refactor(routing): rename local/claude to fast/thinking model pair
All checks were successful
CI / Lint / Test / Vet (pull_request) Successful in 10s
CI / Mirror to GitHub (pull_request) Has been skipped

The routing decision is about reasoning capacity, not cost or provider.
Fast model (koala/qwen35-9b-fast) handles high-pass-rate calls; thinking
model (iguana/gemma4-26b) handles low-pass-rate calls. Removes the
implicit Anthropic dependency from the routing pod — both models go
through LiteLLM.

Renames: HYPERGUILD_LOCAL_MODEL → HYPERGUILD_FAST_MODEL,
HYPERGUILD_CLAUDE_MODEL → HYPERGUILD_THINKING_MODEL,
Router.LocalModel → FastModel, Router.ClaudeModel → ThinkingModel,
log decision "claude_fallback" → "thinking_fallback".

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mathias Bergqvist
2026-05-08 16:39:42 +02:00
parent 43a8255272
commit 5b207425ed
11 changed files with 71 additions and 59 deletions

View File

@@ -24,8 +24,8 @@ type Router struct {
Fetcher *Fetcher
Logger *Logger
Policy Policy
LocalModel string
ClaudeModel string
FastModel string
ThinkingModel string
Complete CompleteFunc
}
@@ -40,9 +40,9 @@ func (r *Router) Run(ctx context.Context, in RunInput) (string, int64, error) {
hash := CanonicalHash(in.System, in.User)
decision := r.Policy.Decide(pr, hash)
model := r.ClaudeModel
model := r.ThinkingModel
if decision == DecideLocal {
model = r.LocalModel
model = r.FastModel
}
out, ms, err := r.Complete(ctx, model, in.System, in.User)
@@ -59,13 +59,13 @@ func (r *Router) Run(ctx context.Context, in RunInput) (string, int64, error) {
}
if err != nil && decision == DecideLocal {
slog.Warn("router: local failed, falling open to claude", "skill", in.Skill, "err", err)
out, ms, err = r.Complete(ctx, r.ClaudeModel, in.System, in.User)
slog.Warn("router: fast failed, falling open to thinking model", "skill", in.Skill, "err", err)
out, ms, err = r.Complete(ctx, r.ThinkingModel, in.System, in.User)
if lerr := r.Logger.LogDecision(ctx, LogEntry{
SessionID: in.SessionID,
Skill: in.Skill,
Decision: "claude_fallback",
Message: fmt.Sprintf("model=%s, after-local-error", r.ClaudeModel),
Decision: "thinking_fallback",
Message: fmt.Sprintf("model=%s, after-fast-error", r.ThinkingModel),
ProjectRoot: in.ProjectRoot,
DurationMs: ms,
Failed: err != nil,