Teknium e0592b6d43 fix(codex): masked "invalid_prompt: Request blocked." replay rejection reaches the replay-strip recovery ...

The ChatGPT Codex backend answers a rejected encrypted-reasoning replay with the
same bare 400 {code: invalid_prompt, message: "Request blocked."} it uses for
genuine blocks. classify_api_error bucketed it as format_error, so the one-shot
repair that already exists for invalid_encrypted_content (disable replay, strip
cached codex_reasoning_items, retry once) never ran and the turn aborted.

Classify exactly that envelope from provider openai-codex — SDK 400 body, SSE
``error`` frame, or the ``response.failed`` text — as invalid_encrypted_content
while keeping format_error's abort-and-fallback hints, so the only behavioural
delta is turn_recovery's replay strip, which still requires cached reasoning
items. A block with nothing to strip aborts exactly as before; other providers,
other messages/codes and the #18028 safety refusals are untouched.

evals/codex_masked_replay_review.py drives a real AIAgent (codex_responses)
against a synthetic local Responses server for the before/after check.
Refs #92353, #92357, #94077.

2026-09-06 05:40:02 -07:00

..

lsp

fix(lsp): share one pyright process across git worktrees via workspaceFolders

2026-09-03 02:32:15 -07:00

transports

…

__init__.py

…

test_413_image_payload_recovery.py

refactor(agent): extract 413/context-overflow compression recovery into agent/turn_overflow.py

2026-09-02 13:30:17 -07:00

test_account_usage.py

…

test_acp_openai_bridge.py

fix(copilot-acp): stop substituted models impersonating the requested one

2026-09-02 20:51:07 +05:30

test_acp_provider_rails.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_anthropic_adapter.py

test(anthropic): trim DeepSeek proxy replay tests to two invariants + local wire probe

2026-09-06 05:37:03 -07:00

test_anthropic_billing_guidance.py

…

test_anthropic_borrowed_row_authority.py

…

test_anthropic_credential_persist_failure.py

…

test_anthropic_keychain.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_kimi_signed_thinking_replay.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_kwargs_sanitize.py

…

test_anthropic_mcp_prefix_strip.py

…

test_anthropic_oauth_pkce.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_oauth_stress.py

…

test_anthropic_oauth_ua_prefix.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_output_field_leak.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_request_blank_block_guard.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_request_client_reuse.py

…

test_anthropic_spent_rotation_verdict.py

…

test_anthropic_structured_output.py

…

test_anthropic_thinking_block_order.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_thinking_disable.py

…

test_anthropic_token_scope_isolation.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_anthropic_whitespace_text_blocks.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_api_content_sidecar.py

…

test_arcee_trinity_overrides.py

…

test_async_token_accounting.py

…

test_async_utils.py

…

test_aux_affordable_402_retry.py

…

test_aux_progress_streaming.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_aux_stream_host_deadline_sibling_wires.py

fix(compression): stop the Codex and Anthropic aux summary streams at the host deadline too (#99692)

2026-09-01 23:56:06 -07:00

test_aux_stream_host_deadline.py

fix(compression): stop the summary stream at the host's own deadline

2026-09-01 23:56:06 -07:00

test_auxiliary_anthropic_pool_fallback_regression.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_auxiliary_client_anthropic_custom.py

…

test_auxiliary_client_azure_foundry.py

…

test_auxiliary_client_base_url_host_validation_52608.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_auxiliary_client_bootstrap_skew.py

…

test_auxiliary_client_nous_401_cache_key.py

fix: sibling Nous 401 recovery adopts a peer's refresh instead of rotating again

2026-09-02 21:22:07 -07:00

test_auxiliary_client_proxy_env.py

…

test_auxiliary_client_resolve_dedup.py

…

test_auxiliary_client_ssl_verify.py

fix(test-seams): monkeypatch.setattr facade aliases — also patch the defining module (57 files)

2026-09-03 19:33:28 -07:00

test_auxiliary_client_xai_oauth_recovery.py

…

test_auxiliary_client.py

simplify(compat): models — drop 52 re-exports from hermes_cli.models, repoint 16 callers + 41 test files

2026-09-03 13:48:49 -07:00

test_auxiliary_compression_timeout_floor.py

…

test_auxiliary_concurrency.py

…

test_auxiliary_config_bridge.py

fix(integration): repoint auxiliary bridge source-inspection test to generalized field loop

2026-09-03 02:06:51 -07:00

test_auxiliary_explicit_base_anthropic.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_auxiliary_explicit_cancellation.py

simplify(compat): approval — drop 43 facade re-exports + _command_detection_variants late-bind seam, repoint 30 callers + 46 test files

2026-09-03 13:49:57 -07:00

test_auxiliary_main_first.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_auxiliary_named_custom_providers.py

simplify(compat): interrupt — drop _ThreadAwareEventProxy/_interrupt_event legacy alias, repoint 2 test files

2026-09-03 14:00:59 -07:00

test_auxiliary_openrouter_max_tokens.py

…

test_auxiliary_relay.py

…

test_auxiliary_runtime_cache_key.py

…

test_auxiliary_transient_retry.py

…

test_auxiliary_transport_autodetect.py

…

test_auxiliary_user_default_headers.py

…

test_azure_identity_adapter.py

…

test_backend_identity.py

refactor(agent/adapters): simplify plugin_llm, backend_identity, stream hooks (-447 LOC)

2026-09-02 13:29:47 -07:00

test_background_review_tool_call_guard.py

…

test_background_review_usage.py

refactor(agent/background_review,anthropic_adapter): drop dead is_background_review_enabled (tests repointed to load_background_review_settings), share _new_sdk_client, table call-detail defaults

2026-09-02 19:12:32 -07:00

test_battery.py

…

test_bedrock_1m_context.py

…

test_bedrock_adapter.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_bedrock_empty_text_blocks.py

…

test_bedrock_integration.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_bedrock_interrupt_post_worker.py

…

test_bedrock_transport_replay.py

…

test_billing_links.py

…

test_billing_unverified_carrythrough.py

…

test_billing_usage.py

…

test_billing_view.py

…

test_bot_profile_prompt_isolation.py

…

test_bounded_response.py

refactor(agent/adapters): simplify azure identity, response guards, error surface, retry utils (-603 LOC)

2026-09-02 13:29:47 -07:00

test_budget_reasoning_details_exclusion.py

…

test_builtin_memory_disabled_surface.py

…

test_cache_disabled_on_stubs.py

…

test_canon_args_memo_parity.py

…

test_cascading_interrupt_6600.py

…

test_chat_completion_helpers_provider_sort.py

…

test_cjk_token_estimation.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_close_interrupted_tool_sequence.py

…

test_codex_app_server_event_bridge.py

…

test_codex_app_server_persist.py

…

test_codex_aux_no_progress_timeout.py

…

test_codex_aux_timeout_fd_ownership.py

…

test_codex_cloudflare_headers.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_codex_gpt55_autoraise_notice.py

…

test_codex_happy_eyeballs.py

fix(codex): extend Happy-Eyeballs racing to Codex OAuth/auth clients; pin async native racing

2026-09-01 12:08:11 -07:00

test_codex_request_transport_diagnostics.py

…

test_codex_responses_adapter.py

…

test_codex_responses_settle_pending_tool_calls.py

…

test_codex_runtime_live_events.py

…

test_codex_ttfb_watchdog.py

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

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

test_codex_usage_attribution.py

…

test_coding_context.py

…

test_command_token_source.py

simplify(compat): interrupt — drop _ThreadAwareEventProxy/_interrupt_event legacy alias, repoint 2 test files

2026-09-03 14:00:59 -07:00

test_compaction_anti_thrash.py

…

test_compaction_ops_notification_anchor.py

…

test_compaction_redaction_boundaries.py

…

test_compress_context_progress_timeout.py

…

test_compress_focus.py

…

test_compress_signal_leak.py

…

test_compressed_summary_metadata.py

…

test_compression_adoption_preserves_live_tail.py

…

test_compression_anti_thrash_persistence.py

…

test_compression_anti_thrash_recovery.py

fix(compression): persist the anti-thrash recovery deadline so gateway agent rebuilds cannot block a session forever

2026-09-02 04:14:10 -07:00

test_compression_attempt_lifecycle.py

fix(compression): provider-proven overflow gets one real compaction attempt while the failure cooldown is armed

2026-09-02 05:33:22 -07:00

test_compression_attempt_ownership.py

…

test_compression_attempt_telemetry.py

…

test_compression_busy_steer_anchor.py

fix(compression): anchor on the LAST intent row — newer user turn outranks older steer (#100053 follow-up)

2026-09-02 04:12:12 -07:00

test_compression_concurrent_fork.py

fix(compression): heartbeat honours the quiet-engine contract and the single start line

2026-09-03 11:27:55 +05:30

test_compression_count_warning_36908.py

…

test_compression_fallback_budget.py

…

test_compression_interrupt_protection.py

…

test_compression_logging_session_context.py

…

test_compression_max_attempts_config.py

…

test_compression_orphan_recovery.py

simplify(compat): hermes_state — drop 81 re-exports + 3 registry aliases + 3 shims, repoint 45 callers + 60 test files

2026-09-03 13:46:50 -07:00

test_compression_progress.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_compression_review_76354.py

…

test_compression_rotation_state.py

…

test_compression_small_ctx_threshold_floor.py

…

test_compression_split_failure_cooldown.py

…

test_compression_stall_fallback_78981.py

…

test_compression_stall_interrupt_96775.py

…

test_compression_worker_isolation_76354.py

…

test_compressor_actionable_tail_anchor.py

…

test_compressor_assistant_tail_anchor.py

…

test_compressor_historical_media.py

…

test_compressor_image_tokens.py

…

test_compressor_media_stripping.py

…

test_compressor_stale_tool_images.py

…

test_compressor_tail_cut_oob_fix.py

…

test_compressor_tail_cut_tool_pair_floor.py

…

test_compressor_tool_call_budget.py

…

test_compressor_truncated_summary_guard.py

…

test_compressor_zero_user_guard.py

…

test_context_breakdown.py

…

test_context_compressor_cross_session_guard.py

…

test_context_compressor_reasoning_fallback.py

…

test_context_compressor_session_end_clears_state.py

…

test_context_compressor_structural_backoff.py

…

test_context_compressor_summary_continuity.py

…

test_context_compressor_temporal_anchoring.py

…

test_context_compressor_zero_user_provenance.py

simplify(compat): file_tools/send_message_tool/cronjob_tools/process_registry — drop 34 re-exports, repoint 5 callers + 27 test files

2026-09-03 13:30:27 -07:00

test_context_compressor.py

fix(gateway): hygiene compaction keeps the profile secret scope under multiplexing

2026-09-01 22:28:52 -07:00

test_context_engine_host_contract.py

…

test_context_engine_on_turn_complete_usage.py

…

test_context_engine_select_context.py

…

test_context_engine.py

…

test_context_references.py

refactor(context): fold simplify findings into oversized-file fallback

2026-09-05 16:44:23 +05:30

test_context_refs_concurrent.py

…

test_context_route_mismatch.py

…

test_conversation_loop_interpreter_shutdown.py

…

test_copilot_acp_client.py

fix(copilot-acp): prefer stable session config for model selection

2026-09-02 20:51:07 +05:30

test_copilot_acp_deprecation.py

…

test_credential_pool_anthropic_refresh_race.py

refactor(auth): reuse _CLEAR_STATUS and the merge's None short-circuit in the reset path

2026-09-05 17:43:45 +05:30

test_credential_pool_deferred_refresh.py

…

test_credential_pool_key_rotation.py

…

test_credential_pool_lease_refresh_reselect.py

…

test_credential_pool_no_entries_log_throttle.py

…

test_credential_pool_nous_refresh_stampede.py

fix(test-seams): monkeypatch.setattr facade aliases — also patch the defining module (57 files)

2026-09-03 19:33:28 -07:00

test_credential_pool_oat_authtype.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_credential_pool_oauth_writethrough.py

fix(test-seams): monkeypatch.setattr facade aliases — also patch the defining module (57 files)

2026-09-03 19:33:28 -07:00

test_credential_pool_profile_oauth_fork.py

fix(auth): memoize the shared-store skip and cover the aliased anthropic singleton

2026-09-03 03:31:54 +05:30

test_credential_pool_provider_boundary.py

…

test_credential_pool_quarantine_locking.py

…

test_credential_pool_routing.py

…

test_credential_pool_sole_cooldown.py

…

test_credential_pool_unmatched_rotation_bound.py

…

test_credential_pool.py

fix(auth): make hermes auth reset actually clear a binding cooldown

2026-09-05 17:43:45 +05:30

test_credits_cold_start.py

…

test_credits_fixture_snapshot.py

…

test_credits_policy.py

simplify(compat): models — drop 52 re-exports from hermes_cli.models, repoint 16 callers + 41 test files

2026-09-03 13:48:49 -07:00

test_credits_tracker.py

…

test_credits_view.py

…

test_cron_inflight_prompt_reappend_100818.py

fix(compressor): keep pending tool_calls, avoid double anchors, no header stacking

