feat: add Launch Args setting for Claude provider by akarabach · Pull Request #1971 · pingdotgg/t3code

akarabach · 2026-04-12T21:45:39Z

What changed

Added a generic Launch arguments text field to the Claude provider settings. Users can pass any CLI flags (e.g. --chrome, --effort high, --debug) that get forwarded to the Claude Code process on session start.

This addresses the original need (Chrome browser integration) while being generic enough to support any future CLI flag without further code changes.

Why

Claude Code supports many CLI flags (see claude --help), but T3 Code uses @anthropic-ai/claude-agent-sdk's query() function which never forwarded any of them. The SDK's extraArgs option (Record<string, string | null>) is the only way to pass additional flags.

Design decisions

Generic launchArgs string instead of enableChrome boolean — per review feedback from @juliusmarminge, a generic field is more future-proof than a Chrome-specific toggle.

Custom parser instead of node:util.parseArgs — Node's built-in parseArgs requires explicit type definitions for each flag to distinguish boolean flags from value-taking flags. Since we accept arbitrary user-provided flags, it can't determine that --chrome is boolean while --effort high takes a value. Our 15-line parseLaunchArgs uses the standard heuristic (if the next token doesn't start with --, it's a value) — same approach as minimist. We chose not to add an external dependency for this.

Changes (5 files)

packages/contracts/src/settings.ts — added launchArgs: string (default "") to ClaudeSettings schema and ClaudeSettingsPatch
apps/server/src/provider/Layers/ClaudeAdapter.ts — added parseLaunchArgs() that converts CLI-style input to the SDK's extraArgs format; wired into queryOptions
apps/web/src/components/settings/SettingsPanels.tsx — added Launch arguments text input in the Claude provider details panel
apps/server/src/provider/Layers/ClaudeAdapter.test.ts — 12 unit tests for parseLaunchArgs covering real Claude CLI flags (--chrome, --effort high, --model claude-sonnet-4-6, --max-budget-usd 5.00, etc.) and edge cases
apps/server/src/serverSettings.test.ts — updated assertions for new field

Screenshots

Settings panel with Launch arguments field

Tested

--chrome flag — confirmed Claude session launches with Chrome browser integration
--chrome --debug — multiple flags forwarded correctly
Clearing the field and starting a new session — no extra args passed
Unit tests pass for parseLaunchArgs (12 tests)

Test plan

Start T3 Code locally (bun run dev)
Open Settings → Claude provider → expand details
Verify "Launch arguments" input appears below the binary path field
Type --chrome → start a new Claude session → confirm Chrome/browser tools are available
Clear the field → start another session → confirm no Chrome tools
Fresh install (no existing settings) → confirm launchArgs defaults to empty string

Note

Medium Risk
Adds user-configurable CLI arguments that are forwarded into Claude session startup, which can change provider runtime behavior and could cause unexpected failures if malformed flags are entered.

Overview
Adds a new Claude provider setting, launchArgs, exposed in the web Settings UI and defaulted/patchable via the contracts schema.

On the server, Claude session startup now parses launchArgs into an extraArgs map and forwards it to the @anthropic-ai/claude-agent-sdk query options when creating a session.

Introduces a small shared parseCliArgs utility (with tests) and refactors scripts/update-release-package-versions.ts to use it; server settings tests are updated for the new default field.

^{Reviewed by Cursor Bugbot for commit 459c130. Bugbot is set up for automated code reviews on this repo. Configure here.}

Note

Add Launch Args setting for Claude provider

Adds a launchArgs string field to ClaudeSettings (defaulting to empty) and the patch schema in settings.ts, allowing users to pass extra CLI flags to the Claude agent on session start.
Adds a new parseCliArgs utility in packages/shared/src/cliArgs.ts that parses a string or argv array into { flags, positionals }, supporting --key value, --key=value, and boolean flag forms.
The Claude adapter in ClaudeAdapter.ts now parses launchArgs via parseCliArgs and forwards the resulting flags as extraArgs when building query options.
The settings UI in SettingsPanels.tsx exposes a "Launch arguments" input field for the Claude agent section.
Refactors parseArgs in update-release-package-versions.ts to use parseCliArgs, fixing --github-output incorrectly consuming the version positional.

^{Macroscope summarized 459c130.}

Claude Code supports a --chrome flag to launch with Chrome browser integration, but the SDK query path used by T3 Code never passed it. Add an `enableChrome` boolean to Claude provider settings (default off) and forward it via the SDK's `extraArgs` option when enabled.

coderabbitai · 2026-04-12T21:45:51Z

Important

Review skipped

Auto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Repository UI

Review profile: CHILL

Plan: Pro

Run ID: c8c34ab9-ae42-4140-b94b-6e70852e67c5

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

juliusmarminge · 2026-04-12T21:49:22Z

a setting for launchArgs or something feels more generic?

macroscopeapp · 2026-04-12T22:06:32Z

Approvability

Verdict: Needs human review

This PR introduces a new user-facing feature (Launch Args setting for Claude) that propagates user input to CLI invocations. An unresolved review comment identifies a parsing bug with quoted multi-word values, and another reviewer questions potential code duplication with an existing CLI parser.

^{You can customize Macroscope's approvability policy. Learn more.}

- fix test - add tests for parser

Dismissing prior approval to re-evaluate cfefd47

apps/server/src/provider/Layers/ClaudeAdapter.ts

juliusmarminge · 2026-04-12T22:56:07Z

apps/server/src/provider/Layers/ClaudeAdapter.ts

+ *   "--chrome --debug"        → { chrome: null, debug: null }
+ *   "--chrome --max-turns 5"  → { chrome: null, "max-turns": "5" }
+ */
+export function parseLaunchArgs(args: string): Record<string, string | null> {


Pretty sure we already have one of these for git?

scripts/update-release-package-versions.ts

cursor

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 459c130. Configure here.}

cursor · 2026-04-13T09:46:38Z

packages/shared/src/cliArgs.ts

+ */
+export function parseCliArgs(args: string | readonly string[], options?: ParseCliArgsOptions): ParsedCliArgs {
+  const tokens =
+    typeof args === "string" ? args.trim().split(/\s+/).filter(Boolean) : Array.from(args);


Whitespace splitting silently misparses quoted multi-word values

Medium Severity

The string input path in parseCliArgs uses args.trim().split(/\s+/) without any quote handling. When a user enters something like --append-system-prompt "think step by step" in the Launch arguments field, the tokenizer splits on every space, producing ["--append-system-prompt", '"think', "step", "by", 'step"']. The flag captures only "think (with a literal quote char) as its value, while the remaining words become positionals. Since the Claude adapter only uses .flags and silently discards .positionals, the user gets a corrupted, truncated flag value with no error or warning. Claude CLI flags like --append-system-prompt naturally accept multi-word values, making this a realistic user scenario.

Additional Locations (1)

apps/server/src/provider/Layers/ClaudeAdapter.ts#L2683-L2684

^{Reviewed by Cursor Bugbot for commit 459c130. Configure here.}

github-actions bot added size:M 30-99 changed lines (additions + deletions). vouch:unvouched PR author is not yet trusted in the VOUCHED list. labels Apr 12, 2026

macroscopeapp bot previously approved these changes Apr 12, 2026

View reviewed changes

akarabach added 2 commits April 13, 2026 01:27

feat: launch args instead of specific chrome flag

9873c01

- fix test - add tests for parser

feat: use normal string with spaces

cfefd47

akarabach changed the title ~~feat: add Enable Chrome setting for Claude provider~~ feat: add Launch Args setting for Claude provider Apr 12, 2026

cursor bot reviewed Apr 12, 2026

View reviewed changes

apps/server/src/provider/Layers/ClaudeAdapter.ts Outdated Show resolved Hide resolved

feat: fix parse args twice

1730291

cursor bot reviewed Apr 12, 2026

View reviewed changes

apps/server/src/provider/Layers/ClaudeAdapter.ts Outdated Show resolved Hide resolved

juliusmarminge reviewed Apr 13, 2026

View reviewed changes

feat: common parser of cli args, unit tests

5533364

github-actions bot added size:L 100-499 changed lines (additions + deletions). and removed size:M 30-99 changed lines (additions + deletions). labels Apr 13, 2026

cursor bot reviewed Apr 13, 2026

View reviewed changes

scripts/update-release-package-versions.ts Outdated Show resolved Hide resolved

feat: fixes cursor comment add boolean flags parameter

459c130

cursor bot reviewed Apr 13, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: add Launch Args setting for Claude provider#1971

feat: add Launch Args setting for Claude provider#1971
akarabach wants to merge 6 commits intopingdotgg:mainfrom
akarabach:feat/claude-chrome-integration

akarabach commented Apr 12, 2026 •

edited by macroscopeapp bot

Loading

Uh oh!

coderabbitai bot commented Apr 12, 2026 •

edited

Loading

Review skipped

Uh oh!

juliusmarminge commented Apr 12, 2026

Uh oh!

macroscopeapp bot commented Apr 12, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

juliusmarminge Apr 12, 2026

Uh oh!

Uh oh!

cursor bot left a comment

Uh oh!

cursor bot Apr 13, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

akarabach commented Apr 12, 2026 • edited by macroscopeapp bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What changed

Why

Design decisions

Changes (5 files)

Screenshots

Settings panel with Launch arguments field

Tested

Test plan

Add Launch Args setting for Claude provider

Uh oh!

coderabbitai bot commented Apr 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Uh oh!

juliusmarminge commented Apr 12, 2026

Uh oh!

macroscopeapp bot commented Apr 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Approvability

Uh oh!

Uh oh!

Uh oh!

juliusmarminge Apr 12, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

cursor bot left a comment

Choose a reason for hiding this comment

Uh oh!

cursor bot Apr 13, 2026

Choose a reason for hiding this comment

Whitespace splitting silently misparses quoted multi-word values

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

akarabach commented Apr 12, 2026 •

edited by macroscopeapp bot

Loading

coderabbitai bot commented Apr 12, 2026 •

edited

Loading

macroscopeapp bot commented Apr 12, 2026 •

edited

Loading