common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix(opencode): re-derive api_mode per target model on /model switch

Browse Source 
opencode-zen and opencode-go each serve both anthropic_messages
(e.g. minimax-m2.7) and chat_completions (e.g. deepseek-v4-flash)
models behind a single base_url. The api_mode resolver in
hermes_cli/runtime_provider.py honoured the persisted
model_cfg.api_mode (set by the previous default model) before checking
the opencode model registry, so /model deepseek-v4-flash from a session
whose default was minimax-m2.7 inherited 'anthropic_messages', stripped
'/v1' from base_url (the Anthropic SDK adds its own /v1/messages), and
404'd.

Promote the opencode detection branch above the configured_mode check
in both api_mode resolution paths:

- _resolve_runtime_from_pool_entry (pool-backed providers)
- _resolve_api_key_runtime          (api-key providers, fallback path)

Both branches now call opencode_model_api_mode(provider, effective_model)
unconditionally for opencode-zen/go before considering any persisted
api_mode, so the mode always reflects the model the user just switched
to.

Existing tests pass (12/12 in tests/hermes_cli/test_model_switch_opencode_anthropic.py).

Fixes #16878
This commit is contained in:
Sanjay
2026-04-28 00:52:05 -07:00
committed by Teknium
parent 755f050c67
commit b52ceccfa8
1 changed files with 19 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
hermes_cli/runtime_provider.py
View File

@@ -260,11 +260,16 @@ def _resolve_runtime_from_pool_entry(
if cfg_base_url:
base_url = cfg_base_url
configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
if configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
api_mode = configured_mode
elif provider in ("opencode-zen", "opencode-go"):
if provider in ("opencode-zen", "opencode-go"):
# Re-derive api_mode from the effective model rather than the
# persisted api_mode: the opencode providers serve both
# anthropic_messages and chat_completions models, so the previous
# session's mode must not leak across /model switches.
# Refs #16878.
from hermes_cli.models import opencode_model_api_mode
api_mode = opencode_model_api_mode(provider, effective_model)
elif configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
api_mode = configured_mode
else:
# Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
# Kimi /coding, api.openai.com → codex_responses, api.x.ai →
@@ -1212,15 +1217,20 @@ def resolve_runtime_provider(
configured_provider = str(model_cfg.get("provider") or "").strip().lower()
# Only honor persisted api_mode when it belongs to the same provider family.
configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
if configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
api_mode = configured_mode
elif provider in ("opencode-zen", "opencode-go"):
if provider in ("opencode-zen", "opencode-go"):
# opencode-zen/go must always re-derive api_mode from the
# target model (not the stale persisted api_mode), because
# the same provider serves both anthropic_messages
# (e.g. minimax-m2.7) and chat_completions (e.g.
# deepseek-v4-flash) and switching models via /model would
# otherwise carry the previous mode forward, stripping /v1
# from base_url for chat_completions models and 404'ing.
# Refs #16878.
from hermes_cli.models import opencode_model_api_mode
# Prefer the target_model from the caller (explicit mid-session
# switch) over the stale model.default; see _resolve_runtime_from_pool_entry
# for the same rationale.
_effective = target_model or model_cfg.get("default", "")
api_mode = opencode_model_api_mode(provider, _effective)
elif configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
api_mode = configured_mode
else:
# Auto-detect Anthropic-compatible endpoints by URL convention
# (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)