-08-28 03:46:24 -07:00

test_70773_shared_client_fd_corruption.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_81641_text_turn_incremental_persistence.py

refactor: follow-up for salvaged PR #81692

2026-08-10 09:38:28 +05:30

test_92450_outer_error_retry_bound.py

fix: set failed=True for repeated_outer_errors exit + drop append_message

2026-08-24 04:47:07 +05:30

test_agent_guardrails.py

Revert "fix(agent): harden canonical tool call deduplication"

2026-08-16 10:51:11 -07:00

test_anthropic_mid_tool_call_drop.py

fix(streaming): close the same mid-tool-call drop gap on the Anthropic path

2026-08-07 18:07:19 +05:30

test_anthropic_prompt_cache_policy.py

fix: align cache-policy pre-gate identity with the capability matcher

2026-08-24 14:58:42 +05:30

test_anthropic_response_header_capture.py

nous portal anthropic wire

2026-07-27 11:53:48 -04:00

test_anthropic_third_party_oauth_guard.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_anthropic_truncation_continuation.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_api_max_retries_config.py

test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep)

2026-07-29 15:37:24 -07:00

test_async_httpx_del_neuter.py

fix(state): close leaked SessionDB connections on exception paths (#83226)

2026-08-14 21:41:26 -07:00

test_auth_provider_failover.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_authorization_gate.py

refactor: fold /simplify-code findings

2026-08-06 17:03:10 +05:30

test_background_review_cache_parity.py

fix(background-review): inherit prefill messages + OpenRouter provider pins on non-routed forks

2026-08-02 23:48:42 +05:30

test_background_review_cost_controls.py

fix(agent): trim background_review to the enabled switch

2026-08-16 10:27:52 -07:00

test_background_review_input_budget.py

fix(review): bound same-model background review replay

2026-08-23 18:25:19 -07:00

test_background_review_summary.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_background_review_toolset_restriction.py

feat: allow configured background review tools

2026-08-29 19:10:06 -07:00

test_background_review.py

fix(agent): isolate background review snapshots

2026-09-02 13:28:41 +05:30

test_callable_api_key.py

fix(cli): /config displays the live agent credential, not the env-var constructor seed

2026-08-19 19:42:07 -07:00

test_codex_app_server_compaction.py

fix(compression): arm the failure cooldown when codex compaction fails

2026-08-29 22:29:28 +05:30

test_codex_app_server_integration.py

perf(tools): use load_config_readonly on the approval guard path

2026-08-02 21:17:49 +05:30

test_codex_app_server_lifecycle.py

fix: close the Codex app-server session on agent teardown

2026-08-04 11:25:18 +05:30

test_codex_multimodal_tool_result.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_codex_no_tools_nonetype.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_codex_sdk_transform_bypass.py

style: ruff format test_codex_sdk_transform_bypass.py

2026-08-24 15:30:30 +05:30

test_codex_silent_hang_hint.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_codex_xai_oauth_recovery.py

test: teach the hand-rolled fake pools the failure_reason kwarg

2026-08-04 23:33:39 +05:30

test_commit_memory_session_context_engine.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_compress_context_fallback_shim.py

fix(compression): dedupe current-turn rows when rotation splits the session mid-turn

2026-08-28 02:47:34 +05:30

test_compress_focus_plugin_fallback.py

…

test_compression_abort_state_reset.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_compression_boundary_hook.py

fix(compressor): never commit a compression that grows the transcript (in-place path)

2026-08-15 10:22:47 +05:30

test_compression_boundary.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_compression_budget_rearm.py

feat(agent): context size anchors on provider-reported usage — estimation shrinks to the last turn

2026-08-28 07:51:31 -07:00

test_compression_budget_refund.py

test: vary marathon-turn fixture args — identical calls now legitimately dedupe to stubs

2026-08-20 00:16:22 -07:00

test_compression_closed_adoption.py

fix(compression): adopt live continuation tip at flush across multi-hop chains

2026-08-14 21:39:44 -07:00

test_compression_feasibility.py

test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep)

