hermes-bsd/tests/agent
fesalfayed 64628ea89b fix(anthropic): demote dead thinking signature when orphan-strip mutates the latest turn
Extended-thinking Claude models (4.6+, e.g. Opus 4.8) emit a signed `thinking`
block on assistant turns that also carry parallel `tool_use` blocks. Anthropic
signs that block against the full, original turn content.

When a parallel tool batch is interrupted before every `tool_result` returns,
`_strip_orphaned_tool_blocks` removes the unanswered `tool_use` on replay — which
mutates the turn. The latest-assistant branch of `_manage_thinking_signatures`
then replays the now-stale signed thinking block verbatim, and Anthropic rejects
the request with a non-retryable HTTP 400:

    messages.N.content.M: `thinking` or `redacted_thinking` blocks in the latest
    assistant message cannot be modified. These blocks must remain as they were
    in the original response.

Because the poisoned turn is rebuilt from the persisted store every turn, the
gateway crash-loops with no self-recovery (a soft session reset does not clear
it). The drifting content index in the error is the changing count of stripped
`tool_use` blocks across rebuilds.

Fix: when orphan-stripping removes a `tool_use` from a turn that also holds a
thinking/redacted_thinking block, flag the turn. `_manage_thinking_signatures`
then demotes every thinking block on that latest turn to a plain text block
(preserving the reasoning text) instead of replaying a signature that can no
longer validate. An intact turn is unaffected — its signed thinking is still
replayed verbatim. The internal flag is stripped before the payload is sent.

Adds two regression tests:
- demotion when an orphaned parallel tool_use is stripped
- control: signed thinking preserved verbatim when nothing is stripped
2026-05-31 06:14:34 -07:00
..
lsp fix(lsp): detect Windows wrapper binaries in installer probes 2026-05-30 02:08:36 -07:00
transports chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
__init__.py
test_anthropic_adapter.py fix(anthropic): demote dead thinking signature when orphan-strip mutates the latest turn 2026-05-31 06:14:34 -07:00
test_anthropic_keychain.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_anthropic_mcp_prefix_strip.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_anthropic_oauth_pkce.py fix(auth): don't launch a text-mode browser inside the terminal for OAuth (#34479) 2026-05-29 01:23:06 -07:00
test_arcee_trinity_overrides.py
test_async_utils.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_auxiliary_client.py fix(auxiliary): stop capping output with max_tokens by default (#34530) (#34845) 2026-05-29 17:24:30 -07:00
test_auxiliary_client_anthropic_custom.py
test_auxiliary_client_azure_foundry.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_auxiliary_client_xai_oauth_recovery.py fix(auxiliary): detect xAI OAuth 403 bad-credentials as auth error 2026-05-29 00:28:02 -07:00
test_auxiliary_config_bridge.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_auxiliary_main_first.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_auxiliary_named_custom_providers.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_auxiliary_transport_autodetect.py
test_azure_identity_adapter.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_bedrock_1m_context.py
test_bedrock_adapter.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_bedrock_integration.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_codex_cloudflare_headers.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_codex_responses_adapter.py feat(prompt): universal task-completion guidance + local Python toolchain probe (#34340) 2026-05-28 22:26:09 -07:00
test_codex_ttfb_watchdog.py fix(codex): relax no-byte TTFB watchdog default from 12s to 120s 2026-05-29 02:02:25 -07:00
test_compress_focus.py
test_compression_concurrent_fork.py fix(compression): fail open when lock subsystem is missing (version skew) (#34475) 2026-05-29 01:32:32 -07:00
test_compressor_historical_media.py
test_compressor_image_tokens.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_context_compressor.py fix(compression): avoid repeat preflight compaction from rough estimates 2026-05-29 19:05:03 -07:00
test_context_compressor_summary_continuity.py test: cover ci-unblocker production regressions 2026-05-27 22:14:53 -07:00
test_context_engine.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_context_engine_host_contract.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_context_references.py
test_copilot_acp_client.py
test_copilot_acp_deprecation.py
test_credential_pool.py fix(auth): address Nous JWT fallback review 2026-05-29 02:24:48 -07:00
test_credential_pool_routing.py
test_crossloop_client_cache.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_curator.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_curator_activity.py
test_curator_backup.py
test_curator_classification.py
test_curator_reports.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_custom_provider_extra_body.py
test_deepseek_anthropic_thinking.py
test_direct_provider_url_detection.py
test_display.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_display_emoji.py
test_display_todo_progress.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_display_tool_failure.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_error_classifier.py fix(agent): fallback immediately on provider content-policy blocks (#33883) 2026-05-28 07:28:24 -07:00
test_external_skills.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_external_skills_dirs_cache.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_file_safety.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_file_safety_credentials.py
test_file_safety_cross_profile.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_gemini_cloudcode.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_gemini_fast_fallback.py
test_gemini_free_tier_gate.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_gemini_native_adapter.py
test_gemini_schema.py
test_i18n.py
test_image_gen_registry.py
test_image_routing.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_insights.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_jiter_preload.py fix(agent): preload jiter native parser 2026-05-28 00:20:11 -07:00
test_kimi_coding_anthropic_thinking.py
test_last_total_tokens.py
test_local_stream_timeout.py
test_markdown_tables.py
test_memory_provider.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_memory_session_switch.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_memory_user_id.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_minimax_auxiliary_url.py
test_minimax_provider.py
test_model_metadata.py test: remove low-value model-catalog mirror tests 2026-05-29 23:45:05 -07:00
test_model_metadata_local_ctx.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_model_metadata_ssl.py
test_models_dev.py test: remove low-value model-catalog mirror tests 2026-05-29 23:45:05 -07:00
test_moonshot_schema.py
test_non_stream_stale_timeout.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_nous_oauth_401_guidance.py
test_nous_rate_guard.py
test_onboarding.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_openrouter_response_cache.py
test_plugin_llm.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_portal_tags.py
test_prompt_builder.py feat(video_gen): wire Nous subscription override into hermes tools UX 2026-05-29 22:26:24 +05:30
test_prompt_caching.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_proxy_and_url_validation.py
test_rate_limit_tracker.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_redact.py test(redact): assert Discord mentions pass through unchanged 2026-05-30 20:48:41 -07:00
test_resume_stale_active_task.py fix(compressor): strip stale handoff prefix on resume; reconcile #26290+#32787 (#35344) 2026-05-30 07:29:21 -07:00
test_save_url_image.py
test_set_runtime_main_custom_provider.py test(auxiliary): e2e routing assertions for custom-provider aux resolution 2026-05-30 02:38:59 -07:00
test_shell_hooks.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_shell_hooks_consent.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_skill_bundles.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_skill_commands.py
test_skill_commands_reload.py
test_skill_utils.py
test_streaming_context_scrubber.py
test_subagent_progress.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_subagent_stop_hook.py
test_subdirectory_hints.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_summary_prefix_semantics.py fix(compression): drop conflicting 'resume Active Task' directive in summary prefix 2026-05-30 07:29:21 -07:00
test_system_prompt_restore.py
test_think_scrubber.py
test_title_generator.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_tool_dispatch_helpers.py
test_tool_guardrails.py
test_tool_result_classification.py
test_transcription_registry.py
test_tts_registry.py
test_unsupported_parameter_retry.py
test_unsupported_temperature_retry.py fix(auxiliary): stop capping output with max_tokens by default (#34530) (#34845) 2026-05-29 17:24:30 -07:00
test_usage_pricing.py remove Vercel AI Gateway and Vercel Sandbox (#33067) 2026-05-27 00:43:32 -07:00
test_video_gen_registry.py
test_vision_resolved_args.py
test_vision_routing_31179.py