hermes-agent/tests/agent/transports
Kasun Athaudahetti 2d422720b5 fix(codex): size and propagate timeouts for Responses-API requests; lower stale defaults
Codex / Responses-API requests had three latent timeout bugs that combined
into the long silent hangs reported on #21444:

1. The non-stream stale-call detector estimated context tokens from
   ``api_kwargs["messages"]`` only. Codex / Responses-API payloads carry
   their conversational load in ``input`` (with ``instructions`` and
   ``tools``), so every Codex turn logged ``context=~0 tokens`` and the
   detector never applied its >50k / >100k tier bumps.

2. ``providers.<id>.request_timeout_seconds`` was silently dropped on the
   main Codex path. The chat_completions path and the auxiliary Codex
   adapter both forwarded it; the main path skipped it through three
   places (``build_api_kwargs``, ``ResponsesApiTransport.build_kwargs``,
   ``_preflight_codex_api_kwargs``).

3. The streaming stale detector had the same payload-shape bug for
   ``codex_responses`` requests, which route through the non-streaming
   detector (it's the path that emits the user-facing
   "No response from provider for 300s (non-streaming, ...)" warning that
   reporters keep pasting).

This commit:

- Adds ``estimate_request_context_tokens`` in ``chat_completion_helpers``,
  used by both the non-stream and stream detectors. Handles ``messages``
  (Chat Completions), ``input + instructions + tools`` (Responses API),
  bare lists, and an unknown-dict fallback.
- Forwards ``timeout`` through ``ResponsesApiTransport.build_kwargs``
  and ``_preflight_codex_api_kwargs`` (with guards against
  zero/negative/inf/bool values), and wires
  ``_resolved_api_call_timeout()`` into the Codex branch of
  ``build_api_kwargs``.
- Lowers the implicit non-stream stale defaults so fallback providers
  kick in faster when upstream stalls:
    * base   300s -> 90s
    * >50k   450s -> 150s
    * >100k  600s -> 240s
  These only apply when the user has *not* set
  ``providers.<id>.stale_timeout_seconds`` or
  ``HERMES_API_CALL_STALE_TIMEOUT``. Explicit config still wins.
- Adds regression tests for the estimator shapes, the new defaults, the
  context-tier scaling, transport timeout pass-through, and preflight
  timeout pass-through / rejection of invalid values.

Closes #21444
Supersedes #21652 #24126 #31855

Co-authored-by: Hoang V. Pham <26063003+hehehe0803@users.noreply.github.com>
2026-05-25 01:47:55 -07:00
..
__init__.py feat: add transport types + migrate Anthropic normalize path 2026-04-20 23:06:00 -07:00
test_bedrock_transport.py fix(bedrock): preserve reasoningContent across converse normalization 2026-05-07 05:17:16 -07:00
test_chat_completions.py fix(transport): strip Hermes-internal scaffolding keys before chat.completions 2026-05-24 15:15:37 -07:00
test_codex_app_server_runtime.py fix(codex): allow kanban worker board writes 2026-05-17 11:50:43 -07:00
test_codex_app_server_session.py fix(tui): handle images with codex app-server 2026-05-23 20:40:09 -07:00
test_codex_event_projector.py feat(codex-runtime): optional codex app-server runtime for OpenAI/Codex models (#24182) 2026-05-13 17:18:15 -07:00
test_codex_transport.py fix(codex): size and propagate timeouts for Responses-API requests; lower stale defaults 2026-05-25 01:47:55 -07:00
test_hermes_tools_mcp_server.py feat(codex-runtime): optional codex app-server runtime for OpenAI/Codex models (#24182) 2026-05-13 17:18:15 -07:00
test_transport.py fix(agent): preserve Codex message items for replay 2026-04-25 18:22:06 -07:00
test_types.py fix(agent): preserve Codex message items for replay 2026-04-25 18:22:06 -07:00