KrustyPlanet/hermes-agent
6
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
hermes-agent/tests/agent
History
sasquatch9818 020d263ef6 fix(agent): defang untrusted-tool-result delimiter against tag injection 
`_maybe_wrap_untrusted` is the architectural defense against indirect
prompt injection. It wraps attacker-controllable tool output
(web_extract, web_search, browser_*, mcp_*) in
`<untrusted_tool_result>...</untrusted_tool_result>` so the model treats
it as data. The content was interpolated verbatim, so the boundary was
forgeable.

Two holes. A poisoned page that embeds `</untrusted_tool_result>` closes
the block early — everything after it reads as trusted instructions. And
the `startswith("<untrusted_tool_result")` re-entrancy guard returned
content that merely started with the opening tag completely unwrapped, so
an attacker just prefixed the tag to drop all data framing.

Fix neutralizes any embedded delimiter token (case-insensitive) before
interpolation and drops the forgeable fast-path, so content is always
sealed in exactly one well-formed block. Re-wrapping an already-wrapped
forward is harmless — it stays framed as data.

## What does this PR do?

Closes an indirect prompt-injection bypass in the untrusted-tool-result
wrapper. Attacker content can no longer break out of, or forge, the
trust boundary.

## Related Issue

N/A

## Type of Change

- [x] 🔒 Security fix

## Changes Made

- `agent/tool_dispatch_helpers.py`: add `_neutralize_delimiters` (case-insensitive defang of the `untrusted_tool_result` token); `_maybe_wrap_untrusted` now always neutralizes then wraps, and the forgeable `startswith` re-entrancy guard is removed.
- `tests/agent/test_tool_dispatch_helpers.py`: replace the double-wrap test (it encoded the bypass) with regression tests for embedded closing tag, leading opening tag, and a cased closing tag.

## How to Test

1. `scripts/run_tests.sh tests/agent/test_tool_dispatch_helpers.py` — 29 pass.
2. Embedded `</untrusted_tool_result>` mid-content: real closing delimiter appears once, at the end; payload trapped inside.
3. Content starting with the opening tag: data framing is applied, not skipped.

## Checklist

### Code

- [x] I've read the Contributing Guide
- [x] My commit messages follow Conventional Commits
- [x] I searched for existing PRs to make sure this isn't a duplicate
- [x] My PR contains only changes related to this fix
- [x] I've run the affected tests and they pass
- [x] I've added tests for my changes
- [x] I've tested on my platform: macOS 15 (Darwin 25.5)

### Documentation & Housekeeping

- [x] I've updated relevant documentation (docstrings) — or N/A
- [x] cli-config.yaml.example — N/A
- [x] CONTRIBUTING.md / AGENTS.md — N/A
- [x] Cross-platform impact — N/A (pure-Python, stdlib `re`)
- [x] Tool descriptions/schemas — N/A
2026-07-01 01:54:45 -07:00
..
lsp feat(lsp): add PowerShellEditorServices language server (#55930) 2026-06-30 16:22:18 -07:00
transports fix(cache): content-address prompt_cache_key so recurring cron jobs reuse the warm prefix (#52295) 2026-06-24 21:46:30 -07:00
__init__.py
test_anthropic_adapter.py fix(anthropic): stop SDK auto-retry double-firing and raise Retry-After cap to 600s 2026-06-27 19:23:15 -07:00
test_anthropic_billing_guidance.py feat(classifier): Anthropic-specific guidance for subscription exhaustion 2026-07-01 01:36:34 -07:00
test_anthropic_keychain.py fix(anthropic): adopt Claude Code's already-refreshed token before racing refresh 2026-06-27 19:14:43 -07:00
test_anthropic_kwargs_sanitize.py fix(anthropic): strip Responses-only kwargs before Messages SDK call (#31673) (#42155) 2026-06-08 09:36:38 -07:00
test_anthropic_mcp_prefix_strip.py fix(anthropic): also normalize MCP-server tool names to mcp__ on OAuth wire 2026-06-17 13:20:29 +05:30
test_anthropic_oauth_pkce.py test(anthropic-oauth): cover login token-endpoint host + fallback 2026-06-23 23:59:40 -07:00
test_anthropic_output_field_leak.py fix(anthropic): strip output-only SDK fields from replayed content blocks 2026-06-10 20:45:16 -07:00
test_anthropic_thinking_block_order.py refactor: keep anthropic_content_blocks in-memory only (no state.db column) 2026-06-10 20:45:16 -07:00
test_arcee_trinity_overrides.py feat(compression): raise compaction trigger to 85% for gpt-5.5 on Codex OAuth (#40957) 2026-06-07 01:40:50 -07:00
test_async_utils.py fix(ci): rip out some xdist legacy stuff... how did these ever work?? 2026-06-26 19:15:18 -07:00
test_auxiliary_client.py fix(runtime): honor NOUS_INFERENCE_BASE_URL across pool/explicit/aux paths 2026-07-01 01:52:06 -07:00
test_auxiliary_client_anthropic_custom.py fix(anthropic): complete third-party Anthropic-compatible provider support (#12846) 2026-04-19 22:43:09 -07:00
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_base_url_host_validation_52608.py fix(auxiliary): gate Anthropic base_url override on Anthropic-compatible host (#52608) 2026-06-26 11:21:05 +05:30
test_auxiliary_client_proxy_env.py test(auxiliary): cover env-only proxy policy for auxiliary clients (#53702) 2026-06-27 21:22:49 -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 fix(vision): cap vision_analyze fan-out concurrency process-wide 2026-06-29 01:27:10 -07:00
test_auxiliary_main_first.py fix(moa): resolve auxiliary tasks to the aggregator, not the preset name (#53827) 2026-06-27 14:21:26 -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 fix(providers): support anthropic proxy v1 endpoints 2026-06-14 02:09:16 -07:00
test_auxiliary_user_default_headers.py fix(aux): honor model.default_headers on auxiliary client too (#40033) 2026-06-07 02:02:40 -07:00
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 feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
test_bedrock_adapter.py fix(bedrock): check boto3 version >= 1.34.59 before using converse_stream 2026-06-15 05:25:17 -07:00
test_bedrock_integration.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_billing_view.py feat(billing): /billing terminal billing — interactive TUI + CLI client (#45449) 2026-06-19 01:53:32 +05:30
test_cascading_interrupt_6600.py fix(agent): don't retry interrupt-induced transport errors (cascading-interrupt hang) 2026-06-08 02:19:13 -07:00
test_chat_completion_helpers_provider_sort.py fix(agent): validate OpenRouter provider sort before request dispatch 2026-06-27 11:43:08 -07:00
test_close_interrupted_tool_sequence.py fix(agent): close tool-call sequence on all interrupt aborts, not just finalize_turn 2026-06-25 12:24:34 -05:00
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 fix(xai): OAuth Responses native web_search, incomplete guard, grok-composer context 2026-06-17 17:33:32 -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_coding_context.py feat(agent): add configurable coding_instructions 2026-06-30 00:59:59 -05:00
test_compress_focus.py refactor(agent): drop unused tail_start param from _derive_auto_focus_topic 2026-06-11 23:03:52 -07:00
test_compressed_summary_metadata.py test: compressed-summary metadata flag set in-process, stripped on wire 2026-06-12 16:47:15 -07:00
test_compression_concurrent_fork.py test(compression): tolerate safe contention rollback in concurrent-fork test (#55597) 2026-06-30 04:22:47 -07:00
test_compression_count_warning_36908.py fix(agent): route repeated-compression warning through _emit_status (#36908) 2026-06-21 11:34:47 -07:00
test_compression_interrupt_protection.py fix(compression): protect the summary call from mid-flight interrupts 2026-06-20 21:32:30 -07:00
test_compression_logging_session_context.py test(compression): pin rotation-fallback tests to in_place=False ahead of default flip 2026-06-25 12:56:05 -07:00
test_compression_progress.py fix(agent): align preflight token-progress floor to 5% (#23767, #39548) 2026-06-22 15:51:52 +05:30
test_compression_rotation_state.py test(compression): pin rotation-fallback tests to in_place=False ahead of default flip 2026-06-25 12:56:05 -07:00
test_compressor_assistant_tail_anchor.py fix(compressor): skip context-summary markers as last-user tail anchor 2026-07-01 01:20:02 -07:00
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 chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_compressor_media_stripping.py fix(agent): strip MEDIA directives from compressor summarizer input (#14665) 2026-06-12 01:14:28 -07:00
test_compressor_tool_call_budget.py fix(compressor): count tool_call envelope in tail-budget token estimate (#28053) 2026-06-22 16:26:56 +05:30
test_context_breakdown.py feat(desktop): add context usage breakdown popover 2026-06-29 09:18:10 -04:00
test_context_compressor.py test(compressor): tidy blank-line spacing + assert placeholder never overwrites text 2026-07-01 14:24:41 +05:30
test_context_compressor_cross_session_guard.py fix(compression): guard against cross-session stale _previous_summary contamination 2026-06-07 22:09:45 -07:00
test_context_compressor_summary_continuity.py test: cover ci-unblocker production regressions 2026-05-27 22:14:53 -07:00
test_context_compressor_temporal_anchoring.py fix(agent): frame compaction handoff sections as historical context 2026-06-11 13:57:13 -07:00
test_context_engine.py fix(context): clamp -1 post-compression sentinel in sibling status paths 2026-07-01 13:36:50 +05:30
test_context_engine_host_contract.py fix(agent): keep cooldown state on the active session (#54465) 2026-06-30 13:36:29 +05:30
test_context_references.py fix(agent): make a binary @file: reference actionable instead of a dead end 2026-06-09 19:16:46 -05:00
test_context_refs_concurrent.py perf(context-refs): expand @-references concurrently 2026-06-30 00:19:49 -07:00
test_copilot_acp_client.py fix(agent): stream copilot ACP chat completions 2026-06-28 22:52:51 -07:00
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(pool): sync anthropic entry on access_token change, not just refresh_token 2026-06-30 03:45:12 -07:00
test_credential_pool_oauth_writethrough.py fix(auth): write rotated Codex/xAI pool grant through to global root (#48415) (#52760) 2026-06-25 19:14:06 -07:00
test_credential_pool_routing.py refactor: remove smart_model_routing feature (#12732) 2026-04-19 18:12:55 -07:00
test_credits_cold_start.py fix(credits): suppress usage gauge when top-up funds exist + add display.credits_notices toggle (#44716) 2026-06-12 01:06:46 -07:00
test_credits_fixture_snapshot.py feat(credits): usage-aware credits — in-session notices, /usage view, dev readout (#40011) 2026-06-06 13:18:18 +05:30
test_credits_policy.py feat(billing): /credits command — balance + portal top-up handoff (#44776) 2026-06-12 08:51:10 +00:00
test_credits_tracker.py feat(credits): usage-aware credits — in-session notices, /usage view, dev readout (#40011) 2026-06-06 13:18:18 +05:30
test_credits_view.py feat(billing): /credits command — balance + portal top-up handoff (#44776) 2026-06-12 08:51:10 +00:00