2026-07-29 15:37:24 -07:00

test_compression_lock_defer.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_compression_persistence.py

test: adapt summary-continuity + rotation-flush fixtures to the lean default

2026-08-26 07:16:04 -07:00

test_compression_timeout_terminal.py

test(agent): loosen brittle error/final_response equality to substring

2026-09-01 03:48:40 +05:30

test_compression_trigger_excludes_reasoning.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_compressor_fallback_update.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_concurrent_interrupt.py

…

test_context_token_tracking.py

…

test_continuation_ceiling_wedge.py

fix(agent): separate continuation fragments so joined text does not glue

2026-08-08 14:56:38 +05:30

test_continuation_repetition_guard.py

fix(agent+discord): guard truncated-response continuation loops and cap Discord split delivery (#86581)

2026-08-16 01:55:51 -07:00

test_conversation_fallback_state.py

fix(agent): discard bare tool-call marker before fallback/persistence (#78148)

2026-08-04 11:26:15 +05:30

test_copilot_native_vision_headers.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_corruption_recovery_guidance.py

fix: prevent handoff leg data loss + surface state.db corruption to users

2026-08-17 13:19:58 +05:30

test_create_openai_client_disables_sdk_retries.py

fix(agent): disable OpenAI SDK auto-retry that double-fires inside the rate-limit loop

2026-06-27 19:23:15 -07:00

test_create_openai_client_kwargs_isolation.py

…

test_create_openai_client_proxy_env.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_create_openai_client_reuse.py

test(agent): cover inline hard timeout and in-flight pool-request abort

2026-08-14 21:19:55 -07:00

test_create_openai_client_ssl_verify.py

fix(agent): honor custom CA certs for custom_providers HTTPS endpoints

2026-07-02 04:51:56 +05:30

test_credential_pool_interrupt.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_credential_rotation_route_settings.py

fix(agent): adopt .env credential/base-url edits at the turn boundary (#67843)

2026-08-04 17:53:17 +00:00

test_credits_notices_toggle.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_cross_process_turn_lease.py

fix(gateway): reject unstamped durable ordinal rewinds

2026-08-15 13:36:25 -07:00

test_custom_provider_extra_headers_client.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_deepseek_reasoning_content_echo.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_deepseek_v4_thinking_live.py

…

test_dict_tool_call_args.py

…

test_direct_contexts_stream_inline.py

fix(agent): delegated children and cron turns stream again — inline, no worker

2026-09-01 21:42:19 -07:00

test_dropped_tool_call_recovery.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_empty_response_recovery_persistence.py

perf(state): batch the turn flush into one SQLite transaction

2026-08-03 20:43:38 +05:30

test_empty_terminal_reasoning_surface.py

feat(agent): surface a labeled reasoning excerpt at the empty-response terminal

2026-07-26 20:59:21 -07:00

test_env_credential_turn_refresh.py

fix(agent): rebind pool entry id after env credential refresh

2026-08-08 19:17:02 -07:00

test_exit_cleanup_interrupt.py

fix(state): consolidate gateway SessionDB writers via process-wide shared registry

2026-09-01 20:55:35 +05:30

test_fallback_api_mode_preservation.py

fix: explicit fallback api_mode always wins; clean up dead-code guard

2026-08-13 12:31:02 -07:00

test_fallback_credential_isolation.py

fix(fallback): attach credential pool after provider switch

2026-06-27 04:39:26 -07:00

test_fallback_reasoning_override.py

fix(compaction): clarify runtime capability state

2026-08-30 05:16:10 -07:00

test_file_mutation_verifier.py

test(agent): pin measured-work regression for display-flag config cache

2026-08-15 00:36:03 -07:00

test_fireworks_live.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_first_chunk_at_hook.py

test: regression coverage for first_chunk_at in post_api_request hook

2026-09-01 08:30:45 -07:00

test_flush_diverts_on_corrupt_state_db.py

fix(state): quarantine SessionDB handle after structural corruption

2026-09-02 16:57:21 +05:30

test_gemini_native_reservation.py

fix(agent_init): reserve Gemini's default maxOutputTokens in the compressor when max_tokens is unset

