| Age | Commit message (Collapse) | Author | Files | Lines |
|
The model sends the description without a final period, so the prompt
read "...tool Fill in". opencode now starts in its plan agent, which
cannot edit, so its prompt asks for a proposal instead.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
project.sh makes a folder in ~/Programming/GIT with AGENTS.md, CLAUDE.md,
README.md and LICENSE (GPLv2 only, GPLv2+, GPLv3 or MIT, texts shipped in
licenses/), commits it signed, and opens Claude Code or opencode in a
kitty tab, or a new window when no kitty listens. The tool description
asks the model to confirm before calling. Check: test-project.sh.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
dnd, presentation, nolock and quiet through statusctl. The output is
read back after a set, so a set that did not land is not reported as
done, and a running game's hold on presentation is named. test-mode.sh
checks it against a scratch runtime dir.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
Six tasks: tag voice-v1 and strip voice, SQLite history, the two-way
protocol and reply loop, assistant.sh, a live check against the router,
docs. Every code block was assembled stage by stage into a scratch copy
and its self-check run; the planning-time deviations from the spec are
listed at the top and folded back into it by the docs task.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
Eleven tasks: the local-memory CLI with its self-check, detached commit
and push, install, assistant tools and prompt block, llamachat memory
module, config key, tool loop and local-only UI gate, the private server
repo, guardrails against cloud agents, and the live measurement.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|