detached ed7e2b4

Merge pull request #201 from harryvgiunta/yolo-auto-provider

feat: add Yolo-Auto provider
commit
ed7e2b431d5a141354d729b4f48715b7cbba92e6
author
Patric Eckhart · · 2026-09-23 15:08 UTC
committer
GitHub · · 2026-09-23 15:08 UTC
merge of
e967eb8 + 97b6cc7 · diff against the first parent
signature
GPG UnverifiedB5690EEEBB952194 The key is unknown
refs
tag: v0.3.88
16 files · +475 -7
Unified
UnifiedSplit
M README.md +1 -1
@@ -18,7 +18,7 @@
1818 Yet another coding agent harness, lightweight and written (vibe-slopped) in go.
1919
2020 - one static binary.
21-- built-in providers for Anthropic, OpenAI/Codex/Responses, Kimi, DeepSeek, Google Gemini/Vertex, GitHub Copilot, Bedrock, Azure OpenAI, OpenRouter, Groq, Cerebras, xAI, Together, Hugging Face, Mistral, Moonshot, Z.AI, Xiaomi, MiniMax, Fireworks, Vercel AI Gateway, OpenCode, Cloudflare AI, and Ollama/local models.
21+- built-in providers for Anthropic, OpenAI/Codex/Responses, Kimi, DeepSeek, Google Gemini/Vertex, GitHub Copilot, Bedrock, Azure OpenAI, OpenRouter, Yolo-Auto, Groq, Cerebras, xAI, Together, Hugging Face, Mistral, Moonshot, Z.AI, Xiaomi, MiniMax, Fireworks, Vercel AI Gateway, OpenCode, Cloudflare AI, and Ollama/local models.
2222 - built-in tools (read, write, edit, bash, glob).
2323 - three run modes (interactive tui, print, json).
2424 - built-in telegram bot.
@@ -18,7 +18,7 @@
18 Yet another coding agent harness, lightweight and written (vibe-slopped) in go.18 Yet another coding agent harness, lightweight and written (vibe-slopped) in go.
19 19
20 - one static binary.20 - one static binary.
21-- built-in providers for Anthropic, OpenAI/Codex/Responses, Kimi, DeepSeek, Google Gemini/Vertex, GitHub Copilot, Bedrock, Azure OpenAI, OpenRouter, Groq, Cerebras, xAI, Together, Hugging Face, Mistral, Moonshot, Z.AI, Xiaomi, MiniMax, Fireworks, Vercel AI Gateway, OpenCode, Cloudflare AI, and Ollama/local models.21+- built-in providers for Anthropic, OpenAI/Codex/Responses, Kimi, DeepSeek, Google Gemini/Vertex, GitHub Copilot, Bedrock, Azure OpenAI, OpenRouter, Yolo-Auto, Groq, Cerebras, xAI, Together, Hugging Face, Mistral, Moonshot, Z.AI, Xiaomi, MiniMax, Fireworks, Vercel AI Gateway, OpenCode, Cloudflare AI, and Ollama/local models.
22 - built-in tools (read, write, edit, bash, glob).22 - built-in tools (read, write, edit, bash, glob).
23 - three run modes (interactive tui, print, json).23 - three run modes (interactive tui, print, json).
24 - built-in telegram bot.24 - built-in telegram bot.
M docs/providers.md +16 -0
@@ -181,6 +181,7 @@ show instructions and should be configured with environment variables.
181181 | Hugging Face | `HF_TOKEN` | `huggingface` |
182182 | OpenRouter | `OPENROUTER_API_KEY` | `openrouter` |
183183 | Gondola | `GONDOLA_API_KEY` | `gondola` |
184+| Yolo-Auto | `YOLO_AUTO_API_KEY` | `yolo-auto` |
184185 | Mistral | `MISTRAL_API_KEY` | `mistral` |
185186 | ZAI | `ZAI_API_KEY` | `zai` |
186187 | Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
@@ -201,6 +202,21 @@ show instructions and should be configured with environment variables.
201202 When Gondola credentials are available, zot refreshes its public text-model
202203 catalog in the background and adds the discovered models to `/model`.
203204
205+Yolo-Auto is an OpenAI-compatible gateway with flat-rate plans, so no per-token
206+prices are shown. The default model, `qwen3.8-flash`, is available on free and
207+paid plans. The optional `yolo` route requires a paid plan. These models and
208+`yolo-small` ship with conservative client limits.
209+
210+With `YOLO_AUTO_API_KEY` set or a key saved through `/login`, zot lists
211+`/v1/models` in the background on each catalog refresh, independently of the
212+six-hour public catalog cache. Discovered models use the key's plan-bounded
213+context windows and advertised reasoning levels, replacing the seed metadata.
214+The last discovered metadata is cached for startup resolution until the
215+background refresh completes. If discovery fails, zot falls back to the seed
216+models and conservative limits instead of retaining the previous key's live
217+metadata. Create a key at https://yolo-auto.com and see
218+https://yolo-auto.com/docs for the API reference.
219+
204220 Example:
205221
206222 ```bash
@@ -181,6 +181,7 @@ show instructions and should be configured with environment variables.
181 | Hugging Face | `HF_TOKEN` | `huggingface` |181 | Hugging Face | `HF_TOKEN` | `huggingface` |
182 | OpenRouter | `OPENROUTER_API_KEY` | `openrouter` |182 | OpenRouter | `OPENROUTER_API_KEY` | `openrouter` |
183 | Gondola | `GONDOLA_API_KEY` | `gondola` |183 | Gondola | `GONDOLA_API_KEY` | `gondola` |
184+| Yolo-Auto | `YOLO_AUTO_API_KEY` | `yolo-auto` |
184 | Mistral | `MISTRAL_API_KEY` | `mistral` |185 | Mistral | `MISTRAL_API_KEY` | `mistral` |
185 | ZAI | `ZAI_API_KEY` | `zai` |186 | ZAI | `ZAI_API_KEY` | `zai` |
186 | Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |187 | Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
@@ -201,6 +202,21 @@ show instructions and should be configured with environment variables.
201 When Gondola credentials are available, zot refreshes its public text-model202 When Gondola credentials are available, zot refreshes its public text-model
202 catalog in the background and adds the discovered models to `/model`.203 catalog in the background and adds the discovered models to `/model`.
203 204
205+Yolo-Auto is an OpenAI-compatible gateway with flat-rate plans, so no per-token
206+prices are shown. The default model, `qwen3.8-flash`, is available on free and
207+paid plans. The optional `yolo` route requires a paid plan. These models and
208+`yolo-small` ship with conservative client limits.
209+
210+With `YOLO_AUTO_API_KEY` set or a key saved through `/login`, zot lists
211+`/v1/models` in the background on each catalog refresh, independently of the
212+six-hour public catalog cache. Discovered models use the key's plan-bounded
213+context windows and advertised reasoning levels, replacing the seed metadata.
214+The last discovered metadata is cached for startup resolution until the
215+background refresh completes. If discovery fails, zot falls back to the seed
216+models and conservative limits instead of retaining the previous key's live
217+metadata. Create a key at https://yolo-auto.com and see
218+https://yolo-auto.com/docs for the API reference.