2026-08-31 12:22:55 -07:00

test_identity_flush.py

fix(agent): preserve live turns in compaction carriers

2026-08-13 21:38:30 +02:00

test_image_generate_parallel.py

feat(image): parallelize image_generate batches

2026-08-03 22:53:32 +05:30

test_image_rejection_fallback.py

fix(sanitize): preserve assistant messages with tool_calls when stripping images

2026-08-28 05:17:26 -07:00

test_image_shrink_recovery.py

fix(agent): classify "media exceeds size limit" as image_too_large

2026-08-28 04:58:06 -07:00

test_in_place_commit_rollback_99477.py

fix(compression): roll the live transcript back when an in-place compaction commit fails (#99477)

2026-09-01 09:28:31 -07:00

test_in_place_compaction.py

fix(compression): salvage follow-up — todo snapshot last-resort, reuse prune helpers

2026-08-20 11:36:54 +05:30

test_in_place_persist_marker_98450.py

fix(compression): stamp _DB_PERSISTED_MARKER after in-place batch compaction commit (#98450)

2026-08-30 19:46:11 -07:00

test_infinite_compaction_loop.py

fix(agent): never floor an anchored pressure figure; keep the estimator total on lone surrogates

2026-09-03 03:09:06 +05:30

test_init_fallback_on_exhausted_pool.py

fix(agent): run init-time fallback for ANY exhausted primary provider

2026-09-01 02:00:05 -07:00

test_interactive_interrupt.py

fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)

2026-07-05 13:42:46 -07:00

test_interpreter_shutdown_turn_exit.py

fix: quitting the CLI no longer spams shutdown-race API errors onto the shell

2026-08-23 16:04:41 -07:00

test_interrupt_propagation.py

fix(agent): separate cancellation diagnostics from tool output

2026-08-23 18:25:19 -07:00

test_invalid_context_length_warning.py

test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep)

2026-07-29 15:37:24 -07:00

test_iteration_budget_race.py

…

test_jsondecodeerror_retryable.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_last_reasoning_per_turn.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_length_continuation_thinking_exhaustion.py

test(agent): pin the reasoning-off continuation to exactly one request; document its prompt-cache cost

2026-09-02 00:55:42 -07:00

test_lmstudio_load_mode.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_long_context_tier_429.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_malformed_tool_arguments.py

refactor(agent): remove the inter-tool delay

2026-07-29 15:21:26 -07:00

test_materialize_data_url_cleanup.py

…

test_memory_nudge_counter_hydration.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_memory_provider_init.py

fix(state): close leaked SessionDB connections on exception paths (#83226)

2026-08-14 21:41:26 -07:00

test_memory_sync_interrupted.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_message_sequence_repair.py

fix(gemini): strip call ids on insert, name the realignments in the log

2026-09-01 14:56:30 +05:30

test_moa_fanout_cadence.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_moa_loop_mode.py

test: trim salvage of #65076 to a lean regression set

2026-08-21 15:02:29 -07:00

test_moa_privacy_filter.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_moa_streaming.py

fix(moa): restore a valid preset after fallback model drift

2026-07-31 21:52:36 -07:00

test_model_streaming_config.py

fix(agent): honor model.streaming: false as a non-streaming escape hatch (#72901)

2026-09-01 22:14:06 -07:00

test_multimodal_tool_content_recovery.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_native_compaction_nontext_retention.py

test(native-compaction): cover image-only retention with an interleaved assistant message

2026-08-30 05:15:54 -07:00

test_native_compaction_summary_retention.py

fix(native_compaction): preserve compression summary messages during pre-checkpoint pruning

2026-08-21 17:24:22 +05:30

test_native_compaction_switch_capabilities.py

fix(compaction): clarify runtime capability state

2026-08-30 05:16:10 -07:00

test_native_compaction.py

fix(gateway): preserve native compaction capability on resume

2026-08-30 05:16:10 -07:00

test_nonretryable_error_html_summary.py

refactor(agent): remove the inter-tool delay

2026-07-29 15:21:26 -07:00

test_notice_spine.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_nous_429_fallback_reentry.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_nous_fallback_unavailable.py

test: avoid OpenRouter dependency in Nous fallback coverage

2026-07-01 05:06:00 -07:00

test_openai_client_lifecycle.py

perf(agent): reuse the per-request OpenAI wire client across sequential LLM calls

