fix(fallback): merge fallback_providers with legacy fallback_model configurations

This commit is contained in:
QuenVix 2026-05-23 09:31:27 +03:00 committed by Teknium
parent 7f1b2b4569
commit 7245bc77eb
8 changed files with 178 additions and 38 deletions

11
cli.py
View file

@ -51,6 +51,8 @@ os.environ["HERMES_QUIET"] = "1" # Our own modules
import yaml
from hermes_cli.fallback_config import get_fallback_chain
# prompt_toolkit for fixed input area TUI
from prompt_toolkit.history import FileHistory
from prompt_toolkit.styles import Style as PTStyle
@ -3049,12 +3051,9 @@ class HermesCLI:
pass
# Fallback provider chain — tried in order when primary fails after retries.
# Supports new list format (fallback_providers) and legacy single-dict (fallback_model).
fb = CLI_CONFIG.get("fallback_providers") or CLI_CONFIG.get("fallback_model") or []
# Normalize legacy single-dict to a one-element list
if isinstance(fb, dict):
fb = [fb] if fb.get("provider") and fb.get("model") else []
self._fallback_model = fb
# Merge new ``fallback_providers`` entries with any legacy
# ``fallback_model`` entries so old configs still participate.
self._fallback_model = get_fallback_chain(CLI_CONFIG)
# Signature of the currently-initialised agent's runtime. Used to
# rebuild the agent when provider / model / base_url changes across

View file

@ -54,6 +54,7 @@ from agent.account_usage import fetch_account_usage, render_account_usage_lines
from agent.async_utils import safe_schedule_threadsafe
from agent.i18n import t
from hermes_cli.config import cfg_get
from hermes_cli.fallback_config import get_fallback_chain
# --- Agent cache tuning ---------------------------------------------------
# Bounds the per-session AIAgent cache to prevent unbounded growth in
@ -1008,14 +1009,10 @@ def _try_resolve_fallback_provider() -> dict | None:
return None
with open(cfg_path, encoding="utf-8") as _f:
cfg = _y.safe_load(_f) or {}
fb = cfg.get("fallback_providers") or cfg.get("fallback_model")
if not fb:
fb_list = get_fallback_chain(cfg)
if not fb_list:
return None
# Normalize to list
fb_list = fb if isinstance(fb, list) else [fb]
for entry in fb_list:
if not isinstance(entry, dict):
continue
try:
explicit_api_key = entry.get("api_key")
if not explicit_api_key:
@ -2888,12 +2885,12 @@ class GatewayRunner:
return {}
@staticmethod
def _load_fallback_model() -> list | dict | None:
def _load_fallback_model() -> list | None:
"""Load fallback provider chain from config.yaml.
Returns a list of provider dicts (``fallback_providers``), a single
dict (legacy ``fallback_model``), or None if not configured.
AIAgent.__init__ normalizes both formats into a chain.
Returns the merged effective chain from ``fallback_providers`` plus any
legacy ``fallback_model`` entries. ``fallback_providers`` stays first
when both keys are present.
"""
try:
import yaml as _y
@ -2901,7 +2898,7 @@ class GatewayRunner:
if cfg_path.exists():
with open(cfg_path, encoding="utf-8") as _f:
cfg = _y.safe_load(_f) or {}
fb = cfg.get("fallback_providers") or cfg.get("fallback_model") or None
fb = get_fallback_chain(cfg)
if fb:
return fb
except Exception:

View file

@ -21,6 +21,8 @@ from __future__ import annotations
import copy
from typing import Any, Dict, List, Optional
from hermes_cli.fallback_config import get_fallback_chain
# ---------------------------------------------------------------------------
# Helpers
@ -30,20 +32,11 @@ def _read_chain(config: Dict[str, Any]) -> List[Dict[str, Any]]:
"""Return the normalized fallback chain as a list of dicts.
Accepts both the new list format (``fallback_providers``) and the legacy
single-dict format (``fallback_model``). The returned list is always a
fresh copy callers can mutate without touching the config dict.
``fallback_model`` format. When both are present, the effective chain is
merged with ``fallback_providers`` entries kept first. The returned list is
always a fresh copy callers can mutate without touching the config dict.
"""
chain = config.get("fallback_providers") or []
if isinstance(chain, list):
result = [dict(e) for e in chain if isinstance(e, dict) and e.get("provider") and e.get("model")]
if result:
return result
legacy = config.get("fallback_model")
if isinstance(legacy, dict) and legacy.get("provider") and legacy.get("model"):
return [dict(legacy)]
if isinstance(legacy, list):
return [dict(e) for e in legacy if isinstance(e, dict) and e.get("provider") and e.get("model")]
return []
return get_fallback_chain(config)
def _write_chain(config: Dict[str, Any], chain: List[Dict[str, Any]]) -> None:

View file

@ -0,0 +1,72 @@
"""Helpers for reading the effective fallback provider chain from config."""
from __future__ import annotations
from typing import Any
def _normalized_base_url(value: Any) -> str:
if not isinstance(value, str):
return ""
return value.strip().rstrip("/")
def _iter_fallback_entries(raw: Any) -> list[dict[str, Any]]:
if isinstance(raw, dict):
candidates = [raw]
elif isinstance(raw, list):
candidates = raw
else:
return []
entries: list[dict[str, Any]] = []
for entry in candidates:
if not isinstance(entry, dict):
continue
provider = str(entry.get("provider") or "").strip()
model = str(entry.get("model") or "").strip()
if not provider or not model:
continue
normalized = dict(entry)
normalized["provider"] = provider
normalized["model"] = model
base_url = _normalized_base_url(entry.get("base_url"))
if base_url:
normalized["base_url"] = base_url
entries.append(normalized)
return entries
def _entry_identity(entry: dict[str, Any]) -> tuple[str, str, str]:
return (
str(entry.get("provider") or "").strip().lower(),
str(entry.get("model") or "").strip().lower(),
_normalized_base_url(entry.get("base_url")).lower(),
)
def get_fallback_chain(config: dict[str, Any] | None) -> list[dict[str, Any]]:
"""Return the effective fallback chain merged across old and new config keys.
``fallback_providers`` remains the primary source of truth and keeps its
order. Legacy ``fallback_model`` entries are appended afterwards unless
they target the same provider/model/base_url route as an earlier entry.
The returned list always contains fresh dict copies.
"""
config = config or {}
chain: list[dict[str, Any]] = []
seen: set[tuple[str, str, str]] = set()
for key in ("fallback_providers", "fallback_model"):
for entry in _iter_fallback_entries(config.get(key)):
identity = _entry_identity(entry)
if identity in seen:
continue
seen.add(identity)
chain.append(entry)
return chain

View file

@ -28,6 +28,8 @@ import sys
from contextlib import redirect_stderr, redirect_stdout
from typing import Optional
from hermes_cli.fallback_config import get_fallback_chain
def _normalize_toolsets(toolsets: object = None) -> list[str] | None:
if not toolsets:
@ -301,14 +303,9 @@ def _run_agent(
toolsets_list = sorted(_get_platform_tools(cfg, "cli"))
session_db = _create_session_db_for_oneshot()
# Read fallback chain from profile config — supports both the new list
# format (fallback_providers) and the legacy single-dict (fallback_model).
# Mirrors the same normalization in cli.py so oneshot workers (e.g. kanban
# workers spawned via `hermes -p <profile> chat -q ...`) honour the
# profile's fallback chain just like interactive sessions do.
_fb = cfg.get("fallback_providers") or cfg.get("fallback_model") or []
if isinstance(_fb, dict):
_fb = [_fb] if _fb.get("provider") and _fb.get("model") else []
# Read the effective fallback chain from profile config so oneshot workers
# honour the same merge semantics as interactive CLI and gateway sessions.
_fb = get_fallback_chain(cfg)
agent = AIAgent(
api_key=runtime.get("api_key"),

View file

@ -102,6 +102,20 @@ class TestVerboseAndToolProgress:
assert cli.tool_progress_mode in {"off", "new", "all", "verbose"}
class TestFallbackChainInit:
def test_merges_new_and_legacy_fallback_config(self):
cli = _make_cli(config_overrides={
"fallback_providers": [
{"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
],
"fallback_model": {"provider": "nous", "model": "Hermes-4"},
})
assert cli._fallback_model == [
{"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
{"provider": "nous", "model": "Hermes-4"},
]
class TestBusyInputMode:
def test_default_busy_input_mode_is_interrupt(self):
cli = _make_cli()

View file

@ -71,3 +71,46 @@ class TestResolveRuntimeAgentKwargsAuthFallback:
from gateway.run import _resolve_runtime_agent_kwargs
with pytest.raises(RuntimeError):
_resolve_runtime_agent_kwargs()
def test_legacy_fallback_is_appended_after_fallback_providers(self, tmp_path, monkeypatch):
"""When both keys exist, the legacy entry still participates in resolution."""
config_path = tmp_path / "config.yaml"
config_path.write_text(
"fallback_providers:\n"
" - provider: openrouter\n"
" model: anthropic/claude-sonnet-4.6\n"
"fallback_model:\n"
" provider: nous\n"
" model: Hermes-4\n"
)
monkeypatch.setattr("gateway.run._hermes_home", tmp_path)
calls = []
def _mock_resolve(**kwargs):
requested = kwargs.get("requested")
calls.append(requested)
if requested == "openrouter":
raise RuntimeError("openrouter unavailable")
return {
"api_key": "nous-key",
"base_url": "https://portal.nousresearch.com/v1",
"provider": "nous",
"api_mode": "chat_completions",
"command": None,
"args": None,
"credential_pool": None,
}
with patch(
"hermes_cli.runtime_provider.resolve_runtime_provider",
side_effect=_mock_resolve,
):
from gateway.run import _try_resolve_fallback_provider
result = _try_resolve_fallback_provider()
assert calls == ["openrouter", "nous"]
assert result["provider"] == "nous"
assert result["model"] == "Hermes-4"

View file

@ -55,6 +55,31 @@ class TestReadChain:
{"provider": "nous", "model": "Hermes-4-Llama-3.1-405B"},
]
def test_merges_new_and_legacy_formats(self):
from hermes_cli.fallback_cmd import _read_chain
cfg = {
"fallback_providers": [
{"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
],
"fallback_model": {"provider": "nous", "model": "Hermes-4"},
}
assert _read_chain(cfg) == [
{"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
{"provider": "nous", "model": "Hermes-4"},
]
def test_legacy_duplicate_is_deduplicated_after_merge(self):
from hermes_cli.fallback_cmd import _read_chain
cfg = {
"fallback_providers": [
{"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
],
"fallback_model": {"provider": "OpenRouter", "model": "anthropic/claude-sonnet-4.6"},
}
assert _read_chain(cfg) == [
{"provider": "openrouter", "model": "anthropic/claude-sonnet-4.6"},
]
def test_migrates_legacy_single_dict(self):
from hermes_cli.fallback_cmd import _read_chain
cfg = {"fallback_model": {"provider": "openrouter", "model": "gpt-5.4"}}