219+
204 Example:220 Example:
205 221
206 ```bash222 ```bash
M packages/agent/build.go +7 -1
@@ -193,6 +193,8 @@ func defaultModelForProvider(prov string) string {
193193 return "anthropic/claude-sonnet-4.5"
194194 case "gondola":
195195 return "kimi-k3"
196+ case "yolo-auto":
197+ return "qwen3.8-flash"
196198 case "mistral":
197199 return "mistral-large-latest"
198200 case "zai":
@@ -234,7 +236,7 @@ func defaultModelForProvider(prov string) string {
234236 var knownProviders = []string{
235237 "anthropic", "openai", "openai-codex", "openai-responses", "kimi", "deepseek", "google", "ollama", provider.LlamaCPPProviderID, provider.LMStudioProviderID,
236238 "moonshotai", "moonshotai-cn",
237- "cerebras", "groq", "xai", "together", "huggingface", "openrouter", "gondola",
239+ "cerebras", "groq", "xai", "together", "huggingface", "openrouter", "gondola", "yolo-auto",
238240 "mistral", "zai",
239241 "xiaomi", "xiaomi-token-plan-ams", "xiaomi-token-plan-cn", "xiaomi-token-plan-sgp",
240242 "minimax", "minimax-cn",
@@ -900,6 +902,8 @@ func (r Resolved) NewClient() provider.Client {
900902 return wrap(provider.NewOpenRouter(r.Credential, r.BaseURL))
901903 case "gondola":
902904 return wrap(provider.NewGondola(r.Credential, r.BaseURL))
905+ case "yolo-auto":
906+ return wrap(provider.NewYoloAuto(r.Credential, r.BaseURL))
903907 case "zai":
904908 return wrap(provider.NewZAI(r.Credential, r.BaseURL))
905909 case "xiaomi":
@@ -1209,6 +1213,8 @@ func envVarName(provider string) string {
12091213 return "OPENROUTER"
12101214 case "gondola":
12111215 return "GONDOLA"
1216+ case "yolo-auto":
1217+ return "YOLO_AUTO"
12121218 case "mistral":
12131219 return "MISTRAL"
12141220 case "zai":
@@ -193,6 +193,8 @@ func defaultModelForProvider(prov string) string {
193 return "anthropic/claude-sonnet-4.5"193 return "anthropic/claude-sonnet-4.5"
194 case "gondola":194 case "gondola":
195 return "kimi-k3"195 return "kimi-k3"
196+ case "yolo-auto":
197+ return "qwen3.8-flash"
196 case "mistral":198 case "mistral":
197 return "mistral-large-latest"199 return "mistral-large-latest"
198 case "zai":200 case "zai":
@@ -234,7 +236,7 @@ func defaultModelForProvider(prov string) string {
234 var knownProviders = []string{236 var knownProviders = []string{
235 "anthropic", "openai", "openai-codex", "openai-responses", "kimi", "deepseek", "google", "ollama", provider.LlamaCPPProviderID, provider.LMStudioProviderID,237 "anthropic", "openai", "openai-codex", "openai-responses", "kimi", "deepseek", "google", "ollama", provider.LlamaCPPProviderID, provider.LMStudioProviderID,
236 "moonshotai", "moonshotai-cn",238 "moonshotai", "moonshotai-cn",
237- "cerebras", "groq", "xai", "together", "huggingface", "openrouter", "gondola",239+ "cerebras", "groq", "xai", "together", "huggingface", "openrouter", "gondola", "yolo-auto",
238 "mistral", "zai",240 "mistral", "zai",
239 "xiaomi", "xiaomi-token-plan-ams", "xiaomi-token-plan-cn", "xiaomi-token-plan-sgp",241 "xiaomi", "xiaomi-token-plan-ams", "xiaomi-token-plan-cn", "xiaomi-token-plan-sgp",
240 "minimax", "minimax-cn",242 "minimax", "minimax-cn",
@@ -900,6 +902,8 @@ func (r Resolved) NewClient() provider.Client {
900 return wrap(provider.NewOpenRouter(r.Credential, r.BaseURL))902 return wrap(provider.NewOpenRouter(r.Credential, r.BaseURL))
901 case "gondola":903 case "gondola":
902 return wrap(provider.NewGondola(r.Credential, r.BaseURL))904 return wrap(provider.NewGondola(r.Credential, r.BaseURL))
905+ case "yolo-auto":
906+ return wrap(provider.NewYoloAuto(r.Credential, r.BaseURL))
903 case "zai":907 case "zai":
904 return wrap(provider.NewZAI(r.Credential, r.BaseURL))908 return wrap(provider.NewZAI(r.Credential, r.BaseURL))
905 case "xiaomi":909 case "xiaomi":
@@ -1209,6 +1213,8 @@ func envVarName(provider string) string {
1209 return "OPENROUTER"1213 return "OPENROUTER"
1210 case "gondola":1214 case "gondola":
1211 return "GONDOLA"1215 return "GONDOLA"
1216+ case "yolo-auto":
1217+ return "YOLO_AUTO"
1212 case "mistral":1218 case "mistral":
1213 return "MISTRAL"1219 return "MISTRAL"
1214 case "zai":1220 case "zai":
M packages/agent/config.go +4 -0
@@ -466,6 +466,10 @@ func resolveCredentialFull(ctx context.Context, provider, explicit string, comma
466466 if v := os.Getenv("GONDOLA_API_KEY"); v != "" {
467467 return v, "apikey", "", nil
468468 }
469+ case "yolo-auto":
470+ if v := os.Getenv("YOLO_AUTO_API_KEY"); v != "" {
471+ return v, "apikey", "", nil
472+ }
469473 case "mistral":
470474 if v := os.Getenv("MISTRAL_API_KEY"); v != "" {
471475 return v, "apikey", "", nil
@@ -466,6 +466,10 @@ func resolveCredentialFull(ctx context.Context, provider, explicit string, comma
466 if v := os.Getenv("GONDOLA_API_KEY"); v != "" {466 if v := os.Getenv("GONDOLA_API_KEY"); v != "" {
467 return v, "apikey", "", nil467 return v, "apikey", "", nil
468 }468 }
469+ case "yolo-auto":
470+ if v := os.Getenv("YOLO_AUTO_API_KEY"); v != "" {
471+ return v, "apikey", "", nil
472+ }
469 case "mistral":473 case "mistral":
470 if v := os.Getenv("MISTRAL_API_KEY"); v != "" {474 if v := os.Getenv("MISTRAL_API_KEY"); v != "" {
471 return v, "apikey", "", nil475 return v, "apikey", "", nil
M packages/agent/modelsync.go +28 -4
@@ -206,9 +206,17 @@ func refreshModels() {
206206 cached, _ := provider.LoadCache(ModelCachePath())
207207 cacheFresh := cached.IsFresh()
208208
209+ // Refresh per-key limits even while the public catalog cache is fresh.
210+ // Use a separate deadline so slow public discovery cannot starve this call.
211+ yoloCtx, yoloCancel := context.WithTimeout(context.Background(), 15*time.Second)
212+ var yoloModels []provider.Model
213+ if cred, _, err := resolveCredentialForBackground(yoloCtx, "yolo-auto"); err == nil {
214+ yoloModels, _ = provider.DiscoverYoloAuto(yoloCtx, cred, "")
215+ }
216+ yoloCancel()
217+
209218 ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
210219 defer cancel()
211-
212220 var all []provider.Model
213221 var openrouterCred string
214222 var haveOpenRouter bool
@@ -272,18 +280,34 @@ func refreshModels() {
272280 }
273281 }
274282
275- if len(all) == 0 {
276- return
277- }
283+ // Do not carry forward another key's models or limits, even on failure.
284+ all = mergeYoloAutoModels(all, yoloModels)
278285 provider.SetLiveModels(all)
279286 // Keep explicit metadata overrides above refreshed server catalogs.
280287 LoadUserModels()
288+ if len(all) == 0 {
289+ // Clear old account entries without marking an empty catalog fresh.
290+ _ = provider.SaveCache(ModelCachePath(), provider.ModelCache{})
291+ return
292+ }
281293 _ = provider.SaveCache(ModelCachePath(), provider.ModelCache{
282294 FetchedAt: modelCacheFetchedAt(cached, !cacheFresh, time.Now().UTC()),
283295 Models: all,
284296 })
285297 }
286298
299+// mergeYoloAutoModels replaces account metadata without disturbing the public
300+// catalog. Cached entries aid offline resolution, but never suppress discovery.
301+func mergeYoloAutoModels(existing, live []provider.Model) []provider.Model {
302+ out := make([]provider.Model, 0, len(existing)+len(live))
303+ for _, model := range existing {
304+ if model.Provider != "yolo-auto" {
305+ out = append(out, model)
306+ }
307+ }
308+ return append(out, live...)
309+}
310+
287311 func modelCacheFetchedAt(cached provider.ModelCache, catalogRefreshed bool, now time.Time) time.Time {
288312 if catalogRefreshed {
289313 return now
@@ -206,9 +206,17 @@ func refreshModels() {
206 cached, _ := provider.LoadCache(ModelCachePath())206 cached, _ := provider.LoadCache(ModelCachePath())
207 cacheFresh := cached.IsFresh()207 cacheFresh := cached.IsFresh()
208 208
209+ // Refresh per-key limits even while the public catalog cache is fresh.
210+ // Use a separate deadline so slow public discovery cannot starve this call.
211+ yoloCtx, yoloCancel := context.WithTimeout(context.Background(), 15*time.Second)
212+ var yoloModels []provider.Model
213+ if cred, _, err := resolveCredentialForBackground(yoloCtx, "yolo-auto"); err == nil {
214+ yoloModels, _ = provider.DiscoverYoloAuto(yoloCtx, cred, "")
215+ }
216+ yoloCancel()
217+
209 ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)218 ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
210 defer cancel()219 defer cancel()
211-
212 var all []provider.Model220 var all []provider.Model
213 var openrouterCred string221 var openrouterCred string
214 var haveOpenRouter bool222 var haveOpenRouter bool
@@ -272,18 +280,34 @@ func refreshModels() {
272 }280 }
273 }281 }
274 282
275- if len(all) == 0 {283+ // Do not carry forward another key's models or limits, even on failure.
276- return284+ all = mergeYoloAutoModels(all, yoloModels)
277- }
278 provider.SetLiveModels(all)285 provider.SetLiveModels(all)
279 // Keep explicit metadata overrides above refreshed server catalogs.286 // Keep explicit metadata overrides above refreshed server catalogs.
280 LoadUserModels()287 LoadUserModels()
288+ if len(all) == 0 {
289+ // Clear old account entries without marking an empty catalog fresh.
290+ _ = provider.SaveCache(ModelCachePath(), provider.ModelCache{})
291+ return
292+ }
281 _ = provider.SaveCache(ModelCachePath(), provider.ModelCache{293 _ = provider.SaveCache(ModelCachePath(), provider.ModelCache{
282 FetchedAt: modelCacheFetchedAt(cached, !cacheFresh, time.Now().UTC()),294 FetchedAt: modelCacheFetchedAt(cached, !cacheFresh, time.Now().UTC()),
283 Models: all,295 Models: all,
284 })296 })
285 }297 }
286 298
299+// mergeYoloAutoModels replaces account metadata without disturbing the public
300+// catalog. Cached entries aid offline resolution, but never suppress discovery.
301+func mergeYoloAutoModels(existing, live []provider.Model) []provider.Model {
302+ out := make([]provider.Model, 0, len(existing)+len(live))
303+ for _, model := range existing {
304+ if model.Provider != "yolo-auto" {
305+ out = append(out, model)
306+ }
307+ }
308+ return append(out, live...)
309+}
310+
287 func modelCacheFetchedAt(cached provider.ModelCache, catalogRefreshed bool, now time.Time) time.Time {311 func modelCacheFetchedAt(cached provider.ModelCache, catalogRefreshed bool, now time.Time) time.Time {
288 if catalogRefreshed {312 if catalogRefreshed {
289 return now313 return now
A packages/agent/yolo_auto_test.go +126 -0
@@ -0,0 +1,126 @@
1+package agent
2+
3+import (
4+ "fmt"
5+ "io"
6+ "net/http"
7+ "strings"
8+ "testing"
9+ "time"
10+
11+ "github.com/patriceckhart/zot/packages/provider"
12+)
13+
14+type yoloAutoTestTransport func(*http.Request) (*http.Response, error)
15+
16+func (f yoloAutoTestTransport) RoundTrip(r *http.Request) (*http.Response, error) {
17+ return f(r)
18+}
19+
20+func TestYoloAutoDefaultAvailableOffline(t *testing.T) {
21+ id := defaultModelForProvider("yolo-auto")
22+ if id != "qwen3.8-flash" {
23+ t.Fatalf("default = %q, want free-plan model", id)
24+ }
25+ if _, err := provider.FindModel("yolo-auto", id); err != nil {
26+ t.Fatal(err)
27+ }
28+}
29+
30+func TestYoloAutoRefreshIgnoresSharedCache(t *testing.T) {
31+ t.Setenv("ZOT_HOME", t.TempDir())
32+ t.Setenv("OPENROUTER_API_KEY", "")
33+ t.Setenv("YOLO_AUTO_API_KEY", "test-pro")
34+ cachedAt := time.Now().UTC()
35+ if err := provider.SaveCache(ModelCachePath(), provider.ModelCache{
36+ FetchedAt: cachedAt,
37+ Models: []provider.Model{
38+ {Provider: "openai", ID: "cached-public-model"},
39+ {Provider: "yolo-auto", ID: "old-account-model", ContextWindow: 262144},
40+ },
41+ }); err != nil {
42+ t.Fatal(err)
43+ }
44+ provider.SetLiveModels(nil)
45+ t.Cleanup(func() { provider.SetLiveModels(nil) })
46+ LoadCachedModels()
47+
48+ original := http.DefaultTransport
49+ t.Cleanup(func() { http.DefaultTransport = original })
50+ calls := 0
51+ http.DefaultTransport = yoloAutoTestTransport(func(r *http.Request) (*http.Response, error) {
52+ if r.URL.String() != "https://yolo-auto.com/v1/models" {
53+ return nil, fmt.Errorf("unexpected discovery request: %s", r.URL)
54+ }
55+ calls++
56+ body := `{"data":[{"id":"qwen3.8-flash","context_length":262144,"thinking":["high"]},{"id":"pro-only"}]}`
57+ switch r.Header.Get("Authorization") {
58+ case "Bearer test-pro":
59+ case "Bearer test-free":
60+ body = `{"data":[{"id":"qwen3.8-flash","context_length":131072,"thinking":["high"]}]}`
61+ default:
62+ return nil, fmt.Errorf("unexpected credential")
63+ }
64+ return &http.Response{StatusCode: http.StatusOK, Body: io.NopCloser(strings.NewReader(body)), Header: make(http.Header)}, nil
65+ })
66+
67+ for _, tc := range []struct {
68+ key string
69+ window int
70+ }{
71+ {"test-pro", 262144},
72+ {"test-free", 131072},
73+ } {
74+ t.Setenv("YOLO_AUTO_API_KEY", tc.key)
75+ refreshModels()
76+ model, err := provider.FindModel("yolo-auto", "qwen3.8-flash")
77+ if err != nil {
78+ t.Fatal(err)
79+ }
80+ if model.ContextWindow != tc.window {
81+ t.Errorf("context = %d, want %d", model.ContextWindow, tc.window)
82+ }
83+ }
84+ if calls != 2 {
85+ t.Errorf("discovery calls = %d, want 2 despite fresh cache", calls)
86+ }
87+ if _, err := provider.FindModel("yolo-auto", "pro-only"); err == nil {
88+ t.Error("previous account model survived refresh")
89+ }
90+ cached, err := provider.LoadCache(ModelCachePath())
91+ if err != nil {
92+ t.Fatal(err)
93+ }
94+ if !cached.FetchedAt.Equal(cachedAt) {
95+ t.Error("account refresh extended public cache lifetime")
96+ }
97+ for _, model := range cached.Models {
98+ if model.Provider == "yolo-auto" && (model.ID != "qwen3.8-flash" || model.ContextWindow != 131072) {
99+ t.Errorf("previous account metadata survived in cache: %+v", model)
100+ }
101+ }
102+ if _, err := provider.FindModel("yolo-auto", "old-account-model"); err == nil {
103+ t.Error("previous cached account model survived refresh")
104+ }
105+ if _, err := provider.FindModel("openai", "cached-public-model"); err != nil {
106+ t.Error("unrelated cached model lost")
107+ }
108+
109+ // Failed discovery and logout must drop the previous account's metadata.
110+ for _, key := range []string{"test-invalid", ""} {
111+ t.Setenv("YOLO_AUTO_API_KEY", "test-pro")
112+ refreshModels()
113+ t.Setenv("YOLO_AUTO_API_KEY", key)
114+ refreshModels()
115+ model, err := provider.FindModel("yolo-auto", "qwen3.8-flash")
116+ if err != nil {
117+ t.Fatal(err)
118+ }
119+ if model.Source != "catalog" || len(model.ReasoningLevelMap) != 0 {
120+ t.Errorf("account metadata survived failed discovery or logout: %+v", model)
121+ }
122+ if _, err := provider.FindModel("yolo-auto", "pro-only"); err == nil {
123+ t.Error("previous account model survived failed discovery or logout")
124+ }
125+ }
126+}
@@ -0,0 +1,126 @@
1+package agent
2+
3+import (
4+ "fmt"
5+ "io"
6+ "net/http"
7+ "strings"
8+ "testing"
9+ "time"
10+
11+ "github.com/patriceckhart/zot/packages/provider"
12+)
13+
14+type yoloAutoTestTransport func(*http.Request) (*http.Response, error)
15+
16+func (f yoloAutoTestTransport) RoundTrip(r *http.Request) (*http.Response, error) {
17+ return f(r)
18+}
19+
20+func TestYoloAutoDefaultAvailableOffline(t *testing.T) {
21+ id := defaultModelForProvider("yolo-auto")
22+ if id != "qwen3.8-flash" {
23+ t.Fatalf("default = %q, want free-plan model", id)
24+ }
25+ if _, err := provider.FindModel("yolo-auto", id); err != nil {
26+ t.Fatal(err)
27+ }
28+}
29+
30+func TestYoloAutoRefreshIgnoresSharedCache(t *testing.T) {
31+ t.Setenv("ZOT_HOME", t.TempDir())
32+ t.Setenv("OPENROUTER_API_KEY", "")
33+ t.Setenv("YOLO_AUTO_API_KEY", "test-pro")
34+ cachedAt := time.Now().UTC()
35+ if err := provider.SaveCache(ModelCachePath(), provider.ModelCache{
36+ FetchedAt: cachedAt,
37+ Models: []provider.Model{
38+ {Provider: "openai", ID: "cached-public-model"},
39+ {Provider: "yolo-auto", ID: "old-account-model", ContextWindow: 262144},
40+ },
41+ }); err != nil {
42+ t.Fatal(err)
43+ }
44+ provider.SetLiveModels(nil)
45+ t.Cleanup(func() { provider.SetLiveModels(nil) })
46+ LoadCachedModels()
47+
48+ original := http.DefaultTransport
49+ t.Cleanup(func() { http.DefaultTransport = original })
50+ calls := 0
51+ http.DefaultTransport = yoloAutoTestTransport(func(r *http.Request) (*http.Response, error) {
52+ if r.URL.String() != "https://yolo-auto.com/v1/models" {
53+ return nil, fmt.Errorf("unexpected discovery request: %s", r.URL)
54+ }
55+ calls++
56+ body := `{"data":[{"id":"qwen3.8-flash","context_length":262144,"thinking":["high"]},{"id":"pro-only"}]}`
57+ switch r.Header.Get("Authorization") {
58+ case "Bearer test-pro":
59+ case "Bearer test-free":
60+ body = `{"data":[{"id":"qwen3.8-flash","context_length":131072,"thinking":["high"]}]}`
61+ default:
62+ return nil, fmt.Errorf("unexpected credential")
63+ }
64+ return &http.Response{StatusCode: http.StatusOK, Body: io.NopCloser(strings.NewReader(body)), Header: make(http.Header)}, nil
65+ })
66+
67+ for _, tc := range []struct {
68+ key string
69+ window int
70+ }{
71+ {"test-pro", 262144},
72+ {"test-free", 131072},
73+ } {
74+ t.Setenv("YOLO_AUTO_API_KEY", tc.key)
75+ refreshModels()
76+ model, err := provider.FindModel("yolo-auto", "qwen3.8-flash")
77+ if err != nil {
78+ t.Fatal(err)
79+ }
80+ if model.ContextWindow != tc.window {
81+ t.Errorf("context = %d, want %d", model.ContextWindow, tc.window)
82+ }
83+ }
84+ if calls != 2 {
85+ t.Errorf("discovery calls = %d, want 2 despite fresh cache", calls)
86+ }
87+ if _, err := provider.FindModel("yolo-auto", "pro-only"); err == nil {
88+ t.Error("previous account model survived refresh")
89+ }
90+ cached, err := provider.LoadCache(ModelCachePath())
91+ if err != nil {
92+ t.Fatal(err)
93+ }
94+ if !cached.FetchedAt.Equal(cachedAt) {
95+ t.Error("account refresh extended public cache lifetime")
96+ }
97+ for _, model := range cached.Models {
98+ if model.Provider == "yolo-auto" && (model.ID != "qwen3.8-flash" || model.ContextWindow != 131072) {
99+ t.Errorf("previous account metadata survived in cache: %+v", model)
100+ }
101+ }
102+ if _, err := provider.FindModel("yolo-auto", "old-account-model"); err == nil {
103+ t.Error("previous cached account model survived refresh")
104+ }
105+ if _, err := provider.FindModel("openai", "cached-public-model"); err != nil {
106+ t.Error("unrelated cached model lost")
107+ }
108+
109+ // Failed discovery and logout must drop the previous account's metadata.
110+ for _, key := range []string{"test-invalid", ""} {
111+ t.Setenv("YOLO_AUTO_API_KEY", "test-pro")
112+ refreshModels()
113+ t.Setenv("YOLO_AUTO_API_KEY", key)
114+ refreshModels()
115+ model, err := provider.FindModel("yolo-auto", "qwen3.8-flash")
116+ if err != nil {
117+ t.Fatal(err)
118+ }
119+ if model.Source != "catalog" || len(model.ReasoningLevelMap) != 0 {
120+ t.Errorf("account metadata survived failed discovery or logout: %+v", model)
121+ }
122+ if _, err := provider.FindModel("yolo-auto", "pro-only"); err == nil {
123+ t.Error("previous account model survived failed discovery or logout")
124+ }
125+ }
126+}
M packages/provider/auth/probe.go +6 -0
@@ -108,6 +108,12 @@ func probeAPIKey(ctx context.Context, provider, key string, c *http.Client) erro
108108 return err
109109 }
110110 req.Header.Set("authorization", "Bearer "+key)
111+ case "yolo-auto":
112+ req, err = http.NewRequestWithContext(ctx, "GET", "https://yolo-auto.com/v1/models", nil)
113+ if err != nil {
114+ return err
115+ }
116+ req.Header.Set("authorization", "Bearer "+key)
111117 case "huggingface":
112118 req, err = http.NewRequestWithContext(ctx, "GET", "https://router.huggingface.co/v1/models", nil)
113119 if err != nil {
@@ -108,6 +108,12 @@ func probeAPIKey(ctx context.Context, provider, key string, c *http.Client) erro
108 return err108 return err
109 }109 }
110 req.Header.Set("authorization", "Bearer "+key)110 req.Header.Set("authorization", "Bearer "+key)
111+ case "yolo-auto":
112+ req, err = http.NewRequestWithContext(ctx, "GET", "https://yolo-auto.com/v1/models", nil)
113+ if err != nil {
114+ return err
115+ }
116+ req.Header.Set("authorization", "Bearer "+key)
111 case "huggingface":117 case "huggingface":
112 req, err = http.NewRequestWithContext(ctx, "GET", "https://router.huggingface.co/v1/models", nil)118 req, err = http.NewRequestWithContext(ctx, "GET", "https://router.huggingface.co/v1/models", nil)
113 if err != nil {119 if err != nil {
M packages/provider/auth/server.go +1 -1
@@ -138,7 +138,7 @@ func APIKeyProviders() []string {
138138 return []string{
139139 "anthropic", "openai", "kimi", "deepseek", "google", "llama.cpp", "lmstudio",
140140 "moonshotai", "moonshotai-cn", "groq", "cerebras", "xai", "together",
141- "huggingface", "openrouter", "gondola", "mistral", "zai",
141+ "huggingface", "openrouter", "gondola", "yolo-auto", "mistral", "zai",
142142 "xiaomi", "xiaomi-token-plan-ams", "xiaomi-token-plan-cn", "xiaomi-token-plan-sgp",
143143 "minimax", "minimax-cn", "fireworks", "vercel-ai-gateway",
144144 "opencode", "opencode-go", "amazon-bedrock", "google-vertex", "azure-openai-responses",
@@ -138,7 +138,7 @@ func APIKeyProviders() []string {
138 return []string{138 return []string{
139 "anthropic", "openai", "kimi", "deepseek", "google", "llama.cpp", "lmstudio",139 "anthropic", "openai", "kimi", "deepseek", "google", "llama.cpp", "lmstudio",
140 "moonshotai", "moonshotai-cn", "groq", "cerebras", "xai", "together",140 "moonshotai", "moonshotai-cn", "groq", "cerebras", "xai", "together",
141- "huggingface", "openrouter", "gondola", "mistral", "zai",141+ "huggingface", "openrouter", "gondola", "yolo-auto", "mistral", "zai",
142 "xiaomi", "xiaomi-token-plan-ams", "xiaomi-token-plan-cn", "xiaomi-token-plan-sgp",142 "xiaomi", "xiaomi-token-plan-ams", "xiaomi-token-plan-cn", "xiaomi-token-plan-sgp",
143 "minimax", "minimax-cn", "fireworks", "vercel-ai-gateway",143 "minimax", "minimax-cn", "fireworks", "vercel-ai-gateway",
144 "opencode", "opencode-go", "amazon-bedrock", "google-vertex", "azure-openai-responses",144 "opencode", "opencode-go", "amazon-bedrock", "google-vertex", "azure-openai-responses",
M packages/provider/discover.go +89 -0
@@ -230,6 +230,14 @@ func looksLikeChatModel(id string) bool {
230230 const (
231231 openrouterDefaultBaseURL = "https://openrouter.ai/api/v1"
232232 gondolaDefaultBaseURL = "https://api.gondola-ai.com/v1"
233+ yoloAutoDefaultBaseURL = "https://yolo-auto.com/v1"
234+
235+ // Yolo-Auto's documented conservative client limits. The provider is
236+ // flat-rate with plan-bounded windows, so the window is a safe floor
237+ // rather than a ceiling; /v1/models reports the per-key window and
238+ // DiscoverYoloAuto prefers it.
