fix(anthropic): reactive recovery for OAuth 1M-context beta rejection (#17752)

Keep context-1m-2025-08-07 in OAuth requests by default so 1M-capable
subscriptions retain full context. When Anthropic rejects a request with
400 'long context beta is not yet available for this subscription',
disable the beta for the rest of the session, rebuild the client, and
retry once.

Addresses #17680 (thanks @JayGwod for the clean reproduction) without
forcing every OAuth user off the 1M context window.

Changes:
- agent/error_classifier.py: new FailoverReason.oauth_long_context_beta_forbidden;
  pattern matches 400 + 'long context beta' + 'not yet available'. Narrow
  enough that the existing 429 tier-gate pattern keeps its own reason.
- agent/anthropic_adapter.py: _common_betas_for_base_url,
  build_anthropic_client, build_anthropic_kwargs gain drop_context_1m_beta
  kwarg. Default=False (1M stays). OAuth OAUTH_ONLY_BETAS unchanged.
- agent/transports/anthropic.py: build_kwargs forwards the flag.
- run_agent.py: self._oauth_1m_beta_disabled flag, retry-once guard,
  recovery branch next to the image-shrink path. _rebuild_anthropic_client
  honors the flag. The main build_kwargs call site threads it through for
  fast-mode extra_headers.
- hermes_cli/doctor.py, hermes_cli/models.py: sibling OAuth /v1/models
  probes get the same reactive retry — previously they'd falsely report
  the Anthropic API as unreachable for affected subscriptions.

Tests: 2190 tests/agent/ + 94 adjacent integration tests pass. New unit
tests cover the classifier pattern (including the collision guard against
the 429 tier-gate) and the drop_context_1m_beta adapter behavior (default
keeps 1M, flag strips only 1M while preserving every other beta).
This commit is contained in:
Teknium
2026-04-29 21:56:54 -07:00
committed by GitHub
parent 4d363499db
commit 828d3a320b
8 changed files with 264 additions and 23 deletions