2026-09-03 11:27:40 +05:30

test_cron_inline_api_call_62151.py

…

test_crossloop_client_cache.py

…

test_curator_activity.py

…

test_curator_backup.py

fix(curator): carry .git file pointers too and document the deleted-skill drop

2026-09-03 01:43:22 +05:30

test_curator_classification.py

…

test_curator_reports.py

…

test_curator.py

simplify(compat): tests — repoint 638 web_server.<name> references (321 attr, 217 monkeypatch/patch.object, 60 from-imports, 40 patch() strings) across 65 test files to the owning modules

2026-09-03 14:21:52 -07:00

test_cursor_optimizations_parity.py

fix(compat-fallout): repoint 8 test files off dropped facade names (run_agent._DB_PERSISTED_MARKER/_EPHEMERAL_SCAFFOLDING_FLAGS/_is_ephemeral_scaffolding, cli.AIAgent, main._make_tui_argv/_print_curator_recent_run_notice/_format_time_ago, model_switch._collect_authed_provider_slugs, acp has_provider shim); arg_coercion test imports model_tools to populate registry

2026-09-03 15:50:55 -07:00

test_custom_pool_mismatch_guard.py

…

test_custom_provider_ca_probes.py

simplify(compat): interrupt — drop _ThreadAwareEventProxy/_interrupt_event legacy alias, repoint 2 test files

2026-09-03 14:00:59 -07:00

test_custom_provider_extra_body_matching.py

…

test_custom_provider_extra_body.py

…

test_custom_providers_vision.py

…

test_deadline.py

refactor(agent/runtime): deadline/file_safety/estop/lifecycle leaf modules — dedupe result plumbing, drop dead guard code

2026-09-02 13:29:48 -07:00

test_declared_conversation_scope.py

…

test_deepseek_anthropic_thinking.py

test(anthropic): trim DeepSeek proxy replay tests to two invariants + local wire probe

2026-09-06 05:37:03 -07:00

test_direct_provider_url_detection.py

…

test_display_emoji.py

…

test_display_todo_progress.py

…

test_display_tool_failure.py

…

test_display.py

…

test_empty_response_guard.py

fix(agent): handle usage-less empty responses

2026-09-03 03:41:52 -07:00

test_empty_tool_name_loop_dampening.py

fix(compat-fallout): module-restore also rebinds pkg.<child> attributes so 'from pkg import child' matches sys.modules after the wipe

2026-09-03 16:20:10 -07:00

test_endpoint_blackhole.py

…

test_engine_preflight_wire.py

…

test_error_classifier.py

fix(codex): masked "invalid_prompt: Request blocked." replay rejection reaches the replay-strip recovery

2026-09-06 05:40:02 -07:00

test_error_surface.py

…

test_estimator_parity_84371.py

…

test_external_skills_dirs_cache.py

…

test_external_skills.py

…

test_failover_identity.py

…

test_fast_compression_lane.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_fast_mode_auto.py

feat(fast): bounded /fast auto|cold windows behind one route-aware gate

2026-09-02 05:33:13 -07:00

test_file_safety_container_mirror.py

refactor(tools): wire file_operations to extracted common/lint/search modules; restore literal security pins in lazy_deps

2026-09-02 14:43:45 -07:00

test_file_safety_credentials.py

simplify(compat): doctor/status — drop 13 re-exports + the doctor_* globals() facade (97 names), repoint 6 callers / 13 tests

2026-09-03 13:10:52 -07:00

test_file_safety_cross_profile.py

refactor(agent/image+safety): route vision probes/inline executors on data tables, dedupe path guards (-25% LOC)

2026-09-02 18:58:42 -07:00

test_file_safety_sandbox_mirror.py

refactor(agent/runtime): deadline/file_safety/estop/lifecycle leaf modules — dedupe result plumbing, drop dead guard code

2026-09-02 13:29:48 -07:00

test_file_safety_session_state.py

…

test_file_safety.py

…

test_gateway_turn_sidecar.py

…

test_gemini_fast_fallback.py

…

test_gemini_free_tier_gate.py

…

test_gemini_native_adapter.py

…

test_gemini_schema.py

…

test_gemini_standard_key_guidance.py

…

test_ghost_skill_pruning.py

…

test_hygiene_timeout_cooldown_isolation.py

…

test_i18n.py

…

test_idle_compaction_lock_and_guards.py

fix(compaction): stop idle compaction re-summarising a transcript that has not grown

