fix(auxiliary): honor main fallback chain for auto tasks (#47235)

This commit is contained in:
Teknium
2026-06-16 06:23:24 -07:00
committed by GitHub
parent 4d470b3dbb
commit 4858942c55
7 changed files with 290 additions and 38 deletions
+159 -27
View File
@@ -3079,23 +3079,20 @@ def _try_configured_fallback_chain(
if not fb_provider or fb_provider.lower() == skip:
continue
fb_model = str(entry.get("model", "")).strip() or None
fb_base_url = str(entry.get("base_url", "")).strip() or None
fb_api_key = str(entry.get("api_key", "")).strip() or None
label = f"fallback_chain[{i}]({fb_provider})"
try:
fb_client = _resolve_single_provider(
fb_provider, fb_model, fb_base_url, fb_api_key)
fb_client, resolved_model = _resolve_fallback_entry(entry)
except Exception:
fb_client = None
fb_client, resolved_model = None, None
if fb_client is not None:
logger.info(
"Auxiliary %s: %s on %s — configured fallback to %s (%s)",
task, reason, failed_provider, label, fb_model or "default",
task, reason, failed_provider, label, resolved_model or fb_model or "default",
)
return fb_client, fb_model, label
return fb_client, resolved_model or fb_model, label
tried.append(label)
if tried:
@@ -3106,6 +3103,103 @@ def _try_configured_fallback_chain(
return None, None, ""
def _fallback_entry_api_key(entry: Dict[str, Any]) -> Optional[str]:
"""Resolve inline or env-backed API key from a fallback-chain entry."""
explicit = str(entry.get("api_key") or "").strip()
if explicit:
return explicit
key_env = str(entry.get("key_env") or entry.get("api_key_env") or "").strip()
if key_env:
return os.getenv(key_env, "").strip() or None
return None
def _resolve_fallback_entry(entry: Dict[str, Any]) -> Tuple[Optional[Any], Optional[str]]:
"""Resolve one fallback entry through the central provider router."""
provider = str(entry.get("provider") or "").strip()
model = str(entry.get("model") or "").strip() or None
if not provider or not model:
return None, None
base_url = str(entry.get("base_url") or "").strip() or None
api_key = _fallback_entry_api_key(entry)
api_mode = str(entry.get("api_mode") or entry.get("transport") or "").strip() or None
return resolve_provider_client(
provider,
model=model,
explicit_base_url=base_url,
explicit_api_key=api_key,
api_mode=api_mode,
)
def _try_main_fallback_chain(
task: Optional[str],
failed_provider: str = "",
reason: str = "error",
) -> Tuple[Optional[Any], Optional[str], str]:
"""Try the top-level main-agent fallback chain for an auxiliary call.
``provider: auto`` auxiliary tasks should respect the user's declared
main fallback policy before dropping into Hermes' built-in discovery
chain. The top-level chain is read through ``get_fallback_chain`` so
both modern ``fallback_providers`` and legacy ``fallback_model`` entries
participate in the same order as the main agent.
"""
try:
from hermes_cli.config import load_config
from hermes_cli.fallback_config import get_fallback_chain
chain = get_fallback_chain(load_config())
except Exception as exc:
logger.debug("Auxiliary %s: could not load main fallback chain: %s", task or "call", exc)
return None, None, ""
if not chain:
return None, None, ""
failed_norm = (failed_provider or "").strip().lower()
main_norm = (_read_main_provider() or "").strip().lower()
skip = {p for p in (failed_norm, main_norm, "auto") if p}
tried: List[str] = []
for i, entry in enumerate(chain):
if not isinstance(entry, dict):
continue
fb_provider = str(entry.get("provider") or "").strip()
fb_model = str(entry.get("model") or "").strip()
if not fb_provider or not fb_model:
continue
fb_norm = fb_provider.lower()
label = f"fallback_providers[{i}]({fb_provider})"
if fb_norm in skip:
tried.append(f"{label} (skipped)")
continue
if _is_provider_unhealthy(fb_norm):
_log_skip_unhealthy(fb_norm, task)
tried.append(f"{label} (unhealthy)")
continue
try:
fb_client, resolved_model = _resolve_fallback_entry(entry)
except Exception as exc:
logger.debug("Auxiliary %s: main fallback %s failed to resolve: %s", task or "call", label, exc)
fb_client, resolved_model = None, None
if fb_client is not None:
logger.info(
"Auxiliary %s: %s on %s — main fallback chain to %s (%s)",
task or "call", reason, failed_provider or "auto", label,
resolved_model or fb_model,
)
return fb_client, resolved_model or fb_model, fb_provider
tried.append(label)
if tried:
logger.debug(
"Auxiliary %s: main fallback chain exhausted (tried: %s)",
task or "call", ", ".join(tried),
)
return None, None, ""
def _resolve_single_provider(
provider: str,
model: Optional[str] = None,
@@ -3116,16 +3210,19 @@ def _resolve_single_provider(
Uses the existing provider resolution infrastructure where possible.
"""
# Reuse resolve_provider_client which handles provider→client mapping
# Reuse resolve_provider_client which handles provider→client mapping.
client, resolved_model = resolve_provider_client(
provider=provider,
model=model,
base_url=base_url,
api_key=api_key,
explicit_base_url=base_url,
explicit_api_key=api_key,
)
return client
def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Optional[OpenAI], Optional[str]]:
def _resolve_auto(
main_runtime: Optional[Dict[str, Any]] = None,
task: Optional[str] = None,
) -> Tuple[Optional[OpenAI], Optional[str]]:
"""Full auto-detection chain.
Priority:
@@ -3223,7 +3320,22 @@ def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Option
main_provider, resolved or main_model)
return client, resolved or main_model
# ── Step 2: aggregator / fallback chain ──────────────────────────────
# ── Step 2: user-configured fallback policy ─────────────────────────
# In auto mode, respect the task-specific fallback chain first, then the
# main agent's top-level fallback_providers/fallback_model chain. The
# hardcoded provider discovery chain below is only the convenience default
# for users who have not declared a fallback policy.
if task:
fb_client, fb_model, _fb_label = _try_configured_fallback_chain(
task, main_provider or "auto", reason="main provider unavailable")
if fb_client is not None:
return fb_client, fb_model
fb_client, fb_model, _fb_label = _try_main_fallback_chain(
task, main_provider or "auto", reason="main provider unavailable")
if fb_client is not None:
return fb_client, fb_model
# ── Step 3: aggregator / fallback chain ──────────────────────────────
tried = []
for label, try_fn in _get_provider_chain():
if _is_provider_unhealthy(label):
@@ -3344,6 +3456,7 @@ def resolve_provider_client(
api_mode: str = None,
main_runtime: Optional[Dict[str, Any]] = None,
is_vision: bool = False,
task: Optional[str] = None,
) -> Tuple[Optional[Any], Optional[str]]:
"""Central router: given a provider name and optional model, return a
configured client with the correct auth, base URL, and API format.
@@ -3464,7 +3577,7 @@ def resolve_provider_client(
# ── Auto: try all providers in priority order ────────────────────
if provider == "auto":
client, resolved = _resolve_auto(main_runtime=main_runtime)
client, resolved = _resolve_auto(main_runtime=main_runtime, task=task)
if client is None:
return None, None
# When auto-detection lands on a non-OpenRouter provider (e.g. a
@@ -4357,11 +4470,16 @@ def _client_cache_key(
api_mode: Optional[str] = None,
main_runtime: Optional[Dict[str, Any]] = None,
is_vision: bool = False,
task: Optional[str] = None,
) -> tuple:
runtime = _normalize_main_runtime(main_runtime)
runtime_key = tuple(runtime.get(field, "") for field in _MAIN_RUNTIME_FIELDS) if provider == "auto" else ()
# `auto` can now resolve through task-specific or main fallback policy,
# so the task participates in the cache key. Non-auto providers keep the
# old cache shape because the explicit provider/model tuple is sufficient.
task_key = (task or "") if provider == "auto" else ""
pool_hint = _pool_cache_hint(provider, main_runtime=main_runtime)
return (provider, async_mode, base_url or "", api_key or "", api_mode or "", runtime_key, is_vision, pool_hint)
return (provider, async_mode, base_url or "", api_key or "", api_mode or "", runtime_key, is_vision, task_key, pool_hint)
def _store_cached_client(cache_key: tuple, client: Any, default_model: Optional[str], *, bound_loop: Any = None) -> None:
@@ -4554,6 +4672,7 @@ def _get_cached_client(
api_mode: str = None,
main_runtime: Optional[Dict[str, Any]] = None,
is_vision: bool = False,
task: Optional[str] = None,
) -> Tuple[Optional[Any], Optional[str]]:
"""Get or create a cached client for the given provider.
@@ -4591,6 +4710,7 @@ def _get_cached_client(
api_mode=api_mode,
main_runtime=main_runtime,
is_vision=is_vision,
task=task,
)
with _client_cache_lock:
if cache_key in _client_cache:
@@ -4635,6 +4755,7 @@ def _get_cached_client(
api_mode=api_mode,
main_runtime=runtime,
is_vision=is_vision,
task=task,
)
if client is not None:
# For async clients, remember which loop they were created on so we
@@ -5140,7 +5261,7 @@ def call_llm(
if not resolved_base_url:
logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
task or "call", resolved_provider)
client, final_model = _get_cached_client("auto", main_runtime=main_runtime)
client, final_model = _get_cached_client("auto", main_runtime=main_runtime, task=task)
if client is None:
raise RuntimeError(
f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -5466,14 +5587,19 @@ def call_llm(
# Fallback order (#26882, #26803):
# 1. User-configured fallback_chain (per-task) if set
# 2. Main agent model (last-resort safety net)
# For auto users (no explicit aux provider), use the full
# auto-detection chain instead — its Step 1 IS the main agent
# model, so users on `auto` already get main-model fallback.
# 2. For auto: top-level main fallback_providers/fallback_model
# 3. For auto: built-in auxiliary discovery chain
# 4. For explicit aux providers: main agent model safety net
fb_client, fb_model, fb_label = (None, None, "")
if is_auto:
fb_client, fb_model, fb_label = _try_payment_fallback(
resolved_provider, task, reason=reason)
fb_client, fb_model, fb_label = _try_configured_fallback_chain(
task, resolved_provider or "auto", reason=reason)
if fb_client is None:
fb_client, fb_model, fb_label = _try_main_fallback_chain(
task, resolved_provider or "auto", reason=reason)
if fb_client is None:
fb_client, fb_model, fb_label = _try_payment_fallback(
resolved_provider, task, reason=reason)
else:
fb_client, fb_model, fb_label = _try_configured_fallback_chain(
task, resolved_provider or "auto", reason=reason)
@@ -5636,7 +5762,7 @@ async def async_call_llm(
if not resolved_base_url:
logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
task or "call", resolved_provider)
client, final_model = _get_cached_client("auto", async_mode=True)
client, final_model = _get_cached_client("auto", async_mode=True, main_runtime=main_runtime, task=task)
if client is None:
raise RuntimeError(
f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -5904,13 +6030,19 @@ async def async_call_llm(
# Fallback order (#26882, #26803):
# 1. User-configured fallback_chain (per-task) if set
# 2. Main agent model (last-resort safety net)
# Auto users get the full auto-detection chain instead — its
# Step 1 IS the main agent model.
# 2. For auto: top-level main fallback_providers/fallback_model
# 3. For auto: built-in auxiliary discovery chain
# 4. For explicit aux providers: main agent model safety net
fb_client, fb_model, fb_label = (None, None, "")
if is_auto:
fb_client, fb_model, fb_label = _try_payment_fallback(
resolved_provider, task, reason=reason)
fb_client, fb_model, fb_label = _try_configured_fallback_chain(
task, resolved_provider or "auto", reason=reason)
if fb_client is None:
fb_client, fb_model, fb_label = _try_main_fallback_chain(
task, resolved_provider or "auto", reason=reason)
if fb_client is None:
fb_client, fb_model, fb_label = _try_payment_fallback(
resolved_provider, task, reason=reason)
else:
fb_client, fb_model, fb_label = _try_configured_fallback_chain(
task, resolved_provider or "auto", reason=reason)