hermes-bsd/tests/agent
teknium1 9b5dae17a5 feat(context-engine): host contract for external context engines
Condenses the substance of PRs #16453, #17453, #16451, #17600, and #13373
into a minimal generic host contract that external context engine plugins
(e.g. hermes-lcm) need to integrate cleanly. Drops scaffolding that
duplicated existing infrastructure or had marginal value.

Five concrete changes:

1. `_transition_context_engine_session()` on AIAgent — generic lifecycle
   helper that fires on_session_end → on_session_reset → on_session_start
   → optional carry_over_new_session_context. Engines implement only the
   hooks they need; missing hooks are skipped. Built-in compressor keeps
   its existing reset-only behavior because callers default to no
   metadata. `reset_session_state()` now optionally accepts
   previous_messages / old_session_id / carry_over_context and delegates
   to the transition helper when provided. (#16453)

2. `conversation_id` passed to `on_session_start()` — both the
   agent-init call site and the compression-boundary call site now
   forward `self._gateway_session_key` so plugin engines have a stable
   conversation identity that survives session_id rotation (compression
   splits, /new, resume). The key already existed on AIAgent; it just
   wasn't reaching engines. (#16453)

3. Canonical cache buckets forwarded to engines — the usage dict passed
   to `update_from_response()` now includes input_tokens, output_tokens,
   cache_read_tokens, cache_write_tokens, and reasoning_tokens on top of
   the legacy prompt/completion/total keys. Engines can make decisions on
   cache-hit ratios and reasoning costs instead of only aggregates. ABC
   docstring updated. (#17453)

4. Plugin-registered context engines visible in the picker —
   `_discover_context_engines()` in plugins_cmd.py now also includes
   engines registered via `ctx.register_context_engine()` from plugin
   manifests, deduplicating by name so repo-shipped descriptions win on
   collision. (#16451)

5. `_EngineCollector.register_command()` — context engines using the
   standard `register(ctx)` pattern can now expose slash commands (e.g.
   `/lcm`). Routes to the global plugin command registry with the same
   conflict-rejection policy regular plugins use (no shadowing built-ins,
   no clobbering other plugins). Previously these calls hit a no-op and
   the slash commands silently never appeared. (#17600)

Dropped from the original 5 PRs:

- Compression boundary signal (`boundary_reason="compression"`) from
  #16453 — already on main at `agent/conversation_compression.py:412-424`,
  landed via the bg-review extraction.

- `discover_plugins()` before fallback in run_agent.py from #16451 —
  redundant: `get_plugin_context_engine()` already routes through
  `_ensure_plugins_discovered()` which is idempotent.

- Runtime identity diagnostics method + helpers from #13373 (+251 LOC) —
  operators can already read engine state via `engine.get_status()`;
  the diagnostics view added marginal value relative to its surface area.

- The 553-LOC slash-command machinery from #17600 — replaced with a
  20-LOC `register_command` method on the collector that reuses the
  existing plugin command registry instead of building a parallel one.

Net: ~215 LOC of host-contract changes + 282 LOC of focused tests, vs
~1,176 LOC across the original 5 PRs.

Co-authored-by: Tosko4 <1294707+Tosko4@users.noreply.github.com>

Closes #16453.
Closes #17453.
Closes #16451.
Closes #17600.
Closes #13373.
Related: stephenschoettler/hermes-lcm#68.
2026-05-28 01:45:30 -07:00
..
lsp fix(lint): skip per-file shell linter when LSP will handle the file (#29054) 2026-05-20 01:46:40 -05:00
transports fix(xai-oauth): gate slash-enum strip on model name + add regression tests (#28490) 2026-05-27 05:25:38 -07:00
__init__.py
test_anthropic_adapter.py fix(security): close TOCTOU window when saving Claude Code OAuth credentials (#21152) 2026-05-24 17:45:12 -07:00
test_anthropic_keychain.py
test_anthropic_mcp_prefix_strip.py fix(anthropic): skip mcp_ prefix on outgoing tool schemas when already prefixed 2026-05-24 15:27:45 -07:00
test_anthropic_oauth_pkce.py test(security): regression guard for OAuth PKCE state/verifier separation 2026-05-16 02:38:02 -07:00
test_arcee_trinity_overrides.py
test_async_utils.py fix(async): close unscheduled coroutines in all threadsafe bridges (#26584) 2026-05-15 14:00:01 -07:00
test_auxiliary_client.py feat(auth) normalise the way in which we check whether a user has free/paid access to nous portal so we can expose behaviour and error messages accordingly. 2026-05-28 00:19:31 -07:00
test_auxiliary_client_anthropic_custom.py
test_auxiliary_client_azure_foundry.py feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
test_auxiliary_config_bridge.py feat(plugins): add register_auxiliary_task() to PluginContext API 2026-05-23 17:49:47 -07:00
test_auxiliary_main_first.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_auxiliary_named_custom_providers.py
test_auxiliary_transport_autodetect.py
test_azure_identity_adapter.py feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
test_bedrock_1m_context.py feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
test_bedrock_adapter.py test(ci): stabilize shared optional dependency baselines 2026-05-13 17:32:22 -07:00
test_bedrock_integration.py test(ci): stabilize shared optional dependency baselines 2026-05-13 17:32:22 -07:00
test_codex_cloudflare_headers.py
test_codex_responses_adapter.py fix(codex): drop transient rs_tmp reasoning replay state 2026-05-27 02:25:59 -07:00
test_codex_ttfb_watchdog.py fix(agent): tolerate large codex stream prefill 2026-05-27 11:19:55 -07:00
test_compress_focus.py
test_compressor_historical_media.py Port from Kilo-Org/kilocode#9434: strip historical media after compression (#27189) 2026-05-16 17:18:25 -07:00
test_compressor_image_tokens.py
test_context_compressor.py test: keep tirith checks hermetic 2026-05-23 02:20:14 -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
test_context_engine_host_contract.py feat(context-engine): host contract for external context engines 2026-05-28 01:45:30 -07:00
test_context_references.py
test_copilot_acp_client.py
test_copilot_acp_deprecation.py fix(copilot-acp): tighten deprecation detection + sharpen GitHub Models 413 hint 2026-05-16 02:24:48 -07:00
test_credential_pool.py fix(anthropic): API-key path skips OAuth autodiscovery + prunes stale entries 2026-05-25 17:41:40 -07:00
test_credential_pool_routing.py
test_crossloop_client_cache.py
test_curator.py fix: preserve skill packages during curator consolidation 2026-05-27 13:39:58 -07:00
test_curator_activity.py
test_curator_backup.py
test_curator_classification.py
test_curator_reports.py
test_custom_provider_extra_body.py fix(custom): pass custom provider extra body 2026-05-21 07:48:53 -07:00
test_deepseek_anthropic_thinking.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_direct_provider_url_detection.py
test_display.py fix: classify landed file mutations with diagnostics 2026-05-13 06:46:23 -07:00
test_display_emoji.py
test_display_todo_progress.py feat(cli): show todo progress as done/total fraction 2026-05-23 21:03:51 -07:00
test_display_tool_failure.py test(display): cover failure-suffix rendering + update scrollback test 2026-05-23 21:03:51 -07:00
test_error_classifier.py feat(auth) normalise the way in which we check whether a user has free/paid access to nous portal so we can expose behaviour and error messages accordingly. 2026-05-28 00:19:31 -07:00
test_external_skills.py
test_external_skills_dirs_cache.py
test_file_safety.py fix(security): block read_file on project-local .env files 2026-05-25 03:40:47 -07:00
test_file_safety_credentials.py fix(security): block read_file on project-local .env files 2026-05-25 03:40:47 -07:00
test_file_safety_cross_profile.py fix(profiles): cross-profile soft guard on file-write tools + system-prompt hint (#31290) 2026-05-24 00:38:17 -07:00
test_gemini_cloudcode.py fix(agent/gemini-cloudcode): seed delta defaults for reasoning-only stream chunks 2026-05-14 08:03:56 -07:00
test_gemini_fast_fallback.py fix: wrap _pool_may_recover_from_rate_limit call through run_agent namespace 2026-05-18 20:04:57 -07:00
test_gemini_free_tier_gate.py
test_gemini_native_adapter.py
test_gemini_schema.py
test_i18n.py
test_image_gen_registry.py
test_image_routing.py fix(agent): consult supports_vision override in auto-mode routing 2026-05-20 23:27:10 -07:00
test_insights.py
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 fix(compressor): ABC compliance — total_tokens, api_mode, logger consistency 2026-05-23 17:38:19 -07:00
test_local_stream_timeout.py
test_markdown_tables.py fix(cli): vertical fallback for markdown tables wider than terminal (#23948) 2026-05-11 16:49:13 -07:00
test_memory_provider.py fix(agent): widen toolset gate to context engine tools (#5544 sibling) 2026-05-21 23:18:37 -07:00
test_memory_session_switch.py
test_memory_user_id.py
test_minimax_auxiliary_url.py
test_minimax_provider.py
test_model_metadata.py chore(models): drop retired grok-4-1-fast from metadata, tests, docs 2026-05-25 14:51:43 -07:00
test_model_metadata_local_ctx.py
test_model_metadata_ssl.py
test_models_dev.py remove Vercel AI Gateway and Vercel Sandbox (#33067) 2026-05-27 00:43:32 -07:00
test_moonshot_schema.py fix(moonshot): strip $ref siblings and collapse tuple items in tool schemas (#27104) 2026-05-16 13:02:19 -07:00
test_non_stream_stale_timeout.py fix(codex): size and propagate timeouts for Responses-API requests; lower stale defaults 2026-05-25 01:47:55 -07:00
test_nous_oauth_401_guidance.py feat(errors): actionable guidance for Nous OAuth 401s (#32082) 2026-05-25 06:06:51 -07:00
test_nous_rate_guard.py
test_onboarding.py
test_openrouter_response_cache.py
test_plugin_llm.py
test_portal_tags.py feat(nous): unified client=hermes-client-v<version> tag on every Portal request (#24779) 2026-05-12 20:49:20 -07:00
test_prompt_builder.py remove Vercel AI Gateway and Vercel Sandbox (#33067) 2026-05-27 00:43:32 -07:00
test_prompt_caching.py fix(cache): kill long-lived prefix layout — system prompt is now byte-static within a session (#24778) 2026-05-12 20:46:04 -07:00
test_proxy_and_url_validation.py
test_rate_limit_tracker.py
test_redact.py fix(debug): redact BlueBubbles webhook secrets 2026-05-24 15:43:48 -07:00
test_save_url_image.py fix(image_gen): cache xAI ephemeral URL responses to disk (#26942) (#31759) 2026-05-24 18:10:47 -07:00
test_shell_hooks.py fix(security): restore type safety and extract constant in shell hook block handler 2026-05-17 02:31:18 -07:00
test_shell_hooks_consent.py
test_skill_bundles.py feat(skills): add skill bundles — alias /<name> loads multiple skills (#28373) 2026-05-18 21:38:05 -07:00
test_skill_commands.py test: use subprocesses for each test file (#29016) 2026-05-21 16:40:04 +05:30
test_skill_commands_reload.py
test_skill_utils.py fix(skills): load Linux-tagged skills on Termux (android sys.platform) 2026-05-21 19:08:38 -07:00
test_streaming_context_scrubber.py 🐛 fix(memory): require newline after context tag 2026-05-18 10:53:08 -07:00
test_subagent_progress.py
test_subagent_stop_hook.py
test_subdirectory_hints.py fix(subdirectory_hints): prevent loading AGENTS.md outside workspace 2026-05-25 23:17:33 -07:00
test_system_prompt_restore.py perf(prompt-cache): date-only timestamp + loud gateway-DB roundtrip logging 2026-05-17 23:20:37 -07:00
test_think_scrubber.py
test_title_generator.py
test_tool_dispatch_helpers.py feat(security): promptware defense — shared threat patterns + memory load-time scan + tool-result delimiters (#32269) 2026-05-25 14:52:24 -07:00
test_tool_guardrails.py fix: add recovery hints to loop guard warnings 2026-05-19 00:12:12 -07:00
test_tool_result_classification.py fix: classify landed file mutations with diagnostics 2026-05-13 06:46:23 -07:00
test_transcription_registry.py feat(stt): add register_transcription_provider() plugin hook 2026-05-25 01:41:19 -07:00
test_tts_registry.py feat(tts): add register_tts_provider() plugin hook (closes #30398) 2026-05-24 18:04:54 -07:00
test_unsupported_parameter_retry.py
test_unsupported_temperature_retry.py
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 feat(video_gen): unified video_generate tool with pluggable provider backends (#25126) 2026-05-13 16:39:41 -07:00
test_vision_resolved_args.py
test_vision_routing_31179.py fix(vision): route auxiliary.vision.provider=openai to api.openai.com, skip text-only main (#31452) 2026-05-24 15:01:28 -07:00