llm-chat/Cargo.toml
flemming-it d5b000e18e feat: report what a call cost in tokens
Three dialects spell the same two numbers differently: Ollama counts
in `prompt_eval_count` and `eval_count`, the OpenAI shape in
`usage.prompt_tokens` and `usage.completion_tokens`, Anthropic in
`usage.input_tokens` and `usage.output_tokens`. All three now reach
the caller as `tokens_prompt` and `tokens_completion`, which the hub
lifts into the audit log by itself.

An answer that carries no count leaves both fields empty rather than
reporting a zero: a zero is a measurement, and this is the absence of
one. Half a count is reported as far as it goes.

The cost of a model call was the one part of the audit question
"which model produced this, and what did it cost" that nothing
answered (model pool M3).

Signed-off-by: flemming-it <sf@flemming.it>
2026-10-26 03:54:39 +01:00

49 lines
1.1 KiB
TOML

# Standalone Cargo.toml — targets wasm32-wasip2.
#
# Build with:
# cargo build --release --target wasm32-wasip2
[package]
name = "llm_chat"
version = "0.3.0"
edition = "2024"
license = "Apache-2.0"
publish = false
description = "F∆I module providing llm.chat"
[lib]
# cdylib for the wasm artifact, rlib so integration tests can
# link against the module's `invoke` function on the host.
crate-type = ["cdylib", "rlib"]
[dependencies]
chain-module-sdk = { git = "https://git.flemming.ai/fai/chain-module-sdk-rust.git", tag = "v0.3.0" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
thiserror = "2"
# WASI-0.2 HTTP client. Only compiled into the wasm32-wasip2 build.
[target.'cfg(target_arch = "wasm32")'.dependencies]
waki = "0.5"
[dev-dependencies]
serde_json = "1"
[profile.release]
opt-level = "s"
lto = true
codegen-units = 1
strip = "symbols"
[lints.rust]
unsafe_op_in_unsafe_fn = "warn"
[lints.clippy]
unwrap_used = "deny"
expect_used = "deny"
panic = "deny"
print_stdout = "deny"
print_stderr = "deny"
[workspace]
# Empty so this package is NOT picked up by a parent.