doubleo7/Cargo.toml
Austin Schaefer 9212914282 feat: deep research agentic loop with rig AgentRunner + Gemma models
Pins rig to the newest published crates.io release (0.41.0) instead of
the git main branch, and adapts swear_cleanup's revise.rs to that
release's API (OneOrMany::first() returns T directly, raw_completion
folded into CompletionResponse::raw_response).

The research agent (gemma4:26b) drives rig's AgentRunner tool-calling
loop with two lean #[rig::tool_macro] tools — a DuckDuckGo HTML search
and a page-text fetcher — to gather and cross-check findings. A second
agent (gemma4-e4b) turns those findings into a structured report; the
smaller/faster model suffices there since it's reformatting already-
digested notes rather than doing multi-step research reasoning.
2026-08-14 12:40:09 +02:00

15 lines
409 B
TOML

[package]
name = "doubleo7"
version = "0.1.0"
edition = "2024"
[dependencies]
anyhow = "1.0.104"
reqwest = { version = "0.13.4", features = ["query"] }
rig = { version = "0.41.0", features = ["test-utils"] }
scraper = "0.25"
serde = "1.0.229"
tokio = { version = "1.53.1", features = ["full"] }
toml = "1.1.4+spec-1.1.0"
tracing = "0.1"
tracing-subscriber = { version = "0.3.23", features = ["env-filter"] }