Skip to content

Commit 828aa23

Browse files
committed
Update ChangeLog
1 parent f9a15a8 commit 828aa23

3 files changed

Lines changed: 10 additions & 2 deletions

File tree

ChangeLog.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,14 @@
22

33
All notable user-facing changes to Swival.
44

5+
## 1.0.28
6+
7+
- `/audit` gained an adjudication phase that runs between verification and artifact generation. Each verified finding faces a panel of three independent reviewers, each told to refute it from a different angle (reachability, threat model, severity), and only findings confirmed by a majority make it into reports and patches. Survivors get their severity recalibrated down to the realistic worst case, and dropped findings are listed in the README with the reason, so the gap between verified and written counts is always explained.
8+
- New `--max-output-lines` and `--max-output-kb` options (also available as config keys and `Session` parameters) make tool output caps tunable. The first sets the default number of lines a file read returns, the second the byte cap applied to file reads, directory listings, grep, outline, and fetched URLs.
9+
- Child processes spawned by Swival no longer inherit the bundled virtualenv `bin/` in their `PATH`. Packaged installs (such as Homebrew) used to leak that directory into every command the agent ran, which could shadow the user's own toolchain, most visibly a rustup-managed `cargo` being hijacked by a brew-installed Rust.
10+
- The `README.md` index that `/audit` writes into `audit-findings/` is now much more readable: a proper title, a summary with a severity breakdown, and sentence-case section headers with common security acronyms spelled correctly.
11+
- GEAP reliability fixes: the bundled LiteLLM has been updated to a version that restores GEAP routing, and background summarization calls no longer fail with credential errors.
12+
513
## 1.0.27
614

715
- Swival now auto-detects model context windows when `--max-context-tokens` is omitted. Hosted providers use LiteLLM's model registry, llama.cpp reads the server's runtime `n_ctx`, and OpenAI-compatible servers can advertise their limit via `/v1/models`.

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[project]
22
name = "swival"
3-
version = "1.0.27"
3+
version = "1.0.28"
44
description = "A small, powerful CLI coding agent for open AI models"
55
readme = "README.md"
66
license = "MIT"

uv.lock

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

0 commit comments

Comments
 (0)