2026-07-28 19:06:59 +05:30

test_opencode_free_client_headers.py

feat: opencode-free is fully keyless — no env var, no account, anonymous wire

2026-08-21 00:24:32 -07:00

test_overflow_overhead_aware_tokens.py

fix(compression): route overhead-aware tokens in post-tool compress + add recovery-path tests

2026-08-03 10:01:45 +05:30

test_partial_stream_finish_reason.py

fix(agent): accept marker-only finish_reason after stream supersession

2026-09-01 10:27:06 -07:00

test_per_model_compression_threshold.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_per_model_threshold_init_ordering.py

test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep)

2026-07-29 15:37:24 -07:00

test_percentage_clamp.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_plugin_context_engine_init.py

test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep)

2026-07-29 15:37:24 -07:00

test_plugin_stream_hooks.py

test(plugins): assert per-hook stream ordering, not cross-thread interleaving

2026-08-12 19:15:02 -07:00

test_post_tool_compression_attempt_cap.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_pre_compress_memory_context.py

refactor(memory): renumber checkpoint API — v1 is the implicit historical contract, v2 opts into fail-closed checkpoints

2026-08-25 03:55:55 -07:00

test_preflight_compression_cap_e2e.py

test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep)

2026-07-29 15:37:24 -07:00

test_preflight_timeout_typed_result.py

fix(agent): surface preflight compression timeout as typed result, not generic error

2026-09-01 03:48:40 +05:30

test_primary_runtime_restore.py

fix(auth): look up keyed custom providers by durable pool slug

2026-09-01 22:42:27 +05:30

test_proactive_prune_loop_wiring.py

fix(cache): make proactive pruning durable and cache-aware

2026-08-06 02:22:08 +05:30

test_provider_attribution_headers.py

fix: send Hermes Agent attribution headers to OpenCode Zen and Go

2026-08-13 02:03:40 -07:00

test_provider_fallback.py

fix(runtime): key-scoped fallback extra_body re-resolution + request_overrides in switch_model snapshot

2026-08-29 19:13:12 -07:00

test_provider_parity.py

Revert "remove Vercel AI Gateway and Vercel Sandbox (#33067)"

2026-07-29 19:48:37 -07:00

test_reasoning_echo_resolver_e2e.py

test: production-shape resolver + init-read coverage for reasoning_echo

2026-08-20 00:03:50 +05:30

test_repair_tool_call_arguments.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_repair_tool_call_name.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_request_client_reuse_abort_races.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_reset_aware_primary_restore.py

fix(credential_pool): unpack the tuple in next_available_at's gate

2026-08-03 19:32:50 +05:30

test_retry_status_buffer.py

fix(fallback): surface provider transitions and primary recovery

2026-08-25 12:12:08 +05:30

test_review_prompt_class_first.py

fix(background-review): teach review prompts the enforced read-before-write handshake

2026-08-25 00:18:35 -07:00

test_run_agent_codex_responses.py

fix(codex): retired stream requests must not synthesize a completed response

2026-09-01 22:14:06 -07:00

test_run_agent_multimodal_prologue.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_run_agent.py

fix(agent): reasoning-off continuation reaches the wire on the legacy chat path; reset one-shot flag per turn

2026-09-02 00:55:42 -07:00

test_sanitiser_escalation.py

feat(agent): escalate repeated transcript-sanitiser heals with a one-time user notice (#96870)

2026-08-31 13:11:41 -07:00

test_sequential_chats_live.py

…

test_sequential_tool_timeout.py

fix(agent): separate cancellation diagnostics from tool output

2026-08-23 18:25:19 -07:00

test_session_activity_persist.py

refactor(agent): pin session activity heartbeat cadence + harden best-effort write

