Luxe 0.1.2: Windows fixes, working compaction, and compaction progress in the dock

This commit is contained in:
Evan Whittaker
2026-10-18 15:04:51 -05:00
parent 4ed87ee4e4
commit 33b87c78a8
69 changed files with 1470 additions and 424 deletions

View File

@@ -2281,6 +2281,14 @@ on `PATH`, and the agent needs a POSIX shell for most commands. Without one, com
If WSL is installed, Luxe skips the `bash.exe` in `System32`, which would run commands inside Linux
against a different filesystem.
Python on Windows is `py` or `python`. `python3` is usually the Microsoft Store's placeholder, so
Luxe tries `py -3` first. For the Python debugger, run `py -m pip install debugpy`. The agent's
commands run Python in UTF-8 mode (`PYTHONUTF8=1`) unless you have set it yourself, so output with
characters outside your code page doesn't crash them.
Windows Terminal keeps a column at the right edge for its scrollbar. To give it to Luxe, set
**Scrollbar visibility** to **Hidden** in your profile's **Appearance** settings.
## Where Luxe keeps files
| | Linux and macOS | Windows |
@@ -3831,7 +3839,7 @@ what you do not recognize.
| `refresh_sessions` | | Answered by `sessions_refreshed` |
| `refresh_workspace` | | Answered by `workspace_updated` |
| `request_context_composition` | | What fills the context window; answered by `context_composition` |
| `compact_now` | `{"focus": "the API decisions"}`, or nothing | Summarize now; answered by `compaction_done` |
| `compact_now` | `{"focus": "the API decisions"}`, or nothing | Summarize now; answered by `compaction_started`, then `compaction_done` or `compaction_stopped` |
| `load_guided_review` | `{"request_id": "…", "target": {"kind": "working_tree"}}` | Capture a Guided Review; see [below](#guided-review) |
| `load_file_diff` | `{"request_id": "…", "path": "src/main.rs"}` | One file's change, outside any review; answered by `file_diff_loaded` |
| `list_directory` | `{"request_id": "…", "path": "src"}` | One project folder's entries, without what `.gitignore` ignores unless `"include_ignored": true`, which marks each such entry `"ignored": true`; answered by `directory_listed` |
@@ -3962,6 +3970,7 @@ There are around sixty. These are the ones a front end is built on:
| `review_started`, `review_finished` | A requested review began on `model`, and came back with a `verdict` (`continue`, `fix` or `unavailable`) and `findings`. On `fix` the findings also become the agent's next turn. |
| `turn_usage`, `session_usage`, `plan_usage` | Cost per call, for the session, and what a subscription has left |
| `context_usage`, `context_composition` | How full the context window is, and with what |
| `compaction_started`, `compaction_done`, `compaction_stopped` | A summary of the conversation is being written, on request or mid-turn. It can take a minute. It always ends in `compaction_done` (with `tokens_after`) or `compaction_stopped` (failed or cancelled). |
| `workspace_updated` | The project, Git changes, todos and tools: what the dock shows |
| `session_loaded`, `sessions_refreshed` | A transcript was restored; the session list changed |
| `notice`, `error` | Something to show. `error` ends the turn. |
@@ -4213,8 +4222,9 @@ your own terminal is how you give both. So when a step needs one, the agent puts
in a code block, you copy it into another terminal and run it, then tell the agent it is done.
The same goes for a command that waits on you at a terminal, such as a password, a confirmation or
an interactive installer. Commands the agent runs have no terminal at all, so one of those fails at
once and says what it wanted, rather than waiting where nobody can answer.
an interactive installer. Commands the agent runs have no terminal and nothing to read from, so one
of those fails or carries on with empty input, rather than waiting where nobody can answer. Most,
such as `sudo`, say what they wanted; a shell's `read` just gets an empty answer.
To allow it anyway, decide ahead of time in your global file. It only helps where no password is
needed, such as a passwordless `sudo` rule for one program:
@@ -4879,4 +4889,7 @@ script -f /tmp/luxe.tty -c luxe # replay with `cat` or `scriptreplay`
asciinema rec /tmp/luxe.cast -c luxe
```
Windows has neither. Take a screenshot instead, and in Windows Terminal right-click the tab and
choose **Export Text** to save what the screen shows.
Attach the recording and the log from the same time.