2026-09-03 03:07:33 +05:30

test_idle_compaction.py

fix(compaction): stop idle compaction re-summarising a transcript that has not grown

2026-09-03 03:07:33 +05:30

test_image_gen_registry.py

…

test_image_routing.py

…

test_insights.py

…

test_intent_ack_continuation.py

refactor(agent): agent_runtime_helpers — drop dead predicates, dedupe runtime restore/switch/recovery, compact narratives

2026-09-02 13:29:31 -07:00

test_interrupt_compat.py

…

test_jiter_preload.py

…

test_kanban_stop.py

…

test_kimi_coding_anthropic_thinking.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_last_total_tokens.py

…

test_lean_single_aux_call.py

…

test_learn_prompt.py

…

test_learning_graph_render.py

…

test_learning_graph.py

…

test_learning_mutations.py

…

test_litellm_tool_part_cache_markers.py

…

test_lmstudio_reasoning.py

…

test_load_time_durability_stamp_92231.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_local_probe_disk_cache.py

…

test_local_stream_timeout.py

…

test_lock_fallback_base_semantics.py

review-fix(locks): keep the lock-free cache read only for manual codex /compress (BASE exception)

2026-09-03 12:42:38 -07:00

test_manual_compression_feedback.py

…

test_manual_compression_refusal_feedback.py

…

test_markdown_tables.py

…

test_memory_async_sync.py

…

test_memory_boundary_commit.py

…

test_memory_provider_unavailable_warning.py

…

test_memory_provider.py

…

test_memory_recall_indicator.py

…

test_memory_session_switch.py

…

test_memory_skill_scaffolding.py

…

test_memory_user_id.py

…

test_memory_write_bridge.py

…

test_message_content.py

…

test_message_metadata.py

…

test_message_sanitization_policy.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_meta_agent_init.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_meta_usage_cache_reporting.py

…

test_micro_compaction.py

refactor(turn): split finalize_turn into phase helpers (576 -> 264 LOC)

2026-09-02 16:46:33 -07:00

test_minimax_auxiliary_url.py

…

test_minimax_provider.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_moa_aggregator_cache_control.py

…

test_moa_aggregator_cost_slot.py

…

test_moa_cold_start_cache_66793.py

…

test_moa_context_max_tokens.py

…

test_moa_observability_bridge.py

…

test_moa_prepared_request_client_swap.py

…

test_moa_progress.py

…

test_moa_quiet_reference_output.py

fix(compat): pointers resolve to the object that MOVED, not a same-named stranger; stdin checker binds stdin= to the splatted definition

2026-09-03 22:00:01 -07:00

test_moa_reasoning_effort.py

…

test_moa_reference_system_prompt.py

…

test_moa_slot_api_mode.py

…

test_moa_slot_max_tokens.py

…

test_moa_switch_api_mode.py

…

test_moa_trace_streamed_capture.py

…

test_model_extra_type_guard.py

…

test_model_metadata_local_ctx.py

…

test_model_metadata_ssl.py

…

test_model_metadata.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_models_dev_meta_mapping.py

fix(models_dev): alias opencode-free to the Zen "opencode" catalog; pin Muse Spark 1M invariant

2026-09-03 00:58:16 -07:00

test_models_dev.py

…

test_moonshot_schema.py

…

test_native_preflight_estimate.py

simplify(compat): conversation_loop — drop 9 re-exports, repoint 7 callers, 35 test sites

2026-09-03 13:12:23 -07:00

test_non_stream_stale_timeout.py

…

test_none_deref_guards.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_nous_credits_gauge.py

…

test_nous_credits_snapshot.py

…

test_nous_oauth_401_guidance.py

refactor(agent/turn_recovery): _vlines/_plines print helpers, lift unicode/401-diagnostic/auth-guidance phases, dedupe failed-turn dicts, flatten validate_response_shape

2026-09-02 18:29:20 -07:00

test_nous_portal_anthropic_wire.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_nous_rate_guard.py

…

test_onboarding.py

…

test_oneshot.py

…

test_opencode_free_provider.py

refactor(cli/setup.py): drop dead _DEFAULT_PROVIDER_MODELS table and _setup_qqbot shim; compact prose, imports and banners

2026-09-02 15:53:44 -07:00

test_opencode_session_affinity.py

feat(opencode): send x-opencode-session on every OpenCode request for backend affinity

