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

@@ -1023,10 +1023,16 @@ def run_doctor(args):
print(" Checking Anthropic API...", end="", flush=True)
try:
import httpx
from agent.anthropic_adapter import _is_oauth_token, _COMMON_BETAS, _OAUTH_ONLY_BETAS
from agent.anthropic_adapter import (
_is_oauth_token,
_COMMON_BETAS,
_OAUTH_ONLY_BETAS,
_CONTEXT_1M_BETA,
)
headers = {"anthropic-version": "2023-06-01"}
if _is_oauth_token(anthropic_key):
is_oauth = _is_oauth_token(anthropic_key)
if is_oauth:
headers["Authorization"] = f"Bearer {anthropic_key}"
headers["anthropic-beta"] = ",".join(_COMMON_BETAS + _OAUTH_ONLY_BETAS)
else:
@@ -1036,6 +1042,25 @@ def run_doctor(args):
headers=headers,
timeout=10
)
# Reactive recovery: OAuth subscriptions that don't include 1M
# context reject the request with 400 "long context beta is not
# yet available for this subscription". Retry once with that
# beta stripped so the doctor check doesn't falsely report the
# Anthropic API as unreachable for those users.
if (
is_oauth
and response.status_code == 400
and "long context beta" in response.text.lower()
and "not yet available" in response.text.lower()
):
headers["anthropic-beta"] = ",".join(
[b for b in _COMMON_BETAS if b != _CONTEXT_1M_BETA] + list(_OAUTH_ONLY_BETAS)
)
response = httpx.get(
"https://api.anthropic.com/v1/models",
headers=headers,
timeout=10,
)
if response.status_code == 200:
print(f"\r {color('', Colors.GREEN)} Anthropic API ")
elif response.status_code == 401:

View File

@@ -2034,28 +2034,56 @@ def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
return None
headers: dict[str, str] = {"anthropic-version": "2023-06-01"}
if _is_oauth_token(token):
is_oauth = _is_oauth_token(token)
if is_oauth:
headers["Authorization"] = f"Bearer {token}"
from agent.anthropic_adapter import _COMMON_BETAS, _OAUTH_ONLY_BETAS
from agent.anthropic_adapter import _COMMON_BETAS, _OAUTH_ONLY_BETAS, _CONTEXT_1M_BETA
headers["anthropic-beta"] = ",".join(_COMMON_BETAS + _OAUTH_ONLY_BETAS)
else:
headers["x-api-key"] = token
req = urllib.request.Request(
"https://api.anthropic.com/v1/models",
headers=headers,
)
try:
def _do_request(h: dict[str, str]):
req = urllib.request.Request(
"https://api.anthropic.com/v1/models",
headers=h,
)
with urllib.request.urlopen(req, timeout=timeout) as resp:
data = json.loads(resp.read().decode())
models = [m["id"] for m in data.get("data", []) if m.get("id")]
# Sort: latest/largest first (opus > sonnet > haiku, higher version first)
return sorted(models, key=lambda m: (
"opus" not in m, # opus first
"sonnet" not in m, # then sonnet
"haiku" not in m, # then haiku
m, # alphabetical within tier
))
return json.loads(resp.read().decode())
try:
try:
data = _do_request(headers)
except urllib.error.HTTPError as http_err:
# Reactive recovery for OAuth subscriptions that reject the 1M
# context beta with 400 "long context beta is not yet available
# for this subscription". Retry once without the beta; re-raise
# anything else so the outer except logs it.
if (
is_oauth
and http_err.code == 400
):
try:
body_text = http_err.read().decode(errors="ignore").lower()
except Exception:
body_text = ""
if "long context beta" in body_text and "not yet available" in body_text:
headers["anthropic-beta"] = ",".join(
[b for b in _COMMON_BETAS if b != _CONTEXT_1M_BETA]
+ list(_OAUTH_ONLY_BETAS)
)
data = _do_request(headers)
else:
raise
else:
raise
models = [m["id"] for m in data.get("data", []) if m.get("id")]
# Sort: latest/largest first (opus > sonnet > haiku, higher version first)
return sorted(models, key=lambda m: (
"opus" not in m, # opus first
"sonnet" not in m, # then sonnet
"haiku" not in m, # then haiku
m, # alphabetical within tier
))
except Exception as e:
import logging
logging.getLogger(__name__).debug("Failed to fetch Anthropic models: %s", e)