mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-18 04:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

refactor(transports/codex): trim duplicated cache-key comments

Browse source 
The xAI prompt_cache_key block carried two long comment paragraphs
that either restated setdefault semantics, narrated the SDK
type-validation mechanism, or recapped the historical motivation for
the extra_body indirection — all already covered by the test
docstring at test_xai_responses_sends_cache_key_via_extra_body
(which links to the xAI docs). Also restored the truncated link in
the body-injection comment.

No behavior change.
This commit is contained in:
Jaaneek 2026-05-15 18:28:01 +01:00 • committed by Teknium
parent e13c1b8060
commit 7fdc16dd4a
2 changed files with 6 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

20
agent/transports/codex.py
View file

@ -102,11 +102,8 @@ class ResponsesApiTransport(ProviderTransport):
kwargs["parallel_tool_calls"] = True
session_id = params.get("session_id")
# xAI's Responses API uses `prompt_cache_key` (body-level) as the
# cache-routing key, not a top-level kwarg — the body-field
# injection below survives openai SDK builds whose
# Responses.stream() signature drops the kwarg. Everything else
# that ISN'T github/xAI keeps using the typed kwarg.
# xAI Responses takes prompt_cache_key in extra_body (set further
# down); GitHub Models opts out of cache-key routing entirely.
if not is_github_responses and not is_xai_responses and session_id:
kwargs["prompt_cache_key"] = session_id
@ -172,15 +169,10 @@ class ResponsesApiTransport(ProviderTransport):
merged_extra_headers["x-grok-conv-id"] = session_id
kwargs["extra_headers"] = merged_extra_headers
# xAI Responses cache-routing field. Lives in the request body
# (per https://docs.x.ai/.../prompt-caching/maximizing-cache-hits),
# so we ship it via extra_body — the openai SDK serializes
# extra_body fields into the JSON body without per-field type
# validation, sidestepping the TypeError that fires on
# Responses.stream() builds whose `prompt_cache_key` kwarg has
# been dropped. Setdefault preserves a caller-supplied value
# (e.g. request_overrides.extra_body.prompt_cache_key) over
# the auto-derived session_id.
# xAI Responses cache-routing — body-level field per
# https://docs.x.ai/developers/advanced-api-usage/prompt-caching/maximizing-cache-hits.
# Sent via extra_body (not the typed kwarg) so it survives openai
# SDK builds whose Responses.stream() signature has dropped the field.
existing_extra_body = kwargs.get("extra_body")
merged_extra_body: Dict[str, Any] = {}
if isinstance(existing_extra_body, dict):

5
tests/agent/transports/test_codex_transport.py
View file

@ -117,13 +117,8 @@ class TestCodexBuildKwargs:
session_id="conv-xai-1",
is_xai_responses=True,
)
# Top-level prompt_cache_key must NOT be set for xAI — the SDK
# signature drop is what motivated the extra_body indirection in
# the first place. The cache-routing field must travel in the
# body via extra_body.
assert "prompt_cache_key" not in kw
assert kw.get("extra_body", {}).get("prompt_cache_key") == "conv-xai-1"
# Header kept as belt-and-braces.
assert kw.get("extra_headers", {}).get("x-grok-conv-id") == "conv-xai-1"
def test_xai_responses_extra_body_preserves_caller_fields(self, transport):