luxe 0.1.4: remembered models, wheel-driven lists, and a steadier phone app
- luxe starts on the model you last chose in this project, then the last one anywhere. Signing in opens the model picker instead of choosing for you. - Every list in a modal takes the mouse wheel and a draggable scrollbar. - The phone app shows reasoning in full, stays put while you read back through a long session, and shows a question's answer on its card. - On Windows, luxe update replaces the running luxe, and a signed-in install no longer sees setup again. - The file tree no longer shows "engine busy" in a large project, loop output is easier to follow, and the name is written lowercase. The CHANGELOG has the full list.
This commit is contained in:
@@ -1,8 +1,8 @@
|
||||
---
|
||||
title: "Sessions and context"
|
||||
summary: "Resume past sessions, see what fills the context window, and how Luxe keeps long sessions going."
|
||||
summary: "Resume past sessions, see what fills the context window, and how luxe keeps long sessions going."
|
||||
order: 8
|
||||
group: "Using Luxe"
|
||||
group: "Using luxe"
|
||||
---
|
||||
|
||||
## Sessions
|
||||
@@ -10,7 +10,7 @@ group: "Using Luxe"
|
||||
Every conversation is saved as it goes, in `.luxe/sessions/` inside the project. Quitting loses
|
||||
nothing.
|
||||
|
||||
| To | In Luxe | From the command line |
|
||||
| To | In luxe | From the command line |
|
||||
| --- | --- | --- |
|
||||
| Pick up the last session | **Resume** on the start screen | `luxe -c` |
|
||||
| Find an older one | Type part of its title on the start screen, or open **Sessions…** (`/sessions`) | `luxe sessions list`, then `luxe --resume <id>` |
|
||||
@@ -40,7 +40,7 @@ threshold. A price you set in `models.json` replaces the catalog's, tiers and al
|
||||
Anthropic keeps a cached prompt for five minutes after it was last read. A turn that waits longer
|
||||
than that, on a slow command, a permission prompt or a question, loses the cache, and the next
|
||||
request pays to write the whole conversation again: about $2 on a 400k-token Opus session. So while
|
||||
a turn runs, Luxe re-sends its last request with a one-token reply just before the five minutes are
|
||||
a turn runs, luxe re-sends its last request with a one-token reply just before the five minutes are
|
||||
up. That costs a cache read, a tenth of the write it saves.
|
||||
|
||||
`agent.cache_warming` decides when:
|
||||
@@ -52,7 +52,7 @@ up. That costs a cache read, a tenth of the write it saves.
|
||||
| `off` | Never |
|
||||
|
||||
A refresh goes out only when it is expected to save at least $0.05, so a short conversation is
|
||||
never refreshed. Between turns Luxe cannot know you will reply, so `idle` refreshes only a large
|
||||
never refreshed. Between turns luxe cannot know you will reply, so `idle` refreshes only a large
|
||||
conversation. On real sessions it lost money overall, which is why it is not the default. Refreshes
|
||||
are never sent on a subscription plan, or for an Anthropic model using a fixed thinking budget,
|
||||
whose cache would change on replay. Their cost shows under **cache warming** in `/cost`.
|
||||
@@ -82,7 +82,7 @@ more on every turn instead of on each pause.
|
||||
| tool schemas | The tools the agent can call | `tools.disabled`; see [Tools](tools.md) |
|
||||
| instructions | Your `AGENTS.md` files | A shorter file; see [Project context](project-context.md) |
|
||||
| skills | The list of skills the agent can load | Fewer, or shorter descriptions |
|
||||
| harness | Luxe's own instructions | Nothing; this is fixed |
|
||||
| harness | luxe's own instructions | Nothing; this is fixed |
|
||||
| appended | One-time context added to a resumed session, such as what changed while you were away | `/new` |
|
||||
|
||||
The largest single items are named under a row, which is usually how you find a `read` or `bash`
|
||||
@@ -90,7 +90,7 @@ call that should have been narrower. The total is what the provider reported for
|
||||
|
||||
## Compaction
|
||||
|
||||
When a conversation fills 90% of the usable window, Luxe summarizes it and carries on, keeping the
|
||||
When a conversation fills 90% of the usable window, luxe summarizes it and carries on, keeping the
|
||||
most recent part word for word. The summary records the goal, constraints, progress, decisions,
|
||||
next steps and the files the session touched. You see a line like
|
||||
`Compacted the conversation — 82k → 21k of context.`
|
||||
@@ -99,7 +99,7 @@ next steps and the files the session touched. You see a line like
|
||||
conversation that already fits in what `keep_recent` keeps has nothing to summarize, and `/compact`
|
||||
says so.
|
||||
|
||||
Before summarizing, from 80% full, Luxe first replaces old tool output in the request with a short
|
||||
Before summarizing, from 80% full, luxe first replaces old tool output in the request with a short
|
||||
placeholder. The session file keeps everything; only what is sent changes.
|
||||
|
||||
To change when and how it happens:
|
||||
@@ -127,7 +127,7 @@ To change when and how it happens:
|
||||
| `summarizer` | the session's model | The model that writes the summary, as `provider/id`, on a provider you have set up. A smaller, cheaper model is usually enough, and `/cost` prices its spend as it does any other model's. |
|
||||
|
||||
This works in a project's `.luxe/config.json` too, and so does `agent.cache_warming`, which a project
|
||||
can turn down but not up. The compaction settings in `/settings` apply the next time Luxe starts.
|
||||
can turn down but not up. The compaction settings in `/settings` apply the next time luxe starts.
|
||||
|
||||
## Long command output
|
||||
|
||||
|
||||
Reference in New Issue
Block a user