239+ yoloAutoContextWindow = 131072
240+ yoloAutoMaxOutput = 32768
233241 )
234242
235243 // DiscoverOpenRouter lists models from OpenRouter's public /models
@@ -458,6 +466,87 @@ func DiscoverGondola(ctx context.Context, baseURL string) ([]Model, error) {
458466 return out, nil
459467 }
460468
469+// DiscoverYoloAuto lists the models a Yolo-Auto key can reach from the
470+// provider's OpenAI-compatible /v1/models endpoint. Each entry reports the
471+// plan-bounded context window and, when the alias supports them, the
472+// thinking levels it accepts.
473+func DiscoverYoloAuto(ctx context.Context, apiKey, baseURL string) ([]Model, error) {
474+ if baseURL == "" {
475+ baseURL = yoloAutoDefaultBaseURL
476+ }
477+ baseURL = strings.TrimRight(baseURL, "/")
478+ client := &http.Client{Timeout: 15 * time.Second}
479+ req, err := http.NewRequestWithContext(ctx, "GET", baseURL+"/models", nil)
480+ if err != nil {
481+ return nil, err
482+ }
483+ if apiKey != "" {
484+ req.Header.Set("authorization", "Bearer "+apiKey)
485+ }
486+ resp, err := client.Do(req)
487+ if err != nil {
488+ return nil, err
489+ }
490+ defer resp.Body.Close()
491+ body, _ := io.ReadAll(resp.Body)
492+ if resp.StatusCode != http.StatusOK {
493+ return nil, fmt.Errorf("yolo-auto discover http %d: %s", resp.StatusCode, strings.TrimSpace(string(body)))
494+ }
495+ var page struct {
496+ Data []struct {
497+ ID string `json:"id"`
498+ ContextLength int `json:"context_length"`
499+ MaxModelLen int `json:"max_model_len"`
500+ Thinking []string `json:"thinking"`
501+ } `json:"data"`
502+ }
503+ if err := json.Unmarshal(body, &page); err != nil {
504+ return nil, fmt.Errorf("yolo-auto discover parse: %w", err)
505+ }
506+ out := make([]Model, 0, len(page.Data))
507+ for _, d := range page.Data {
508+ id := strings.TrimSpace(d.ID)
509+ if id == "" || strings.Contains(strings.ToLower(id), "embed") {
510+ continue
511+ }
512+ contextWindow := d.ContextLength
513+ if contextWindow == 0 {
514+ contextWindow = d.MaxModelLen
515+ }
516+ if contextWindow == 0 {
517+ contextWindow = yoloAutoContextWindow
518+ }
519+ out = append(out, Model{
520+ Provider: "yolo-auto",
521+ ID: id,
522+ DisplayName: id,
523+ ContextWindow: contextWindow,
524+ MaxOutput: yoloAutoMaxOutput,
525+ Reasoning: len(d.Thinking) > 0,
526+ ReasoningLevelMap: yoloAutoReasoningLevels(d.Thinking),
527+ BaseURL: baseURL,
528+ Source: "live",
529+ })
530+ }
531+ return out, nil
532+}
533+
534+// yoloAutoReasoningLevels restricts the generic chat-completions defaults to
535+// the endpoint's advertised efforts, including minimal and xhigh when offered.
536+func yoloAutoReasoningLevels(thinking []string) map[string]string {
537+ levels := make(map[string]string)
538+ for _, level := range reasoningLevelOrder[1:] {
539+ levels[level] = ""
540+ }
541+ for _, effort := range thinking {
542+ level := NormalizeReasoning(effort)
543+ if _, known := levels[level]; known {
544+ levels[level] = level
545+ }
546+ }
547+ return levels
548+}
549+
461550 // perMillionTokens converts a per-token USD price string to USD per 1M
462551 // tokens. Empty or unparseable values become 0.
463552 func perMillionTokens(s string) float64 {
@@ -230,6 +230,14 @@ func looksLikeChatModel(id string) bool {
230 const (230 const (
231 openrouterDefaultBaseURL = "https://openrouter.ai/api/v1"231 openrouterDefaultBaseURL = "https://openrouter.ai/api/v1"
232 gondolaDefaultBaseURL = "https://api.gondola-ai.com/v1"232 gondolaDefaultBaseURL = "https://api.gondola-ai.com/v1"
233+ yoloAutoDefaultBaseURL = "https://yolo-auto.com/v1"
234+
235+ // Yolo-Auto's documented conservative client limits. The provider is
236+ // flat-rate with plan-bounded windows, so the window is a safe floor
237+ // rather than a ceiling; /v1/models reports the per-key window and
238+ // DiscoverYoloAuto prefers it.
239+ yoloAutoContextWindow = 131072
240+ yoloAutoMaxOutput = 32768
233 )241 )
234 242
235 // DiscoverOpenRouter lists models from OpenRouter's public /models243 // DiscoverOpenRouter lists models from OpenRouter's public /models
@@ -458,6 +466,87 @@ func DiscoverGondola(ctx context.Context, baseURL string) ([]Model, error) {
458 return out, nil466 return out, nil
459 }467 }
460 468
469+// DiscoverYoloAuto lists the models a Yolo-Auto key can reach from the
470+// provider's OpenAI-compatible /v1/models endpoint. Each entry reports the
471+// plan-bounded context window and, when the alias supports them, the
472+// thinking levels it accepts.
473+func DiscoverYoloAuto(ctx context.Context, apiKey, baseURL string) ([]Model, error) {
474+ if baseURL == "" {
475+ baseURL = yoloAutoDefaultBaseURL
476+ }
477+ baseURL = strings.TrimRight(baseURL, "/")
478+ client := &http.Client{Timeout: 15 * time.Second}
479+ req, err := http.NewRequestWithContext(ctx, "GET", baseURL+"/models", nil)
480+ if err != nil {
481+ return nil, err
482+ }
483+ if apiKey != "" {
484+ req.Header.Set("authorization", "Bearer "+apiKey)
485+ }
486+ resp, err := client.Do(req)
487+ if err != nil {
488+ return nil, err
489+ }
490+ defer resp.Body.Close()
491+ body, _ := io.ReadAll(resp.Body)
492+ if resp.StatusCode != http.StatusOK {
493+ return nil, fmt.Errorf("yolo-auto discover http %d: %s", resp.StatusCode, strings.TrimSpace(string(body)))
494+ }
495+ var page struct {
496+ Data []struct {
497+ ID string `json:"id"`
498+ ContextLength int `json:"context_length"`
499+ MaxModelLen int `json:"max_model_len"`
500+ Thinking []string `json:"thinking"`
501+ } `json:"data"`
502+ }
503+ if err := json.Unmarshal(body, &page); err != nil {
504+ return nil, fmt.Errorf("yolo-auto discover parse: %w", err)
505+ }
506+ out := make([]Model, 0, len(page.Data))
507+ for _, d := range page.Data {
508+ id := strings.TrimSpace(d.ID)
509+ if id == "" || strings.Contains(strings.ToLower(id), "embed") {
510+ continue
511+ }
512+ contextWindow := d.ContextLength
513+ if contextWindow == 0 {
514+ contextWindow = d.MaxModelLen
515+ }
516+ if contextWindow == 0 {
517+ contextWindow = yoloAutoContextWindow
518+ }
519+ out = append(out, Model{
520+ Provider: "yolo-auto",
521+ ID: id,
522+ DisplayName: id,
523+ ContextWindow: contextWindow,
524+ MaxOutput: yoloAutoMaxOutput,
525+ Reasoning: len(d.Thinking) > 0,
526+ ReasoningLevelMap: yoloAutoReasoningLevels(d.Thinking),
527+ BaseURL: baseURL,
528+ Source: "live",
529+ })
530+ }
531+ return out, nil
532+}
533+
534+// yoloAutoReasoningLevels restricts the generic chat-completions defaults to
535+// the endpoint's advertised efforts, including minimal and xhigh when offered.