2026-09-02 21:46:36 -07:00

test_openrouter_response_cache.py

…

test_openrouter_silent_default_purge.py

…

test_org_skill_namespace.py

simplify(compat): tool_search/skills_sync_client — drop 22 re-exports, repoint 5 callers + 5 test files; drop stale re-export prose in web_tools_truncate/file_operations_lint

2026-09-03 13:33:47 -07:00

test_outbound_stale_vision.py

fix(agent): evict stale screenshot payloads before send

2026-09-03 04:51:51 +05:30

test_outbound_webhooks.py

feat(webhooks): stamp the emitting profile on outbound webhook payloads

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

test_per_model_provider_routing.py

feat(openrouter): per-model provider_routing.models.<id> overrides

2026-09-06 02:18:14 -07:00

test_periodic_scheduler.py

perf(agents): run per-child timers on one shared scheduler thread

2026-09-03 02:44:24 -07:00

test_pet_engine.py

…

test_pet_generate.py

refactor(agent/runtime): pet — shared flood/placement helpers in atlas, provider resolution loop, dead helpers removed

2026-09-02 13:29:47 -07:00

test_phantom_tool_references.py

simplify(compat): skills_sync/skill_manager/kanban/computer_use — drop 37 re-exports/aliases, repoint 8 callers + 9 test files

2026-09-03 13:27:01 -07:00

test_plan_prompt.py

simplify(compat): hermes_cli/commands — drop the last PEP 562 lazy re-export hook (25 names), repoint 10 callers + 11 test files to commands_platforms/commands_completion

2026-09-03 17:00:26 -07:00

test_platform_hint_desktop.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_platform_hint_overrides.py

…

test_plugin_context_references.py

…

test_plugin_llm_task_routing.py

simplify(compat): hermes_cli.main — drop 198 re-exports/aliases (155 eager + 45 lazy PEP 562 + _warn_stale_dashboard_processes alias + _time/_self/_LAZY_* machinery), repoint 17 source callers + 91 test files

2026-09-03 15:07:39 -07:00

test_plugin_llm.py

…

test_plugin_prompt_sections.py

…

test_portal_tags.py

…

test_post_compression_trim.py

…

test_pre_compress_checkpoint_contract.py

refactor(agent/agent_init): repoint micro-compaction source pin to table entry

2026-09-02 20:37:46 -07:00

test_pre_compress_memory_context.py

…

test_preflight_compression_gate.py

…

test_preflight_compression_timeout_fail_closed.py

…

test_preflight_lock_defer.py

…

test_proactive_prune_config.py

…

test_proactive_prune_rearm_threshold.py

test(compression): pin rearm-reset wiring through a public boundary

2026-09-03 12:26:22 +05:30

test_proactive_prune_restart_safety.py

…

test_proactive_tool_result_pruning.py

fix(compression): do not let prune rearm lock out over-threshold sessions

2026-09-03 12:23:55 +05:30

test_probe_cache_followups.py

…

test_profile_home_override_precedence.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_project_skills.py

refactor(agent/prompt): remove dead code, unify duplicated helpers, compact docstrings across prompt/skill/redaction modules

2026-09-02 13:53:57 -07:00

test_prompt_builder.py

refactor(ssh): drop probe-only bookkeeping the probe never reads

2026-09-06 13:32:51 +05:30

test_prompt_cache_boundary.py

refactor(agent/prompt): remove dead code, unify duplicated helpers, compact docstrings across prompt/skill/redaction modules

2026-09-02 13:53:57 -07:00

test_prompt_cache_scope.py

…

test_prompt_cache_ttl_propagation.py

refactor(turn): lift iteration entry/announce, Nous rate guard, API interrupt, retry-restart consumer and preflight-timeout result out of run_conversation

2026-09-02 16:37:14 -07:00

test_prompt_caching.py

refactor(turn): extract per-iteration request assembly (api_messages/MoA/cache plan/pressure) into agent/turn_request_assembly.py

2026-09-02 16:10:07 -07:00

test_protected_tail_pressure_61932.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_provider_client_seam.py

test/docs: trim seam tests to invariants, document create_client and external-process fields

2026-09-02 09:57:39 -07:00

test_provider_projection.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_proxy_and_url_validation.py

…

test_pydantic_dump_warning_leak.py

simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites)

2026-09-03 13:16:47 -07:00

test_rate_limit_tracker.py

…

test_reactions.py

…

test_reasoning_effort_module.py

refactor(agent/models): compact pricing snapshot, billing/subscription views, reasoning helpers

2026-09-02 13:52:51 -07:00

test_reasoning_effort_wire_translation.py

…

test_reasoning_stale_timeout_floor.py

…

test_reasoning_summaries.py

…

test_redact.py

test(redact): corpus-level before/after coverage for value-aware gating (#96607)

2026-09-01 12:07:16 -07:00

test_reference_handoff_active_turn.py

…

test_refine_focus.py

…

test_refine_snapshot_isolation.py

refactor(agent): clone the review snapshot once at the spawn chokepoint

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

test_relay_llm.py

…

test_relay_nested_execution.py

…

test_relay_runtime_bounded_scope_ops.py

…

test_relay_runtime_plugins.py

…

test_relay_scope_pop_metadata.py

…

test_relay_session_segments.py

…

test_relay_tools.py

…

test_repetition_guard.py

…

test_replay_budget_accounting.py

…

test_replay_cleanup.py

…

test_request_client_reuse.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_restore_primary_pool_reselect.py

…

test_resume_stale_active_task.py

…

test_review_engine.py

simplify(compat): tests — repoint 638 web_server.<name> references (321 attr, 217 monkeypatch/patch.object, 60 from-imports, 40 patch() strings) across 65 test files to the owning modules

2026-09-03 14:21:52 -07:00

test_review_idle_queue.py

feat: local models — managed llama.cpp runtime with one-click desktop setup

2026-09-01 16:01:53 -04:00

test_rotation_flush_persisted_boundary_68196.py

…

test_run_budget.py

…

test_runtime_cwd.py

…

test_salvage_grown_transcript.py

…

test_save_url_image.py

refactor(agent/image+safety): route vision probes/inline executors on data tables, dedupe path guards (-25% LOC)

2026-09-02 18:58:42 -07:00

test_secret_scope_tier1_migration.py

…

test_secret_scope.py

fix(tools): propagate caller contextvars in DaemonThreadPoolExecutor.submit

2026-09-01 22:28:52 -07:00

test_send_path_history_isolation.py

refactor(turn): extract preflight gate + per-iteration transcript prep into agent/turn_preflight_gate.py, agent/turn_iteration_prep.py

2026-09-02 16:27:44 -07:00

test_sequential_tool_interrupt.py

…

test_session_activity.py

refactor(gateway): iteration-progress formatter lives in agent/session_activity, tests trimmed to the invariant bar

2026-09-06 05:35:12 -07:00

test_session_rotation_flush_cold_resume_68454.py

…

test_set_runtime_main_custom_provider.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_shared_http_transport.py

perf(agents): share one httpx transport pool across every agent's client

2026-09-03 02:35:21 -07:00

test_shell_hooks_consent.py

…

test_shell_hooks_tree_kill.py

…

test_shell_hooks.py

…

test_side_question.py

…

test_skill_bundles.py

…

test_skill_commands_reload.py

…

test_skill_commands.py

fix(webhook): load URL-resolved profile's skills under multiplex

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

test_skill_invocation_description.py

…

test_skill_session_platform_gate.py

…

test_skill_todo_retention_parity.py

…

test_skill_utils.py

…

test_skills_guidance_content_filter.py

test(agent): assert SKILLS_GUIDANCE wiring behaviorally instead of via source grep

2026-09-02 19:41:47 -07:00

test_skip_background_review.py

…

test_skip_memory_store_65429.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_soul_md_profile_isolation.py

…

test_ssl_ca_guard.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_ssl_verify.py

…

test_stale_replay_prune.py

…

test_stall_guards.py

refactor(agent/runtime): hooks/guardrails/dispatch — unify shell-hook and webhook plumbing, table-driven guardrail thresholds

2026-09-02 13:29:48 -07:00

test_stream_chunk_byte_estimate.py

…

test_stream_read_timeout_floor.py

…

test_stream_single_writer_guard.py

…

test_streaming_context_scrubber.py

…

test_structured_output_rejection_retry.py

…

test_studio_bridge_affinity.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_subagent_lifecycle.py

…

test_subagent_progress.py

feat(delegate): tag every subagent progress line with its batch id

2026-09-02 01:06:24 -07:00

test_subagent_stop_hook.py

…

test_subdirectory_hints_tilde.py

…

test_subdirectory_hints.py

fix(context): subdirectory AGENTS.md hints keep head+tail and warn when over the ceiling; ceiling 8k -> 32k

2026-09-04 02:03:08 -07:00

test_subprocess_env_guard.py

fix(integration): bang_shell builds its env via build_subprocess_env()

