fix(anthropic): live model fetching + adaptive thinking for 4.5+ models
- Add _fetch_anthropic_models() to hermes_cli/models.py — hits the Anthropic /v1/models endpoint to get the live model catalog. Handles both API key and OAuth token auth headers. - Wire it into provider_model_ids() so both 'hermes model' and 'hermes setup model' show the live list instead of a stale static one. - Update static _PROVIDER_MODELS fallback with full current catalog: opus-4-6, sonnet-4-6, opus-4-5, sonnet-4-5, opus-4, sonnet-4, haiku-4-5 - Update model_metadata.py with context lengths for all current models. - Fix thinking parameter for 4.5+ models: use type='adaptive' instead of type='enabled' (Anthropic deprecated 'enabled' for newer models, warns at runtime). Detects model version from the model name string. Verified live: hermes model → Anthropic → auto-detected creds → shows 7 live models hermes chat --provider anthropic --model claude-opus-4-6 → works
This commit is contained in:
@@ -363,11 +363,16 @@ def build_anthropic_kwargs(
|
||||
kwargs["tool_choice"] = {"type": "tool", "name": tool_choice}
|
||||
|
||||
# Map reasoning_config to Anthropic's thinking parameter
|
||||
# Newer models (4.6+) prefer "adaptive" thinking; older models use "enabled"
|
||||
if reasoning_config and isinstance(reasoning_config, dict):
|
||||
if reasoning_config.get("enabled") is not False:
|
||||
effort = reasoning_config.get("effort", "medium")
|
||||
budget = THINKING_BUDGET.get(effort, 8000)
|
||||
kwargs["thinking"] = {"type": "enabled", "budget_tokens": budget}
|
||||
# Use adaptive thinking for 4.5+ models (they deprecate type=enabled)
|
||||
if any(v in model for v in ("4-6", "4-5", "4.6", "4.5")):
|
||||
kwargs["thinking"] = {"type": "adaptive", "budget_tokens": budget}
|
||||
else:
|
||||
kwargs["thinking"] = {"type": "enabled", "budget_tokens": budget}
|
||||
kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
|
||||
|
||||
return kwargs
|
||||
|
||||
@@ -42,6 +42,11 @@ DEFAULT_CONTEXT_LENGTHS = {
|
||||
"anthropic/claude-sonnet-4-20250514": 200000,
|
||||
"anthropic/claude-haiku-4.5": 200000,
|
||||
# Bare Anthropic model IDs (for native API provider)
|
||||
"claude-opus-4-6": 200000,
|
||||
"claude-sonnet-4-6": 200000,
|
||||
"claude-opus-4-5-20251101": 200000,
|
||||
"claude-sonnet-4-5-20250929": 200000,
|
||||
"claude-opus-4-1-20250805": 200000,
|
||||
"claude-opus-4-20250514": 200000,
|
||||
"claude-sonnet-4-20250514": 200000,
|
||||
"claude-haiku-4-5-20251001": 200000,
|
||||
|
||||
@@ -69,8 +69,12 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
|
||||
"MiniMax-M2.1",
|
||||
],
|
||||
"anthropic": [
|
||||
"claude-sonnet-4-20250514",
|
||||
"claude-opus-4-6",
|
||||
"claude-sonnet-4-6",
|
||||
"claude-opus-4-5-20251101",
|
||||
"claude-sonnet-4-5-20250929",
|
||||
"claude-opus-4-20250514",
|
||||
"claude-sonnet-4-20250514",
|
||||
"claude-haiku-4-5-20251001",
|
||||
],
|
||||
}
|
||||
@@ -242,9 +246,54 @@ def provider_model_ids(provider: Optional[str]) -> list[str]:
|
||||
return live
|
||||
except Exception:
|
||||
pass
|
||||
if normalized == "anthropic":
|
||||
live = _fetch_anthropic_models()
|
||||
if live:
|
||||
return live
|
||||
return list(_PROVIDER_MODELS.get(normalized, []))
|
||||
|
||||
|
||||
def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
|
||||
"""Fetch available models from the Anthropic /v1/models endpoint.
|
||||
|
||||
Uses resolve_anthropic_token() to find credentials (env vars or
|
||||
Claude Code auto-discovery). Returns sorted model IDs or None.
|
||||
"""
|
||||
try:
|
||||
from agent.anthropic_adapter import resolve_anthropic_token, _is_oauth_token
|
||||
except ImportError:
|
||||
return None
|
||||
|
||||
token = resolve_anthropic_token()
|
||||
if not token:
|
||||
return None
|
||||
|
||||
headers: dict[str, str] = {"anthropic-version": "2023-06-01"}
|
||||
if _is_oauth_token(token):
|
||||
headers["Authorization"] = f"Bearer {token}"
|
||||
headers["anthropic-beta"] = "oauth-2025-04-20"
|
||||
else:
|
||||
headers["x-api-key"] = token
|
||||
|
||||
req = urllib.request.Request(
|
||||
"https://api.anthropic.com/v1/models",
|
||||
headers=headers,
|
||||
)
|
||||
try:
|
||||
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
|
||||
))
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def fetch_api_models(
|
||||
api_key: Optional[str],
|
||||
base_url: Optional[str],
|
||||
|
||||
@@ -1229,9 +1229,12 @@ def setup_model_provider(config: dict):
|
||||
_set_default_model(config, custom)
|
||||
# else: keep current
|
||||
elif selected_provider == "anthropic":
|
||||
anthropic_models = [
|
||||
"claude-sonnet-4-20250514",
|
||||
"claude-opus-4-20250514",
|
||||
# Try live model list first, fall back to static
|
||||
from hermes_cli.models import provider_model_ids
|
||||
live_models = provider_model_ids("anthropic")
|
||||
anthropic_models = live_models if live_models else [
|
||||
"claude-opus-4-6",
|
||||
"claude-sonnet-4-6",
|
||||
"claude-haiku-4-5-20251001",
|
||||
]
|
||||
model_choices = list(anthropic_models)
|
||||
|
||||
Reference in New Issue
Block a user