536+func yoloAutoReasoningLevels(thinking []string) map[string]string {
537+ levels := make(map[string]string)
538+ for _, level := range reasoningLevelOrder[1:] {
539+ levels[level] = ""
540+ }
541+ for _, effort := range thinking {
542+ level := NormalizeReasoning(effort)
543+ if _, known := levels[level]; known {
544+ levels[level] = level
545+ }
546+ }
547+ return levels
548+}
549+
461 // perMillionTokens converts a per-token USD price string to USD per 1M550 // perMillionTokens converts a per-token USD price string to USD per 1M
462 // tokens. Empty or unparseable values become 0.551 // tokens. Empty or unparseable values become 0.
463 func perMillionTokens(s string) float64 {552 func perMillionTokens(s string) float64 {
A packages/provider/discover_yolo_auto_test.go +125 -0
@@ -0,0 +1,125 @@
1+package provider
2+
3+import (
4+ "context"
5+ "fmt"
6+ "net/http"
7+ "net/http/httptest"
8+ "slices"
9+ "testing"
10+)
11+
12+func TestDiscoverYoloAutoListsKeyModels(t *testing.T) {
13+ const body = `{"object":"list","data":[
14+ {"id":"yolo","object":"model","context_length":262144,"max_model_len":262144,
15+ "thinking":["minimal","low","medium","high","xhigh"]},
16+ {"id":"yolo-small","object":"model","context_length":262144,"max_model_len":262144,
17+ "thinking":null},
18+ {"id":"text-embedding-3-small","object":"model"}
19+ ]}`
20+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
21+ if r.URL.Path != "/models" {
22+ t.Fatalf("request path = %q", r.URL.Path)
23+ }
24+ if got := r.Header.Get("authorization"); got != "Bearer yolo_test" {
25+ t.Fatalf("authorization = %q", got)
26+ }
27+ w.Header().Set("content-type", "application/json")
28+ fmt.Fprint(w, body)
29+ }))
30+ defer srv.Close()
31+
32+ models, err := DiscoverYoloAuto(context.Background(), "yolo_test", srv.URL+"/")
33+ if err != nil {
34+ t.Fatal(err)
35+ }
36+ if len(models) != 2 {
37+ t.Fatalf("models = %+v", models)
38+ }
39+
40+ yolo := models[0]
41+ if yolo.Provider != "yolo-auto" || yolo.ID != "yolo" || yolo.DisplayName != "yolo" ||
42+ yolo.ContextWindow != 262144 || yolo.MaxOutput != yoloAutoMaxOutput || !yolo.Reasoning ||
43+ yolo.BaseURL != srv.URL || yolo.Source != "live" {
44+ t.Fatalf("yolo model = %+v", yolo)
45+ }
46+
47+ small := models[1]
48+ if small.ID != "yolo-small" || small.ContextWindow != 262144 || small.Reasoning {
49+ t.Fatalf("second model = %+v", small)
50+ }
51+}
52+
53+func TestDiscoverYoloAutoFallsBackToDocumentedLimits(t *testing.T) {
54+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
55+ w.Header().Set("content-type", "application/json")
56+ fmt.Fprint(w, `{"data":[{"id":"yolo"}]}`)
57+ }))
58+ defer srv.Close()
59+
60+ models, err := DiscoverYoloAuto(context.Background(), "yolo_test", srv.URL)
61+ if err != nil {
62+ t.Fatal(err)
63+ }
64+ if len(models) != 1 || models[0].ContextWindow != yoloAutoContextWindow {
65+ t.Fatalf("models = %+v", models)
66+ }
67+}
68+
69+func TestYoloAutoDiscoveryReachesActiveCatalogAndWire(t *testing.T) {
70+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
71+ fmt.Fprint(w, `{"data":[
72+ {"id":"yolo","context_length":262144,"thinking":["minimal","low","medium","high","xhigh"]},
73+ {"id":"qwen3.8-flash","context_length":65536,"thinking":["high"]},
74+ {"id":"yolo-small","max_model_len":65536,"thinking":null}
75+ ]}`)
76+ }))
77+ defer srv.Close()
78+ models, err := DiscoverYoloAuto(context.Background(), "test", srv.URL)
79+ if err != nil {
80+ t.Fatal(err)
81+ }
82+ SetLiveModels(models)
83+ t.Cleanup(func() { SetLiveModels(nil) })
84+ for _, discovered := range models {
85+ active, err := FindModel("yolo-auto", discovered.ID)
86+ if err != nil {
87+ t.Fatal(err)
88+ }
89+ if active.ContextWindow != discovered.ContextWindow || active.Reasoning != discovered.Reasoning || active.BaseURL != srv.URL {
90+ t.Errorf("active metadata does not match discovery: %+v", active)
91+ }
92+ if active.ID == "yolo" && !slices.Equal(AvailableReasoningLevels(active), []string{"", "minimum", "low", "medium", "high", "xhigh"}) {
93+ t.Errorf("available levels = %q", AvailableReasoningLevels(active))
94+ }
95+ }
96+ client := NewYoloAuto("test", srv.URL).(*openaiClient)
97+ for _, tc := range []struct{ model, level, want string }{
98+ {"yolo", "minimum", "minimal"},
99+ {"yolo", "xhigh", "xhigh"},
100+ {"yolo", "max", "xhigh"},
101+ {"yolo", "off", ""},
102+ {"qwen3.8-flash", "low", "high"},
103+ {"yolo-small", "high", ""},
104+ } {
105+ wire, err := client.buildRequest(Request{Model: tc.model, Reasoning: tc.level})
106+ if err != nil {
107+ t.Fatal(err)
108+ }
109+ if wire.ReasoningEffort != tc.want {
110+ t.Errorf("%s/%s effort = %q, want %q", tc.model, tc.level, wire.ReasoningEffort, tc.want)
111+ }
112+ }
113+}
114+
115+func TestDiscoverYoloAutoReportsHTTPError(t *testing.T) {
116+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
117+ http.Error(w, "unauthorized", http.StatusUnauthorized)
118+ }))
119+ defer srv.Close()
120+
121+ _, err := DiscoverYoloAuto(context.Background(), "yolo_test", srv.URL)
122+ if err == nil {
123+ t.Fatal("expected discovery error")
124+ }
125+}
@@ -0,0 +1,125 @@
1+package provider
2+
3+import (
4+ "context"
5+ "fmt"
6+ "net/http"
7+ "net/http/httptest"
8+ "slices"
9+ "testing"
10+)
11+
12+func TestDiscoverYoloAutoListsKeyModels(t *testing.T) {
13+ const body = `{"object":"list","data":[
14+ {"id":"yolo","object":"model","context_length":262144,"max_model_len":262144,
15+ "thinking":["minimal","low","medium","high","xhigh"]},
16+ {"id":"yolo-small","object":"model","context_length":262144,"max_model_len":262144,
17+ "thinking":null},
18+ {"id":"text-embedding-3-small","object":"model"}
19+ ]}`
20+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
21+ if r.URL.Path != "/models" {
22+ t.Fatalf("request path = %q", r.URL.Path)
23+ }
24+ if got := r.Header.Get("authorization"); got != "Bearer yolo_test" {
25+ t.Fatalf("authorization = %q", got)
26+ }
27+ w.Header().Set("content-type", "application/json")
28+ fmt.Fprint(w, body)
29+ }))
30+ defer srv.Close()
31+
32+ models, err := DiscoverYoloAuto(context.Background(), "yolo_test", srv.URL+"/")
33+ if err != nil {
34+ t.Fatal(err)
35+ }
36+ if len(models) != 2 {
37+ t.Fatalf("models = %+v", models)
38+ }
39+
40+ yolo := models[0]
41+ if yolo.Provider != "yolo-auto" || yolo.ID != "yolo" || yolo.DisplayName != "yolo" ||
42+ yolo.ContextWindow != 262144 || yolo.MaxOutput != yoloAutoMaxOutput || !yolo.Reasoning ||
43+ yolo.BaseURL != srv.URL || yolo.Source != "live" {
44+ t.Fatalf("yolo model = %+v", yolo)
45+ }
46+
47+ small := models[1]
48+ if small.ID != "yolo-small" || small.ContextWindow != 262144 || small.Reasoning {
49+ t.Fatalf("second model = %+v", small)
50+ }
51+}
52+
53+func TestDiscoverYoloAutoFallsBackToDocumentedLimits(t *testing.T) {
54+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
55+ w.Header().Set("content-type", "application/json")
56+ fmt.Fprint(w, `{"data":[{"id":"yolo"}]}`)
57+ }))
58+ defer srv.Close()
59+
60+ models, err := DiscoverYoloAuto(context.Background(), "yolo_test", srv.URL)
61+ if err != nil {
62+ t.Fatal(err)
63+ }
64+ if len(models) != 1 || models[0].ContextWindow != yoloAutoContextWindow {
65+ t.Fatalf("models = %+v", models)
66+ }
67+}
68+
69+func TestYoloAutoDiscoveryReachesActiveCatalogAndWire(t *testing.T) {
70+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
71+ fmt.Fprint(w, `{"data":[
72+ {"id":"yolo","context_length":262144,"thinking":["minimal","low","medium","high","xhigh"]},
73+ {"id":"qwen3.8-flash","context_length":65536,"thinking":["high"]},
74+ {"id":"yolo-small","max_model_len":65536,"thinking":null}
75+ ]}`)
76+ }))
77+ defer srv.Close()
78+ models, err := DiscoverYoloAuto(context.Background(), "test", srv.URL)
79+ if err != nil {
80+ t.Fatal(err)
81+ }
82+ SetLiveModels(models)
83+ t.Cleanup(func() { SetLiveModels(nil) })
84+ for _, discovered := range models {
85+ active, err := FindModel("yolo-auto", discovered.ID)
86+ if err != nil {
87+ t.Fatal(err)
88+ }
89+ if active.ContextWindow != discovered.ContextWindow || active.Reasoning != discovered.Reasoning || active.BaseURL != srv.URL {
90+ t.Errorf("active metadata does not match discovery: %+v", active)
91+ }
92+ if active.ID == "yolo" && !slices.Equal(AvailableReasoningLevels(active), []string{"", "minimum", "low", "medium", "high", "xhigh"}) {
93+ t.Errorf("available levels = %q", AvailableReasoningLevels(active))
94+ }
95+ }
96+ client := NewYoloAuto("test", srv.URL).(*openaiClient)
97+ for _, tc := range []struct{ model, level, want string }{
98+ {"yolo", "minimum", "minimal"},
99+ {"yolo", "xhigh", "xhigh"},
100+ {"yolo", "max", "xhigh"},
101+ {"yolo", "off", ""},
102+ {"qwen3.8-flash", "low", "high"},
103+ {"yolo-small", "high", ""},
104+ } {
105+ wire, err := client.buildRequest(Request{Model: tc.model, Reasoning: tc.level})
106+ if err != nil {
107+ t.Fatal(err)
108+ }
109+ if wire.ReasoningEffort != tc.want {
110+ t.Errorf("%s/%s effort = %q, want %q", tc.model, tc.level, wire.ReasoningEffort, tc.want)
111+ }
112+ }
113+}
114+
115+func TestDiscoverYoloAutoReportsHTTPError(t *testing.T) {
116+ srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
117+ http.Error(w, "unauthorized", http.StatusUnauthorized)
118+ }))
119+ defer srv.Close()
120+
121+ _, err := DiscoverYoloAuto(context.Background(), "yolo_test", srv.URL)
122+ if err == nil {
123+ t.Fatal("expected discovery error")
124+ }
125+}
M packages/provider/extra_providers.go +6 -0
@@ -122,6 +122,12 @@ func NewGondola(apiKey, baseURL string) Client {
122122 return NewOpenAICompat("gondola", apiKey, baseURL, gondolaDefaultBaseURL)
123123 }
124124
125+// NewYoloAuto: Yolo-Auto, an OpenAI Chat Completions-compatible gateway
126+// addressed by the `yolo` and `yolo-small` model aliases.
127+func NewYoloAuto(apiKey, baseURL string) Client {
128+ return NewOpenAICompat("yolo-auto", apiKey, baseURL, yoloAutoDefaultBaseURL)
129+}
130+
125131 // NewOpenCode is the opencode.ai Zen endpoint. Mixed APIs upstream; this
126132 // constructor wires the openai-completions flavor only. Models that need
127133 // the anthropic-messages flavor under the same provider should be built
@@ -122,6 +122,12 @@ func NewGondola(apiKey, baseURL string) Client {
122 return NewOpenAICompat("gondola", apiKey, baseURL, gondolaDefaultBaseURL)122 return NewOpenAICompat("gondola", apiKey, baseURL, gondolaDefaultBaseURL)
123 }123 }
124 124
125+// NewYoloAuto: Yolo-Auto, an OpenAI Chat Completions-compatible gateway
126+// addressed by the `yolo` and `yolo-small` model aliases.
127+func NewYoloAuto(apiKey, baseURL string) Client {
128+ return NewOpenAICompat("yolo-auto", apiKey, baseURL, yoloAutoDefaultBaseURL)
129+}
130+
125 // NewOpenCode is the opencode.ai Zen endpoint. Mixed APIs upstream; this131 // NewOpenCode is the opencode.ai Zen endpoint. Mixed APIs upstream; this
126 // constructor wires the openai-completions flavor only. Models that need132 // constructor wires the openai-completions flavor only. Models that need
127 // the anthropic-messages flavor under the same provider should be built133 // the anthropic-messages flavor under the same provider should be built
M packages/provider/labels.go +2 -0
@@ -41,6 +41,8 @@ func ProviderLabel(id string) string {
4141 return "OpenRouter"
4242 case "gondola":
4343 return "Gondola"
44+ case "yolo-auto":
45+ return "Yolo-Auto"
4446 case "mistral":
4547 return "Mistral"
4648 case "zai":
@@ -41,6 +41,8 @@ func ProviderLabel(id string) string {
41 return "OpenRouter"41 return "OpenRouter"
42 case "gondola":42 case "gondola":
43 return "Gondola"43 return "Gondola"
44+ case "yolo-auto":
45+ return "Yolo-Auto"
44 case "mistral":46 case "mistral":
45 return "Mistral"47 return "Mistral"
46 case "zai":48 case "zai":
M packages/provider/merge.go +6 -0
@@ -28,6 +28,12 @@ func MergeCatalog(live []Model) []Model {
2828 for _, l := range live {
2929 k := byKey(l.Provider, l.ID)
3030 if s, ok := staticIndex[k]; ok {
31+ // Yolo-Auto reports authoritative, account-specific limits and
32+ // capabilities. Its seed entries are only offline fallbacks.
33+ if l.Provider == "yolo-auto" {
34+ staticIndex[k] = l
35+ continue
36+ }
3137 // Keep static prices & context window (live endpoint rarely
3238 // exposes these), but mark as live and non-speculative.
3339 s.Source = "live"
@@ -28,6 +28,12 @@ func MergeCatalog(live []Model) []Model {
28 for _, l := range live {28 for _, l := range live {
29 k := byKey(l.Provider, l.ID)29 k := byKey(l.Provider, l.ID)
30 if s, ok := staticIndex[k]; ok {30 if s, ok := staticIndex[k]; ok {
31+ // Yolo-Auto reports authoritative, account-specific limits and
32+ // capabilities. Its seed entries are only offline fallbacks.
33+ if l.Provider == "yolo-auto" {
34+ staticIndex[k] = l
35+ continue
36+ }
31 // Keep static prices & context window (live endpoint rarely37 // Keep static prices & context window (live endpoint rarely
32 // exposes these), but mark as live and non-speculative.38 // exposes these), but mark as live and non-speculative.
33 s.Source = "live"39 s.Source = "live"
M packages/provider/models.go +26 -0
@@ -272,6 +272,32 @@ var Catalog = []Model{
272272 BaseURL: gondolaDefaultBaseURL,
273273 },
274274
275+ // ---- Yolo-Auto ----
276+ // Seed entries only: `qwen3.8-flash` is the free and paid default returned by
277+ // defaultModelForProvider so it resolves offline. Yolo-Auto is an
278+ // OpenAI-compatible gateway on flat-rate plans with no per-token
279+ // billing, so no per-token prices are listed. The limits are the
280+ // provider's documented conservative client settings; the full catalog,
281+ // including each key's plan-bounded window, comes from /v1/models
282+ // (DiscoverYoloAuto).
283+ {
284+ Provider: "yolo-auto", ID: "qwen3.8-flash", DisplayName: "Qwen3.8 Flash",
285+ ContextWindow: yoloAutoContextWindow, MaxOutput: yoloAutoMaxOutput,
286+ Reasoning: true,
287+ BaseURL: yoloAutoDefaultBaseURL,
288+ },
289+ {
290+ Provider: "yolo-auto", ID: "yolo", DisplayName: "Yolo",
291+ ContextWindow: yoloAutoContextWindow, MaxOutput: yoloAutoMaxOutput,
292+ Reasoning: true,
293+ BaseURL: yoloAutoDefaultBaseURL,
294+ },
295+ {
296+ Provider: "yolo-auto", ID: "yolo-small", DisplayName: "Yolo Small",
297+ ContextWindow: yoloAutoContextWindow, MaxOutput: yoloAutoMaxOutput,
298+ BaseURL: yoloAutoDefaultBaseURL,
299+ },
300+
275301 // ---- Anthropic / newer families ----
276302 {
277303 Provider: "anthropic", ID: "claude-opus-4-5", DisplayName: "Claude Opus 4.5 (latest)",
@@ -272,6 +272,32 @@ var Catalog = []Model{
272 BaseURL: gondolaDefaultBaseURL,272 BaseURL: gondolaDefaultBaseURL,
273 },273 },
274 274
275+ // ---- Yolo-Auto ----
276+ // Seed entries only: `qwen3.8-flash` is the free and paid default returned by
277+ // defaultModelForProvider so it resolves offline. Yolo-Auto is an
278+ // OpenAI-compatible gateway on flat-rate plans with no per-token
279+ // billing, so no per-token prices are listed. The limits are the
280+ // provider's documented conservative client settings; the full catalog,
281+ // including each key's plan-bounded window, comes from /v1/models
282+ // (DiscoverYoloAuto).
283+ {
284+ Provider: "yolo-auto", ID: "qwen3.8-flash", DisplayName: "Qwen3.8 Flash",
285+ ContextWindow: yoloAutoContextWindow, MaxOutput: yoloAutoMaxOutput,
286+ Reasoning: true,
287+ BaseURL: yoloAutoDefaultBaseURL,
288+ },
289+ {
290+ Provider: "yolo-auto", ID: "yolo", DisplayName: "Yolo",
291+ ContextWindow: yoloAutoContextWindow, MaxOutput: yoloAutoMaxOutput,
292+ Reasoning: true,
293+ BaseURL: yoloAutoDefaultBaseURL,
294+ },
295+ {
296+ Provider: "yolo-auto", ID: "yolo-small", DisplayName: "Yolo Small",
297+ ContextWindow: yoloAutoContextWindow, MaxOutput: yoloAutoMaxOutput,
298+ BaseURL: yoloAutoDefaultBaseURL,
299+ },
300+
275 // ---- Anthropic / newer families ----301 // ---- Anthropic / newer families ----
276 {302 {
277 Provider: "anthropic", ID: "claude-opus-4-5", DisplayName: "Claude Opus 4.5 (latest)",303 Provider: "anthropic", ID: "claude-opus-4-5", DisplayName: "Claude Opus 4.5 (latest)",
M packages/provider/openai.go +4 -0
@@ -275,6 +275,10 @@ func (c *openaiClient) buildRequest(req Request) (*oaiRequest, error) {
275275 // values and take precedence over conservative protocol defaults.
276276 effort = reasoning
277277 }
278+ if c.Name() == "yolo-auto" && effort == "minimum" {
279+ // The advertised wire value is minimal, not zot's UI spelling.
280+ effort = "minimal"
281+ }
278282 if effort != "" {
279283 out.ReasoningEffort = effort
280284 }
@@ -275,6 +275,10 @@ func (c *openaiClient) buildRequest(req Request) (*oaiRequest, error) {
275 // values and take precedence over conservative protocol defaults.275 // values and take precedence over conservative protocol defaults.
276 effort = reasoning276 effort = reasoning
277 }277 }
278+ if c.Name() == "yolo-auto" && effort == "minimum" {
279+ // The advertised wire value is minimal, not zot's UI spelling.
280+ effort = "minimal"
281+ }
278 if effort != "" {282 if effort != "" {
279 out.ReasoningEffort = effort283 out.ReasoningEffort = effort
280 }284 }
M packages/provider/provider_test.go +28 -0
@@ -511,6 +511,34 @@ func TestGondolaSeedCatalog(t *testing.T) {
511511 }
512512 }
513513
514+func TestYoloAutoSeedCatalog(t *testing.T) {
515+ // The free-plan default must resolve without a live refresh.
516+ flash, err := FindModel("yolo-auto", "qwen3.8-flash")
517+ if err != nil {
518+ t.Fatal(err)
519+ }
520+ if flash.ContextWindow != yoloAutoContextWindow || flash.MaxOutput != yoloAutoMaxOutput ||
521+ !flash.Reasoning || flash.BaseURL != yoloAutoDefaultBaseURL {
522+ t.Fatalf("unexpected Qwen model: %+v", flash)
523+ }
524+ yolo, err := FindModel("yolo-auto", "yolo")
525+ if err != nil {
526+ t.Fatal(err)
527+ }
528+ if yolo.ContextWindow != yoloAutoContextWindow || yolo.MaxOutput != yoloAutoMaxOutput ||
529+ !yolo.Reasoning || yolo.BaseURL != yoloAutoDefaultBaseURL {
530+ t.Fatalf("unexpected Yolo model: %+v", yolo)
531+ }
532+
533+ small, err := FindModel("yolo-auto", "yolo-small")
534+ if err != nil {
535+ t.Fatal(err)
536+ }
537+ if small.BaseURL != yoloAutoDefaultBaseURL || small.Reasoning {
538+ t.Fatalf("unexpected Yolo Small model: %+v", small)
539+ }
540+}
541+
514542 func TestOpenAICompatAnthropicReasoningEffort(t *testing.T) {
515543 c := NewOpenRouter("token", "").(*openaiClient)
516544 wire, err := c.buildRequest(Request{
@@ -511,6 +511,34 @@ func TestGondolaSeedCatalog(t *testing.T) {
511 }511 }
512 }512 }
513 513
514+func TestYoloAutoSeedCatalog(t *testing.T) {
515+ // The free-plan default must resolve without a live refresh.
516+ flash, err := FindModel("yolo-auto", "qwen3.8-flash")
517+ if err != nil {
518+ t.Fatal(err)
519+ }
520+ if flash.ContextWindow != yoloAutoContextWindow || flash.MaxOutput != yoloAutoMaxOutput ||
521+ !flash.Reasoning || flash.BaseURL != yoloAutoDefaultBaseURL {
522+ t.Fatalf("unexpected Qwen model: %+v", flash)
523+ }
524+ yolo, err := FindModel("yolo-auto", "yolo")
525+ if err != nil {
526+ t.Fatal(err)
527+ }
528+ if yolo.ContextWindow != yoloAutoContextWindow || yolo.MaxOutput != yoloAutoMaxOutput ||
529+ !yolo.Reasoning || yolo.BaseURL != yoloAutoDefaultBaseURL {
530+ t.Fatalf("unexpected Yolo model: %+v", yolo)
531+ }
532+
533+ small, err := FindModel("yolo-auto", "yolo-small")
534+ if err != nil {
535+ t.Fatal(err)
536+ }
537+ if small.BaseURL != yoloAutoDefaultBaseURL || small.Reasoning {
538+ t.Fatalf("unexpected Yolo Small model: %+v", small)
539+ }
540+}
541+
514 func TestOpenAICompatAnthropicReasoningEffort(t *testing.T) {542 func TestOpenAICompatAnthropicReasoningEffort(t *testing.T) {
515 c := NewOpenRouter("token", "").(*openaiClient)543 c := NewOpenRouter("token", "").(*openaiClient)
516 wire, err := c.buildRequest(Request{544 wire, err := c.buildRequest(Request{

Keyboard shortcuts

Single-key shortcuts are on. ctrl k and esc work whatever this says.

ctrl k :
go to a section, branch, tag, file or repository
?
this list
j k
move the row cursor down / up
enter
open the row under the cursor; on Files, a directory opens or closes in place
↑ ↓ ← → home end
in the file tree (focus on a row): previous / next row, close / open a directory or go to its parent / first entry, first / last row. They never open a file
l h
on Files: open a directory or a file / close a directory or go up to its parent, then to the parent page. Elsewhere: into the side panel (on a merge request, its files) / back to the content; there j k move between its controls
g g G
first / last row
/
filter the list; on Files, find a file anywhere in the repository (esc clears, enter opens the best match)
b
switch branch or tag
g s g f g c g b g m g i g r g a
tabs: summary, files, commits, branches & tags, merge requests, issues, releases, actions (when available)
g h
home
w
wide mode: use the whole width of the screen, or not (remembered)
y
copy a permalink pinned to the commit
d u x
diff: split / unified / collapse or expand all
e E
diff: the whole file in view / every file, with the lines the hunks hide
n
merge request: next note in the diff
esc
close a dialog, leave a field

Branches 1

Tags 476

↑↓ moveenter openesc close