mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-10-07 03:00:29 +00:00
feat(model): add gemini-3.5-flash (#403)
## Summary Updates the built-in Gemini catalog for the current Gemini API lineup by adding `gemini-3.5-flash` and promoting `gemini-3.1-flash-lite` to the canonical small default. The old `gemini-3.1-flash-lite-preview` ID remains accepted as an alias and resolves to the stable API ID, avoiding a breaking change for existing workflows. The catalog test changes remove Gemini-specific data assertions and keep only a generic small-default invariant, so future declarative catalog updates do not require Rust test churn. ## Verification - `cargo nextest run -p fabro-model` - `cargo +nightly-2026-04-14 fmt --check --all` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 (unknown context, default reasoning) via [Codex](https://openai.com/codex)
This commit is contained in:
Bryan Helmkamp
GitHub
parent
705079a271
commit
bb3f4bd62b
3 changed files with 53 additions and 98 deletions
|
|
@ -28,8 +28,9 @@ No single model is best at everything. Fabro lets you assign the right model to
|
|||
| `gpt-5.4-pro` | openai | `gpt54-pro` | 1M | $30.00 / $180.00 | 20 tok/s |
|
||||
| `gemini-3.1-pro-preview` | gemini | `gemini-pro` | 1M | $2.00 / $12.00 | 85 tok/s |
|
||||
| `gemini-3.1-pro-preview-customtools` | gemini | `gemini-customtools` | 1M | $2.00 / $12.00 | 85 tok/s |
|
||||
| `gemini-3.5-flash` | gemini | `gemini-35-flash` | 1M | $1.50 / $9.00 | 150 tok/s |
|
||||
| `gemini-3-flash-preview` | gemini | `gemini-flash` | 1M | $0.50 / $3.00 | 150 tok/s |
|
||||
| `gemini-3.1-flash-lite-preview` | gemini | `gemini-flash-lite` | 1M | $0.25 / $1.50 | 200 tok/s |
|
||||
| `gemini-3.1-flash-lite` | gemini | `gemini-flash-lite`, `gemini-3.1-flash-lite-preview` | 1M | $0.25 / $1.50 | 200 tok/s |
|
||||
| `kimi-k2.5` | kimi | `kimi` | 262K | $0.60 / $3.00 | 50 tok/s |
|
||||
| `glm-4.7` | zai | `glm`, `glm4` | 203K | $0.60 / $2.20 | 100 tok/s |
|
||||
| `minimax-m2.5` | minimax | `minimax` | 197K | $0.30 / $1.20 | 45 tok/s |
|
||||
|
|
|
|||
|
|
@ -1910,35 +1910,26 @@ enabled = true
|
|||
fn builtin_small_defaults_are_marked_per_provider() {
|
||||
let catalog = Catalog::builtin();
|
||||
|
||||
assert_eq!(
|
||||
catalog
|
||||
.small_default_for_provider(&ProviderId::anthropic())
|
||||
.unwrap()
|
||||
.id,
|
||||
"claude-haiku-4-5"
|
||||
);
|
||||
assert_eq!(
|
||||
catalog
|
||||
.small_default_for_provider(&ProviderId::openai())
|
||||
.unwrap()
|
||||
.id,
|
||||
"gpt-5.4-mini"
|
||||
);
|
||||
assert_eq!(
|
||||
catalog
|
||||
.small_default_for_provider(&ProviderId::gemini())
|
||||
.unwrap()
|
||||
.id,
|
||||
"gemini-3.1-flash-lite-preview"
|
||||
);
|
||||
assert!(catalog.get("claude-haiku-4-5").unwrap().small_default);
|
||||
assert!(catalog.get("gpt-5.4-mini").unwrap().small_default);
|
||||
let small_defaults = catalog
|
||||
.list(None)
|
||||
.into_iter()
|
||||
.filter(|model| model.small_default)
|
||||
.collect::<Vec<_>>();
|
||||
|
||||
assert!(
|
||||
catalog
|
||||
.get("gemini-3.1-flash-lite-preview")
|
||||
.unwrap()
|
||||
.small_default
|
||||
!small_defaults.is_empty(),
|
||||
"built-in catalog should mark at least one small default model"
|
||||
);
|
||||
|
||||
for model in small_defaults {
|
||||
assert_eq!(
|
||||
catalog
|
||||
.small_default_for_provider(&model.provider)
|
||||
.unwrap()
|
||||
.id,
|
||||
model.id
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
|
@ -3693,68 +3684,6 @@ reasoning_effort = "levels"
|
|||
assert!(Catalog::builtin().get("nonexistent-model").is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn gemini_3_1_flash_lite_in_catalog() {
|
||||
let m = Catalog::builtin()
|
||||
.get("gemini-3.1-flash-lite-preview")
|
||||
.unwrap();
|
||||
insta::assert_debug_snapshot!(m, @r#"
|
||||
Model {
|
||||
id: "gemini-3.1-flash-lite-preview",
|
||||
provider: gemini,
|
||||
family: "gemini-3",
|
||||
display_name: "Gemini 3.1 Flash Lite (Preview)",
|
||||
limits: ModelLimits {
|
||||
context_window: 1048576,
|
||||
max_output: Some(
|
||||
65536,
|
||||
),
|
||||
},
|
||||
training: Some(
|
||||
"2025-01-01",
|
||||
),
|
||||
knowledge_cutoff: Some(
|
||||
"January 2025",
|
||||
),
|
||||
features: ModelFeatures {
|
||||
tools: true,
|
||||
vision: true,
|
||||
reasoning: true,
|
||||
reasoning_effort: Levels,
|
||||
prompt_cache: false,
|
||||
},
|
||||
costs: ModelCosts {
|
||||
input_cost_per_mtok: Some(
|
||||
0.25,
|
||||
),
|
||||
output_cost_per_mtok: Some(
|
||||
1.5,
|
||||
),
|
||||
cache_input_cost_per_mtok: Some(
|
||||
0.0625,
|
||||
),
|
||||
},
|
||||
estimated_output_tps: Some(
|
||||
200.0,
|
||||
),
|
||||
aliases: [
|
||||
"gemini-flash-lite",
|
||||
],
|
||||
default: false,
|
||||
small_default: true,
|
||||
configured: false,
|
||||
}
|
||||
"#);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn gemini_flash_lite_alias() {
|
||||
assert_eq!(
|
||||
Catalog::builtin().get("gemini-flash-lite").unwrap().id,
|
||||
"gemini-3.1-flash-lite-preview"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn kimi_k2_5_in_catalog() {
|
||||
let m = Catalog::builtin().get("kimi-k2.5").unwrap();
|
||||
|
|
|
|||
|
|
@ -60,6 +60,31 @@ input_cost_per_mtok = 2.0
|
|||
output_cost_per_mtok = 12.0
|
||||
cache_input_cost_per_mtok = 0.5
|
||||
|
||||
[models."gemini-3.5-flash"]
|
||||
provider = "gemini"
|
||||
api_id = "gemini-3.5-flash"
|
||||
display_name = "Gemini 3.5 Flash"
|
||||
family = "gemini-3"
|
||||
training = "2025-01-01"
|
||||
knowledge_cutoff = "January 2025"
|
||||
estimated_output_tps = 150
|
||||
aliases = ["gemini-35-flash"]
|
||||
|
||||
[models."gemini-3.5-flash".limits]
|
||||
context_window = 1048576
|
||||
max_output = 65536
|
||||
|
||||
[models."gemini-3.5-flash".features]
|
||||
tools = true
|
||||
vision = true
|
||||
reasoning = true
|
||||
reasoning_effort = "levels"
|
||||
|
||||
[models."gemini-3.5-flash".costs]
|
||||
input_cost_per_mtok = 1.5
|
||||
output_cost_per_mtok = 9.0
|
||||
cache_input_cost_per_mtok = 0.15
|
||||
|
||||
[models."gemini-3-flash-preview"]
|
||||
provider = "gemini"
|
||||
api_id = "gemini-3-flash-preview"
|
||||
|
|
@ -85,28 +110,28 @@ input_cost_per_mtok = 0.5
|
|||
output_cost_per_mtok = 3.0
|
||||
cache_input_cost_per_mtok = 0.125
|
||||
|
||||
[models."gemini-3.1-flash-lite-preview"]
|
||||
[models."gemini-3.1-flash-lite"]
|
||||
provider = "gemini"
|
||||
api_id = "gemini-3.1-flash-lite-preview"
|
||||
display_name = "Gemini 3.1 Flash Lite (Preview)"
|
||||
api_id = "gemini-3.1-flash-lite"
|
||||
display_name = "Gemini 3.1 Flash Lite"
|
||||
family = "gemini-3"
|
||||
training = "2025-01-01"
|
||||
knowledge_cutoff = "January 2025"
|
||||
estimated_output_tps = 200
|
||||
aliases = ["gemini-flash-lite"]
|
||||
aliases = ["gemini-flash-lite", "gemini-3.1-flash-lite-preview"]
|
||||
small_default = true
|
||||
|
||||
[models."gemini-3.1-flash-lite-preview".limits]
|
||||
[models."gemini-3.1-flash-lite".limits]
|
||||
context_window = 1048576
|
||||
max_output = 65536
|
||||
|
||||
[models."gemini-3.1-flash-lite-preview".features]
|
||||
[models."gemini-3.1-flash-lite".features]
|
||||
tools = true
|
||||
vision = true
|
||||
reasoning = true
|
||||
reasoning_effort = "levels"
|
||||
|
||||
[models."gemini-3.1-flash-lite-preview".costs]
|
||||
[models."gemini-3.1-flash-lite".costs]
|
||||
input_cost_per_mtok = 0.25
|
||||
output_cost_per_mtok = 1.5
|
||||
cache_input_cost_per_mtok = 0.0625
|
||||
cache_input_cost_per_mtok = 0.025
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue