Jack Lau f57209bc9f fix(agent): carry the ambiguity of Anthropic's 'out of extra usage' 400 through classification, cooldown, and terminal surfaces ...

Review follow-up (egilewski): the previous commit only hedged the guidance
text; the exact Anthropic 400 was still classified, persisted, and surfaced
as confirmed billing exhaustion. Carry the ambiguity all the way through:

- agent/error_classifier.py: 'out of extra usage' matches on the 400 and
  status-less paths now attach error_context {billing_unverified,
  possible_content_filter}. Reason stays FailoverReason.billing (rotation +
  fallback remain the right recovery either way); ClassifiedError grows a
  billing_unverified property.

- agent/credential_pool.py: new FAILURE_REASON_BILLING_UNVERIFIED. An
  unverified billing exhaustion gets the short transient cooldown instead of
  the one-hour bench, regardless of pool size: a content-filter rejection
  leaves the credential healthy and fails identically on every key, and the
  hour-long sole-credential latch is what replayed the stored error and made
  real fixes look ineffective. A true 402 keeps the full bench. The marker
  persists with the entry so a restart cannot upgrade it back to a bench.

- agent/agent_runtime_helpers.py + run_agent.py: recover_with_credential_pool
  threads billing_unverified and hands the pool 'billing_unverified' as the
  persisted failure_reason.

- agent/conversation_loop.py: the fallback-switch status, max-retries status,
  terminal label, and both structured terminal results hedge when the verdict
  is unverified. New _billing_terminal_label + _billing_failure_result build
  the returned terminal response in one place; the result dict now carries
  billing_unverified and the billing_block gains 'unverified': true. The
  confirmed-billing path (a real 402 or an API-key credit depletion) keeps
  the original assertive wording, so the caveat no longer dilutes it.

Regression tests: classifier marking (400 + status-less + unambiguous-body
negative), pool cooldown TTLs + persistence round-trip, pool failure_reason
plumbing, and the returned terminal response for both unverified and
confirmed verdicts.

Note: tests/agent/test_credential_pool_routing.py::TestFailureAttribution::
test_unmatched_key_does_not_retry_only_pool_entry fails identically on
current main without this change (pre-existing, unrelated).

2026-08-14 21:54:56 -07:00

..

lsp

fix(file-ops): skip per-file tsc when an ancestor tsconfig.json exists (#86640)

2026-08-14 21:17:00 -07:00

transports

fix(test): rename misleading test — non-empty array codex field stripping, not empty array

2026-08-14 21:25:48 -07:00

__init__.py

…

test_account_usage.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_adapter.py

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

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

test_anthropic_billing_guidance.py

fix(agent): carry the ambiguity of Anthropic's 'out of extra usage' 400 through classification, cooldown, and terminal surfaces

2026-08-14 21:54:56 -07:00

test_anthropic_keychain.py

test: run os-specific tests on their real host, not a faked one

2026-08-09 22:09:49 -04:00

test_anthropic_kimi_signed_thinking_replay.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_kwargs_sanitize.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_mcp_prefix_strip.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_oauth_pkce.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_oauth_ua_prefix.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_output_field_leak.py

fix(tests): isolate suite fixtures from host auth

2026-08-12 23:47:28 -07:00

test_anthropic_request_blank_block_guard.py

fix(anthropic): coerce blank system text blocks at extraction (#70909)

2026-08-14 21:27:05 -07:00

test_anthropic_thinking_block_order.py

…

test_anthropic_token_scope_isolation.py

fix(auth): route anthropic adapter credential reads through the profile secret scope

2026-08-01 16:42:51 -07:00

test_anthropic_whitespace_text_blocks.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_content_sidecar.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_arcee_trinity_overrides.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_async_token_accounting.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_async_utils.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_aux_progress_streaming.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_auxiliary_anthropic_pool_fallback_regression.py

…

test_auxiliary_client_anthropic_custom.py

…

test_auxiliary_client_azure_foundry.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_auxiliary_client_base_url_host_validation_52608.py

fix(auxiliary): honor /anthropic-suffixed gateway base_url on aux + fallback calls

2026-08-13 11:41:59 -07:00

test_auxiliary_client_bootstrap_skew.py

…

test_auxiliary_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_auxiliary_client_resolve_dedup.py

…

test_auxiliary_client_ssl_verify.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_auxiliary_client_xai_oauth_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_auxiliary_client.py

fix: update kimi auxiliary test for medium→high mapping

2026-08-13 01:05:49 +05:30

test_auxiliary_compression_timeout_floor.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_auxiliary_concurrency.py

fix(agent): cap auxiliary LLM concurrency per task

2026-08-03 23:01:03 +05:30

test_auxiliary_config_bridge.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_auxiliary_explicit_base_anthropic.py

test(agent): align explicit-base auxiliary tests with host-anchored rewrite policy

2026-08-13 11:45:27 -07:00

test_auxiliary_explicit_cancellation.py

fix(compression): let explicit interrupts cancel safely

2026-08-02 22:15:20 +05:30

test_auxiliary_main_first.py

fix(auxiliary): honor main model for title generation (#83636)

2026-08-11 23:36:47 -05:00

test_auxiliary_named_custom_providers.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_auxiliary_relay.py

Merge updated skill metrics into client resource metrics

2026-08-02 20:12:50 -07:00

test_auxiliary_runtime_cache_key.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_auxiliary_transient_retry.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_auxiliary_transport_autodetect.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_auxiliary_user_default_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_azure_identity_adapter.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_backend_identity.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_battery.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_bedrock_1m_context.py

…

test_bedrock_adapter.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_bedrock_empty_text_blocks.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_bedrock_integration.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_bedrock_interrupt_post_worker.py

Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"

2026-07-27 21:10:51 -07:00

test_billing_links.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_billing_unverified_carrythrough.py

fix(agent): carry the ambiguity of Anthropic's 'out of extra usage' 400 through classification, cooldown, and terminal surfaces

2026-08-14 21:54:56 -07:00

test_billing_usage.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_billing_view.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_bot_profile_prompt_isolation.py

test(agent): cover agent-in-profile-A with ambient home bound to profile B

2026-08-14 13:56:58 -07:00

test_bounded_response.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_budget_reasoning_details_exclusion.py

fix(agent): exclude reasoning_details envelope from tail-budget walk (#73298)

2026-07-31 23:16:58 -07:00

test_cache_disabled_on_stubs.py

refactor(agent): share the cache_ttl disable predicate across init and stub paths

2026-08-02 11:52:59 +05:30

test_canon_args_memo_parity.py

fix(agent): stop the send-path repair from rewriting persisted history

2026-08-07 16:57:11 +05:30

test_cascading_interrupt_6600.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_chat_completion_helpers_provider_sort.py

…

test_cjk_token_estimation.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_close_interrupted_tool_sequence.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_app_server_event_bridge.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_app_server_persist.py

feat(codex): honor redirect and hard stop in the app-server runtime

2026-07-22 12:02:40 -05:00

test_codex_cloudflare_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_codex_gpt55_autoraise_notice.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_codex_request_transport_diagnostics.py

fix: widen APIConnectionError handling to finalization drain loop

2026-08-12 12:42:39 +05:30

test_codex_responses_adapter.py

fix(codex): defang reserved Harmony tokens in requests

2026-07-31 22:53:20 -07:00

test_codex_runtime_live_events.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_ttfb_watchdog.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_coding_context.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_compaction_anti_thrash.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_compaction_redaction_boundaries.py

fix(compression): apply strict redaction at every compaction text boundary (#69294)

2026-07-22 08:11:40 -07:00

test_compress_context_progress_timeout.py

test(agent): deflake progress-extension timing per FLAKY policy (re-review #8)

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

test_compress_focus.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_signal_leak.py

fix: prevent stale lock-skip signal leaking between compress_context calls

2026-07-23 08:19:14 -07:00

test_compressed_summary_metadata.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_adoption_preserves_live_tail.py

fix(compression): preserve live tail before snapshot adoption

2026-08-09 22:29:39 +05:30

test_compression_anti_thrash_persistence.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_anti_thrash_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_compression_attempt_telemetry.py

fix: adapt compression attempt logging to current main aux-call contract

2026-07-22 08:13:41 -07:00

test_compression_concurrent_fork.py

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

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

test_compression_count_warning_36908.py

…

test_compression_fallback_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_compression_interrupt_protection.py

fix(compression): let explicit interrupts cancel safely

2026-08-02 22:15:20 +05:30

test_compression_logging_session_context.py

…

test_compression_max_attempts_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_compression_orphan_recovery.py

fix(sessions): recover compression parents without continuations

2026-08-07 13:24:56 +05:30

test_compression_progress.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_review_76354.py

feat(agent): emit pool_saturated compression-attempt telemetry (re-review #6)

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

test_compression_rotation_state.py

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

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

test_compression_small_ctx_threshold_floor.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_worker_isolation_76354.py

test: skip live aux feasibility probe in worker-isolation regressions

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

test_compressor_actionable_tail_anchor.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_assistant_tail_anchor.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_historical_media.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_image_tokens.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_media_stripping.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_tail_cut_oob_fix.py

test(agent): add compress()-level E2E regression for short tool-suffix OOB (#75588)

2026-07-31 23:16:58 -07:00

test_compressor_tail_cut_tool_pair_floor.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_tool_call_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_compressor_zero_user_guard.py

fix(agent): preserve a non-empty user query after compression

2026-07-31 23:16:58 -07:00

test_context_breakdown.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_context_compressor_cross_session_guard.py

…

test_context_compressor_session_end_clears_state.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_context_compressor_summary_continuity.py

test(compression): cover degenerate compress_end same-session handoff keep

2026-08-14 20:52:16 -07:00

test_context_compressor_temporal_anchoring.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_context_compressor_zero_user_provenance.py

fix(compression): ignore background process notifications

2026-08-14 01:08:13 -07:00

test_context_compressor.py

refactor(compression): fold simplify findings — dedup floor constant, drift-guard test

2026-08-08 14:27:31 +05:30

test_context_engine_host_contract.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_context_engine_on_turn_complete_usage.py

docs+test(context-engine): sync public guide coverage note; pin finalization-seam observation contract

2026-07-23 19:44:35 -07:00

test_context_engine_select_context.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_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_context_references.py

fix(docker): read attached binary files in backend (#76577)

2026-08-08 05:44:18 -07:00

test_context_refs_concurrent.py

test: prove concurrency with barriers/witnesses instead of wall-clock bounds

2026-07-29 21:30:53 -07:00

test_context_route_mismatch.py

test(gateway): cover named-custom context pin on session-info banner

2026-08-04 11:00:04 +05:30

test_copilot_acp_client.py

fix(test): hermetic env-detection tests — pin container/supervisor/HOME probes (#422)

2026-07-29 18:55:10 -07:00

test_copilot_acp_deprecation.py

…

test_credential_pool_deferred_refresh.py

fix(credential_pool): serialize deferred-refresh pool mutations

2026-08-03 19:08:09 +05:30

test_credential_pool_key_rotation.py

fix(credential-pool): clear exhaustion state on key rotation (#22622)

2026-08-04 11:35:06 -06:00

test_credential_pool_lease_refresh_reselect.py

fix(credential-pool): re-select in acquire_lease after a deferred refresh

2026-08-04 13:12:24 +05:30

test_credential_pool_no_entries_log_throttle.py

…

test_credential_pool_oat_authtype.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_pool_oauth_writethrough.py

fix(auth): apply same source-path write-through fix to non-pool xAI path

2026-07-31 22:32:48 -07:00

test_credential_pool_provider_boundary.py

…

test_credential_pool_quarantine_locking.py

fix(credential-pool): lock the quarantine read-modify-write of _entries

2026-08-04 13:20:15 +05:30

test_credential_pool_routing.py

fix(tests): isolate suite fixtures from host auth

2026-08-12 23:47:28 -07:00

test_credential_pool_sole_cooldown.py

fix(agent): carry the ambiguity of Anthropic's 'out of extra usage' 400 through classification, cooldown, and terminal surfaces

2026-08-14 21:54:56 -07:00

test_credential_pool_unmatched_rotation_bound.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_pool.py

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

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

test_credits_cold_start.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_credits_fixture_snapshot.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_credits_policy.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_credits_tracker.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_credits_view.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_cron_inline_api_call_62151.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_crossloop_client_cache.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_curator_activity.py

…

test_curator_backup.py

fix(curator): restore the real skills tree when a rollback extract dies part-way

2026-07-31 22:34:57 -07:00

test_curator_classification.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_curator_reports.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_curator.py

fix(curator): protect cron skills referenced by absolute path

2026-08-08 06:04:14 -07:00

test_cursor_optimizations_parity.py

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

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

test_custom_pool_mismatch_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_custom_provider_ca_probes.py

test(providers): tolerate stream kwarg in metadata probe mock

2026-08-14 16:37:36 -07:00

test_custom_provider_extra_body_matching.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_custom_provider_extra_body.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_custom_providers_vision.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_deadline.py

feat(agent): resolve sequential tool deadline via timeouts.tools.sequential_call (#85125 2a)

2026-08-15 02:21:39 +05:30

test_deepseek_anthropic_thinking.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_direct_provider_url_detection.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_display_emoji.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_display_todo_progress.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_display_tool_failure.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_display.py

refactor(discord): simplify tool preview links

2026-08-02 21:48:06 -07:00

test_empty_tool_name_loop_dampening.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_endpoint_blackhole.py

fix(agent): stop re-probing endpoints that blackhole TCP connects

2026-08-03 21:53:13 +05:30

test_engine_preflight_wire.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_error_classifier.py

fix(agent): carry the ambiguity of Anthropic's 'out of extra usage' 400 through classification, cooldown, and terminal surfaces

2026-08-14 21:54:56 -07:00

test_external_skills_dirs_cache.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_external_skills.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_failover_identity.py

fix: restore empty-response fallback retry, dedupe alibaba set, thread TTL into aux replan

2026-08-13 15:24:47 +05:30

test_file_safety_container_mirror.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_file_safety_credentials.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_file_safety_cross_profile.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_file_safety_sandbox_mirror.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_file_safety_session_state.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_file_safety.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_gateway_turn_sidecar.py

perf(gateway): byte-stable session context prompts

2026-07-19 14:58:59 +05:30

test_gemini_fast_fallback.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_gemini_free_tier_gate.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_gemini_native_adapter.py

fix(gemini): interpose placeholder model turn between tool result and user text

2026-08-05 17:21:01 -07:00

test_gemini_schema.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_gemini_standard_key_guidance.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_ghost_skill_pruning.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_i18n.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_idle_compaction_lock_and_guards.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_idle_compaction.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_image_gen_registry.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_image_routing.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_insights.py

refactor(usage): simplify-pass follow-ups

2026-08-14 02:04:24 +05:30

test_intent_ack_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_interrupt_compat.py

fix(compression): let explicit interrupts cancel safely

2026-08-02 22:15:20 +05:30

test_jiter_preload.py

…

test_kanban_stop.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_kimi_coding_anthropic_thinking.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_total_tokens.py

…

test_learn_prompt.py

fix(learn): process large sources incrementally

2026-08-08 05:09:43 -07:00

test_learning_graph_render.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_learning_graph.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_learning_mutations.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_lmstudio_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_local_probe_disk_cache.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_local_stream_timeout.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_manual_compression_feedback.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_markdown_tables.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_async_sync.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_boundary_commit.py

test: prove concurrency with barriers/witnesses instead of wall-clock bounds

2026-07-29 21:30:53 -07:00

test_memory_provider_unavailable_warning.py

feat(hindsight): memory provider improvements — recall_sync, retain_source, setup templates, memory indicators, error hints

2026-08-13 23:15:25 +05:30

test_memory_provider.py

fix: support packaged memory provider skills

2026-08-13 11:49:14 -07:00

test_memory_recall_indicator.py

fix: security + efficiency review fixes for salvaged PR #74379

2026-08-13 23:15:25 +05:30

test_memory_session_switch.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_skill_scaffolding.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_user_id.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_write_bridge.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_content.py

…

test_message_sanitization_policy.py

refactor(agent): single-owner call_id + reasoning_content sanitization policies (wire-parity verified)

2026-07-29 12:29:39 -07:00

test_micro_compaction.py

test(agent): cover reference-only handoff sole-active-turn regression

2026-08-07 19:44:35 +05:30

test_minimax_auxiliary_url.py

fix(auxiliary): keep ZAI Coding Plan routing

2026-08-13 12:30:29 -07:00

test_minimax_provider.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_aggregator_cache_control.py

perf(prompt-caching): preserve tool-loop cache boundaries (#20880)

2026-08-01 14:27:12 +05:30

test_moa_aggregator_cost_slot.py

…

test_moa_cold_start_cache_66793.py

perf(moa): cache resolved preset + per-slot runtime to cut cold-start latency (#66793)

2026-08-03 22:43:15 +05:30

test_moa_context_max_tokens.py

fix(moa): stop reference_max_tokens from also capping the aggregator

2026-07-23 16:17:27 -07:00

test_moa_observability_bridge.py

feat(langfuse): widen tracing to errors, sessions, subagents, and MoA fan-out

2026-08-13 23:10:16 +05:30

test_moa_prepared_request_client_swap.py

fix(agent): stop the MoA prepared request reaching a swapped-in native client

2026-08-14 21:36:41 -07:00

test_moa_progress.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_quiet_reference_output.py

fix(moa): scope quiet relay to machine-readable CLI

2026-07-23 18:40:09 -07:00

test_moa_reasoning_effort.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_reference_system_prompt.py

chore(moa): add trailing newline to reference-prompt test file

2026-07-23 18:40:09 -07:00

test_moa_slot_api_mode.py

fix(agent): propagate prompt-cache TTL to MoA/aux, clamp Qwen 1h, re-preflight on failover (#84733)

2026-08-13 15:24:47 +05:30

test_moa_slot_max_tokens.py

fix(agent): propagate prompt-cache TTL to MoA/aux, clamp Qwen 1h, re-preflight on failover (#84733)

2026-08-13 15:24:47 +05:30

test_moa_switch_api_mode.py

…

test_moa_trace_streamed_capture.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_model_extra_type_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_model_metadata_local_ctx.py

fix(model_metadata): read llama.cpp context from meta.n_ctx + accept sole model

2026-08-04 11:08:32 +05:30

test_model_metadata_ssl.py

fix(tests): eliminate flaky/broken tests — shadow sys.path inserts, unmocked network in compressor tests, stale-SDK feishu pin guard, quadratic redact regexes

2026-07-29 15:12:28 -07:00

test_model_metadata.py

fix(agent): reject stale 32k metadata for MiniMax

2026-08-13 11:12:05 -07:00

test_models_dev_meta_mapping.py

fix(models_dev): map meta-ai provider to models.dev 'meta' id (salvage #81418) (#84679)

2026-08-12 14:42:00 -04:00

test_models_dev.py

refactor(models): simplify-pass follow-ups on the refresh path

2026-08-14 03:31:22 +05:30

test_moonshot_schema.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_non_stream_stale_timeout.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_none_deref_guards.py

…

test_nous_credits_gauge.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_credits_snapshot.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_oauth_401_guidance.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_portal_anthropic_wire.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_rate_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_onboarding.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_oneshot.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_openrouter_response_cache.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_org_skill_namespace.py

refactor(sync): put every Skill Sync verb under hermes sync; drop HSP naming

2026-07-29 07:47:06 +10:00

test_outbound_webhooks.py

fix(hooks): flush outbound queue at interpreter exit

2026-08-02 15:01:11 -07:00

test_pet_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_pet_generate.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_platform_hint_desktop.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_platform_hint_overrides.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_references.py

feat(plugins): allow plugins to register custom @-prefix context references

2026-08-12 18:41:59 -07:00

test_plugin_llm_task_routing.py

fix(plugins): complete task-routed LLM integration

2026-08-12 16:25:20 -07:00

test_plugin_llm.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_prompt_sections.py

feat(plugins): add cache-safe system prompt sections

2026-08-12 16:34:58 -07:00

test_portal_tags.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_post_compression_trim.py

perf(compressor): release allocator pages after successful compaction

2026-08-03 22:55:36 +05:30

test_pre_compress_memory_context.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_preflight_compression_gate.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_preflight_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_proactive_prune_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_proactive_prune_restart_safety.py

fix(compression): durable-sync the prune runway on model switch + fast no-op for incapable stores

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

test_proactive_tool_result_pruning.py

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

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

test_probe_cache_followups.py

fix(model_metadata): rewrite localhost->IPv4 for the remaining local probe sites

2026-08-03 21:12:56 +05:30

test_profile_home_override_precedence.py

fix(agent): bound HERMES_HOME override wins over shared session-db home

2026-08-14 14:37:00 -07:00

test_prompt_builder.py

test: run os-specific tests on their real host, not a faked one

2026-08-09 22:09:49 -04:00

test_prompt_cache_boundary.py

refactor(cache): share the boundary-declaration helper and simplify the registry

2026-08-09 15:25:12 +05:30

test_prompt_cache_ttl_propagation.py

refactor: hoist preflight clear into restart handler, single-source qwen predicate

2026-08-13 15:24:47 +05:30

test_prompt_caching.py

fix(agent): propagate prompt-cache TTL to MoA/aux, clamp Qwen 1h, re-preflight on failover (#84733)

2026-08-13 15:24:47 +05:30

test_protected_tail_pressure_61932.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_proxy_and_url_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_pydantic_dump_warning_leak.py

fix: suppress pydantic serializer warnings leaking to the terminal

2026-08-08 23:14:30 -07:00

test_rate_limit_tracker.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_reactions.py

…

test_reasoning_stale_timeout_floor.py

add grok 4.6 (#84661)

2026-08-12 13:37:04 -04:00

test_reasoning_summaries.py

fix(reasoning): keep gpt-5.x summary parts as separate blocks on the chat wire

2026-08-06 22:02:37 -05:00

test_redact.py

fix(redact): narrow control-split join guard to line-crossing spans

2026-08-07 17:50:03 +05:30

test_reference_handoff_active_turn.py

test(agent): cover reference-only handoff sole-active-turn regression

2026-08-07 19:44:35 +05:30

test_refine_focus.py

feat: /refine — run the memory/skill self-improvement review on demand

2026-08-05 22:40:51 -07:00

test_relay_llm.py

fix(moa): carry completed responses through the managed Relay path

2026-07-31 21:52:35 -07:00

test_relay_nested_execution.py

fix(relay): bypass managed execution for nested calls inside managed callbacks

2026-08-08 23:46:17 -07:00

test_relay_runtime_bounded_scope_ops.py

fix(relay): bound the interpreter-shutdown fallback lane; unwedge test fakes at teardown

2026-08-12 19:19:54 -07:00

test_relay_session_segments.py

fix(relay): defer rotating-compaction session close while a turn is live

2026-08-13 10:45:15 -07:00

test_relay_tools.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_replay_budget_accounting.py

fix(compression): charge stale thinking to the tail budget only on the newest assistant turn (#73624)

2026-08-08 17:42:34 -07:00

test_replay_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_request_client_reuse.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_restore_primary_pool_reselect.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_resume_stale_active_task.py

test(agent): cover reference-only handoff sole-active-turn regression

2026-08-07 19:44:35 +05:30

test_rotation_flush_persisted_boundary_68196.py

fix(agent): pass persisted-prefix boundary when rotation flushes on cold resume (#68196)

2026-07-21 12:11:31 +05:30

test_runtime_cwd.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_save_url_image.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_secret_scope_tier1_migration.py

test(secrets): consolidated tier-1 migration regression suite

2026-08-02 10:02:33 -07:00

test_secret_scope.py

fix(secrets): allowlist API_SERVER listener settings as global deployment env

2026-08-02 09:59:52 -07:00

test_send_path_history_isolation.py

fix(agent): make the send-path copy structural — close the write-through class

2026-08-07 16:57:11 +05:30

test_session_activity.py

chore: round-2 review nits (re-review #9)

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

test_session_rotation_flush_cold_resume_68454.py

test: drop source-grep change-detector from #68480

2026-07-22 10:00:39 +05:30

test_set_runtime_main_custom_provider.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_shell_hooks_consent.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_shell_hooks_tree_kill.py

fix(hooks): kill the whole process tree when a shell hook times out

2026-08-12 19:44:04 -07:00

test_shell_hooks.py

feat(plugins): rename hook to transform_api_error_classification per #64231 verdict

2026-08-13 09:36:02 -07:00

test_skill_bundles.py

Merge updated tool metrics into skill metrics

2026-07-31 07:30:30 -07:00

test_skill_commands_reload.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_skill_commands.py

Merge updated tool metrics into skill metrics

2026-07-31 07:30:30 -07:00

test_skill_invocation_description.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_skill_utils.py

test: run os-specific tests on their real host, not a faked one

2026-08-09 22:09:49 -04:00

test_skills_guidance_content_filter.py

fix(agent): reword SKILLS_GUIDANCE trigger and stop mislabelling its 400 as billing

2026-08-14 21:54:56 -07:00

test_skip_background_review.py

fix: follow-up for salvaged PR #18255

2026-08-08 00:07:14 +05:30

test_skip_memory_store_65429.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_soul_md_profile_isolation.py

fix(agent): scope SOUL.md load to the agent's own profile home (#50233)

2026-08-14 14:15:42 -07:00

test_ssl_ca_guard.py

fix(ssl_guard): tolerate truststore SSLContext.get_ca_certs() NotImplementedError on Windows

2026-08-08 15:10:24 +05:30

test_ssl_verify.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_stale_replay_prune.py

fix(compression): correct prune boundary + exempt native compaction checkpoints

2026-08-08 14:09:41 -07:00

test_stream_chunk_byte_estimate.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_read_timeout_floor.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_single_writer_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_streaming_context_scrubber.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_subagent_lifecycle.py

fix(compression): let explicit interrupts cancel safely

2026-08-02 22:15:20 +05:30

test_subagent_progress.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_subagent_stop_hook.py

feat(delegation): validate batch task quality before spawning children

2026-08-07 08:57:57 -07:00

test_subdirectory_hints_tilde.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_subdirectory_hints.py

fix(context): dedupe subdirectory hints by content digest and skip backup/vendor dirs

2026-08-03 20:43:34 +05:30

test_subprocess_env_guard.py

refactor: single build_subprocess_env() factory for all child-process spawns (profile + secret-scrub single owner)

2026-07-29 10:14:11 -07:00

test_subscription_view.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_tool_result_type_safety.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_summary_prefix_semantics.py

test(agent): cover reference-only handoff sole-active-turn regression

2026-08-07 19:44:35 +05:30

test_summary_prefix_tool_use.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_summary_role_template_alternation.py

fix(compression): choose summary role by template-visible alternation

2026-07-30 21:07:36 +05:30

test_surrogate_chokepoints.py

fix(agent,gateway): class-level lone-surrogate chokepoints (#80366 #55143 #55309 #50959 #19819)

2026-08-08 12:31:19 -07:00

test_synthetic_turn_display_kind.py

fix(agent): type a synthesized user turn when its row is written

2026-07-28 03:54:16 -05:00

test_system_prompt_restore.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_system_prompt.py

fix(agent): scope SOUL.md load to the agent's own profile home (#50233)

2026-08-14 14:15:42 -07:00

test_think_scrubber.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_timeout_guidance.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_thread_scoped_output.py

fix: preserve session history when a turn crashes

2026-08-06 23:08:23 -05:00

test_title_generator.py

refactor(title): decide on the stored title and the real turns behind it

2026-08-09 04:33:58 -05:00

test_tool_call_arg_no_redaction.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_dispatch_helpers.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_executor_checkpoint_paths.py

fix(checkpoints): honor gateway config and task cwd (#68195)

2026-07-20 13:04:12 -07:00

test_tool_guardrails.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_result_classification.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_trace_upload.py

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

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

test_transcription_registry.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_tts_registry.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_turn_context_overflow_warning.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_turn_context.py

feat(hindsight): memory provider improvements — recall_sync, retain_source, setup templates, memory indicators, error hints

2026-08-13 23:15:25 +05:30

test_turn_finalizer_cleanup_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_turn_finalizer_final_response_persistence.py

fix(agent): invalidate flush-scan cursor when finalizer pops db marker

2026-07-31 23:18:12 -07:00

test_turn_finalizer_interrupt_alternation.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_turn_finalizer_iteration_limit_exit.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_turn_overlap_tripwire.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_turn_retry_state.py

feat(compression): native OpenAI Responses server-side compaction for gpt-5.6

2026-08-08 11:24:45 -07:00

test_turn_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_unsupported_parameter_retry.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_unsupported_temperature_retry.py

…

test_usage_pricing.py

test(usage): codex cache_write_tokens + Qwen/Kimi flat cached_tokens coverage (#70543)

2026-08-13 22:09:37 -07:00

test_verification_evidence_fd_leak.py

fix(gateway,tools,agent): close leaked SQLite connections in delivery, delegation, and verification ledgers

2026-07-24 15:55:08 -07:00

test_verification_evidence.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_stop_caching.py

fix(tests): update two more append_message.call_args assertions to append_messages_batch

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

test_verification_stop.py

fix: make verify_on_stop opt-in everywhere (default False, not auto) (#84383)

2026-08-12 01:15:25 -07:00

test_verify_hooks.py

…

test_vertex_adapter.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_video_gen_registry.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_resolved_args.py

…

test_vision_routing_31179.py

fix(tests): restore original module identities after vision-routing reloads (#61597)

2026-07-29 18:55:10 -07:00