teknium1 a6ad3cc3ff fix(review): derive the default input budget from the fork's resolved context window ...

The salvaged commit (#114651) re-probed the endpoint through get_model_context_length
at spawn time. The review fork is a full AIAgent whose context_compressor.context_length
is already resolved by the same chain (config override, catalog, persisted provider limit,
endpoint probe), so read that instead: no second lookup, and the budget tracks exactly
the window the fork's own compaction uses. Tests trimmed to two invariants on the new seam.

Docs: `auxiliary.background_review.max_input_tokens` and its derived default in
website/docs/user-guide/features/memory.md, including the note that a top-level
`background_review:` block is not read (#114645 secondary).

Co-authored-by: Artie Fisher <artiefisher123@gmail.com>

2026-09-18 19:18:57 -07:00

..

lsp

test(lsp): reproduce multi-root attach under state lock

2026-09-16 16:50:07 -07:00

transports

test(agent): pass issuer_model through the Perplexity alias normalize stub

2026-09-18 09:54:13 -07:00

__init__.py

…

conftest.py

fix(aux): structured-output rejection no longer kills fallback candidates or costs a doomed first request

2026-09-17 09:11:38 -07:00

repro_image_shrink_brick.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_402_not_retried.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_413_compression.py

fix(compression): announce the compacting status before the lazy feasibility probe

2026-09-15 05:19:57 -07:00

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_860_dedup.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_account_usage_fetch.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_account_usage.py

fix: refresh the credential that 401'd on the Codex /usage retry

2026-09-15 04:53:38 -07:00

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_actual_auxiliary_routing.py

fix(providers): block Actual at Responses send sites (E-1047)

2026-09-10 15:13:02 -04:00

test_agent_guardrails.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_anthropic_adapter.py

fix(anthropic): a possessive 'hermes-agent's' is prose and is still rewritten

2026-09-19 01:44:10 +05:30

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_borrowed_row_authority.py

fix(auth): keep the borrowed claude_code row out of token authority and carry the spent-rotation verdict through resolution

2026-08-29 18:34:35 -07:00

test_anthropic_client_auth.py

test(anthropic): one wire_headers probe; the bearer mirror lives only in the portal wire test

2026-09-11 13:06:16 +05:30

test_anthropic_credential_persist_failure.py

fix(auth): keep the borrowed claude_code row out of token authority and carry the spent-rotation verdict through resolution

2026-08-29 18:34:35 -07:00

test_anthropic_dead_grant_hints.py

fix(auth): Claude Code dead refresh token is reported once; CLAUDE_CONFIG_DIR honoured; no 'claude setup-token' hints

2026-09-17 09:02:26 -07:00

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

fix(anthropic): alias session_search/memory OAuth billing-classifier triggers

2026-09-01 16:27:20 +05:30

test_anthropic_mid_tool_call_drop.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_anthropic_model_cooldowns.py

fix(anthropic): model-scoped 429 cooldowns live in a pool sibling; restore path no longer NameErrors

2026-09-16 17:16:06 -07:00

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

fix(auth): named profiles no longer inherit the root profile's auth.json (#111724)

2026-09-16 14:34:59 -07:00

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_owned_routing.py

test: exercise owned OAuth recovery through the unchanged ladder surface

2026-09-07 08:07:26 -07:00

test_anthropic_prompt_cache_policy.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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

perf(run-agent): reuse the Anthropic request-local client instead of rebuilding it per call

2026-08-15 00:34:29 -07:00

test_anthropic_response_header_capture.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_anthropic_spent_rotation_verdict.py

fix: prefer owned Anthropic grants and bind auxiliary refresh to request credentials

2026-09-07 08:07:26 -07:00

test_anthropic_stream_pool_cleanup.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_anthropic_structured_output.py

fix(aux): translate top-level response_format kwarg on the Anthropic adapter

2026-08-18 20:34:46 -04:00

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

fix(anthropic): send an explicit thinking disable on the native Messages wire

2026-08-20 12:29:11 -05:00

test_anthropic_third_party_oauth_guard.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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_truncation_continuation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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_row_addressed_backfill.py

simplify(agent): sidecar backfill — drop the hasattr guard and the duplicated row-id predicate; tests 7→6

2026-09-09 10:32:01 +05:30

test_api_content_sidecar.py

fix(agent): preserve tool cache in iteration summary

2026-09-14 20:35:28 +05:30

test_api_max_retries_config.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_arcee_trinity_overrides.py

fix(compression): -900k Codex variants keep the global 50% threshold; 85% autoraise stays on 272K base slugs

2026-08-23 02:54:30 -07:00

test_astra_baseline_runtime.py

perf(models): stop revalidating a fresh provider cache just because it lists Astra

2026-09-07 21:43:54 +05:30

test_async_httpx_del_neuter.py

fix: digest only the peeked entry's key in the aux client cache hint

2026-09-17 08:51:58 -07:00

test_async_token_accounting.py

test(agent): update enqueue-after-close contract to the #94736 self-heal

2026-08-31 10:51:19 -07:00

test_async_utils.py

…

test_auth_provider_failover.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_authorization_gate.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_aux_affordable_402_retry.py

fix(auxiliary): credit-limited 402s clamp to the affordable budget instead of failing

2026-08-31 13:00:24 -07:00

test_aux_progress_streaming.py

fix(agent): defer codex idle watchdog until progress

2026-09-07 00:41:09 +05:30

test_aux_relay_progress_seam.py

fix(auxiliary): origin-scoped key shield, task overrides over named providers, negotiation-only stream fallback

2026-09-09 16:21:36 -07:00

test_aux_session_endpoint_affinity.py

fix(auxiliary): origin-scoped key shield, task overrides over named providers, negotiation-only stream fallback

2026-09-09 16:21:36 -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_auth_rung_fallthrough.py

fix(aux): explicit-provider auth fallback stays on the task chain through the quarantine re-walk

2026-09-18 10:13:32 -07:00

test_auxiliary_auto_never_guesses_provider.py

fix: bound auto-title timeouts to one window and name them in the log

2026-09-17 08:50:52 -07:00

test_auxiliary_auto_route_xai_oauth_refresh.py

fix: keep API-key xai auto routes off the xai-oauth refresh row

2026-09-17 08:50:15 -07:00

test_auxiliary_client_anthropic_custom.py

…

test_auxiliary_client_azure_foundry.py

fix(anthropic): bearer-only clients omit x-api-key the same copy-safe way

2026-09-11 13:06:16 +05:30

test_auxiliary_client_base_url_host_validation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_auxiliary_client_bootstrap_skew.py

…

test_auxiliary_client_cache_eviction.py

fix(agent): scope auxiliary client eviction to the calling profile and stop closing in-flight clients

2026-09-16 16:51:06 -07:00

test_auxiliary_client_cache_follows_credential.py

test(agent): assert pool purity instead of echoing the ambient credential dict

2026-09-18 09:46:03 -07:00

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

fix(aux): caller thinking-off drops the task effort before the profile merge, never the profile's own disable

2026-09-18 10:14:06 -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_error_classification.py

fix: log the provider in the vision-gate skip and prove capacity 429s do not rotate the pool

2026-09-17 08:53:54 -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

fix(auxiliary): async progress-hook wrapper + route the async primary through it (#98466)

2026-09-09 14:06:12 -07:00

test_auxiliary_fallback_multihop.py

fix(aux): quarantine a transient fallback-candidate failure for seconds, not the payment hold

2026-09-17 09:07:51 -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

fix(aux): named custom anthropic_messages entries send their extra_headers too

2026-09-17 08:53:15 -07:00

test_auxiliary_ollama_local_provider.py

fix(aux): local-server aliases never borrow OPENAI_API_KEY for the lane's base_url

2026-09-17 08:56:27 -07:00

test_auxiliary_openrouter_max_tokens.py

fix(auxiliary): credit-limited 402s clamp to the affordable budget instead of failing

2026-08-31 13:00:24 -07:00

test_auxiliary_parameter_rung_chaining.py

fix(agent): recognise reversed "reasoning_effort 'none' unsupported" on every surface (#114460)

2026-09-18 10:21:05 -07:00

test_auxiliary_provider_supplied_client.py

test(agent): fold the aux create_client() seam tests to two contracts

2026-09-16 11:57:56 +05:30

test_auxiliary_reasoning_field_rejection_retry.py

fix(aux): only treat a standalone reasoning field name as a reasoning rejection; let parameter rungs chain

2026-09-16 17:01:52 -07:00

test_auxiliary_relay.py

…

test_auxiliary_runtime_cache_key.py

fix(auth): key sibling per-process credential memos by profile home under multiplex

2026-09-10 18:11:25 -07:00

test_auxiliary_structured_output.py

fix(aux): scope the response_format rejection memo to the model and to capability errors

2026-09-17 09:11:38 -07:00

test_auxiliary_title_timeout_bound.py

fix: bound auto-title timeouts to one window and name them in the log

2026-09-17 08:50:52 -07:00

test_auxiliary_transient_retry.py

…

test_auxiliary_transport_autodetect.py

…

test_auxiliary_unavailable_nous_reason.py

fix: only WARN about an unavailable Nous auxiliary client when a Nous credential actually failed

2026-09-17 08:49:38 -07:00

test_auxiliary_user_default_headers.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_auxiliary_wire_messages.py

test: preserve reusable localhost provider wire A/B probe

2026-09-07 06:02:22 -07:00

test_azure_identity_adapter.py

…

test_backend_identity.py

fix(agent): preserve route URL path identity

2026-09-07 07:06:58 -07:00

test_background_review_cache_parity.py

fix(agent): same-model review fork keeps the parent's affinity header and Portal conversation root (#109964)

2026-09-14 06:55:54 -07:00

test_background_review_cost_controls.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_background_review_input_budget.py

fix(review): derive the default input budget from the fork's resolved context window

2026-09-18 19:18:57 -07:00

test_background_review_list_shapes.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_background_review_memory_scope.py

fix(review): keep /refine under the background_review origin; attendedness is its own flag

2026-09-09 12:19:13 +05:30

test_background_review_routed_effort.py

fix(agent): routed background reviews honor auxiliary.background_review.reasoning_effort

2026-09-14 05:25:01 -07:00

test_background_review_summary.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_background_review_tool_call_guard.py

fix(background-review): skip the fork when the provider can't emit tool calls

2026-08-26 10:10:11 -07:00

test_background_review_toolset_restriction.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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_background_review.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_battery.py

…

test_bedrock_1m_context.py

…

test_bedrock_adapter.py

fix(bedrock): resolve application-inference-profile ARNs before the prompt-cache allowlist match

2026-09-18 15:15:02 -07:00

test_bedrock_context_cache.py

fix(bedrock): restore Grok context with provider-confirmed cache provenance

2026-09-17 18:36:10 -07:00

test_bedrock_empty_text_blocks.py

…

test_bedrock_guardrail_claude_route.py

fix: Bedrock Guardrails enforced on the Claude route and blocks surface as refusals

2026-09-11 01:37:22 -07:00

test_bedrock_integration.py

The free tier is created in one place, at boot, only behind HERMES_GUEST_ONBOARDING=1 (NS-847) (#107697)

2026-09-11 03:45:33 +05:30

test_bedrock_interrupt_post_worker.py

fix(agent): cover provider wait teardown paths

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

test_bedrock_transport_replay.py

fix(agent): preserve Bedrock redacted reasoning replay

2026-09-01 08:30:26 -07:00

test_billing_links.py

…

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_billing_view.py

…

test_bitwarden_secrets.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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

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

fix(compression): opaque encrypted_content costs 0 in every local token estimate

2026-09-06 13:21:17 -07:00

test_builtin_memory_disabled_surface.py

fix(memory): bound invalid-target error and restore recovery hint

2026-08-20 20:20:23 -07:00

test_cache_disabled_on_stubs.py

…

test_callable_api_key.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_canon_args_memo_parity.py

…

test_capability_probe_credentials.py

fix: failed probe credentials cannot fall through to configured auth

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

test_cascading_interrupt.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_chat_completion_helpers_provider_sort.py

…

test_chat_sdk_transform_bypass.py

test: pin the non-SDK facade gate alongside the escape hatch

2026-09-15 19:23:53 -07:00

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

fix: restore complete message timestamp coverage

2026-08-15 01:04:19 -07:00

test_codex_app_server_compaction.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_codex_app_server_event_bridge.py

…

test_codex_app_server_integration.py

fix(tui): tolerate agents without session_cwd in _register_session_cwd; adapt stubs to the cwd kwarg

2026-09-15 22:30:11 -07:00

test_codex_app_server_lifecycle.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_codex_app_server_persist.py

fix: satisfy the no-locked-pure-readers gate and close the DB before rmtree

2026-08-31 14:02:55 -07:00

test_codex_aux_no_progress_timeout.py

test(auxiliary): watchdog timeout asserts owner-thread FD release

2026-08-31 13:00:18 -07:00

test_codex_aux_timeout_fd_ownership.py

test(agent): make aux timeout FD test deterministic

2026-09-15 18:48:35 -07:00

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_echo_ownership.py

fix(codex): keep transport echoes out of durable user history

2026-09-07 08:09:57 -07:00

test_codex_gpt55_autoraise_notice.py

…

test_codex_happy_eyeballs.py

fix(bootstrap): race IPv6/IPv4 for every sync connect from the process bootstrap, not per client

2026-09-18 09:56:28 -07:00

test_codex_incomplete_budget_escalation.py

fix: seed Responses budget escalation from the observed ceiling when no cap is configured

2026-09-16 14:23:55 -07:00

test_codex_multimodal_tool_result.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_codex_no_tools_nonetype.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_codex_request_transport_diagnostics.py

…

test_codex_responses_adapter.py

fix(codex): uniquify replayed call_ids that recur across turns

2026-09-15 04:49:47 -07:00

test_codex_responses_settle_pending_tool_calls.py

fix: reuse first-observed sequence when announced items land via output_item.done

2026-08-23 19:02:30 -07:00

test_codex_runtime_live_events.py

…

test_codex_sdk_transform_bypass.py

refactor(agent): import the transform bypass from its defining module, no re-export shim

2026-09-15 19:23:53 -07:00

test_codex_silent_hang_hint.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_codex_ttfb_watchdog.py

test(agent): codex TTFB fixture starts from a clean HERMES_CODEX_TTFB_* env

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

test_codex_usage_attribution.py

fix(codex): identify Hermes requests

2026-08-24 11:25:04 -07:00

test_codex_watchdog_reasoning_effort.py

fix(codex): floor every effort >= high and keep the run-budget cap over it

2026-09-16 17:45:01 -07:00

test_codex_xai_oauth_recovery.py

fix(anthropic): model-scoped 429 cooldowns live in a pool sibling; restore path no longer NameErrors

2026-09-16 17:16:06 -07:00

test_coding_context.py

…

test_command_secret_source.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_command_token_source.py

refactor(aux): _normalize_api_key is the one callable-or-string key normaliser

2026-09-17 23:59:41 +05:30

test_commit_memory_session_context_engine.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compaction_anti_thrash.py

test(compression): align no-op strike tests with structural backoff (#93022)

2026-08-23 18:27:07 -07:00

test_compaction_ops_notification_anchor.py

fix(compaction): exclude operational notifications from tail anchor and auto-focus (#92703)

2026-08-26 21:38:20 -07:00

test_compaction_prompt_rebuild.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compaction_redaction_boundaries.py

…

test_compress_context_fallback_shim.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compress_context_progress_timeout.py

fix(compression): a timed-out preflight compaction sends a fitting request and prune-commits an over-window one

2026-09-18 10:36:11 -07:00

test_compress_focus_plugin_fallback.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compress_focus.py

…

test_compress_signal_leak.py

…

test_compressed_summary_metadata.py

…

test_compression_abort_state_reset.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_adoption_preserves_live_tail.py

