Compare commits

...

3 Commits

Author SHA1 Message Date
Alexander Whitestone
a90162bafc fix: add _classify_runtime with complete cloud model prefix list (#628)
Some checks failed
Forge CI / smoke-and-build (pull_request) Failing after 36s
`_classify_runtime` was missing from the codebase, and the existing
`_PROVIDER_PREFIXES` set lacked several cloud vendor prefixes that users
commonly encounter via OpenRouter-style model IDs.

Changes:
- Add `_CLOUD_MODEL_PREFIXES` frozenset covering all known cloud vendors,
  including the previously missing: deepseek, cohere, mistral/mistralai,
  meta-llama, databricks, together, togetherai
- Add `_LOCAL_PROVIDER_NAMES` and `_CLOUD_PROVIDER_NAMES` frozensets for
  provider-name-based classification
- Implement `_classify_runtime(model, base_url, provider)` that classifies
  a runtime as "cloud" or "local" using URL → provider → model-prefix priority
- Extend `_PROVIDER_PREFIXES` with the same missing cloud vendors so that
  `_strip_provider_prefix` also handles cohere:, mistralai:, etc.
- Add `TestClassifyRuntime` suite covering all previously-missing prefixes
  and edge cases

Fixes #628

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-14 11:57:36 -04:00
954fd992eb Merge pull request 'perf: lazy session creation — defer DB write until first message (#314)' (#449) from whip/314-1776127532 into main
Some checks failed
Forge CI / smoke-and-build (push) Failing after 55s
Forge CI / smoke-and-build (pull_request) Failing after 1m12s
perf: lazy session creation (#314)

Closes #314.
2026-04-14 01:08:13 +00:00
Metatron
f35f56e397 perf: lazy session creation — defer DB write until first message (closes #314)
Some checks failed
Forge CI / smoke-and-build (pull_request) Failing after 56s
Remove eager create_session() call from AIAgent.__init__(). Sessions
are now created lazily on first _flush_messages_to_session_db() call
via ensure_session() which uses INSERT OR IGNORE.

Impact: eliminates 32.4% of sessions (3,564 of 10,985) that were
created at agent init but never received any messages.

The existing ensure_session() fallback in _flush_messages_to_session_db()
already handles this pattern — it was originally designed for recovery
after transient SQLite lock failures. Now it's the primary creation path.

Compression-initiated sessions still use create_session() directly
(line ~5995) since they have messages to write immediately.
2026-04-13 20:52:06 -04:00
3 changed files with 182 additions and 25 deletions

