hermes-agent/tests/run_agent
AIandI0x1 2d0d05a337 fix(agent): detect truncated streaming tool calls before execution
When a streaming response is cut mid-tool-call (connection drop, timeout),
the accumulated function.arguments is invalid JSON. The mock response
builder defaulted finish_reason to 'stop', so the agent loop treated it
as a valid completed turn and tried to execute tools with broken args.

Fix: validate tool call arguments with json.loads() during mock response
reconstruction. If any are invalid JSON, override finish_reason to
'length'. In the main loop's length handler, if tool calls are present,
refuse to execute and return partial=True with a clear error instead of
silently failing or wasting retries.

Also fixes _thinking_exhausted to not short-circuit when tool calls are
present — truncated tool calls are not thinking exhaustion.

Original cherry-picked from PR #6776 by AIandI0x1.
Closes #6638.
2026-04-09 17:03:54 -07:00
..
__init__.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_413_compression.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_860_dedup.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_1630_context_overflow_loop.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_agent_guardrails.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_agent_loop.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_agent_loop_tool_calling.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_agent_loop_vllm.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_anthropic_error_handling.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_async_httpx_del_neuter.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_compression_boundary.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_compression_persistence.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_compressor_fallback_update.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_context_pressure.py fix(agent): tiered context pressure warnings + gateway dedup (#6411) 2026-04-08 21:31:44 -07:00
test_context_token_tracking.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_dict_tool_call_args.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_exit_cleanup_interrupt.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_fallback_model.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_flush_memories_codex.py fix(agent): respect config timeout for flush_memories instead of hardcoded 30s 2026-04-08 18:55:33 -07:00
test_interactive_interrupt.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_interrupt_propagation.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_long_context_tier_429.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_openai_client_lifecycle.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_percentage_clamp.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_primary_runtime_restore.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_provider_fallback.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_provider_parity.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_real_interrupt_subagent.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_redirect_stdout_issue.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_run_agent.py fix(agent): detect truncated streaming tool calls before execution 2026-04-09 17:03:54 -07:00
test_run_agent_codex_responses.py fix(codex): align validation with normalization for empty stream output 2026-04-07 17:29:41 -07:00
test_session_meta_filtering.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_session_reset_fix.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_streaming.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_strict_api_validation.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_token_persistence_non_cli.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_tool_arg_coercion.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00