2026-09-03 02:07:33 -07:00

test_subscription_view.py

…

test_summarize_tool_result_type_safety.py

…

test_summary_prefix_semantics.py

…

test_summary_prefix_tool_use.py

…

test_summary_role_template_alternation.py

…

test_surrogate_chokepoints.py

refactor(agent/conversation_loop): lift the API retry loop into _run_api_retry_loop; drop blank lines after lazy imports

2026-09-02 19:11:11 -07:00

test_switch_model_request_overrides.py

…

test_synthetic_turn_display_kind.py

…

test_system_prompt_restore.py

…

test_system_prompt.py

simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files

2026-09-03 13:28:22 -07:00

test_terminal_env_registry.py

…

test_think_scrubber.py

…

test_thinking_timeout_guidance.py

…

test_thread_scoped_output.py

…

test_title_generator.py

refactor(agent/review): simplify curator, background_review, verify, insights, title and learning modules (-22% LOC)

2026-09-02 13:30:25 -07:00

test_tool_call_arg_no_redaction.py

…

test_tool_dispatch_helpers.py

…

test_tool_executor_checkpoint_paths.py

…

test_tool_guardrails.py

fix(guardrails): hard stops catch replays, never legitimate iteration

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

test_tool_result_classification.py

…

test_trace_upload.py

…

test_transcription_registry.py

…

test_treekill_consolidation.py

simplify(compat): tools/browser_tool tests — repoint 56 test files from tools.browser_tool.<name> to the defining browser_tool_* sibling (patch where the name is looked up)

2026-09-03 14:18:25 -07:00

test_tts_registry.py

…

test_turn_base_display_anchor.py

refactor(agent/agent_init): repoint turn-base-anchor source pin to _USAGE_STATE table

2026-09-02 19:46:07 -07:00

test_turn_context_compaction.py

refactor(turn): collapse preflight estimator branch, build_api_messages pops, docstrings; add turn_context_compaction tests

2026-09-02 16:42:25 -07:00

test_turn_context_overflow_warning.py

…

test_turn_context.py

fix(compat-fallout): repoint 4 test files to defining modules (update_cmd._detect_venv_python_processes, main_install_repair subprocess/_resolve_install_target_python, process_bootstrap.OpenAI, tools.mcp_tool gate import)

2026-09-03 15:54:46 -07:00

test_turn_facade_lease.py

Merge origin/main (561b053f79) into simp/forwardport: forward-port 220 main commits into the simplified tree

2026-09-03 03:31:03 -07:00

test_turn_finalizer_cleanup_guard.py

…

test_turn_finalizer_final_response_persistence.py

review-fix(conversation-loop): finalize_turn binds stream-recovered final_response before fallible persist sub-steps (BASE order)

2026-09-03 09:54:04 -07:00

test_turn_finalizer_interrupt_alternation.py

…

test_turn_finalizer_iteration_limit_exit.py

simplify(compat): kanban_db — drop 73 re-exports/aliases, repoint 794 callers

2026-09-03 13:48:14 -07:00

test_turn_liveness.py

…

test_turn_overlap_tripwire.py

…

test_turn_retry_state.py

fix(reasoning): GLM-5.3 on Nous/OpenRouter no longer 400s when thinking is disabled

2026-09-03 05:20:11 -07:00

test_turn_summary.py

…

test_uncompressed_context_guardrail.py

…

test_unsupported_parameter_retry.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_unsupported_temperature_retry.py

simplify(compat): tools/mcp_tool — repoint 20 non-test callers to the defining mcp_tool_* siblings

2026-09-03 13:29:35 -07:00

test_usage_anchor.py

…

test_usage_pricing.py

perf(usage): prefer bundled pricing before metadata fetch

2026-09-03 04:00:51 +05:30

test_verification_evidence_fd_leak.py

…

test_verification_evidence.py

…

test_verification_stop_caching.py

fix(compat-fallout): module-restore also rebinds pkg.<child> attributes so 'from pkg import child' matches sys.modules after the wipe

2026-09-03 16:20:10 -07:00

test_verification_stop.py

…

test_verify_hooks.py

…

test_vertex_adapter.py

…

test_video_gen_registry.py

…

test_vision_resolved_args.py

…

test_vision_routing_31179.py

simplify(compat): tools/browser_tool tests — repoint 56 test files from tools.browser_tool.<name> to the defining browser_tool_* sibling (patch where the name is looked up)

2026-09-03 14:18:25 -07:00

test_would_grow_refusal_runway.py

…