…

test_compression_anti_thrash_persistence.py

fix(compression): structural no-ops defer retries instead of striking the breaker

2026-08-23 18:27:07 -07:00

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): stall cooldown covers one idle window; drifted-prompt INFO once per session

2026-09-16 17:12:33 -07:00

test_compression_attempt_ownership.py

fix(compression): lean compaction makes exactly one auxiliary request per attempt

2026-08-30 09:03:57 -07:00

test_compression_attempt_telemetry.py

perf(compression): add guarded fast summary lane

2026-08-28 12:38:49 +05:30

test_compression_boundary_hook.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_boundary.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_budget_rearm.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_budget_refund.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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_child_source.py

fix(sessions): one-shot runs get a distinct oneshot source that pickers hide

2026-09-17 09:06:59 -07:00

test_compression_closed_adoption.py

fix(ux): plain-language, actionable user-facing messages (core)

2026-09-15 04:12:13 -07:00

test_compression_concurrent_fork.py

test(compression): cover cooldown rollback on a concurrently deleted session (#106271)

2026-09-09 09:21:39 -07:00

test_compression_count_warning.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_fallback_budget.py

…

test_compression_feasibility.py

fix(compression): probe aux feasibility before the first compaction; clear stale clamp notice on un-clamp

2026-09-18 09:49:14 -07:00

test_compression_interrupt_protection.py

…

test_compression_lock_defer.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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_persistence.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_rotation_state.py

fix(compression): rotation heals stale automatic ended_at stamps instead of wedging (#88197)

2026-08-31 09:58:11 -07:00

test_compression_small_ctx_threshold_floor.py

test(compression): sibling asserts the grounded task heading, not the legacy alias

2026-09-18 19:18:23 -07:00

test_compression_split_failure_cooldown.py

refactor(compression): name the split-failure cooldown; drop duplicate tests

2026-08-31 14:09:42 +05:30

test_compression_stall_deterministic_fallback.py

fix(compression): a timed-out preflight compaction sends a fitting request and prune-commits an over-window one

2026-09-18 10:36:11 -07:00

test_compression_stall_fallback.py

fix(compression): slim the same-turn fallback worker and pin it with a real-path test

2026-09-16 17:12:33 -07:00

test_compression_stall_interrupt.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_supersession_split.py

fix(compression): key candidate supersession on working attempts, not entry claims

2026-09-16 16:54:37 -07:00

test_compression_timeout_terminal.py

fix(compression): a timed-out preflight compaction sends a fitting request and prune-commits an over-window one

2026-09-18 10:36:11 -07:00

test_compression_trigger_excludes_reasoning.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compression_worker_isolation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compressor_actionable_tail_anchor.py

…

test_compressor_assistant_tail_anchor.py

…

test_compressor_fallback_update.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_compressor_historical_media.py

fix(compressor): widen compaction-time image aging to first-message and envelope shapes

2026-08-28 06:32:43 -07:00

test_compressor_image_tokens.py

feat(compression): per-image token cost learned from the provider's own usage (#70328, supersedes #70463)

2026-09-06 14:19:42 -07:00

test_compressor_media_stripping.py

…

test_compressor_stale_tool_images.py

fix(compression): share one image-strip policy across demote and retire passes

2026-08-23 15:03:29 +05:30

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

fix(compression): truncated summaries no longer become compaction checkpoints (port of earendil-works/pi#7048)

2026-08-31 10:39:55 -07:00

test_compressor_zero_user_guard.py

…

test_concurrent_interrupt.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_concurrent_multimodal_logging.py

test: trim concurrent multimodal log test to one invariant, reuse the stub

2026-09-15 18:40:03 -07:00

test_content_policy_blocked.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_content_policy_refusal_stop_details.py

test(delegation): trim the goal-duplication test to its two invariants

2026-09-18 09:52:36 -07:00

test_context_breakdown.py

…

test_context_compressor_cross_session_guard.py

refactor(compression): every compaction gate asks real usage first; rough estimates only decide whether to wait

2026-09-06 13:21:17 -07:00

test_context_compressor_custom_providers.py

test(compressor): pin custom_providers threading at the get_model_context_length seam

2026-09-08 02:27:01 +05:30

test_context_compressor_reasoning_fallback.py

fix(compression): take reasoning_content when the summarizer leaves content empty

2026-08-31 20:43:00 -05:00

test_context_compressor_session_end_clears_state.py

refactor(compression): every compaction gate asks real usage first; rough estimates only decide whether to wait

2026-09-06 13:21:17 -07:00

test_context_compressor_structural_backoff.py

fix(compression): structural no-ops defer retries instead of striking the breaker

2026-08-23 18:27:07 -07:00

test_context_compressor_summary_continuity.py

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

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

test_context_compressor_summary_hook_compat.py

fix: preserve false bypass values and single hook invocation

2026-09-07 05:59:08 -07:00

test_context_compressor_task_heading.py

fix(compression): collapse duplicate task sections during snapshot grounding

2026-09-18 19:18:23 -07:00

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(tests): cover the 'no credentials were found' permanent-failure marker

2026-09-18 11:11:44 -07:00

test_context_display_provenance.py

fix(display): retain provider provenance for persisted fallback readings

2026-09-07 08:13:01 -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_estimator_multimodal.py

fix(agent): tolerate schema-valued "type" keys in the watchdog payload estimator (#104793)

2026-09-07 00:49:51 -07:00

test_context_file_sources.py

fix(prompt_builder): load the user's own SOUL.md on a scanner hit instead of blocking it

2026-09-16 17:17:47 -07:00

test_context_overflow_loop.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_context_references.py

fix(profiles): side-thread asyncio.run workers keep the caller's profile scope

2026-09-16 16:59:03 -07:00

test_context_refs_concurrent.py

…

test_context_route_mismatch.py

…

test_context_token_tracking.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_continuation_ceiling_wedge.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_continuation_repetition_guard.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_conversation_compression_manual.py

fix(agent): manual /compress "nothing to compress" gate stays gateway-only

2026-09-13 05:20:26 -07:00

test_conversation_fallback_state.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_conversation_loop_interpreter_shutdown.py

fix(agent): break immediately on interpreter shutdown in conversation loop

2026-08-24 04:14:26 +05:30

test_copilot_acp_client.py

test(acp): trim shared-client process tests to two invariants

2026-09-18 09:33:38 -07:00

test_copilot_acp_deprecation.py

…

test_copilot_initiator.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_copilot_native_vision_headers.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_corruption_recovery_guidance.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_create_openai_client_disables_sdk_retries.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_create_openai_client_kwargs_isolation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_create_openai_client_proxy_env.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_create_openai_client_reuse.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_create_openai_client_ssl_verify.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_credential_pool_anthropic_refresh_race.py

fix: resolve the 33 F821 undefined names outside tui_gateway / feishu / godmode

2026-09-07 22:47:33 +05:30

test_credential_pool_auto_detect.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_credential_pool_deferred_refresh.py

…

test_credential_pool_interrupt.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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(auth): named profiles no longer inherit the root profile's auth.json (#111724)

2026-09-16 14:34:59 -07:00

test_credential_pool_operations.py

fix: place reauthenticated credentials by their saved identity

2026-09-07 08:06:48 -07:00

test_credential_pool_profile_oauth_fork.py

fix(auth): named profiles no longer inherit the root profile's auth.json (#111724)

2026-09-16 14:34:59 -07:00

test_credential_pool_provider_boundary.py

fix(anthropic): model-scoped 429 cooldowns live in a pool sibling; restore path no longer NameErrors

2026-09-16 17:16:06 -07:00

test_credential_pool_quarantine_locking.py

…

test_credential_pool_routing.py

…

test_credential_pool_seed_existing_env_sources.py

feat(credential-pool): numbered env siblings (KEY_2, KEY_3, …) seed rotation

2026-09-15 18:39:31 -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_terminal_refresh_visibility.py

fix(tests): drive the Nous terminal-refresh test through the real resolver

2026-09-18 10:17:59 -07:00

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_credential_rotation_route_settings.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_credits_cold_start.py

…

test_credits_fixture_snapshot.py

…

test_credits_notices_toggle.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_credits_policy.py

The free tier is created in one place, at boot, only behind HERMES_GUEST_ONBOARDING=1 (NS-847) (#107697)

2026-09-11 03:45:33 +05:30

test_credits_tracker.py

…

test_credits_view.py

…

test_cron_inflight_prompt_reappend.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_cron_inline_api_call.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_cross_process_turn_lease.py

fix: attribute gateway lifecycle stops to their system issuer, not the user

2026-09-16 17:48:17 -07:00

test_crossloop_client_cache.py

…

test_ctx_halving_fix.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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

test(curator): stop pinning the unadvertised edit alias in the read-before-write prompt

2026-09-17 08:47:01 -07:00

test_cursor_optimizations_parity.py

fix: resolve the 33 F821 undefined names outside tui_gateway / feishu / godmode

2026-09-07 22:47:33 +05:30

test_custom_pool_mismatch_guard.py

fix(auth): rotate credentials for named custom providers after 401/429

2026-08-23 20:01:18 -07:00

test_custom_provider_ca_probes.py

fix(desktop): stop UI freeze on unreachable provider Closes #81123

2026-09-09 21:16:48 +05:30

test_custom_provider_extra_body_matching.py

…

test_custom_provider_extra_body.py

…

test_custom_provider_extra_headers_client.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_custom_providers_vision.py

…

test_deadline_fork_race.py

fix(process): stop late forks escaping deadline tree cleanup

2026-09-07 08:19:32 -07:00

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

chore(cache): take the pre-merge cleanups on the declared conversation scope

2026-09-01 02:14:35 -07:00

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_deepseek_reasoning_content_echo.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_deepseek_v4_thinking_live.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_detached_fork_lifecycle_hooks.py

fix(agent): isolate detached forks from lifecycle hooks

2026-09-10 13:23:00 +02:00

test_dict_tool_call_args.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_direct_contexts_stream_inline.py

fix(streaming): retry a stream that died before any visible text instead of an empty stub

2026-09-16 17:08:02 -07:00

test_direct_provider_url_detection.py

…

test_display_emoji.py

…

test_display_todo_progress.py

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

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

test_display_tool_failure.py

fix(gateway): bounded redacted result preview on tool.completed run events

2026-09-15 18:42:10 -07:00

test_display.py

fix(display): tool previews never exceed a tiny max_len (1-3)

2026-09-12 08:23:42 -07:00

test_dropped_tool_call_recovery.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_empty_response_guard.py

fix(agent): handle usage-less empty responses

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

test_empty_response_recovery_persistence.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_empty_terminal_reasoning_surface.py

fix(agent): reasoning promoted on a reasoning-only clean stop is never persisted as an ordinary reply

2026-09-16 17:21:57 -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_entitlement_fail_closed.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_env_credential_turn_refresh.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_env_loader_applied_homes.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_env_loader_secret_sources.py

test(cron): keep three invariants for the routed-fire isolation

2026-09-15 11:03:39 +05:30

test_error_classifier.py

fix(errors): auth refusals from a non-stock route name the contacted host

2026-09-18 12:49:40 -07:00

test_error_surface.py

fix(free-tier): the desktop renders a free-tier refusal as its own card, not an OAuth re-login

2026-09-15 20:44:42 +05:30

test_estimator_parity.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_exit_cleanup_interrupt.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_export_current_turn_boundary.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_external_skills_dirs_cache.py

…

test_external_skills.py

…

test_failed_turn_chat_copy.py

test(agent): pin the Codex 401 CLI hint to the profile's own sign-in command

2026-09-18 10:00:29 -07:00

test_failed_turn_site_codes.py

fix(review): derive the default input budget from the fork's resolved context window

2026-09-18 19:18:57 -07:00

test_failover_identity.py

fix(moa): keep the aggregator prefix byte-stable across tool-loop iterations

2026-09-16 17:18:10 -07:00

test_fallback_429_after_timeout.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_fallback_api_mode_preservation.py

feat(providers): remove the keyless opencode-free tier

2026-09-18 15:40:37 +05:30

test_fallback_credential_isolation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_fallback_dynamic_credential.py

fix: distinguish callable Anthropic bearer sources from OAuth text

2026-09-07 06:07:16 -07:00

test_fallback_exhaustion_cooldown.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_fallback_reasoning_override.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_fast_compression_lane.py

test: exercise output-cap removal across native and child surfaces

2026-09-07 06:15:43 -07:00

test_fast_mode_auto.py

refactor(config): one effective-user-config loader replaces 9 hand-rolled raw→overlay→expand pipelines

2026-09-13 05:09:06 -07:00

test_file_mutation_verifier.py

fix(agent): file-mutation footer states failed edits, not "files were NOT modified"

2026-09-15 18:22:12 -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

test: trim #90322 regression to one invariant, drop the hint-splitting workaround

2026-09-07 00:20:11 +05:30

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_write_credentials.py

fix(file-safety): one coordinate helper for the guard homes; trim tests to two invariants

2026-09-18 10:08:58 -07:00

test_file_safety.py

…

test_fireworks_live.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_first_chunk_at_hook.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_flush_diverts_on_corrupt_state_db.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_gateway_turn_sidecar.py

…

test_gemini_alias_native_route.py

test(gemini): verify alias routing and compatible endpoint controls

2026-09-07 08:10:36 -07:00

test_gemini_fast_fallback.py

…

test_gemini_free_tier_gate.py

…

test_gemini_native_adapter.py

fix(gemini): route Vertex AI express keys (AQ.) to aiplatform instead of 403ing on AI Studio

2026-09-18 09:28:39 -07:00

test_gemini_native_reservation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_gemini_schema.py

feat(gemini): send full JSON Schema tool parameters via parametersJsonSchema

2026-09-14 06:44:54 -07:00

test_gemini_standard_key_guidance.py

test(gemini): bind the 400 reason gate for AIza Standard keys

2026-09-17 23:35:16 +05:30

test_gemini_thinking_config.py

test: fold Gemini thinking-budget tests into invariant form

2026-09-12 21:10:02 -07:00

test_gemini_type_arrays.py

fix: preserve native Gemini union constraints

2026-09-07 21:10:50 -07:00

test_ghost_skill_pruning.py

refactor(prompt): memory/skills guidance — one builder, positive posture, session-accurate wording (537 → 255 served, −282/call) (#97760)

2026-08-29 02:30:44 -07:00

test_glm_context_window_resolution.py

fix(metadata): GLM context windows from the live catalog; hyphenated slugs, entry-level overrides, aux inherits main pin

2026-09-10 01:08:18 -07:00

test_grid_sweep_cli_tui_stream_diagnostics.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_hermetic_side_effect_guards.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_hygiene_timeout_cooldown_isolation.py

fix(compression): stop timeout paths from blocking retries

2026-08-31 13:00:33 -07:00

test_i18n.py

fix(multiplex): tool and memory-provider env reads stay inside the routed profile

2026-09-11 15:26:46 -07:00

test_identity_flush.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_idle_compaction_lock_and_guards.py

test(compression): initialise idle checkpoint deferral state

2026-09-06 09:09:00 -07:00

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_corrupt_recovery.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_image_eviction_policy.py

test(agent): pin the eviction policy arithmetic directly

2026-09-17 13:52:36 +05:30

test_image_gen_registry.py

…

test_image_generate_parallel.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_image_rejection_fallback.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_image_routing.py

fix(model): preserve unknown custom capabilities

2026-09-16 17:09:50 -07:00

test_image_shrink_recovery.py

test(agent): oversize 400 bodies classify as image_too_large; spent shrink falls back

2026-09-16 17:09:30 -07:00

test_image_token_cost.py

feat(compression): per-image token cost learned from the provider's own usage (#70328, supersedes #70463)

2026-09-06 14:19:42 -07:00

test_in_place_commit_rollback.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_in_place_compaction.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_in_place_persist_marker.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_infinite_compaction_loop.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_init_fallback_on_exhausted_pool.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_injected_param_strip_retry_registry.py

test: trim the Aug-2026 conformance suites to behaviour invariants on main

2026-09-13 21:13:23 -07:00

test_inline_session_search_profile.py

fix(multiplex): tool and memory-provider env reads stay inside the routed profile

2026-09-11 15:26:46 -07:00

test_inline_tool_executors_memory_args.py

fix: mirror successful memory alias writes to providers

2026-09-07 06:05:13 -07:00

test_insights.py

fix(insights): count tool usage per session before merging the two sources

2026-09-12 08:23:13 -07:00

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_interactive_interrupt.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_interpreter_shutdown_turn_exit.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_interrupt_compat.py

fix(agent): separate cancellation diagnostics from tool output

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

test_interrupt_issuer_attribution.py

fix: attribute gateway lifecycle stops to their system issuer, not the user

2026-09-16 17:48:17 -07:00

test_interrupt_propagation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_invalid_context_length_warning.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_iron_proxy_e2e.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_iron_proxy.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_iteration_budget_race.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_iteration_budget_warning.py

fix: keep budget checkpoints out of cancelled tool results

2026-09-07 08:28:43 -07:00

test_jiter_preload.py

…

test_jsondecodeerror_retryable.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_kanban_budget_checkpoint.py

fix: keep budget checkpoints out of cancelled tool results

2026-09-07 08:28:43 -07:00

test_kanban_stop.py

fix(kanban): stop-guard nudge names every worker exit; sync terminal-tool copies

2026-09-18 09:21:42 -07:00

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_reasoning_per_turn.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_last_total_tokens.py

…

test_lean_single_aux_call.py

fix(compression): lean compaction makes exactly one auxiliary request per attempt

2026-08-30 09:03:57 -07:00

test_learn_prompt.py

revert: remove Collective Wisdom V1 (#94266)

2026-09-11 11:54:49 -07:00

test_learning_graph_render.py

…

test_learning_graph.py

test(journey): one end-to-end invariant for foreground-created skills; docs + list-unmanaged label

2026-09-15 05:38:31 -07:00

test_learning_mutations.py

…

test_length_continuation_thinking_exhaustion.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_length_continuation_window_headroom.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_litellm_tool_part_cache_markers.py

fix(prompt-caching): tool-using sessions no longer 400 behind LiteLLM Anthropic proxies (#89886)

2026-08-29 12:06:48 +05:30

test_lmstudio_load_mode.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_lmstudio_reasoning.py

…

test_load_time_durability_stamp.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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_long_context_tier_429.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_malformed_tool_args_no_fallback.py

fix(agent): a no-fallback verdict wins over the local-ValueError fallback allowance

2026-09-12 08:27:11 -07:00

test_malformed_tool_arguments.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_manual_compression_feedback.py

…

test_manual_compression_refusal_feedback.py

fix(compression): /compress refusal no longer reports a successful rewrite

2026-08-19 22:41:05 -07:00

test_markdown_tables.py

…

test_materialize_data_url_cleanup.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_memory_agent_context.py

test(agent): pin agent_context derivation and the supermemory cron write-off (#80646)

2026-09-19 00:55:05 +05:30

test_memory_async_sync.py

…

test_memory_boundary_commit.py

…

test_memory_nudge_counter_hydration.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_memory_provider_init.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_memory_provider_unavailable_warning.py

…

test_memory_provider.py

chore(tests): encoding="utf-8" on read_text/write_text in test_memory_provider.py

2026-09-12 08:22:57 -07:00

test_memory_recall_indicator.py

refactor(memory): keep the spill, drop registration-trust rework

2026-09-06 13:25:48 -07:00

test_memory_session_switch.py

refactor(memory): keep the spill, drop registration-trust rework

2026-09-06 13:25:48 -07:00

test_memory_skill_scaffolding.py

…

test_memory_sync_interrupted.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_memory_user_id.py

test(honcho): trim salvage coverage to the invariants; drop duplicate ACP session_cwd stamp

2026-09-15 22:30:11 -07:00

test_memory_write_bridge.py

…

test_message_content.py

…

test_message_metadata.py

test: add message_metadata unit tests

2026-08-15 01:04:19 -07:00

test_message_reactions.py

refactor(state): one visibility clause for every reaction path; SQL-side reaction prefilter

2026-09-19 00:59:32 +05:30

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_message_sequence_repair.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_meta_agent_init.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_meta_usage_cache_reporting.py

fix(providers): route api.meta.ai through Responses API for prompt caching

2026-08-17 12:58:51 -07:00

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

fix(agent): anchor ZAI/Kimi base_url host matching to avoid substring false positives

2026-08-14 22:04:16 -07:00

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_missing_provider_credentials_hint.py

fix(auth): missing-credential hints name the real env var or the OAuth login (#114405, #78996)

2026-09-18 11:11:44 -07:00

test_moa_aggregator_cache_control.py

…

test_moa_aggregator_cost_slot.py

…

test_moa_aggregator_prefix_stability.py

fix(anthropic): merged user turns keep each turn as its own text block

2026-09-17 08:46:05 -07:00

test_moa_cold_start_cache.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_moa_context_max_tokens.py

…

test_moa_fanout_cadence.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_moa_loop_mode.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_moa_observability_bridge.py

…

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_prepared_request_leak.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_moa_privacy_filter.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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: exercise output-cap removal across native and child surfaces

2026-09-07 06:15:43 -07:00

test_moa_streaming.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_moa_switch_api_mode.py

test(agent): give the MoA switch fake a reasoning_echo reader

2026-08-19 13:56:11 -05:00

test_moa_trace_streamed_capture.py

…

test_model_extra_type_guard.py

…

test_model_metadata_local_ctx.py

test(model_metadata): lock in max_tokens last-resort fallback + cache self-heal

2026-08-24 03:20:57 -07:00

test_model_metadata_ssl.py

…

test_model_metadata.py

feat(providers): remove the keyless opencode-free tier

2026-09-18 15:40:37 +05:30

test_model_streaming_config.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_models_dev_meta_mapping.py

feat(providers): remove the keyless opencode-free tier

2026-09-18 15:40:37 +05:30

test_models_dev.py

fix(tools): warn once when a check_fn drops a core tool; reject a mistyped catalog_provider

2026-09-17 08:53:48 -07:00

test_moonshot_schema.py

…

test_multimodal_interim.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_multimodal_tool_content_recovery.py

test(agent): keep two invariant NIM serde tests (positive + other-enum negative)

2026-09-15 06:18:31 -07:00

test_multiplex_base_url_scope.py

fix(multiplex): tool and memory-provider env reads stay inside the routed profile

2026-09-11 15:26:46 -07:00

test_multiplex_cloud_credential_clients.py

fix(multiplex): build Bedrock and Entra credential clients from the routed profile

2026-09-12 01:35:05 -07:00

test_native_compaction_nontext_retention.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_native_compaction_summary_retention.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_native_compaction_switch_capabilities.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_native_compaction.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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_nonretryable_error_html_summary.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_nonretryable_result_carries_verdict.py

fix(desktop): expired OAuth grant shows a one-click 'Sign in again' instead of a retryable Provider error

2026-09-09 16:30:24 -07:00

test_nonstream_wait_notice.py

fix: wait sixty seconds before provider silence notices

2026-09-07 05:24:15 -07:00

test_notice_spine.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_notification_persistence.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_nous_429_fallback_reentry.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_nous_credits_gauge.py

…

test_nous_credits_snapshot.py

…

test_nous_fallback_unavailable.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_nous_key_pre_expiry_adoption.py

fix(nous): pre-expiry adoption only ever swaps to a key for the SAME account

2026-09-05 06:09:24 -07:00

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

fix(tests): accept select(model=) in sibling pool stubs; mirror per-model 429 docs to zh-Hans

2026-09-16 17:16:06 -07:00

test_nous_rate_guard.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_nous_usage_profile_context.py

fix(usage): preserve routed profile context in Nous account fetches

2026-09-16 11:06:06 -07:00

test_nous_welcome_client_contract.py

fix(free-tier): review round 2 — route-gate the allowance verdict, keep policy/billing 403s, pool the provision RPC, guard the retry race

2026-09-15 20:44:42 +05:30

test_nous_wire_auto.py

feat(nous): anthropic_wire=auto decides a session's wire from its first response

2026-09-06 09:11:04 -07:00

test_nt_namespace_guard.py

fix: NT-namespace guard fires before every sibling resolve (checkpoint, ACP bridge, @file:)

2026-09-15 04:17:31 -07:00

test_ollama_num_ctx.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_onboarding.py

…

test_onepassword_secrets.py

fix(secrets): preserve OP_CONFIG_DIR for 1Password

2026-09-15 19:10:00 -07:00

test_oneshot.py

…

test_openai_client_lifecycle.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_opencode_session_affinity.py

feat(providers): remove the keyless opencode-free tier

2026-09-18 15:40:37 +05:30

test_openrouter_response_cache.py

…

test_openrouter_silent_default_purge.py

fix(auth): purge silent OpenRouter paid-default adoption (#81952 class fix)

2026-09-01 07:00:38 -07:00

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): quantize eviction by the fit window so heavy tool results hold the frontier

2026-09-17 13:52:36 +05:30

test_outbound_webhooks.py

fix(multiplex): tool and memory-provider env reads stay inside the routed profile

2026-09-11 15:26:46 -07:00

test_outer_error_retry_bound.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_output_cap_parsing.py

Port from cline/cline#12876: classify Anthropic output-cap errors

2026-09-15 03:54:58 -07:00

test_overflow_overhead_aware_tokens.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_overflow_partial_terminal.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_owned_process_cleanup.py

fix(agent): reclaim background processes by execution owner

2026-09-07 04:38:59 -07:00

test_partial_stream_finish_reason.py

fix: treat a reasoning-only stream drop as a drop, not a clean stop

2026-09-13 14:46:42 -07:00

test_per_model_compression_threshold.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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_per_model_threshold_init_ordering.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_percentage_clamp.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_periodic_scheduler_context.py

test(agent): pin periodic scheduler context propagation

2026-09-16 11:06:06 -07:00

test_periodic_scheduler.py

test(agent): the worker-start-failure test intercepts the callback worker again

2026-09-09 12:42:02 +05:30

test_pet_engine.py

test: one class invariant across every remote-fetch site

2026-09-18 10:22:14 -07:00

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

fix: restore TestBridgeDispatch, trim #39797 tests, drop dead execution_guidance_text param

2026-09-15 04:13:13 -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_cron_delivery.py

fix: cron agents carry their delivery channel's platform hint

2026-09-16 21:39:13 -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_engine_init.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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

feat(compaction): system prompt always rebuilds at the commit boundary — updates finally reach long-lived sessions (#98426)

2026-08-30 01:20:27 -07:00

test_plugin_stream_hooks.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_pool_revert_after_cooldown.py

fix: arm the pool revert only when the benched credential outranks the one rotated to

2026-09-18 10:35:37 -07:00

test_portal_tags.py

…

test_post_compression_trim.py

…

test_post_tool_compression_attempt_cap.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_pre_compress_checkpoint_contract.py

fix(compression): scope the checkpoint remediation to capability refusals; trim tests

2026-09-18 13:58:52 -07:00

test_pre_compress_memory_context_handoff.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_pre_compress_memory_context.py

…

test_preflight_compression_cap_e2e.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_preflight_compression_gate.py

…

test_preflight_compression_timeout_fail_closed.py

fix(compression): a timed-out preflight compaction sends a fitting request and prune-commits an over-window one

2026-09-18 10:36:11 -07:00

test_preflight_lock_defer.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_preflight_timeout_typed_result.py

fix(compression): a timed-out preflight compaction sends a fitting request and prune-commits an over-window one

2026-09-18 10:36:11 -07:00

test_primary_runtime_restore.py

fix(compression): keep the aux ceiling and re-probe feasibility on every main-runtime change

2026-09-18 09:49:14 -07:00

test_private_credential_writers.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_proactive_prune_config.py

…

test_proactive_prune_loop_wiring.py

fix: pruned skill_view/read_file results reload after a proactive prune

2026-09-16 17:23:44 -07:00

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

fix(vision): forward the API key to the server-type probe and cache failed verdicts

2026-08-23 17:47:50 -07:00

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

fix(skills): resolve project roots from session cwd

2026-09-18 10:22:47 -07:00

test_prompt_builder.py

fix(prompt_builder): keep blocking a distribution-owned SOUL.md on a scanner hit

2026-09-16 17:17:47 -07:00

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(cache): pin the prompt-cache scope isolation invariant for per-response session ids

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

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.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_provider_attribution_headers.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -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_fallback.py

fix(agent): a MoA preset in the fallback chain activates the preset, not the aggregator alone

2026-09-16 17:07:21 -07:00

test_provider_media.py

fix(video-gen): trust the operator-configured origin on the first download hop

2026-09-18 10:22:14 -07:00

test_provider_parity.py

fix(agent): skip corrupted Gemini thought signatures

2026-09-15 05:42:35 -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_proxy_bypass_shared.py

fix(agent): a malformed port in base_url no longer drops the keepalive transport

2026-09-13 05:09:43 -07:00

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_disable_recovery.py

fix(agent): drop non-invariant disable-rung test; document thinking-state 400 trade-off (#114460)

2026-09-18 10:21:05 -07:00

test_reasoning_echo_resolver_e2e.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_reasoning_effort_module.py

fix: preserve max reasoning for Daybreak alias

2026-09-12 08:06:48 -07:00

test_reasoning_effort_wire_translation.py

fix(agent): cap the ultra reasoning level at the wire vocabulary

2026-08-19 16:04:22 -07:00

test_reasoning_only_stop_persistence.py

fix(agent): route a planning-monologue reasoning-only stop through the stall guard, not a fake completion

2026-09-17 08:53:20 -07:00

test_reasoning_shape_boundaries.py

fix: structured reasoning no longer breaks chat consumers

2026-09-07 08:24:54 -07:00

test_reasoning_stale_timeout_floor.py

fix(deepseek): recognise the version-less deepseek-flash model id

2026-09-10 02:44:26 -07:00

test_reasoning_summaries.py

…

test_recovery_diagnostic_producers.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_redact.py

fix(redact): dotted sk- body cannot span "..", so display masks survive a second pass; Zhipu matcher is 32-hex.16+alnum

2026-09-18 09:58:12 -07:00

test_redaction_registry.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_reference_handoff_active_turn.py

Merge remote-tracking branch 'origin/main' into agent/81234-merge-20260821

2026-08-22 16:47:39 +02:00

test_refine_focus.py

…

test_refine_snapshot_isolation.py

fix(review): keep /refine under the background_review origin; attendedness is its own flag

2026-09-09 12:19:13 +05:30

test_relay_llm.py

fix(relay): upgrade to 0.8.1

2026-08-28 08:28:21 -04:00

test_relay_nested_execution.py

fix(relay): use canonical managed operation names

2026-08-13 12:23:36 -07:00

test_relay_runtime_bounded_scope_ops.py

fix(relay): preserve shutdown scope cleanup

2026-08-19 08:52:03 -07:00

test_relay_runtime_plugins.py

fix(relay): upgrade to 0.8.1

2026-08-28 08:28:21 -04:00

test_relay_scope_pop_metadata.py

fix(agent): omit unsupported metadata on Relay scope.pop

2026-08-15 00:33:01 -07:00

test_relay_session_segments.py

feat(relay): pass API request metadata to Relay tracking

2026-09-10 13:23:24 -07:00

test_relay_tools.py

fix(relay): upgrade to 0.8.1

2026-08-28 08:28:21 -04:00

test_remote_fetch_ssrf_guard.py

test: one class invariant across every remote-fetch site

2026-09-18 10:22:14 -07:00

test_repair_reanchors_current_turn_user_idx.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_repair_tool_call_arguments.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_repair_tool_call_name.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_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_replay_budget_accounting.py

fix(compaction): count api_content in tail budget

2026-09-06 14:04:05 -07:00

test_replay_cleanup.py

refactor(agent): fail loudly on a missing turn clock; single lowercase in is_dangerous_confirmation

2026-09-13 19:23:09 +05:30

test_request_client_reuse_abort_races.py

fix(test): give the stale-abort atomicity test a display consumer so "hello" counts as delivered

2026-09-16 17:08:02 -07:00

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_reset_aware_primary_restore.py

fix(anthropic): model-scoped 429 cooldowns live in a pool sibling; restore path no longer NameErrors

2026-09-16 17:16:06 -07:00

test_responses_empty_tool_replay.py

test: trim Responses blank-carrier coverage to two invariants

2026-09-16 14:23:20 -07:00

test_restore_primary_pool_reselect.py

…

test_resume_stale_active_task.py

…

test_retry_delay_parsers_shared.py

fix(agent): explicit "retry after N s" wins over "resets in ..." in the shared reset table

2026-09-13 05:09:43 -07:00

test_retry_status_buffer.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_retry_utils.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_review_engine.py

fix: make review workers recognizable in live subagent viewers

2026-09-08 04:38:47 -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_review_prompt_class_first.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_rotation_flush_persisted_boundary.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_run_agent_codex_responses.py

fix(agent): cover the remaining refusal-only surfaces and fold the tests

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

test_run_agent_multimodal_prologue.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_run_agent.py

fix(agent): contentless SSE keepalive frames retry without streaming

2026-09-15 18:18:08 -07:00

test_run_budget.py

fix(agent): stop the run-budget wrap-up notice from mutating a persisted tool row

2026-09-09 17:04:30 +05:30

test_runtime_cwd.py

…

test_salvage_grown_transcript.py

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

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

test_sanitiser_escalation.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_save_url_image.py

test: one class invariant across every remote-fetch site

2026-09-18 10:22:14 -07:00

test_secret_scope_env_cache.py

fix(secret_scope): memoise the shared .env tokenizer once per file change

2026-09-17 20:56:27 +05:30

test_secret_scope_tier1_migration.py

refactor(platforms): one scoped-secret reader and spec-driven enablement/YAML-bridge boilerplate across all adapters

2026-09-13 05:32:38 -07:00

test_secret_scope_user_message.py

fix(ux): plain-language, actionable user-facing messages (core)

2026-09-15 04:12:13 -07:00

test_secret_scope.py

fix(ux): plain-language, actionable user-facing messages (core)

2026-09-15 04:12:13 -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_chats_live.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_sequential_deadline_delegate_exempt.py

Desktop connect runs on the connection operation: one card, no link to the model, no renderer polling (NS-868) (#110574)

2026-09-15 00:41:14 +05:30

test_sequential_tool_interrupt.py

fix: make every tool interruptible — sequential executor abandons on user interrupt

2026-08-16 11:32:02 -07:00

test_sequential_tool_timeout.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_session_activity_persist.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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_id_env.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_session_meta_filtering.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_session_reset_fix.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_session_rotation_flush_cold_resume.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_session_snapshot_removal.py

fix: remove automatic session JSON snapshots

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

test_session_source.py

fix(sessions): one-shot runs get a distinct oneshot source that pickers hide

2026-09-17 09:06:59 -07:00

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_client_fd_corruption.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -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(hooks): quote the marker path in the interrupt test's hook script

2026-09-12 07:54:57 -07:00

test_shell_hooks.py

refactor(persistence): 24 hand-rolled atomic JSON/text writers go through utils.atomic_json_write / atomic_write_text

2026-09-13 05:07:11 -07:00

test_side_question.py

feat: /btw rides the background-review cache-parity fork for full-context answers

2026-08-29 08:23:47 -07:00

test_skill_applied_notifications.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_skill_bundles.py

…

test_skill_commands_reload.py

…

test_skill_commands.py

chore(tests): explicit utf-8 encoding in test_skill_commands (windows-footgun ratchet)

2026-09-12 08:25:36 -07:00

test_skill_invocation_description.py

…

test_skill_session_platform_gate.py

refactor(skills): shipped-set slim — 15 to optional, github 6-way merge, pdf absorbs OCR, channel-gated teams pipeline (index −26%) (#98539)

2026-08-30 04:53:39 -07:00

test_skill_todo_retention_parity.py

fix(compression): strip embedded stale todo snapshot from list message content

2026-08-29 20:39:04 -07:00

test_skill_utils.py

fix(skills): literal HOME replacement; ~/$VAR still expands the variable

2026-09-12 08:25:59 -07:00

test_skills_auto_load.py

fix(skills): auto-load resolves under the agent's own home and skips internal forks

2026-09-15 03:34:20 -07:00

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

fix(state): pin the shared storage-failure action copy to the failing profile

2026-09-16 21:15:30 +05:30

test_skip_memory_store.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_soul_legacy_bot_protocol.py

fix: legacy Bot Mode section in SOUL.md no longer taxes every session or shadows the live roster

2026-09-06 13:08:31 -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_sql_injection.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

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

fix(agent): route a planning-monologue reasoning-only stop through the stall guard, not a fake completion

2026-09-17 08:53:20 -07:00

test_start_order_gate.py

fix(agent): concurrent worker survives a dict error result

2026-09-15 18:42:10 -07:00

test_steer.py

test: import _mock_response from tests.agent.test_run_agent

2026-09-18 13:01:12 -04:00

test_stream_chunk_byte_estimate.py

…

test_stream_drop_logging.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_stream_interrupt_retry.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_stream_read_timeout_floor.py

…

test_stream_retry_route_switch.py

fix: stream retry no longer replays the old model on the switched-to provider

2026-09-15 18:21:17 -07:00

test_stream_single_writer_guard.py

…

test_stream_single_writer.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_stream_stale_breaker_reset.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_stream_stale_circuit_breaker.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_stream_stale_kill_unwedge.py

refactor(agent): share the shutdown-only socket primitives with the pool sweep

2026-09-15 12:46:27 +05:30

test_stream_wait_notice.py

fix: wait sixty seconds before provider silence notices

2026-09-07 05:24:15 -07:00

test_streamed_reasoning_details.py

fix(agent): streamed reasoning_details survive for replay continuity (port of earendil-works/pi#8605)

2026-09-13 21:27:35 -07:00

test_streamed_text_accumulation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_streaming_context_scrubber.py

…

test_streaming_tool_call_repair.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_streaming.py

fix(streaming): retry a stream that died before any visible text instead of an empty stub

2026-09-16 17:08:02 -07:00

test_strict_api_validation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_strip_reasoning_tags_cli.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_structured_output_rejection_retry.py

fix(auxiliary): retry without response_format when a provider rejects the object-form json_schema by shape

2026-09-15 04:46:36 -07:00

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

fix(agent): separate cancellation diagnostics from tool output

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

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

fix(hermes_cli): scope hook timeouts and fail closed on pre_tool_call

2026-08-27 16:13:45 +05:30

test_subdirectory_hints_tilde.py

…

test_subdirectory_hints.py

fix(agent): hint-preview truncation log names the real remedy; invariant tests

2026-09-15 18:19:26 -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_api_error.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_summarize_tool_result_type_safety.py

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

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

test_summary_prefix_semantics.py

…

test_summary_prefix_tool_use.py

…

test_summary_role_template_alternation.py

…

test_surrogate_chokepoints.py

refactor(agent): one outbound-kwargs sanitizer seam for the main loop and the summary

2026-09-14 20:35:28 +05:30

test_switch_model_bedrock_sigv4.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_switch_model_context.py

fix(compression): keep the aux ceiling and re-probe feasibility on every main-runtime change

2026-09-18 09:49:14 -07:00

test_switch_model_fallback_prune.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_switch_model_pool_reload.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_switch_model_reapplies_headers.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_switch_model_reasoning_override.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_switch_model_request_overrides.py

fix(agent): match switched-to custom provider by model+base_url, not name

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

test_switch_model_rollback.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_switch_model_stale_base_url.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_synthetic_turn_display_kind.py

…

test_system_prompt_restore.py

refactor(agent): surface-switch note lives in its own sibling; skip it where no sidecar exists

2026-09-09 10:31:26 +05:30

test_system_prompt.py

fix: kanban guidance and stop nudge resolve worker identity through one helper

2026-09-16 17:48:48 -07:00

test_terminal_approval_batch.py

test(approval): align CI with transcript hosting and terminal scope

2026-09-16 06:27:23 -05:00

test_terminal_env_registry.py

feat(terminal): pluggable terminal environment backends via plugin registry

2026-08-24 20:10:44 -07:00

test_text_turn_incremental_persistence.py

test: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_think_scrubber.py

…

test_thinking_only_sanitizer.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_thinking_prefill_trailing_turn.py

test(agent): lock the reasoning-only stop row shape on the stall-guard and prefill paths

2026-09-17 08:53:20 -07:00

test_thinking_sig_recovery_persistence.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_thinking_timeout_guidance.py

…

test_thread_scoped_output.py

fix(agent): stop thread output descriptor leaks

2026-08-15 00:33:01 -07:00

test_title_generator.py

fix(agent): a paste-only opener's expansion footer must not demote the title preview

2026-09-18 10:56:00 -07:00

test_tls_fd_recycle_corruption.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_token_estimator_shared.py

refactor(agent): one Retry-After parser and one reset-grammar table feed every retry wait

2026-09-13 05:09:43 -07:00

test_token_guard_session_source.py

fix(sessions): token-accounting guard stamps the agent's real source; trim salvage

2026-09-15 18:23:07 -07:00

test_token_persistence_non_cli.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_activity_heartbeat.py

fix(agent): stop the tool-activity heartbeat when the executor abandons its worker

2026-09-16 17:08:25 -07:00

test_tool_arg_coercion.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_batch_segmentation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_call_arg_no_redaction.py

…

test_tool_call_args_sanitizer.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_call_guardrail_runtime.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_call_incremental_persistence.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_dispatch_helpers.py

fix(agent): preserve tool results across ID variants

2026-08-23 18:24:43 -07:00

test_tool_executor_checkpoint_paths.py

fix(checkpoints): refuse host rollback and session diff from container sessions on the gateway too

2026-09-18 10:38:08 -07:00

test_tool_executor_contextvar_propagation.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_guardrails.py

fix(guardrails): mark every file-tool loop refusal and exempt it on the live failure seam

2026-09-18 10:03:04 -07:00

test_tool_name_db_persistence.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_tool_result_classification.py

…

test_trace_upload.py

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

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

test_trajectory_file_locking.py

fix(agent): lock save_trajectory() appends so concurrent processes cannot corrupt the JSONL

2026-09-12 08:25:14 -07:00

test_transcript_decoration_idempotence.py

test: trim the Aug-2026 conformance suites to behaviour invariants on main

2026-09-13 21:13:23 -07:00

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_api_call_interrupt.py

fix: only drop an interrupted partial for the runaway repetition shape

2026-09-16 17:10:13 -07:00

test_turn_author.py

docs(gateway): document gateway.bot_loop_guard where ALLOW_BOTS is explained

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

test_turn_base_display_anchor.py

feat(compression): usage anchor survives DB reloads and process restarts (salvage #99585)

2026-09-06 13:21:17 -07:00

test_turn_completion_explainer.py

fix(state): pin the shared storage-failure action copy to the failing profile

2026-09-16 21:15:30 +05:30

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: repoint cross-test imports at the moved modules; opt one backoff test out of the merged agent fixture

2026-09-13 09:18:02 -07:00

test_turn_context.py

fix: cover the title_preview wire seam and the widened _run_after_agent_ready call

2026-09-18 10:56:00 -07:00

test_turn_facade_lease.py

fix(ux): plain-language, actionable user-facing messages (core)

2026-09-15 04:12:13 -07:00

test_turn_finalizer_cleanup_guard.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_turn_finalizer_final_response_persistence.py

fix(ux): plain-language, actionable user-facing messages (core)

2026-09-15 04:12:13 -07:00

test_turn_finalizer_interrupt_alternation.py

fix(agent,gateway): report interrupted and unfinished turns truthfully

2026-09-15 18:21:44 -07:00

test_turn_finalizer_iteration_limit_exit.py

fix(kanban): delegate_task children never act on the parent's HERMES_KANBAN_TASK

2026-09-16 10:43:48 -07:00

test_turn_iteration_prep.py

fix(agent): system watchdog interrupts are attributed to their issuer, not the user

2026-09-16 17:48:17 -07:00

test_turn_liveness_watchdog.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_turn_liveness.py

fix(agent): surface silent turn stalls with a bounded turn-liveness watchdog (#95548, #95663)

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

test_turn_overlap_tripwire.py

…

test_turn_recovery_retry_notice.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_turn_retry_state.py

feat(free-tier): ruled behaviour for every welcome-api failure, with friendly copy and a fault-injecting rehearsal server

2026-09-15 20:44:42 +05:30

test_turn_summary.py

…

test_turn_usage_log_line.py

feat(logging): the API call line carries cache write count, the provider's response id, and the serving upstream

2026-09-06 13:52:15 -07:00

test_uncompressed_context_guardrail.py

refactor(agent): consolidate uncompressed-overflow guard to one warn site + re-arm

2026-08-20 12:35:20 +05:30

test_unicode_ascii_codec.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_unsupported_parameter_retry.py

fix(auxiliary): recognise Bedrock's "doesn't support"/"is deprecated" sampling-param rejections

2026-09-15 04:45:33 -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

feat(compression): usage anchor survives DB reloads and process restarts (salvage #99585)

2026-09-06 13:21:17 -07:00

test_usage_pricing.py

fix(deepseek): deepseek-flash is the canonical Flash id; retired names fold onto it

2026-09-10 02:44:26 -07:00

test_vault_backends.py

fix(secrets): preserve OP_CONFIG_DIR for 1Password

2026-09-15 19:10:00 -07:00

test_verification_continuation_budget.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_verification_evidence_disabled.py

fix: verification evidence ledger is inert while verify_on_stop is off

2026-09-09 02:35:41 -07:00

test_verification_evidence_fd_leak.py

fix: verification evidence ledger is inert while verify_on_stop is off

2026-09-09 02:35:41 -07:00

test_verification_evidence.py

fix: verification evidence ledger is inert while verify_on_stop is off

2026-09-09 02:35:41 -07:00

test_verification_stop_caching.py

fix: remove automatic session JSON snapshots

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

test_verification_stop.py

fix: verification evidence ledger is inert while verify_on_stop is off

2026-09-09 02:35:41 -07:00

test_verify_hooks.py

…

test_vertex_adapter.py

refactor(vertex): fold _creds_cache_key into _sa_snapshot (simplify pass)

2026-08-29 12:33:44 +05:30

test_video_gen_registry.py

…

test_vision_aware_preprocessing.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_vision_resolved_args.py

…

test_vision_routing.py

fix(vision): advertise vision_analyze/browser_vision when the main model sees natively

2026-09-13 14:46:38 -07:00

test_vision_tool_messages.py

test(vision): keep two invariant aggregator-veto tests (tool-result downgrade + fast-path veto)

2026-09-15 04:48:20 -07:00

test_wait_state_visibility.py

test: make tests/ mirror the source tree; drop issue numbers from filenames

2026-09-13 09:18:02 -07:00

test_warning_presentation.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_welcome_error_identity.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_welcome_tier_recovery.py

feat(notifications): opt-in suppression of user-channel warning notifications

2026-09-18 01:43:35 +05:30

test_would_grow_refusal_runway.py

review follow-up: trim overreaching comment sentence, pin durable-copy assertion

2026-08-22 16:07:12 +05:30