feat(tools-pve/asr-pipeline): multi-backend ASR web app with LiteLLM routing

servers/tools-pve/asr-pipeline/asrpipe/llm.py

@@ -1,19 +1,7 @@
 #!/usr/bin/env python3
-"""HTTPS client for the model provider. No agent CLI, no SDK.
+"""HTTPS client for LiteLLM / OpenAI-compatible model gateways. No agent CLI, no SDK.
 
-Deliberately built on urllib so the program has zero third-party HTTP
-dependencies: it must keep working inside a bare systemd unit years from now.
-
-Behaviours encoded from measurement rather than guesswork:
-  * concurrency 6 (HTTP 429 appears at ~12)
-  * HTTP 402 "Payment Required" is transient on ZenMux — credit seems reserved
-    against max_tokens, so a burst of large-budget calls can trip it and then
-    succeed moments later; it gets a much longer backoff than a rate limit
-  * `temperature` is rejected outright by claude-sonnet-5.5 / opus-5 but accepted by
-    haiku-4.5, sonnet-4.6, gemini and qwen, so it cannot be inferred from the
-    vendor prefix; the client self-heals on the 400 and remembers
-  * an empty completion (reasoning models burning the whole budget on hidden
-    thoughts) is retried rather than silently propagated as ""
+Built on urllib so the program has zero third-party HTTP dependencies.
 """
 from __future__ import annotations
 
@@ -30,14 +18,22 @@ from .config import CFG
 from .log import log
 
 PRICES = {
+    "aistudio/gemini-flash-lite-latest": (0.3, 2.5),
+    "vertex/gemini-flash-lite-latest": (0.3, 2.5),
+    "gemini-flash-lite-latest": (0.3, 2.5),
     "google/gemini-3.5-flash-lite": (0.3, 2.5),
-    "google/gemini-3.5-flash": (1.5, 9.0),
+    "aistudio/gemini-flash-latest": (1.5, 9.0),
+    "vertex/gemini-flash-latest": (1.5, 9.0),
+    "aistudio/gemini-pro-latest": (2.5, 12.0),
+    "codex/gpt-sol-latest": (2.0, 8.0),
+    "openai/gpt-sol-latest": (2.0, 8.0),
+    "codex/gpt-luna-latest": (1.5, 6.0),
+    "xai/grok-latest": (2.0, 10.0),
     "anthropic/claude-haiku-4.5": (1.0, 5.0),
     "anthropic/claude-sonnet-5": (2.0, 10.0),
     "anthropic/claude-sonnet-5.5": (2.0, 10.0),
     "anthropic/claude-sonnet-4.6": (3.0, 15.0),
     "anthropic/claude-opus-5": (5.0, 25.0),
-    "qwen/qwen3.7-plus": (0.1373076, 0.5492304),
 }
 
 _sem = threading.BoundedSemaphore(CFG.concurrency)
@@ -45,6 +41,8 @@ _NO_TEMPERATURE: set[str] = {
     "anthropic/claude-sonnet-5",
     "anthropic/claude-sonnet-5.5",
     "anthropic/claude-opus-5",
+    "codex/gpt-sol-latest",
+    "codex/gpt-luna-latest",
 }
 _lock = threading.Lock()
 _key: list[str] = []
@@ -143,7 +141,7 @@ def chat(model: str, prompt: str, *, system: str | None = None,
                 except Exception:
                     pass
                 last = f"HTTP{e.code}: {detail[:200]}"
-                if e.code == 400 and "temperature" in detail:
+                if e.code == 400 and "temperature" in detail.lower():
                     with _lock:
                         _NO_TEMPERATURE.add(model)
                     payload = payload_of()
@@ -151,13 +149,12 @@ def chat(model: str, prompt: str, *, system: str | None = None,
                         cpath = _cache_path(model, payload)
                     retries += 1
                     continue
-                if e.code not in (402, 408, 429, 500, 502, 503, 504):
+                if e.code not in (408, 429, 500, 502, 503, 504):
                     if usage:
                         usage.failures += 1
                     raise RuntimeError(f"{model} {last}") from e
                 retries += 1
-                delay = (min(20 * (attempt + 1), 120) if e.code == 402
-                         else min(2 ** attempt + random.uniform(0, 1.5), 45))
+                delay = min(2 ** attempt + random.uniform(0, 1.5), 45)
                 log(f"llm retry {attempt+1}/{CFG.max_retries} {model} {last} "
                     f"sleep {delay:.0f}s", level="WARN")
                 time.sleep(delay)
@@ -203,8 +200,6 @@ def chat_many(model: str, prompts: list[str], **kw) -> list[str]:
             except BaseException as e:  # noqa: BLE001 - recorded, decided by caller
                 errors.append((i, e))
     if errors:
-        # Partial failure must not silently yield empty chunks: the caller falls
-        # back to the original text for these indices, which the gate then flags.
         for i, e in errors:
             log(f"chunk {i} failed: {e}", level="ERROR")
         raise PartialFailure(out, [i for i, _ in errors])