hermes-agent/tests/run_agent
kshitijk4poor e762a5a473 fix(compression): copy-on-write in image-shrink recovery so degraded images never reach stored history
With the selective prompt-cache copy (#57046), un-marked messages on the
decorated api_messages list share their nested content parts with the
persistent conversation history — the per-message copy in
conversation_loop is shallow and decoration now deep-copies only the
marked messages. try_shrink_image_parts_in_messages previously wrote the
re-encoded image INTO the aliased part/source dicts, so an
image-too-large retry on an Anthropic route would silently replace the
original image bytes in agent.messages (and persist the degraded copy).

Replace the in-place writes with copy-on-write: rebuild the content list
with fresh part/source/image_url dicts and reassign msg['content'] — a
top-level write on the per-call copy that never reaches history.

Adds two regression tests simulating the aliasing; both fail against the
old in-place implementation (mutation-verified).
2026-07-28 20:04:58 +05:30
..
__init__.py
conftest.py
repro_48013_image_shrink_brick.py
test_413_compression.py
test_860_dedup.py
test_1630_context_overflow_loop.py
test_18028_content_policy_blocked.py
test_24996_fallback_exhaustion_cooldown.py
test_28161_anthropic_stream_pool_cleanup.py
test_31273_402_not_retried.py
test_32646_fallback_429_after_timeout.py
test_63425_credential_pool_auto_detect.py
test_66267_multimodal_interim.py
test_70773_shared_client_fd_corruption.py fix(agent): retire replaced shared OpenAI clients instead of cross-thread pool close 2026-07-24 16:04:48 -07:00
test_agent_guardrails.py fix(agent): uniquify duplicate tool-call ids to keep call/result pairing lossless 2026-07-26 20:59:06 -07:00
test_anthropic_prompt_cache_policy.py nous portal anthropic wire 2026-07-27 11:53:48 -04:00
test_anthropic_response_header_capture.py nous portal anthropic wire 2026-07-27 11:53:48 -04:00
test_anthropic_third_party_oauth_guard.py
test_anthropic_truncation_continuation.py
test_api_max_retries_config.py
test_async_httpx_del_neuter.py
test_auth_provider_failover.py
test_background_review.py
test_background_review_cache_parity.py
test_background_review_cost_controls.py
test_background_review_summary.py
test_background_review_toolset_restriction.py
test_callable_api_key.py
test_codex_app_server_compaction.py revert: PR #72817 — session activity watchdog, stall notify, compress timeout 2026-07-28 00:15:00 +05:00
test_codex_app_server_integration.py
test_codex_multimodal_tool_result.py
test_codex_no_tools_nonetype.py
test_codex_silent_hang_hint.py
test_codex_xai_oauth_recovery.py
test_commit_memory_session_context_engine.py
test_compress_focus_plugin_fallback.py
test_compression_abort_state_reset.py
test_compression_boundary.py
test_compression_boundary_hook.py fix(compression): recover rotated session lineage 2026-07-24 16:00:34 -07:00
test_compression_feasibility.py
test_compression_lock_defer.py
test_compression_persistence.py fix(conversation): anchor the cwd staleness read to the host-info block 2026-07-25 19:25:34 -07:00
test_compression_trigger_excludes_reasoning.py
test_compressor_fallback_update.py
test_concurrent_interrupt.py
test_context_token_tracking.py
test_conversation_fallback_state.py
test_copilot_native_vision_headers.py
test_create_openai_client_disables_sdk_retries.py
test_create_openai_client_kwargs_isolation.py
test_create_openai_client_proxy_env.py
test_create_openai_client_reuse.py test(agent): cover mount-pool interrupt abort and zero-socket warning 2026-07-28 18:07:44 +05:30
test_create_openai_client_ssl_verify.py
test_credential_pool_interrupt.py
test_credential_rotation_route_settings.py
test_credits_notices_toggle.py
test_custom_provider_extra_headers_client.py
test_deepseek_reasoning_content_echo.py
test_deepseek_v4_thinking_live.py
test_dict_tool_call_args.py
test_dropped_tool_call_recovery.py fix(agent): make dropped tool-call nudge pair ephemeral scaffolding 2026-07-24 15:56:39 -07:00
test_empty_response_recovery_persistence.py
test_empty_terminal_reasoning_surface.py feat(agent): surface a labeled reasoning excerpt at the empty-response terminal 2026-07-26 20:59:21 -07:00
test_exit_cleanup_interrupt.py
test_fallback_credential_isolation.py
test_fallback_reasoning_override.py
test_file_mutation_verifier.py
test_fireworks_live.py
test_identity_flush.py
test_image_rejection_fallback.py
test_image_shrink_recovery.py fix(compression): copy-on-write in image-shrink recovery so degraded images never reach stored history 2026-07-28 20:04:58 +05:30
test_in_place_compaction.py
test_infinite_compaction_loop.py
test_init_fallback_on_exhausted_pool.py
test_interactive_interrupt.py
test_interrupt_propagation.py
test_invalid_context_length_warning.py
test_iteration_budget_race.py
test_jsondecodeerror_retryable.py
test_last_reasoning_per_turn.py
test_lmstudio_load_mode.py
test_long_context_tier_429.py
test_malformed_tool_arguments.py
test_materialize_data_url_cleanup.py
test_memory_nudge_counter_hydration.py
test_memory_provider_init.py
test_memory_sync_interrupted.py
test_message_sequence_repair.py refactor: single owner for empty-content wire repair (class fix) 2026-07-27 20:27:56 -07:00
test_moa_fanout_cadence.py
test_moa_loop_mode.py
test_moa_privacy_filter.py
test_moa_streaming.py
test_multimodal_tool_content_recovery.py
test_nonretryable_error_html_summary.py
test_notice_spine.py
test_nous_429_fallback_reentry.py
test_nous_fallback_unavailable.py
test_openai_client_lifecycle.py perf(agent): reuse the per-request OpenAI wire client across sequential LLM calls 2026-07-28 19:06:59 +05:30
test_partial_stream_finish_reason.py refactor: single owner for empty-content wire repair (class fix) 2026-07-27 20:27:56 -07:00
test_per_model_compression_threshold.py test(compression): resolve context_length inside mocks across suites hit by lazy-init deferral 2026-07-28 20:04:58 +05:30
test_per_model_threshold_init_ordering.py
test_percentage_clamp.py
test_plugin_context_engine_init.py
test_post_tool_compression_attempt_cap.py
test_pre_compress_memory_context.py
test_preflight_compression_cap_e2e.py
test_primary_runtime_restore.py nous portal anthropic wire 2026-07-27 11:53:48 -04:00
test_proactive_prune_loop_wiring.py
test_provider_attribution_headers.py fix(xai): send Hermes-Agent User-Agent on chat/completions 2026-07-27 17:47:28 -07:00
test_provider_fallback.py nous portal anthropic wire 2026-07-27 11:53:48 -04:00
test_provider_parity.py
test_real_interrupt_subagent.py test(delegate): model socket-abort interrupt for the inline child API path 2026-07-26 20:37:51 -07:00
test_redirect_stdout_issue.py
test_repair_tool_call_arguments.py
test_repair_tool_call_name.py
test_request_client_reuse_abort_races.py perf(agent): reuse the per-request OpenAI wire client across sequential LLM calls 2026-07-28 19:06:59 +05:30
test_retry_status_buffer.py
test_review_prompt_class_first.py
test_run_agent.py refactor: single owner for empty-content wire repair (class fix) 2026-07-27 20:27:56 -07:00
test_run_agent_codex_responses.py test: update credential-refresh tests for retire-not-close contract 2026-07-24 16:04:48 -07:00
test_run_agent_multimodal_prologue.py
test_sequential_chats_live.py
test_session_id_env.py
test_session_meta_filtering.py
test_session_reset_fix.py
test_session_source.py
test_steer.py fix(agent): keep interrupt-checkpoint scaffolding out of the steered transcript 2026-07-28 01:05:02 -05:00
test_stream_drop_logging.py
test_stream_interrupt_retry.py
test_stream_single_writer_65991.py Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
test_stream_stale_breaker_reset.py
test_stream_stale_circuit_breaker.py
test_streaming.py refactor: single owner for empty-content wire repair (class fix) 2026-07-27 20:27:56 -07:00
test_streaming_tool_call_repair.py
test_strict_api_validation.py
test_strip_reasoning_tags_cli.py
test_summarize_api_error.py
test_switch_model_context.py
test_switch_model_fallback_prune.py
test_switch_model_pool_reload_52727.py
test_switch_model_reapplies_headers.py
test_switch_model_reasoning_override.py
test_switch_model_rollback.py
test_switch_model_stale_base_url.py
test_thinking_only_sanitizer.py
test_thinking_sig_recovery_persistence.py
test_tls_fd_recycle_corruption.py test(agent): cover mount-pool interrupt abort and zero-socket warning 2026-07-28 18:07:44 +05:30
test_token_persistence_non_cli.py perf(state): apply per-call token accounting on a background single-writer queue 2026-07-28 18:47:54 +05:30
test_tool_arg_coercion.py
test_tool_batch_segmentation.py
test_tool_call_args_sanitizer.py
test_tool_call_guardrail_runtime.py Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
test_tool_call_incremental_persistence.py fix(session): persist tool activity before projection 2026-07-28 00:14:19 +05:30
test_tool_executor_contextvar_propagation.py
test_tool_name_db_persistence.py
test_turn_completion_explainer.py fix: follow-ups for salvaged PR #72425 2026-07-28 00:14:19 +05:30
test_unicode_ascii_codec.py
test_verification_continuation_budget.py
test_vision_aware_preprocessing.py
test_vision_tool_messages.py
test_wait_state_visibility.py