Add OpenCode Zen support, model health/stats dashboard, and gateway fallback fixes

AI gateway:
- Add a generic, admin-selectable `client_profile` field on gateway_providers
  (e.g. "opencode") so a provider needing special request headers (OpenCode
  Zen's client-identity spoofing) is configured like any other provider, not
  hardcoded by name.
- Track per-(provider, model) reliability/speed/latency health in memory,
  seeded from the existing gateway_usage_ledger at startup - purely
  observational, never influences routing.
- New Stats tab on /admin/gateway: request volume, latency, per-model
  breakdowns, and reliability weight, charted with a vendored Chart.js and
  devplace's own theme tokens.
- Record which model a failed request actually fell back to
  (fallback_used_route), surfaced in the Recent Failures table.
- Stop excluding context_length errors from fallback, and skip a primary
  attempt outright when its known context window is already too small for
  the estimated request size, going straight to the fallback.
- gateway_usage_ledger's provider/fallback_used_route columns and indexes
  are ensured centrally in database/schema.py's init_db(), the single point
  of truth for this table's schema.
- Non-OpenAI upstream routing and client-model passthrough; trust only the
  upstream's own X-Gateway-Model header for served-model attribution.

Devii agent:
- Fix a real lockup: plan/verify tools could be individually disabled via
  the admin tool toggles while still being required by the protocol gate,
  permanently bricking any task that needed tools. They can no longer be
  disabled, and the gate now also checks the tool is actually offered.
- Fix compaction being silently calibrated for a 1M-token model while
  running a much smaller one: context budget is now percentage-based and
  the summarizer's own request is sized to fit the real model.
- Give a specific, actionable retry message when plan()'s own arguments get
  cut off by the output limit, and tighten its schema to discourage
  overlong plans.

Other:
- Backup service: offload completed backups to a remote Hetzner Storage Box.
- Container manager: fix orphan blob leaks from sync races, add a two-phase
  plan/execute `system prune` CLI command.
- Admin gateway UI: replace the JS-rendered model/provider tables with
  server-rendered forms and pages.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DhmEkvutuwtzFVcLbTrhdo
This commit is contained in:
2026-09-09 07:38:24 +02:00
co-authored by Claude Sonnet 5
parent b475e7d6ed
commit 569f1dcc64
67 changed files with 6151 additions and 814 deletions
+109 -1
View File
@@ -15,6 +15,7 @@ from devplacepy.database import (
get_table,
sync_local_cache,
)
from devplacepy.services.openai_gateway import opencode_zen
logger = logging.getLogger(__name__)
@@ -23,6 +24,18 @@ MODELS_TABLE = "gateway_models"
CACHE_NAME = "gateway_routing"
KINDS = ("chat", "embed", "image")
# Admin-selectable on a gateway_providers row's `client_profile` field. A
# generic provider (the default, empty profile) sends no extra headers -
# this exists only for upstreams that reject requests unless they see a
# specific client's headers, e.g. OpenCode Zen's free tier only serves the
# real opencode CLI (spoofed via opencode_zen.opencode_impersonation_headers)
# and returns 429/400 to anything else. Adding a new profile is one entry
# here plus one option in the provider form - no other special-casing.
CLIENT_PROFILES: dict = {
"": None,
"opencode": opencode_zen.opencode_impersonation_headers,
}
_ROUTING_CACHE: dict = {}
@@ -56,6 +69,63 @@ def _image_url_from_base(base_url: str) -> str:
return base_url
def _models_url_from_base(base_url: str) -> str:
base_url = (base_url or "").strip()
if not base_url:
return ""
if base_url.endswith("/chat/completions"):
return base_url[: -len("/chat/completions")] + "/models"
return base_url.rstrip("/") + "/models"
PROVIDER_MODELS_PROBE_TIMEOUT = 8.0
def _default_provider_credentials() -> tuple[str, str]:
from devplacepy.services.manager import service_manager
svc = service_manager.get_service("openai")
cfg = svc.get_config() if svc is not None else {}
return cfg.get("gateway_upstream_url", ""), cfg.get("gateway_api_key", "")
async def fetch_provider_models(
provider_name: str, timeout: float = PROVIDER_MODELS_PROBE_TIMEOUT
) -> Optional[list[str]]:
provider_name = (provider_name or "").strip()
if provider_name:
provider = provider_store.get(provider_name)
if provider is None:
return None
base_url, api_key = provider.get("base_url", ""), provider.get("api_key", "")
else:
base_url, api_key = _default_provider_credentials()
models_url = _models_url_from_base(base_url)
if not models_url:
return None
from devplacepy import stealth
headers = {"authorization": f"Bearer {api_key}"} if api_key else {}
try:
async with stealth.stealth_async_client(timeout=timeout, headers=headers) as client:
response = await client.get(models_url)
except Exception as exc:
logger.info("gateway provider model listing failed for %s: %s", models_url, exc)
return None
if response.status_code != 200:
return None
try:
payload = response.json()
except Exception:
return None
rows = payload.get("data") if isinstance(payload, dict) else None
if not isinstance(rows, list):
return None
ids = [str(row["id"]) for row in rows if isinstance(row, dict) and row.get("id")]
return ids or None
MODEL_TIER2_COLUMNS = (
"context_tier_threshold_tokens",
"price_cache_hit_per_m_tier2",
@@ -73,8 +143,12 @@ def ensure_tables() -> None:
"CREATE TABLE IF NOT EXISTS "
+ PROVIDERS_TABLE
+ " (id INTEGER PRIMARY KEY, name TEXT, base_url TEXT, api_key TEXT, "
"is_active INTEGER DEFAULT 1, created_at TEXT, updated_at TEXT)"
"is_active INTEGER DEFAULT 1, client_profile TEXT DEFAULT '', "
"created_at TEXT, updated_at TEXT)"
)
providers_table = get_table(PROVIDERS_TABLE)
if not providers_table.has_column("client_profile"):
providers_table.create_column_by_example("client_profile", "")
db.query(
"CREATE TABLE IF NOT EXISTS "
+ MODELS_TABLE
@@ -121,6 +195,7 @@ class ProviderIn(BaseModel):
base_url: str = Field(default="", max_length=500)
api_key: str = Field(default="", max_length=400)
is_active: bool = True
client_profile: str = Field(default="", max_length=32)
@field_validator("name")
@classmethod
@@ -140,6 +215,16 @@ class ProviderIn(BaseModel):
raise ValueError("Base URL must be a http(s) URL")
return value
@field_validator("client_profile")
@classmethod
def _clean_client_profile(cls, value: str) -> str:
value = (value or "").strip().lower()
if value not in CLIENT_PROFILES:
raise ValueError(
f"client_profile must be one of: {', '.join(sorted(CLIENT_PROFILES)) or '(none)'}"
)
return value
class ModelRouteIn(BaseModel):
source_model: str = Field(min_length=1, max_length=128)
@@ -280,6 +365,7 @@ def _load() -> dict:
"base_url": str(row.get("base_url") or ""),
"api_key": str(row.get("api_key") or ""),
"is_active": _as_bool(row.get("is_active", 1)),
"client_profile": str(row.get("client_profile") or ""),
}
if MODELS_TABLE in db.tables:
for row in get_table(MODELS_TABLE).all():
@@ -317,6 +403,7 @@ class ProviderStore:
"base_url": payload.base_url,
"api_key": payload.api_key,
"is_active": 1 if payload.is_active else 0,
"client_profile": payload.client_profile,
"updated_at": _now(),
}
if existing:
@@ -500,6 +587,15 @@ def seed_default_deepseek_routes() -> None:
_ROUTING_CACHE.clear()
def _header_hook_for(provider_name: str):
if not provider_name:
return None
provider = provider_store.get(provider_name)
if provider is None:
return None
return CLIENT_PROFILES.get(provider.get("client_profile") or "")
def _provider_overlay(name: str, base_key: str, url_key: str, overlay: dict) -> None:
provider = provider_store.get(name)
if provider is None:
@@ -527,11 +623,15 @@ def chat_overlay(requested_model: Optional[str], base_cfg: dict) -> Optional[dic
"gateway_off_peak_start_minute": route.off_peak_start_minute,
"gateway_off_peak_end_minute": route.off_peak_end_minute,
"gateway_off_peak_discount_pct": route.off_peak_discount_pct,
"gateway_provider_name": route.provider or "default",
}
if route.provider:
_provider_overlay(
route.provider, "gateway_api_key", "gateway_upstream_url", overlay
)
header_hook = _header_hook_for(route.provider)
if header_hook is not None:
overlay["gateway_extra_request_headers"] = header_hook()
if route.context_window:
from devplacepy.services.openai_gateway.usage import parse_context_map
@@ -570,6 +670,7 @@ def embed_overlay(requested_model: Optional[str], base_cfg: dict) -> Optional[di
"gateway_off_peak_start_minute": route.off_peak_start_minute,
"gateway_off_peak_end_minute": route.off_peak_end_minute,
"gateway_off_peak_discount_pct": route.off_peak_discount_pct,
"gateway_provider_name": route.provider or "default",
}
provider = provider_store.get(route.provider) if route.provider else None
if provider:
@@ -577,6 +678,9 @@ def embed_overlay(requested_model: Optional[str], base_cfg: dict) -> Optional[di
overlay["gateway_embed_url"] = _embed_url_from_base(provider["base_url"])
if provider.get("api_key"):
overlay["gateway_embed_key"] = provider["api_key"]
header_hook = _header_hook_for(route.provider)
if header_hook is not None:
overlay["gateway_extra_request_headers"] = header_hook()
return overlay
@@ -591,6 +695,7 @@ def image_overlay(requested_model: Optional[str], base_cfg: dict) -> Optional[di
"gateway_off_peak_start_minute": route.off_peak_start_minute,
"gateway_off_peak_end_minute": route.off_peak_end_minute,
"gateway_off_peak_discount_pct": route.off_peak_discount_pct,
"gateway_provider_name": route.provider or "default",
}
provider = provider_store.get(route.provider) if route.provider else None
if provider:
@@ -598,6 +703,9 @@ def image_overlay(requested_model: Optional[str], base_cfg: dict) -> Optional[di
overlay["gateway_image_url"] = _image_url_from_base(provider["base_url"])
if provider.get("api_key"):
overlay["gateway_image_key"] = provider["api_key"]
header_hook = _header_hook_for(route.provider)
if header_hook is not None:
overlay["gateway_extra_request_headers"] = header_hook()
return overlay