mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: preserve Ollama model:tag colons in context length detection (#2149)

Browse source 
The colon-split logic in get_model_context_length() and
_query_local_context_length() assumed any colon meant provider:model
format (e.g. "local:my-model"). But Ollama uses model:tag format
(e.g. "qwen3.5:27b"), so the split turned "qwen3.5:27b" into just
"27b" — which matches nothing, causing a fallback to the 2M token
probe tier.

Now only recognised provider prefixes (local, openrouter, anthropic,
etc.) are stripped. Ollama model:tag names pass through intact.

Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
This commit is contained in:
Teknium 2026-03-20 03:19:31 -07:00 • committed by GitHub
parent 3a9a1bbb84
commit 471ea81a7d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 77 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

40
agent/model_metadata.py
View file

@ -19,6 +19,34 @@ from hermes_constants import OPENROUTER_MODELS_URL
logger = logging.getLogger(__name__)
# Provider names that can appear as a "provider:" prefix before a model ID.
# Only these are stripped — Ollama-style "model:tag" colons (e.g. "qwen3.5:27b")
# are preserved so the full model name reaches cache lookups and server queries.
_PROVIDER_PREFIXES: frozenset[str] = frozenset({
"openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
"zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
"opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
"custom", "local",
# Common aliases
"glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
"github-models", "kimi", "moonshot", "claude", "deep-seek",
"opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
})
def _strip_provider_prefix(model: str) -> str:
"""Strip a recognised provider prefix from a model string.
``"local:my-model"`` → ``"my-model"``
``"qwen3.5:27b"`` → ``"qwen3.5:27b"`` (unchanged — not a provider prefix)
"""
if ":" not in model or model.startswith("http"):
return model
prefix = model.split(":", 1)[0].strip().lower()
if prefix in _PROVIDER_PREFIXES:
return model.split(":", 1)[1]
return model
_model_metadata_cache: Dict[str, Dict[str, Any]] = {}
_model_metadata_cache_time: float = 0
_MODEL_CACHE_TTL = 3600
@ -579,10 +607,9 @@ def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
"""Query a local server for the model's context length."""
import httpx
# Strip provider prefix (e.g., "local:model-name" → "model-name").
# LM Studio and Ollama don't use provider prefixes in their model IDs.
if ":" in model and not model.startswith("http"):
model = model.split(":", 1)[1]
# Strip recognised provider prefix (e.g., "local:model-name" → "model-name").
# Ollama "model:tag" colons (e.g. "qwen3.5:27b") are intentionally preserved.
model = _strip_provider_prefix(model)
# Strip /v1 suffix to get the server root
server_url = base_url.rstrip("/")
@ -689,9 +716,8 @@ def get_model_context_length(
# Normalise provider-prefixed model names (e.g. "local:model-name" →
# "model-name") so cache lookups and server queries use the bare ID that
# local servers actually know about.
if ":" in model and not model.startswith("http"):
model = model.split(":", 1)[1]
# local servers actually know about. Ollama "model:tag" colons are preserved.
model = _strip_provider_prefix(model)
# 1. Check persistent cache (model+provider)
if base_url: