The presence of `process.argv[1]` in the current invocation does not
imply that the current `pi` process is being invoked as a script.
Specifically, in the case of a bun compiled binary, `process.argv[1]`
will be the virtual path `/$bunfs/root/pi`, which is not a real file on
the filesystem. This causes the subagent extension to inject this path
into the child `pi` invocation, which is interpreted as part of the
prompt, which confuses the subagent.
This change uses the script only if it is not a bunfs virtual script
Co-authored-by: nathyong <nathyong@noreply.github.com>
* fix(coding-agent): surface models.json load errors on stderr in --list-models
When models.json has validation errors, --list-models silently
discarded custom models and overrides without any user-visible
feedback. Now prints the error to stderr via chalk.yellow warning
before listing available models.
* fix(coding-agent): allow custom models for built-in providers in models.json
Built-in providers (openrouter, anthropic, etc.) already have api and
baseUrl on every model, and auth comes from env vars / auth storage.
Relax validation so custom models under built-in providers don't need
redundant baseUrl, apiKey, or api fields. Inherit them from the first
built-in model for that provider.
fixes#2921
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
Previously, getLatestNpmVersion() hardcoded a fetch to
registry.npmjs.org, which 404s for packages on alternate
registries (private, Verdaccio, GitHub Packages, etc.).
The error was silently swallowed, so users never saw update
notifications for these packages.
Replace the direct fetch with
via the existing runCommandCapture helper. This uses the same
registry resolution as npm install (reads .npmrc config chain),
respects the npmCommand setting, and runs with this.cwd for
correct .npmrc lookup.
Messages sent during branch summarization are added to the compaction
queue but never flushed when summarization ends. The user sees the
message in the steering queue and has to manually dequeue and resend it.
The fix is to flush the compaction queue after successful tree
navigation, matching the existing behavior of auto-compaction and
`/compact`. If the user jumps to a user message, the queued message is
sent as a prompt, and the jumped-to text is placed in the editor.
The OpenRouterRouting interface only had only and order, but the runtime
passes the entire object as-is to the OpenRouter API's provider field.
This means all other fields worked at runtime but had no TypeScript
type-checking, no autocomplete, and no config validation.
This adds all fields from the OpenRouter provider selection API
(https://openrouter.ai/docs/guides/routing/provider-selection):
allow_fallbacks, require_parameters, data_collection, zdr,
enforce_distillable_text, ignore, quantizations, sort, max_price,
preferred_min_throughput, preferred_max_latency.
Also fixes the models.md documentation which had an invalid fallbacks
field in the example (not part of the OpenRouter API), replaces it with
a comprehensive example showing all available fields, and clarifies that
openRouterRouting is sent as-is in the provider field.