test_crossloop_client_cache.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_curator.py fix(curator): never archive cron-referenced skills + floor use=0 pruning (#54443) 2026-06-28 15:10:21 -07:00
test_curator_activity.py fix: use skill activity in curator status 2026-04-30 10:31:47 -07:00
test_curator_backup.py fix(curator): stop the rollback safety snapshot from pruning its target 2026-06-17 05:40:05 -07:00
test_curator_classification.py feat(curator): hint at hermes curator pin in the rename block (#23212) 2026-05-10 06:44:53 -07:00
test_curator_reports.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_custom_pool_mismatch_guard.py fix(agent): don't treat custom:<name> pools as cross-provider mismatch (#45289) 2026-06-13 02:01:09 -07:00
test_custom_provider_extra_body.py fix: handle named custom providers and Z.AI overload retries 2026-06-25 00:17:17 -07:00
test_custom_providers_vision.py fix(vision): honor custom_providers per-model supports_vision (#41036) 2026-06-07 21:50:57 -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 fix: restrict provider URL detection to exact hostname matches 2026-04-20 22:14:29 -07:00
test_display.py feat(display): friendly human-phrased tool labels for built-in tools (#55166) 2026-06-29 20:31:17 -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_empty_tool_name_loop_dampening.py fix(agent): dampen empty-name phantom tool-call loop (#47967) (#48109) 2026-06-17 17:32:14 -07:00
test_error_classifier.py fix(classifier): treat Anthropic "out of extra usage" 400 as billing 2026-07-01 01:36:34 -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_failover_identity.py fix(agent): keep system-prompt model identity in sync across provider failover 2026-06-20 10:46:01 -07:00
test_file_safety.py fix(file): block credential paths from search results 2026-07-01 01:02:35 -07:00
test_file_safety_container_mirror.py fix(file-safety): extend sandbox-mirror guard to cover inner-container path (#32049) (#32407) 2026-06-02 14:03:37 +10:00
test_file_safety_credentials.py fix(file): block credential paths from search results 2026-07-01 01:02:35 -07:00
test_file_safety_cross_profile.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_file_safety_sandbox_mirror.py fix(file-safety): add sandbox-mirror soft guard for writes to per-task .hermes mirrors (#32213) 2026-06-02 11:29:24 +10:00
test_gemini_fast_fallback.py feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492) 2026-06-21 19:53:27 -07:00
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 Merge consecutive same-role contents for native Gemini 2026-06-30 11:51:22 -07:00
test_gemini_schema.py fix(gemini): drop integer/number/boolean enums from tool schemas (#15082) 2026-04-24 03:40:00 -07:00
test_i18n.py fix(packaging): ship locales/ i18n catalogs in wheel, sdist, and Nix (#38383) 2026-06-03 12:00:27 -07:00
test_image_gen_registry.py feat(plugins): pluggable image_gen backends + OpenAI provider (#13799) 2026-04-21 21:30:10 -07:00
test_image_routing.py test(vision): cover Ollama /api/show vision capability routing (#54511) 2026-06-28 22:52:59 -07:00
test_insights.py refactor(insights): drop dead pricing/duration wrappers, call usage_pricing directly (#40618) 2026-06-07 18:33:20 -07:00
test_intent_ack_continuation.py fix(agent): flatten multi-part user_message in codex intermediate-ack detector 2026-06-30 03:20:11 -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 fix(anthropic): broaden Kimi thinking-suppression to custom endpoints (#17455) 2026-04-29 06:35:42 -07:00
test_last_total_tokens.py fix(compressor): ABC compliance — total_tokens, api_mode, logger consistency 2026-05-23 17:38:19 -07:00
test_learn_prompt.py fix(learn): honor requirements mixed with sources in /learn requests (#55956) 2026-06-30 16:56:01 -07:00
test_learning_graph.py fix(desktop): scope memory graph cache by profile 2026-06-30 03:44:41 -05:00
test_learning_graph_render.py fix(journey): swap skill/memory inks so drillable rows read as clickable 2026-06-30 11:54:16 -05:00
test_learning_mutations.py test(journey): lock memory write format-parity with the memory tool 2026-06-30 15:16:25 -05:00
test_local_stream_timeout.py fix(local): recognize unqualified hostnames as local endpoints (#9248) 2026-06-05 10:18:10 +10:00
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_async_sync.py fix(memory): run end-of-turn sync off the turn thread (#41945) 2026-06-08 02:18:59 -07:00
test_memory_provider.py fix(agent): validate context/memory tool schemas before wrapping 2026-06-25 02:17:29 +05:30
test_memory_session_switch.py fix(memory): run end-of-turn sync off the turn thread (#41945) 2026-06-08 02:18:59 -07:00
test_memory_skill_scaffolding.py fix(memory): strip skill scaffolding for all providers, not just openviking 2026-06-16 10:37:37 -07:00
test_memory_user_id.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_memory_write_bridge.py refactor(memory): move write-mirror gating behind MemoryManager interface 2026-06-22 07:00:42 -07:00
test_message_content.py fix(openviking): preserve structured sync attribution 2026-06-19 15:23:41 +08:00
test_minimax_auxiliary_url.py
test_minimax_provider.py polish(minimax): address Copilot review comments on M3 default-aux fix 2026-06-04 05:53:35 -07:00
test_moa_slot_api_mode.py fix(moa): propagate api_mode from slot runtime to call_llm 2026-06-30 03:39:50 -07:00
test_moa_switch_api_mode.py fix(moa): pin chat_completions on live switch to a MoA preset 2026-06-30 03:39:50 -07:00
test_model_extra_type_guard.py test+chore: real-path regression test for #15157 model_extra guard + AUTHOR_MAP 2026-06-30 03:27:12 -07:00
test_model_metadata.py fix(moa): resolve context window from the aggregator, not the 256K default (#53780) 2026-06-27 12:08:09 -07:00
test_model_metadata_local_ctx.py fix: normalize lmstudio base urls 2026-06-28 20:46:44 -07:00
test_model_metadata_ssl.py fix(auth): honor SSL CA env vars across httpx + requests callsites 2026-04-24 03:00:33 -07:00
test_models_dev.py test: remove low-value model-catalog mirror tests 2026-05-29 23:45:05 -07:00
test_moonshot_schema.py fix(moonshot): handle union type arrays in tool schemas 2026-06-13 05:51:41 -07:00
test_non_stream_stale_timeout.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_nous_credits_gauge.py feat(credits): usage-aware credits — in-session notices, /usage view, dev readout (#40011) 2026-06-06 13:18:18 +05:30
test_nous_credits_snapshot.py feat(billing): /credits command — balance + portal top-up handoff (#44776) 2026-06-12 08:51:10 +00:00
test_nous_oauth_401_guidance.py feat(cli): make hermes portal the human-readable Portal onboarding alias 2026-06-04 01:19:28 +05:30
test_nous_rate_guard.py fix(nous): don't trip cross-session rate breaker on upstream-capacity 429s (#15898) 2026-04-26 04:53:42 -07:00
test_onboarding.py feat(onboarding): opt-in structured profile-build path on first contact (#41114) 2026-06-07 08:36:48 -07:00
test_oneshot.py feat(agent): one-shot LLM helper + llm.oneshot gateway RPC (#51261) 2026-06-23 08:01:50 +00:00
test_openrouter_response_cache.py fix(openrouter): use canonical X-Title attribution header 2026-05-05 10:13:34 -07:00
test_pet_engine.py fix(pet): snap kitty frames to whole cells 2026-06-30 15:41:44 -05:00
test_pet_generate.py test(pets): make slow pet generation suite opt-in 2026-06-25 00:44:53 -05:00
test_platform_hint_overrides.py feat(prompt): configurable per-platform system-prompt hint overrides 2026-06-18 14:28:01 -07:00
test_plugin_llm.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
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_preflight_compression_gate.py fix(agent): trigger preflight compression on few-but-huge sessions (#27405) 2026-06-25 01:20:23 +05:30
test_prompt_builder.py test(agent): cover .hermes.md no-git-root cwd-only behavior 2026-06-28 20:46:32 -07:00
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 fix(agent): normalize socks:// env proxies for httpx/anthropic 2026-04-21 05:52:46 -07:00
test_rate_limit_tracker.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_reasoning_stale_timeout_floor.py test(reasoning-floor): isolate stale-timeout floor tests from config-module reload races (#54775) 2026-06-29 02:42:54 -07:00
test_redact.py refactor(redact): consolidate CDP-URL log redaction into one chokepoint 2026-07-01 13:43:58 +05:30
test_replay_cleanup.py fix(tui): sanitize replay history on WebUI/TUI session resume (#29086) (#53939) 2026-06-27 20:56:49 -07:00
test_restore_primary_pool_reselect.py fix(pool): re-select from credential pool on primary runtime restore 2026-06-27 20:04:45 -07:00
test_resume_stale_active_task.py fix(agent): strengthen compression preamble against stale task execution (#41607) 2026-06-11 13:57:13 -07:00
test_runtime_cwd.py fix(desktop): stabilize project folder sessions (#37586) 2026-06-02 20:23:09 +00:00
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_secret_scope.py feat(gateway): multiplex phase 2 — fail-closed profile credential isolation (Workstream A) 2026-06-19 07:34:15 -07:00
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 feat(agent): add pre_verify hook and verify-on-stop coding guidance 2026-06-30 00:59:29 -05:00
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: use subprocesses for each test file (#29016) 2026-05-21 16:40:04 +05:30
test_skill_commands_reload.py fix(ci): rip out some xdist legacy stuff... how did these ever work?? 2026-06-26 19:15:18 -07:00
test_skill_utils.py fix(curator): protect external skills from background curation 2026-06-25 22:03:02 -07:00
test_ssl_ca_guard.py fix(ssl): align guard docs and escape hatch 2026-06-13 21:14:32 -07:00
test_stream_read_timeout_floor.py fix(streaming): stop socket read timeout from preempting stale-stream detector (#43570) 2026-06-10 20:21:38 -05:00
test_streaming_context_scrubber.py 🐛 fix(memory): require newline after context tag 2026-05-18 10:53:08 -07:00
test_subagent_progress.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_subagent_stop_hook.py feat: shell hooks — wire shell scripts as Hermes hook callbacks 2026-04-20 20:53:51 -07:00
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(agent): freeze carveout-era SUMMARY_PREFIX for renormalization 2026-06-11 13:57:13 -07:00
test_system_prompt.py feat(tools): add project workspace tools 2026-06-25 16:40:27 -05:00
test_system_prompt_restore.py fix(desktop): keep live model switch metadata truthful 2026-06-16 09:50:17 -05:00
test_think_scrubber.py fix(agent): stateful streaming scrubber for reasoning-block leaks (#17924) (#20184) 2026-05-05 04:33:38 -07:00
test_thinking_timeout_guidance.py fix(agent): detect thinking-timeout for reasoning models and surface actionable guidance instead of misleading file-write advice 2026-06-25 19:00:48 -07:00
test_thread_scoped_output.py fix(bg-review): scope stdout/stderr silencing to the worker thread (#55966) 2026-06-30 17:28:33 -07:00
test_title_generator.py feat(titles): support language-aware title generation (#45296) 2026-06-19 17:15:52 -07:00
test_tool_call_arg_no_redaction.py fix(agent): stop redacting tool-call args in history; fix auth-header quote-eating 2026-06-28 02:44:06 -07:00
test_tool_dispatch_helpers.py fix(agent): defang untrusted-tool-result delimiter against tag injection 2026-07-01 01:54:45 -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_turn_context.py fix(agent): persist compression backoff across resume (#54465) 2026-06-30 13:36:29 +05:30
test_turn_finalizer_cleanup_guard.py fix(agent): complete final text on last turn 2026-06-22 13:57:59 -07:00
test_turn_finalizer_interrupt_alternation.py test(agent): cover interrupt tool-tail alternation close (#48879) 2026-06-23 23:52:28 -07:00
test_turn_retry_state.py fix(agent): route content-filter stream stalls to fallback chain (#32421) 2026-06-28 01:15:21 -07:00
test_unsupported_parameter_retry.py test: remove 50 stale/broken tests to unblock CI (#22098) 2026-05-08 14:55:40 -07:00
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 fix(bedrock): price Claude prompt-cache tokens in /usage (#50307) 2026-06-21 11:48:43 -07:00
test_verification_evidence.py feat(agent): recognize focused ad-hoc verification scripts 2026-06-24 23:03:45 -05:00
test_verification_stop.py feat(agent): restore surface-aware "auto" default for verify_on_stop 2026-06-30 01:43:08 -05:00
test_verify_hooks.py feat(agent): add pre_verify hook and verify-on-stop coding guidance 2026-06-30 00:59:29 -05:00
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 fix(vision): preserve explicit provider auth with custom base_url 2026-05-04 05:05:43 -07:00
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