mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
fix(anthropic): complete third-party Anthropic-compatible provider support (#12846)
Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers. Synthesizes
eight stale community PRs into one consolidated change.
Five fixes:
- URL detection: consolidate three inline `endswith("/anthropic")`
checks in runtime_provider.py into the shared _detect_api_mode_for_url
helper. Third-party /anthropic endpoints now auto-resolve to
api_mode=anthropic_messages via one code path instead of three.
- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
(__init__, switch_model, _try_refresh_anthropic_client_credentials,
_swap_credential, _try_activate_fallback) now gate on
`provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
Claude-Code identity injection on third-party endpoints. Previously
only 2 of 5 sites were guarded.
- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
`(should_cache, use_native_layout)` per endpoint. Replaces three
inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
call-site flag. Native Anthropic and third-party Anthropic gateways
both get the native cache_control layout; OpenRouter gets envelope
layout. Layout is persisted in `_primary_runtime` so fallback
restoration preserves the per-endpoint choice.
- Auxiliary client: `_try_custom_endpoint` honors
`api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
instead of silently downgrading to an OpenAI-wire client. Degrades
gracefully to OpenAI-wire when the anthropic SDK isn't installed.
- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
clears stale `api_key`/`api_mode` when switching to a built-in
provider, so a previous MiniMax custom endpoint's credentials can't
leak into a later OpenRouter session.
- Truncation continuation: length-continuation and tool-call-truncation
retry now cover `anthropic_messages` in addition to `chat_completions`
and `bedrock_converse`. Reuses the existing `_build_assistant_message`
path via `normalize_anthropic_response()` so the interim message
shape is byte-identical to the non-truncated path.
Tests: 6 new files, 42 test cases. Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).
Synthesized from (credits preserved via Co-authored-by trailers):
#7410 @nocoo — URL detection helper
#7393 @keyuyuan — OAuth 5-site guard
#7367 @n-WN — OAuth guard (narrower cousin, kept comment)
#8636 @sgaofen — caching helper + native-vs-proxy layout split
#10954 @Only-Code-A — caching on anthropic_messages+Claude
#7648 @zhongyueming1121 — aux client anthropic_messages branch
#6096 @hansnow — /model switch clears stale api_mode
#9691 @TroyMitchell911 — anthropic_messages truncation continuation
Closes: #7366, #8294 (third-party Anthropic identity + caching).
Supersedes: #7410, #7367, #7393, #8636, #10954, #7648, #6096, #9691.
Rejects: #9621 (OpenAI-wire caching with incomplete blocklist — risky),
#7242 (superseded by #9691, stale branch),
#8321 (targets smart_model_routing which was removed in #12732).
Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
This commit is contained in:
Teknium
GitHub
parent
491cf25eef
commit
65a31ee0d5
11 changed files with 911 additions and 58 deletions
|
|
@ -38,14 +38,21 @@ def _normalize_custom_provider_name(value: str) -> str:
|
|||
def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
|
||||
"""Auto-detect api_mode from the resolved base URL.
|
||||
|
||||
Direct api.openai.com endpoints need the Responses API for GPT-5.x
|
||||
tool calls with reasoning (chat/completions returns 400).
|
||||
- Direct api.openai.com endpoints need the Responses API for GPT-5.x
|
||||
tool calls with reasoning (chat/completions returns 400).
|
||||
- Third-party Anthropic-compatible gateways (MiniMax, Zhipu GLM,
|
||||
LiteLLM proxies, etc.) conventionally expose the native Anthropic
|
||||
protocol under a ``/anthropic`` suffix — treat those as
|
||||
``anthropic_messages`` transport instead of the default
|
||||
``chat_completions``.
|
||||
"""
|
||||
normalized = (base_url or "").strip().lower().rstrip("/")
|
||||
if "api.x.ai" in normalized:
|
||||
return "codex_responses"
|
||||
if "api.openai.com" in normalized and "openrouter" not in normalized:
|
||||
return "codex_responses"
|
||||
if normalized.endswith("/anthropic"):
|
||||
return "anthropic_messages"
|
||||
return None
|
||||
|
||||
|
||||
|
|
@ -194,8 +201,12 @@ def _resolve_runtime_from_pool_entry(
|
|||
elif provider in ("opencode-zen", "opencode-go"):
|
||||
from hermes_cli.models import opencode_model_api_mode
|
||||
api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
|
||||
elif base_url.rstrip("/").endswith("/anthropic"):
|
||||
api_mode = "anthropic_messages"
|
||||
else:
|
||||
# Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
|
||||
# api.openai.com → codex_responses, api.x.ai → codex_responses).
|
||||
detected = _detect_api_mode_for_url(base_url)
|
||||
if detected:
|
||||
api_mode = detected
|
||||
|
||||
# OpenCode base URLs end with /v1 for OpenAI-compatible models, but the
|
||||
# Anthropic SDK prepends its own /v1/messages to the base_url. Strip the
|
||||
|
|
@ -642,8 +653,11 @@ def _resolve_explicit_runtime(
|
|||
configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
|
||||
if configured_mode:
|
||||
api_mode = configured_mode
|
||||
elif base_url.rstrip("/").endswith("/anthropic"):
|
||||
api_mode = "anthropic_messages"
|
||||
else:
|
||||
# Auto-detect Anthropic-compatible endpoints (/anthropic suffix).
|
||||
detected = _detect_api_mode_for_url(base_url)
|
||||
if detected:
|
||||
api_mode = detected
|
||||
|
||||
return {
|
||||
"provider": provider,
|
||||
|
|
@ -965,10 +979,13 @@ def resolve_runtime_provider(
|
|||
elif provider in ("opencode-zen", "opencode-go"):
|
||||
from hermes_cli.models import opencode_model_api_mode
|
||||
api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
|
||||
# Auto-detect Anthropic-compatible endpoints by URL convention
|
||||
# (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)
|
||||
elif base_url.rstrip("/").endswith("/anthropic"):
|
||||
api_mode = "anthropic_messages"
|
||||
else:
|
||||
# Auto-detect Anthropic-compatible endpoints by URL convention
|
||||
# (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)
|
||||
# plus api.openai.com → codex_responses and api.x.ai → codex_responses.
|
||||
detected = _detect_api_mode_for_url(base_url)
|
||||
if detected:
|
||||
api_mode = detected
|
||||
# Strip trailing /v1 for OpenCode Anthropic models (see comment above).
|
||||
if api_mode == "anthropic_messages" and provider in ("opencode-zen", "opencode-go"):
|
||||
base_url = re.sub(r"/v1/?$", "", base_url)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue