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
175 lines
5.5 KiB
Python
175 lines
5.5 KiB
Python
# retoor <retoor@molodetz.nl>
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any, Optional
|
|
|
|
CLIENT_THINKING_KEYS = (
|
|
"think",
|
|
"thinking",
|
|
"reasoning",
|
|
"reasoning_effort",
|
|
"enable_thinking",
|
|
)
|
|
|
|
FALSE_VALUES = {False, 0, "0", "false", "no", "off", "none", "disabled"}
|
|
TRUE_VALUES = {True, 1, "1", "true", "yes", "on", "enabled"}
|
|
EFFORT_VALUES = {"low", "medium", "high", "max", "xhigh"}
|
|
|
|
|
|
def thinking_dialect(url: str) -> str:
|
|
text = (url or "").lower()
|
|
if "deepseek.com" in text:
|
|
return "deepseek"
|
|
if "openrouter.ai" in text:
|
|
return "openrouter"
|
|
if "11434" in text or "ollama" in text:
|
|
return "ollama"
|
|
return "deepseek"
|
|
|
|
|
|
def _resolve_dialect(url: str, dialect: str) -> str:
|
|
effective = dialect.strip().lower()
|
|
if effective in ("", "auto"):
|
|
return thinking_dialect(url)
|
|
return effective
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class UpstreamCapabilities:
|
|
dialect: str
|
|
supports_stream_options: bool
|
|
supports_stream_usage: bool
|
|
supports_thinking_field: bool
|
|
|
|
|
|
def upstream_capabilities(
|
|
url: str, dialect: str = "", ollama_stream_usage: bool = False
|
|
) -> UpstreamCapabilities:
|
|
# Current Ollama docs list stream_options.include_usage as supported, but
|
|
# real deployed server versions vary and some reject it outright (see
|
|
# github.com/ollama/ollama issues #15288/#15293/#14820) - default off,
|
|
# gateway_ollama_stream_usage lets an operator opt in for a known-good build.
|
|
effective = _resolve_dialect(url, dialect)
|
|
if effective == "ollama":
|
|
return UpstreamCapabilities(
|
|
dialect=effective,
|
|
supports_stream_options=bool(ollama_stream_usage),
|
|
supports_stream_usage=bool(ollama_stream_usage),
|
|
supports_thinking_field=True,
|
|
)
|
|
return UpstreamCapabilities(
|
|
dialect=effective,
|
|
supports_stream_options=True,
|
|
supports_stream_usage=True,
|
|
supports_thinking_field=True,
|
|
)
|
|
|
|
|
|
def _as_text(value: Any) -> str:
|
|
if isinstance(value, str):
|
|
return value.strip().lower()
|
|
return ""
|
|
|
|
|
|
def _is_false(value: Any) -> bool:
|
|
if isinstance(value, str):
|
|
return value.strip().lower() in FALSE_VALUES
|
|
return value in FALSE_VALUES
|
|
|
|
|
|
def _is_true(value: Any) -> bool:
|
|
if isinstance(value, str):
|
|
text = value.strip().lower()
|
|
return text in TRUE_VALUES or text in EFFORT_VALUES
|
|
return value in TRUE_VALUES
|
|
|
|
|
|
def client_thinking_enabled(body: Any) -> Optional[bool]:
|
|
if not isinstance(body, dict):
|
|
return None
|
|
thinking = body.get("thinking")
|
|
if isinstance(thinking, dict) and "type" in thinking:
|
|
kind = _as_text(thinking.get("type"))
|
|
if kind in ("disabled", "none", "off"):
|
|
return False
|
|
if kind in ("enabled", "on"):
|
|
return True
|
|
if "think" in body:
|
|
value = body.get("think")
|
|
if _is_false(value):
|
|
return False
|
|
if _is_true(value):
|
|
return True
|
|
return bool(value)
|
|
reasoning = body.get("reasoning")
|
|
if isinstance(reasoning, dict):
|
|
if "enabled" in reasoning:
|
|
return _flag_enabled(reasoning.get("enabled"))
|
|
effort = _as_text(reasoning.get("effort"))
|
|
if effort == "none":
|
|
return False
|
|
if effort in EFFORT_VALUES:
|
|
return True
|
|
if "reasoning_effort" in body:
|
|
effort = _as_text(body.get("reasoning_effort"))
|
|
if effort == "none":
|
|
return False
|
|
if effort in EFFORT_VALUES:
|
|
return True
|
|
if "enable_thinking" in body:
|
|
return _flag_enabled(body.get("enable_thinking"))
|
|
kwargs = body.get("chat_template_kwargs")
|
|
if isinstance(kwargs, dict) and "enable_thinking" in kwargs:
|
|
return _flag_enabled(kwargs.get("enable_thinking"))
|
|
return None
|
|
|
|
|
|
def _flag_enabled(value: Any) -> bool:
|
|
if _is_false(value):
|
|
return False
|
|
if _is_true(value):
|
|
return True
|
|
return bool(value)
|
|
|
|
|
|
def _clear_thinking_fields(payload: dict) -> None:
|
|
for key in CLIENT_THINKING_KEYS:
|
|
payload.pop(key, None)
|
|
kwargs = payload.get("chat_template_kwargs")
|
|
if isinstance(kwargs, dict):
|
|
kwargs.pop("enable_thinking", None)
|
|
if not kwargs:
|
|
payload.pop("chat_template_kwargs", None)
|
|
|
|
|
|
def write_thinking(payload: dict, dialect: str, enabled: bool) -> None:
|
|
_clear_thinking_fields(payload)
|
|
if dialect == "openrouter":
|
|
payload["reasoning"] = {"effort": "high" if enabled else "none"}
|
|
return
|
|
if dialect == "ollama":
|
|
# Ollama's native /api/chat honors a boolean `think`, but its
|
|
# OpenAI-compatible /v1/chat/completions layer does not (confirmed
|
|
# against github.com/ollama/ollama issues #15288/#15293/#14820,
|
|
# Sep 2026): that endpoint maps `reasoning_effort`/`reasoning.effort`
|
|
# onto its internal think flag instead. Send both - `think` is
|
|
# harmless if ignored, `reasoning_effort` is the field the
|
|
# OpenAI-compat endpoint actually honors.
|
|
payload["think"] = bool(enabled)
|
|
payload["reasoning_effort"] = "high" if enabled else "none"
|
|
return
|
|
payload["thinking"] = {"type": "enabled" if enabled else "disabled"}
|
|
|
|
|
|
def apply_thinking(
|
|
payload: dict,
|
|
upstream_url: str,
|
|
default_enabled: bool = False,
|
|
dialect: str = "",
|
|
) -> dict:
|
|
effective = _resolve_dialect(upstream_url, dialect)
|
|
specified = client_thinking_enabled(payload)
|
|
enabled = default_enabled if specified is None else specified
|
|
write_thinking(payload, effective, enabled)
|
|
return payload
|