View File

@@ -32,6 +32,27 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
"glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
"github-models", "kimi", "moonshot", "claude", "deep-seek",
"opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
# Additional cloud vendor prefixes (fixes #628)
"cohere", "mistralai", "mistral", "meta-llama", "databricks", "together",
"togetherai", "together-ai", "nousresearch", "moonshotai", "fireworks",
"perplexity", "ai21", "groq", "cerebras", "nebius",
})
# Vendor prefixes that appear in cloud model IDs (e.g. "openai/gpt-4").
# Used by _classify_runtime to detect cloud runtimes from the model name
# when no base URL is available.
_CLOUD_MODEL_PREFIXES: frozenset[str] = frozenset({
# Providers present before #628
"nous", "nousresearch", "openrouter", "anthropic", "openai",
"zai", "kimi", "moonshotai", "gemini", "google", "minimax",
# Providers added by #628 fix
"deepseek", "cohere", "mistralai", "mistral", "meta-llama",
"databricks", "together", "togetherai",
# Other common cloud vendors
"microsoft", "amazon", "huggingface", "fireworks",
"perplexity", "ai21", "groq", "cerebras", "nebius",
"qwen", "alibaba", "aliyuncs", "dashscope",
"github", "copilot",
})
@@ -253,6 +274,67 @@ def is_local_endpoint(base_url: str) -> bool:
return False
# Provider names that are definitively local (never cloud).
_LOCAL_PROVIDER_NAMES: frozenset[str] = frozenset({
"ollama", "custom", "local",
})
# Provider names that are definitively cloud (not local).
_CLOUD_PROVIDER_NAMES: frozenset[str] = frozenset({
"nous", "openrouter", "anthropic", "openai", "openai-codex",
"zai", "kimi-coding", "gemini", "minimax", "minimax-cn",
"deepseek", "cohere", "mistral", "meta-llama", "databricks", "together",
"huggingface", "copilot", "copilot-acp", "ai-gateway", "kilocode",
"alibaba", "opencode-zen", "opencode-go",
})
def _classify_runtime(
model: str = "",
base_url: str = "",
provider: str = "",
) -> str:
"""Classify a model/endpoint runtime as 'cloud' or 'local'.
Checks in priority order:
1. ``base_url`` — localhost / RFC-1918 → ``"local"``; known external URL → ``"cloud"``
2. ``provider`` name — matches a known local or cloud provider set
3. Model vendor prefix — e.g. ``"openai/gpt-4"`` → ``"cloud"``
4. Default — ``"cloud"`` when the runtime cannot be determined to be local
The cloud-prefix list covers both the providers present before issue #628
(nous, openrouter, anthropic, openai, zai, kimi, gemini, minimax) and the
previously missing ones (deepseek, cohere, mistral, meta-llama, databricks,
together).
Returns ``"cloud"`` or ``"local"``.
"""
# 1. URL-based check — most reliable signal
if base_url:
if is_local_endpoint(base_url):
return "local"
return "cloud"
# 2. Provider name check
provider_norm = (provider or "").strip().lower()
if provider_norm in _LOCAL_PROVIDER_NAMES:
return "local"
if provider_norm in _CLOUD_PROVIDER_NAMES:
return "cloud"
# 3. Model vendor prefix check (e.g. "openai/gpt-4" → vendor "openai")
model_norm = (model or "").strip().lower()
if "/" in model_norm:
vendor = model_norm.split("/")[0].strip()
if vendor in _CLOUD_MODEL_PREFIXES:
return "cloud"
# An unknown vendor with a slash is still likely a cloud model
return "cloud"
# 4. Default — without a URL we cannot confirm local, so assume cloud
return "cloud"
def detect_local_server_type(base_url: str) -> Optional[str]:
"""Detect which local server is running at base_url by probing known endpoints.

View File

@@ -1001,30 +1001,10 @@ class AIAgent:
self._session_db = session_db
self._parent_session_id = parent_session_id
self._last_flushed_db_idx = 0 # tracks DB-write cursor to prevent duplicate writes
if self._session_db:
try:
self._session_db.create_session(
session_id=self.session_id,
source=self.platform or os.environ.get("HERMES_SESSION_SOURCE", "cli"),
model=self.model,
model_config={
"max_iterations": self.max_iterations,
"reasoning_config": reasoning_config,
"max_tokens": max_tokens,
},
user_id=None,
parent_session_id=self._parent_session_id,
)
except Exception as e:
# Transient SQLite lock contention (e.g. CLI and gateway writing
# concurrently) must NOT permanently disable session_search for
# this agent. Keep _session_db alive — subsequent message
# flushes and session_search calls will still work once the
# lock clears. The session row may be missing from the index
# for this run, but that is recoverable (flushes upsert rows).
logger.warning(
"Session DB create_session failed (session_search still available): %s", e
)
# Lazy session creation: defer until first message flush (#314).
# _flush_messages_to_session_db() calls ensure_session() which uses
# INSERT OR IGNORE — creating the row only when messages arrive.
# This eliminates 32% of sessions that are created but never used.
# In-memory todo list for task planning (one per agent/session)
from tools.todo_tool import TodoStore

View File

@@ -7,7 +7,7 @@ terminal access.
"""
import pytest
from agent.model_metadata import is_local_endpoint
from agent.model_metadata import is_local_endpoint, _classify_runtime
class TestIsLocalEndpoint:
@@ -71,3 +71,98 @@ class TestCronDisabledToolsetsLogic:
def test_empty_url_disables_terminal(self):
disabled = self._build_disabled("")
assert "terminal" in disabled
class TestClassifyRuntime:
"""Verify _classify_runtime correctly classifies runtimes as cloud or local.
Covers the bug fixed in #628: missing cloud model prefixes for deepseek,
cohere, mistral, meta-llama, databricks, and together.
"""
# ── URL-based classification ──────────────────────────────────────────
def test_localhost_url_is_local(self):
assert _classify_runtime(base_url="http://localhost:11434/v1") == "local"
def test_127_loopback_is_local(self):
assert _classify_runtime(base_url="http://127.0.0.1:8080/v1") == "local"
def test_rfc1918_is_local(self):
assert _classify_runtime(base_url="http://192.168.1.10:11434/v1") == "local"
def test_openrouter_url_is_cloud(self):
assert _classify_runtime(base_url="https://openrouter.ai/api/v1") == "cloud"
def test_anthropic_url_is_cloud(self):
assert _classify_runtime(base_url="https://api.anthropic.com") == "cloud"
def test_deepseek_url_is_cloud(self):
assert _classify_runtime(base_url="https://api.deepseek.com/v1") == "cloud"
# ── Provider-name classification ──────────────────────────────────────
def test_ollama_provider_is_local(self):
assert _classify_runtime(provider="ollama") == "local"
def test_custom_provider_is_local(self):
assert _classify_runtime(provider="custom") == "local"
def test_openrouter_provider_is_cloud(self):
assert _classify_runtime(provider="openrouter") == "cloud"
def test_nous_provider_is_cloud(self):
assert _classify_runtime(provider="nous") == "cloud"
def test_anthropic_provider_is_cloud(self):
assert _classify_runtime(provider="anthropic") == "cloud"
# ── Previously-missing cloud prefixes (issue #628) ────────────────────
def test_deepseek_model_prefix_is_cloud(self):
assert _classify_runtime(model="deepseek/deepseek-v2") == "cloud"
def test_cohere_model_prefix_is_cloud(self):
assert _classify_runtime(model="cohere/command-r-plus") == "cloud"
def test_mistralai_model_prefix_is_cloud(self):
assert _classify_runtime(model="mistralai/mistral-large-2407") == "cloud"
def test_meta_llama_model_prefix_is_cloud(self):
assert _classify_runtime(model="meta-llama/llama-3.1-70b-instruct") == "cloud"
def test_databricks_model_prefix_is_cloud(self):
assert _classify_runtime(model="databricks/dbrx-instruct") == "cloud"
def test_together_model_prefix_is_cloud(self):
assert _classify_runtime(model="together/together-api-model") == "cloud"
# ── Providers that were already detected before #628 ─────────────────
def test_openai_model_prefix_is_cloud(self):
assert _classify_runtime(model="openai/gpt-4.1") == "cloud"
def test_anthropic_model_prefix_is_cloud(self):
assert _classify_runtime(model="anthropic/claude-opus-4.6") == "cloud"
def test_google_model_prefix_is_cloud(self):
assert _classify_runtime(model="google/gemini-3-pro") == "cloud"
def test_minimax_model_prefix_is_cloud(self):
assert _classify_runtime(model="minimax/minimax-m2.7") == "cloud"
# ── Fallback / edge cases ────────────────────────────────────────────
def test_no_args_defaults_to_cloud(self):
assert _classify_runtime() == "cloud"
def test_empty_strings_default_to_cloud(self):
assert _classify_runtime(model="", base_url="", provider="") == "cloud"
def test_url_takes_priority_over_provider(self):
# Explicit local URL wins even if provider looks like cloud
assert _classify_runtime(model="openai/gpt-4", base_url="http://localhost:11434/v1", provider="openai") == "local"
def test_bare_model_name_without_slash_defaults_to_cloud(self):
# No slash → can't infer vendor → cloud (safe default)
assert _classify_runtime(model="gpt-4o") == "cloud"