v0.4.16

Fix: exclude minified marked.js from lint, fix Solid reactivity warning

v0.4.15

feat: improve audit loop with coder decisions and finding recurrence tracking

• Coder decisions: coding agents can now document their decisions and verification methods via HTML comments, which the auditor prompt includes to avoid re-reporting explained findings.
• Finding recurrence tracking: bug findings that recur across audit rounds are automatically escalated after 3 occurrences, appearing as "Recurring blocking findings" in coder prompts and "Recurring findings — re-evaluate" in auditor prompts. Recurrence resets when a finding is resolved or a section passes audit clean.
• Sandbox host fallback: glob/grep tools with absolute paths outside the workspace mount (e.g., tool-output directories) now defer to host execution instead of erroring inside the container.

v0.4.14

Fixes

• Add PRAGMA busy_timeout=5000 to the readonly forge.db connections in the TUI loop store and dashboard launcher, preventing intermittent "database is locked" errors when reads collide with WAL checkpoints during an active loop. The dashboard's long-lived reader made this previously latent collision likely to surface.
• Suppress git stderr in worktree cleanup and sandbox manager git probes so handled non-zero exits no longer leak fatal: not a git repository to the terminal.

v0.4.13

What's Changed

• fix: correct onlyBuiltDependencies format in pnpm-workspace.yaml
• feat: forge dashboard with project dir resolution (#38)
• feat: paste-plan-dialog (#35)
• refactor: remove plan approval nudge hook, simplify session follow (#34)

Full changelog: v0.4.12...v0.4.13

v0.4.12

What's Changed

• refactor: remove plan approval nudge hook, simplify session follow by @chriswritescode-dev in #34

Full Changelog: v0.4.11...v0.4.12

v0.4.11

What's Changed

• feat: add plan approval nudge hook by @chriswritescode-dev in #32
• refactor(tui): derive execution dialog state from the OpenCode SDK by @chriswritescode-dev in #33

Full Changelog: v0.4.10...v0.4.11

v0.4.10

Changes

• feat: allow editing loaded plans
• fix: capture plans on assistant completion
• chore: bump version to 0.4.10

v0.4.9

Features

• Add sandbox.enabled config option to opt out of Docker sandboxing. When set to false, loops run in worktree-only mode even if Docker is available.

v0.4.8

Fixes

• Stop guarding the question tool on captured plans. The pre-execution hook no longer captures the latest assistant plan or throws 'Forge plan capture failed' when no plan exists. Plan-approval detection now requires all three canonical labels ("New session", "Execute here", "Loop") before routing — unrelated questions that happen to include an "Execute here" option are no longer intercepted.

v0.4.7

Changes

• Separate bash vs forge-bash permissions for sandbox loops (#30)
• Add sandbox option to loop and audit permission rulesets (#30)