View File

@@ -461,7 +461,11 @@ def _requires_bearer_auth(base_url: str | None) -> bool:
return normalized.startswith(("https://api.minimax.io/anthropic", "https://api.minimaxi.com/anthropic"))
def _common_betas_for_base_url(base_url: str | None) -> list[str]:
def _common_betas_for_base_url(
base_url: str | None,
*,
drop_context_1m_beta: bool = False,
) -> list[str]:
"""Return the beta headers that are safe for the configured endpoint.
MiniMax's Anthropic-compatible endpoints (Bearer-auth) reject requests
@@ -472,14 +476,30 @@ def _common_betas_for_base_url(base_url: str | None) -> list[str]:
The ``context-1m-2025-08-07`` beta is also stripped for Bearer-auth
endpoints — MiniMax hosts its own models, not Claude, so the header is
irrelevant at best and risks request rejection at worst.
``drop_context_1m_beta=True`` additionally strips the 1M-context beta on
otherwise-unrelated endpoints. The OAuth retry path flips this flag after
a subscription rejects the beta with
"The long context beta is not yet available for this subscription" so
subsequent requests in the same session don't repeat the probe. See the
reactive recovery loop in ``run_agent.py`` and issue-comment history on
PR #17680 for the full rationale.
"""
if _requires_bearer_auth(base_url):
_stripped = {_TOOL_STREAMING_BETA, _CONTEXT_1M_BETA}
return [b for b in _COMMON_BETAS if b not in _stripped]
if drop_context_1m_beta:
return [b for b in _COMMON_BETAS if b != _CONTEXT_1M_BETA]
return _COMMON_BETAS
def build_anthropic_client(api_key: str, base_url: str = None, timeout: float = None):
def build_anthropic_client(
api_key: str,
base_url: str = None,
timeout: float = None,
*,
drop_context_1m_beta: bool = False,
):
"""Create an Anthropic client, auto-detecting setup-tokens vs API keys.
If *timeout* is provided it overrides the default 900s read timeout. The
@@ -488,6 +508,12 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
Anthropic-compatible providers respect the same knob as OpenAI-wire
providers.
``drop_context_1m_beta=True`` strips ``context-1m-2025-08-07`` from the
client-level ``anthropic-beta`` header. Used by the reactive OAuth retry
path in ``run_agent.py`` when a subscription rejects the beta; leave at
its default on fresh clients so 1M-capable subscriptions keep the
capability.
Returns an anthropic.Anthropic instance.
"""
_anthropic_sdk = _get_anthropic_sdk()
@@ -517,7 +543,10 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
kwargs["default_query"] = {"api-version": "2025-04-15"}
else:
kwargs["base_url"] = normalized_base_url
common_betas = _common_betas_for_base_url(normalized_base_url)
common_betas = _common_betas_for_base_url(
normalized_base_url,
drop_context_1m_beta=drop_context_1m_beta,
)
if _is_kimi_coding_endpoint(base_url):
# Kimi's /coding endpoint requires User-Agent: claude-code/0.1.0
@@ -1689,6 +1718,7 @@ def build_anthropic_kwargs(
context_length: Optional[int] = None,
base_url: str | None = None,
fast_mode: bool = False,
drop_context_1m_beta: bool = False,
) -> Dict[str, Any]:
"""Build kwargs for anthropic.messages.create().
@@ -1877,7 +1907,10 @@ def build_anthropic_kwargs(
kwargs.setdefault("extra_body", {})["speed"] = "fast"
# Build extra_headers with ALL applicable betas (the per-request
# extra_headers override the client-level anthropic-beta header).
betas = list(_common_betas_for_base_url(base_url))
betas = list(_common_betas_for_base_url(
base_url,
drop_context_1m_beta=drop_context_1m_beta,
))
if is_oauth:
betas.extend(_OAUTH_ONLY_BETAS)
betas.append(_FAST_MODE_BETA)

View File

@@ -54,6 +54,7 @@ class FailoverReason(enum.Enum):
# Provider-specific
thinking_signature = "thinking_signature" # Anthropic thinking block sig invalid
long_context_tier = "long_context_tier" # Anthropic "extra usage" tier gate
oauth_long_context_beta_forbidden = "oauth_long_context_beta_forbidden" # Anthropic OAuth subscription rejects 1M context beta — disable beta and retry
# Catch-all
unknown = "unknown" # Unclassifiable — retry with backoff
@@ -450,6 +451,25 @@ def classify_api_error(
should_compress=True,
)
# Anthropic OAuth subscription rejects the 1M-context beta header.
# Observed error body: "The long context beta is not yet available for
# this subscription." Returned as HTTP 400 from native Anthropic when
# the subscription doesn't include 1M context, even though the request
# carries ``anthropic-beta: context-1m-2025-08-07``. The recovery path
# in run_agent.py rebuilds the Anthropic client with the beta stripped
# and retries once. Pattern is narrow enough that it won't collide with
# the 429 tier-gate pattern above (different status, different phrase).
if (
status_code == 400
and "long context beta" in error_msg
and "not yet available" in error_msg
):
return _result(
FailoverReason.oauth_long_context_beta_forbidden,
retryable=True,
should_compress=False,
)
# ── 2. HTTP status code classification ──────────────────────────
if status_code is not None:

View File

@@ -58,6 +58,7 @@ class AnthropicTransport(ProviderTransport):
context_length: int | None
base_url: str | None
fast_mode: bool
drop_context_1m_beta: bool
"""
from agent.anthropic_adapter import build_anthropic_kwargs
@@ -73,6 +74,7 @@ class AnthropicTransport(ProviderTransport):
context_length=params.get("context_length"),
base_url=params.get("base_url"),
fast_mode=params.get("fast_mode", False),
drop_context_1m_beta=params.get("drop_context_1m_beta", False),
)
def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse: