d14f583d92
The repository tracks the latest stable Rust, pinned at the root. A
`rust-version` key states a *floor* -- the oldest toolchain a crate supports --
which is a different promise, and one this repository does not make. It also
said 1.97 while the pin was 1.98.0 and nothing verified it, so it was a claim in
the wrong direction and unchecked in both.
So it goes, everywhere:
59 rust-version = "1.97" (workspace and package declarations)
417 rust-version.workspace = true (members inheriting them)
476 files, 476 deletions, 0 insertions
The 417 are why this is not the sixty-file change it looks like from a grep for
the value. A member inheriting a key that no longer exists does not fall back to
a default -- its manifest stops resolving. Removing the declarations without the
inherits would have broken every workspace that has members.
Deliberately untouched: `joule-code-rs/vendor/wtransport/Cargo.toml`. That is a
vendored third-party crate declaring a floor about itself, not about us, and our
pin is above it. Editing vendored source to satisfy our own policy would make
the copy diverge from upstream for no benefit.
Verified rather than assumed:
- all 493 `Cargo.toml` files in the tree parse (`tomllib`)
- `cargo metadata --no-deps --locked` resolves on `joule-code-rs`, `wai-rs`,
`openpay`, `mesh-rs`, `sandbox-rs` and `jcp-rs` -- the check that actually
exercises workspace inheritance, which a TOML parse does not
- no `Cargo.lock` changed; `rust-version` is not lockfile state
`wai/wai-verify/Cargo.toml` already carried a comment saying it omits
`rust-version` on purpose, so this makes the rest of the tree agree with the one
crate that had already decided.
What this gives up, stated plainly: cargo can no longer greet an older
toolchain with "requires rustc 1.97" and will instead fail wherever the code
first needs something newer. That is the cost of not maintaining a floor, and
it is the right cost when the floor was fiction.
Co-Authored-By: Claude Opus 5 <[email protected]>
14 lines
1.3 KiB
TOML
14 lines
1.3 KiB
TOML
[package]
|
|
name = "jouleclaw-toolcall-repair"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
authors.workspace = true
|
|
description = "Typed tool-call repair primitive. Absorbs the operational insight from Ahmad Awais (Command Code, ~600B tokens/day): open-weight LLMs (DeepSeek V4 Pro, Kimi K2, MiniMax) have specific tool-call mis-shaping variations that they REPEAT 50+ times instead of correcting from a returned schema error. The fix is at the HARNESS layer — detect the variation deterministically, repair the call, return the result PLUS a repair hint so the model learns. Provides DetectPattern (6 variants) + RepairAction (5 variants) + RepairRule + RepairLibrary + .apply() + a `presets` module with reference rules for the patterns Ahmad called out (empty object where array expected, JSON-string instead of array, markdown link inside a path string, null where optional default expected, missing optional field). Composes with jouleclaw-llm (between backend response and consumer), jouleclaw-hindsight (repair hits are Observations; high-frequency repairs surface as paradigm pressure), jouleclaw-promotion-path (a repair rule can itself promote)."
|
|
|
|
[dependencies]
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
thiserror = { workspace = true }
|
|
blake3 = { workspace = true }
|