hermes-agent/tests/run_agent
Teknium ea67e49574
fix(streaming): silent retry when stream dies mid tool-call (#14151)
When the streaming connection dropped AFTER user-visible text was
delivered but a tool call was in flight, we stubbed the turn with a
'⚠ Stream stalled mid tool-call; Ask me to retry' warning — costing
an iteration and breaking the flow.  Users report this happening
increasingly often on long SSE streams through flaky provider routes.

Fix: in the existing inner stream-retry loop, relax the
deltas_were_sent short-circuit.  If a tool call was in flight
(partial_tool_names populated) AND the error is a transient connection
error (timeout, RemoteProtocolError, SSE 'connection lost', etc.),
silently retry instead of bailing out.  Fire a brief 'Connection
dropped mid tool-call; reconnecting…' marker so the user understands
the preamble is about to be re-streamed.

Researched how Claude Code (tombstone + non-streaming fallback),
OpenCode (blind Effect.retry wrapping whole stream), and Clawdbot
(4-way gate: stopReason==error + output==0 + !hadPotentialSideEffects)
handle this.  Chose the narrow Clawdbot-style gate: retry only when
(a) a tool call was actually in flight (otherwise the existing
stub-with-recovered-text is correct for pure-text stalls) and
(b) the error is transient.  Side-effect safety is automatic — no
tool has been dispatched within this single API call yet.

UX trade-off: user sees preamble text twice on retry (OpenCode-style).
Strictly better than a lost action with a 'retry manually' message.
If retries exhaust, falls through to the existing stub-with-warning
path so the user isn't left with zero signal.

Tests: 3 new tests in TestSilentRetryMidToolCall covering
(1) silent retry recovers tool call; (2) exhausted retries fall back
to stub; (3) text-only stalls don't trigger retry.  30/30 pass.
2026-04-22 13:47:33 -07:00
..
__init__.py
…
conftest.py
…
test_413_compression.py
…
test_860_dedup.py
…
test_1630_context_overflow_loop.py
…
test_agent_guardrails.py
…
test_agent_loop.py
…
test_agent_loop_tool_calling.py
…
test_agent_loop_vllm.py
…
test_anthropic_error_handling.py feat(providers): extend request_timeout_seconds to all client paths 2026-04-19 11:23:00 -07:00
test_anthropic_prompt_cache_policy.py fix(cache): enable prompt caching for Qwen on OpenCode/OpenCode-Go/Alibaba (#13528) 2026-04-21 06:40:58 -07:00
test_anthropic_third_party_oauth_guard.py fix(anthropic): complete third-party Anthropic-compatible provider support (#12846) 2026-04-19 22:43:09 -07:00
test_anthropic_truncation_continuation.py fix(anthropic): complete third-party Anthropic-compatible provider support (#12846) 2026-04-19 22:43:09 -07:00
test_async_httpx_del_neuter.py
…
test_compression_boundary.py
…
test_compression_feasibility.py fix(compression): enforce 64k floor on aux model + auto-correct threshold (#12898) 2026-04-20 00:56:04 -07:00
test_compression_persistence.py
…
test_compression_trigger_excludes_reasoning.py fix(compression): exclude completion tokens from compression trigger (#12026) 2026-04-20 05:12:10 -07:00
test_compressor_fallback_update.py
…
test_concurrent_interrupt.py fix(tests): unstick CI — sweep stale tests from recent merges (#12670) 2026-04-19 12:39:58 -07:00
test_context_token_tracking.py feat(providers): extend request_timeout_seconds to all client paths 2026-04-19 11:23:00 -07:00
test_create_openai_client_kwargs_isolation.py
…
test_create_openai_client_proxy_env.py fix(agent): normalize socks:// env proxies for httpx/anthropic 2026-04-21 05:52:46 -07:00
test_create_openai_client_reuse.py
…
test_dict_tool_call_args.py
…
test_exit_cleanup_interrupt.py
…
test_fallback_model.py
…
test_flush_memories_codex.py
…
test_interactive_interrupt.py
…
test_interrupt_propagation.py test: stop testing mutable data — convert change-detectors to invariants (#13363) 2026-04-20 23:20:33 -07:00
test_invalid_context_length_warning.py
…
test_long_context_tier_429.py
…
test_memory_provider_init.py fix(memory): keep Honcho provider opt-in 2026-04-18 22:50:55 -07:00
test_openai_client_lifecycle.py
…
test_percentage_clamp.py
…
test_plugin_context_engine_init.py
…
test_primary_runtime_restore.py
…
test_provider_attribution_headers.py feat: attribution default_headers for ai-gateway provider 2026-04-20 21:02:28 -07:00
test_provider_fallback.py
…
test_provider_parity.py feat: add ResponsesApiTransport + wire all Codex transport paths 2026-04-21 19:48:56 -07:00
test_real_interrupt_subagent.py
…
test_redirect_stdout_issue.py
…
test_repair_tool_call_arguments.py fix: extract _repair_tool_call_arguments helper, add tests, bound loop 2026-04-20 05:12:55 -07:00
test_run_agent.py fix: preserve reasoning_content on Kimi replay 2026-04-22 04:31:59 -07:00
test_run_agent_codex_responses.py feat: add ResponsesApiTransport + wire all Codex transport paths 2026-04-21 19:48:56 -07:00
test_run_agent_multimodal_prologue.py feat(api-server): inline image inputs on /v1/chat/completions and /v1/responses (#12969) 2026-04-20 04:16:13 -07:00
test_sequential_chats_live.py
…
test_session_meta_filtering.py
…
test_session_reset_fix.py
…
test_steer.py refactor(steer): simplify injection marker to 'User guidance:' prefix (#13340) 2026-04-20 22:18:49 -07:00
test_streaming.py fix(streaming): silent retry when stream dies mid tool-call (#14151) 2026-04-22 13:47:33 -07:00
test_strict_api_validation.py
…
test_switch_model_context.py
…
test_switch_model_fallback_prune.py fix(model-switch): drop stale provider from fallback chain and env after /model 2026-04-21 14:31:47 -05:00
test_token_persistence_non_cli.py
…
test_tool_arg_coercion.py
…
test_unicode_ascii_codec.py
…