2026-08-02 16:16:36 -07:00

test_session_id_env.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_session_meta_filtering.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_session_reset_fix.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_session_source.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_start_order_gate.py

fix(agent): keep the start-order gate under the batch deadline and abort abandoned workers

2026-08-06 03:53:38 +05:30

test_steer.py

refactor(prompt): platform-hint diet — 7 heavies compressed, −657 tok across the map (facts probe-pinned) (#97899)

2026-08-29 06:37:06 -07:00

test_stream_drop_logging.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_stream_interrupt_retry.py

fix(streaming): gate the interrupt worker join on live Relay managed execution

2026-08-14 22:11:30 -07:00

test_stream_single_writer_65991.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_stream_stale_breaker_reset.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_stream_stale_circuit_breaker.py

fix(agent): preserve stalled-provider escalation

2026-08-16 01:55:00 -07:00

test_streamed_text_accumulation.py

perf(agent): stop rebuilding the streamed reply text on every delta

2026-09-03 04:46:41 +05:30

test_streaming_tool_call_repair.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_streaming.py

fix(agent): normalize list-shaped streaming content deltas

2026-08-29 12:45:43 +05:30

test_strict_api_validation.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_strip_reasoning_tags_cli.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_summarize_api_error.py

fix: explain provider DNS failures as possible offline state

2026-08-08 14:08:44 -07:00

test_switch_model_context.py

fix(compaction): clarify runtime capability state

2026-08-30 05:16:10 -07:00

test_switch_model_fallback_prune.py

fix(fallback): surface provider transitions and primary recovery

2026-08-25 12:12:08 +05:30

test_switch_model_pool_reload_52727.py

fix(agent): restore primary credential pool after fallback (#62417)

2026-07-11 03:44:02 -07:00

test_switch_model_reapplies_headers.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_switch_model_reasoning_override.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_switch_model_rollback.py

fix(compaction): clarify runtime capability state

2026-08-30 05:16:10 -07:00

test_switch_model_stale_base_url.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_thinking_only_sanitizer.py

fix(agent): preserve live turns in compaction carriers

2026-08-13 21:38:30 +02:00

test_thinking_prefill_trailing_turn.py

test(agent): cover the API-copy build so restoring the marker pop fails

2026-08-10 10:01:44 +05:30

test_thinking_sig_recovery_persistence.py

fix(agent): strip api_messages in thinking-signature recovery so the retry actually omits thinking blocks

2026-06-10 12:39:44 -07:00

test_tls_fd_recycle_corruption.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_token_persistence_non_cli.py

fix(state): consolidate gateway SessionDB writers via process-wide shared registry

2026-09-01 20:55:35 +05:30

test_tool_activity_heartbeat.py

fix(tools): refresh activity heartbeat while a tool call is in flight (#84491)

2026-08-14 21:20:03 -07:00

test_tool_arg_coercion.py

test: sweep sibling tests stale on the tool renames + deferral default

2026-08-29 18:23:07 -07:00

test_tool_batch_segmentation.py

test: budget-replacement assertions accept persisted-output blocks

2026-08-18 02:12:13 -07:00

test_tool_call_args_sanitizer.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_tool_call_guardrail_runtime.py

fix(guardrails): preserve interactive platform defaults

2026-09-02 00:26:57 -07:00

test_tool_call_incremental_persistence.py

fix(desktop): preserve streamed assistant text and unify atomic persistence (#95514)

2026-08-29 11:33:05 +05:30

test_tool_executor_contextvar_propagation.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_tool_name_db_persistence.py

perf(state): batch the turn flush into one SQLite transaction

2026-08-03 20:43:38 +05:30

test_turn_completion_explainer.py

fix(state): quarantine SessionDB handle after structural corruption

2026-09-02 16:57:21 +05:30

test_turn_liveness_watchdog.py

fix: a declined liveness abort must not cancel a pending compression

2026-09-01 03:19:59 +05:30

test_unicode_ascii_codec.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_verification_continuation_budget.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_vision_aware_preprocessing.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_vision_tool_messages.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00

test_wait_state_visibility.py

test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions

2026-07-29 13:10:23 -07:00