hermes-agent/tests
Teknium 1368caf66f
fix(anthropic): smart thinking block signature management (#6112)
Anthropic signs thinking blocks against the full turn content. Any
upstream mutation (context compression, session truncation, orphan
stripping, message merging) invalidates the signature, causing HTTP 400
'Invalid signature in thinking block' — especially in long-lived
gateway sessions.

Strategy (following clawdbot/OpenClaw pattern):

1. Strip thinking/redacted_thinking from all assistant messages EXCEPT
   the last one — preserves reasoning continuity on the current
   tool-use chain while avoiding stale signature errors on older turns.

2. Downgrade unsigned thinking blocks to plain text — Anthropic can't
   validate them, but the reasoning content is preserved.

3. Strip cache_control from thinking/redacted_thinking blocks to
   prevent cache markers from interfering with signature validation.

4. Drop thinking blocks from the second message when merging
   consecutive assistant messages (role alternation enforcement).

5. Error recovery: on HTTP 400 mentioning 'signature' and 'thinking',
   strip all reasoning_details from the conversation and retry once.
   This is the safety net for edge cases the proactive stripping
   misses.

Addresses the issue reported in PR #6086 by @mingginwan while
preserving reasoning continuity (their PR stripped ALL thinking
blocks unconditionally).

Files changed:
- agent/anthropic_adapter.py: thinking block management in
  convert_messages_to_anthropic (strip old turns, downgrade unsigned,
  strip cache_control, merge-time strip)
- run_agent.py: one-shot signature error recovery in retry loop
- tests/test_anthropic_adapter.py: 10 new tests covering all cases
2026-04-08 03:38:08 -07:00
..
acp feat(api): structured run events via /v1/runs SSE endpoint 2026-04-05 12:05:13 -07:00
agent fix(anthropic): smart thinking block signature management (#6112) 2026-04-08 03:38:08 -07:00
cli refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
cron feat(cron): track delivery failures in job status (#6042) 2026-04-07 22:49:01 -07:00
e2e test(e2e): remove section separator comments 2026-04-01 15:23:52 -07:00
environments/benchmarks fix(security): consolidated security hardening — SSRF, timing attack, tar traversal, credential leakage (#5944) 2026-04-07 17:28:37 -07:00
fakes fix: streaming tool call parsing, error handling, and fake HA state mutation 2026-03-14 14:27:20 +03:00
gateway fix: unify reasoning_effort to config.yaml only, remove HERMES_REASONING_EFFORT env var 2026-04-08 03:36:44 -07:00
hermes_cli fix(minimax): correct context lengths, model catalog, thinking guard, aux model, and config base_url 2026-04-08 02:20:46 -07:00
honcho_plugin fix(honcho): migration guard for observation mode default change 2026-04-05 12:34:11 -07:00
integration refactor: remove mini-swe-agent dependency — inline Docker/Modal backends (#2804) 2026-03-24 07:30:25 -07:00
plugins feat(supermemory): add multi-container, search_mode, identity template, and env var override (#5933) 2026-04-07 14:03:46 -07:00
run_agent fix(tools): address PR review — remove _extract_raw_output, BudgetConfig everywhere, read_file hardening 2026-04-08 02:24:32 -07:00
skills fix: protect profile-scoped google workspace oauth tokens 2026-04-03 17:49:18 -07:00
tools fix(process): correct detached crash recovery state 2026-04-08 03:35:43 -07:00
__init__.py A bit of restructuring for simplicity and organization 2025-10-01 23:29:25 +00:00
conftest.py fix(approval): show full command in dangerous command approval (#1553) 2026-03-17 02:02:33 -07:00
run_interrupt_test.py fix: thread safety for concurrent subagent delegation (#1672) 2026-03-17 02:53:33 -07:00
test_batch_runner_checkpoint.py fix: sanitize chat payloads and provider precedence 2026-03-13 23:59:12 -07:00
test_cli_skin_integration.py fix: CLI/UX batch — ChatConsole errors, curses scroll, skin-aware banner, git state banner (#5974) 2026-04-07 17:59:42 -07:00
test_evidence_store.py feat: add OSS Security Forensics skill (Skills Hub) (#1482) 2026-03-15 21:59:53 -07:00
test_hermes_logging.py fix: repair 57 failing CI tests across 14 files (#5823) 2026-04-07 09:58:45 -07:00
test_hermes_state.py fix: merge dotted+hyphenated FTS5 quoting into single pass 2026-04-02 00:49:11 -07:00
test_honcho_client_config.py feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623) 2026-04-02 15:33:51 -07:00
test_mcp_serve.py feat: add MCP server mode — hermes mcp serve (#3795) 2026-03-29 15:47:19 -07:00
test_minisweagent_path.py chore: remove all remaining mini-swe-agent references 2026-03-24 08:19:23 -07:00
test_model_picker_scroll.py fix: CLI/UX batch — ChatConsole errors, curses scroll, skin-aware banner, git state banner (#5974) 2026-04-07 17:59:42 -07:00
test_model_tools.py Add request-scoped plugin lifecycle hooks 2026-04-05 23:31:29 -07:00
test_model_tools_async_bridge.py fix: use per-thread persistent event loops in worker threads 2026-03-20 15:41:06 -04:00
test_ollama_num_ctx.py fix: provider/model resolution — salvage 4 PRs + MiniMax aux URL fix (#5983) 2026-04-07 22:23:28 -07:00
test_packaging_metadata.py chore: prepare Hermes for Homebrew packaging (#4099) 2026-03-30 17:34:43 -07:00
test_project_metadata.py fix: exclude matrix from [all] extras — python-olm is upstream-broken (#4615) 2026-04-02 09:21:37 -07:00
test_retry_utils.py feat(agent): add jittered retry backoff 2026-04-08 00:41:36 -07:00
test_sql_injection.py fix(security): eliminate SQL string formatting in execute() calls 2026-03-19 15:16:35 +01:00
test_timezone.py fix: repair 57 failing CI tests across 14 files (#5823) 2026-04-07 09:58:45 -07:00
test_toolset_distributions.py test: add unit tests for 8 modules (batch 2) 2026-02-26 13:54:20 +03:00
test_toolsets.py fix: add missing Platform.SIGNAL to toolset mappings, update test + config docs 2026-03-09 23:27:19 -07:00
test_trajectory_compressor.py fix: URL-based auth for third-party Anthropic endpoints + CI test fixes (#4148) 2026-03-30 20:36:56 -07:00
test_trajectory_compressor_async.py fix: create AsyncOpenAI lazily in trajectory_compressor to avoid closed event loop (#4013) 2026-03-30 13:16:16 -07:00
test_utils_truthy_values.py Gate tool-gateway behind an env var, so it's not in users' faces until we're ready. Even if users enable it, it'll be blocked server-side for now, until we unlock for non-admin users on tool-gateway. 2026-03-30 13:28:10 +09:00