Integrates isocline's top and bottom bar APIs to display the active
provider, model, and shortcut hints. Updates the status bar on
terminal resize and mode switches.
Updates the `zenai` dependency to support safety finish reasons. Tracks
when a model refuses a request due to safety, prints a specific warning
message, and avoids re-prompting.
Depends on https://github.com/lightpanda-io/zig-v8-fork/pull/179
An improvement to https://github.com/lightpanda-io/browser/pull/2515 to prevent
a v8 assertion if we terminate as an inspector dispatch is happening.
The problem is that if we just immediately terminate, we aren't sure what the
worker thread is doing, and, apparently, if we terminate then dispatch a message
to the inspector, we fail an assertion.
With the way the code was, the only safe solution would be to hold a mutex
over the session dispatch, but that could block the network thread.
So instead of terminating from the network thread, we now ask v8 to execute
a callback. This gets executed on the worker thread, which can then terminate
the execution.
The initial version of 2515 delayed the termination from the network thread.
It's possible that solution would "solve" the issue, simply because it's very
unlikely that a worker would be "stuck" for 5 seconds and then get unstuck.
More likely that it exits immediately, or is stuck in an endless loop. But
that would still leave a window where we could terminate in network and then
dispatch in the worker. Less likely, but still possible. Hopefully this new
mechanism eliminates this from being a problem in all circumstances.
Extracts provider and model settings logic from `Agent.zig` into a new
`settings.zig` module. Replaces custom UTF-8 truncation logic with
`truncateUtf8` from `string.zig`. Also updates the `zenai` dependency.
* agent: add a /model command to chnage current model
And remove the pick-model CLI option
* agent: add /provider to change the current provider
* agent: extract requireLlmNoArg helper
* agent: simplify provider detection
* repl: add tab completion for /model and /provider
Changes `/model` and `/provider` to accept an optional name argument
instead of prompting with a numbered list. Bare commands now print the
current selection, while Tab dynamically completes candidates. Model
lists are fetched and cached to prevent redundant network requests.
* agent: remember last selected provider and model
Persists the last selected AI provider and model in a local
`.lp-agent` file and resumes it on startup. Removes the
interactive provider picker in favor of deterministic auto-detection.
* agent: simplify requireLlm and model resolution
Changes `requireLlm` to return a boolean instead of credentials, and
cleans up the model initialization logic to use `resolved` directly.
Also removes unused user errors.
---------
Co-authored-by: Adrià Arrufat <adria.arrufat@gmail.com>
This is a bit all over the place.
1 - Replace libidn2 with rust-idna. It looks like there are different idna
profiles, and rust-idna (from the servo project) implements the whatwg
one. libidn2 would be too strict in some cases and not strict enough in
others. (Gemini says I could use libidn2 for this, but what it suggested
didn't work, and I couldn't figure it out myself, and claude insisted it
_did not_ have the correct implementation for what we want).
2 - We previously only ran a URL through idna if it wasn't ascii. Turns out
we also need to run it if there's a "xn--" (aka, an IDNA ACE prefix) in
there. This helps us pass hundreds of WPT cases, and it's pretty cheap.
3 - Implement more of the Area WebAPI. Mostly copied from Anchor.
4 - Add username/password accessor to Anchor/Area
5 - window.open validates the URL (i.e. tries to resolve it and handles the
error)
6 - Invalid idna conversion maps to a TypeError
7 - Cleanup closed popups on the next tick (like destroyed pages), rather than
at an interval or on shutdown. This one seems unrelated, but some of these
tests are opening hundreds (thousands?) of popups and then closing them.
Replaces the string `name` in `ToolCall` with `action: browser_tools.Action`.
This avoids repeated string-to-enum parsing and simplifies schema lookups.
Also updates `zenai` dependency to use its JSON duplication helper.
- Simplify prompt handling by relying on default markers.
- Enable brace insertion in the terminal.
- Optimize `lpEnvNames` by pre-allocating capacity.
- Clean up and trim verbose comments across `Terminal.zig`.
Replaces the linenoise library with isocline for improved REPL
functionality. Updates build scripts and moves completion state from
global variables into the Terminal struct.
Integrates the Tavily Search API as the primary search provider when
TAVILY_API_KEY is set. Falls back to scraping Google and DuckDuckGo
on failure or if the key is missing. Updates zenai dependency.
Depends on https://github.com/lightpanda-io/zig-v8-fork/pull/175
This started as an investigation into errors when loading recaptcha. Turns out
our atob/btoa is naive. Specifically, we take a `[]const u8` input which, via
the bridge, goes through the v8 utf8 path. This can result in the input being
fundamentally altered.
This commit introduces a new discriminatory type, js.String.OneByte which uses
the String::NewFromOneByte when going from js->zig and String:WriteOneByte when
going from zig->js, avoiding any changes to the raw data.
Also adds a placeholder MessageEvent.ports getter (which showed up in debugging)
Links to libidn2 and builds libcurl with it. This makes libcurl work, and by
extension browser, work on international domain names, e.g.
zig build run -- fetch "https://räksmörgås.se/"
With it available, we can use it in our WebAPIs which should also support these
domains, e.g:
testing.expectEqual('xn--rksmrgs-5wao1o.se', new URL('https://räksmörgås.se').hostname);
There is more integration to be done here, but this is a first step.
claude wrote all of the build.zig code.
I don't have a strong opinion about this feature, I just dislike that our WPT
/url/* tests are at 1704 / 9095 and, this is the biggest chunk (although, this
specific commit just does the basic integration and probably won't fix too many
WPT cases directly).
