mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-11 03:31:55 +00:00
fix(opencode-go): keep users on opencode-go instead of hijacking to native providers (#20802)
OpenCode Go and OpenCode Zen are flat-namespace model resellers — their /v1/models returns bare IDs (deepseek-v4-flash, minimax-m2.7), and the inference API rejects vendor-prefixed names with HTTP 401 'Model not supported'. Two bugs fixed: 1. `switch_model` in hermes_cli/model_switch.py was silently switching the user off opencode-go to native deepseek when they typed `/model deepseek-v4-flash`. Step d found the model in opencode-go's live catalog, but step e (detect_provider_for_model) still ran and matched the bare name against deepseek's static catalog. Fix: track whether the live catalog resolved it; skip step e when it did. 2. `normalize_model_for_provider` in hermes_cli/model_normalize.py only stripped the exact `opencode-zen/` prefix, leaving arbitrary vendor prefixes like `minimax/minimax-m2.7` (commonly copied from aggregator slugs into fallback_model configs) intact — causing HTTP 401s when the fallback chain activated. Fix: opencode-go/opencode-zen strip ANY leading vendor prefix because their APIs are flat-namespace. Tests: 11 new cases in tests/hermes_cli/test_opencode_go_flat_namespace.py covering both normalization (prefix stripping, regression guards for opencode-zen Claude hyphenation and openrouter vendor-prepending) and switch_model (bare-name resolution on opencode-go's live catalog must not trigger cross-provider hijack). Reported by @Ufonik via Discord; Kimi K2.6 always worked because moonshotai has no overlapping entry in a native provider's static catalog. Deepseek and minimax failed because their v4/v2.7 names existed in the native deepseek/minimax catalogs.
This commit is contained in:
parent
773cf48c50
commit
a24789d738
3 changed files with 183 additions and 8 deletions
|
|
@ -393,14 +393,21 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
|
|||
if provider in _AGGREGATOR_PROVIDERS:
|
||||
return _prepend_vendor(name)
|
||||
|
||||
# --- OpenCode Zen: Claude stays hyphenated; other models keep dots ---
|
||||
if provider == "opencode-zen":
|
||||
bare = _strip_matching_provider_prefix(name, provider)
|
||||
if "/" in bare:
|
||||
return bare
|
||||
if bare.lower().startswith("claude-"):
|
||||
return _dots_to_hyphens(bare)
|
||||
return bare
|
||||
# --- OpenCode Zen / OpenCode Go: flat-namespace resellers.
|
||||
# Their /v1/models API returns bare IDs only (no vendor prefix), and
|
||||
# the inference endpoint rejects vendor-prefixed names with HTTP 401
|
||||
# "Model not supported". Strip ANY leading ``vendor/`` so config
|
||||
# entries like ``minimax/minimax-m2.7`` or ``deepseek/deepseek-v4-flash``
|
||||
# — commonly copied from aggregator slugs into fallback_model lists —
|
||||
# resolve to bare ``minimax-m2.7`` / ``deepseek-v4-flash`` the API
|
||||
# actually serves. See PR reviewing opencode-go fallback 401s. ---
|
||||
if provider in {"opencode-zen", "opencode-go"}:
|
||||
if "/" in name:
|
||||
_, bare_after_slash = name.split("/", 1)
|
||||
name = bare_after_slash.strip() or name
|
||||
if provider == "opencode-zen" and name.lower().startswith("claude-"):
|
||||
return _dots_to_hyphens(name)
|
||||
return name
|
||||
|
||||
# --- Anthropic: strip matching provider prefix, dots -> hyphens ---
|
||||
if provider in _DOT_TO_HYPHEN_PROVIDERS:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue