scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-08-28 05:27:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #2 from RooCodeInc/main

Browse source 
20/11/25
This commit is contained in:
Iskandar Sulaili 2025-11-20 10:44:36 +08:00 • committed by GitHub
commit 2270e42746
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
263 changed files with 13210 additions and 6999 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
.roo/commands/release.md
View file

@ -16,14 +16,14 @@ argument-hint: patch | minor | major
[list of changes]
```
- Always include contributor attribution using format: (thanks @username!)
- For PRs that close issues, also include the issue number and reporter: "- Fix: Description (#123 by @reporter, PR by @contributor)"
- For PRs without linked issues, use the standard format: "- Add support for feature (thanks @contributor!)"
- Always include contributor attribution and the PR number: use "(PR #<prNumber> by @username)".
- For PRs that close issues, include both the issue number and the PR number and authors: "- Fix: Description (#123 by @reporter, PR #456 by @contributor)"
- For PRs without linked issues, include the PR number and author: "- Add support for feature (PR #456 by @contributor)"
- Provide brief descriptions of each item to explain the change
- Order the list from most important to least important
- Example formats:
- With issue: "- Fix: Resolve memory leak in extension (#456 by @issueReporter, PR by @prAuthor)"
- Without issue: "- Add support for Gemini 2.5 Pro caching (thanks @contributor!)"
- With issue: "- Fix: Resolve memory leak in extension (#456 by @issueReporter, PR #789 by @prAuthor)"
- Without issue: "- Add support for Gemini 2.5 Pro caching (PR #789 by @contributor)"
- CRITICAL: Include EVERY SINGLE PR in the changeset - don't assume you know which ones are important. Count the total PRs to verify completeness and cross-reference the list to ensure nothing is missed.
6. If the generate_image tool is available, create a release image at `releases/[version]-release.png`

74
CHANGELOG.md
View file

@ -1,5 +1,79 @@
# Roo Code Changelog
## [3.33.1] - 2025-11-18
![3.33.1 Release - Native Tool Protocol Fixes](/releases/3.33.1-release.png)
- Add native tool calling support to OpenAI-compatible (PR #9369 by @mrubens)
- Fix: Resolve native tool protocol race condition causing 400 errors (PR #9363 by @daniel-lxs)
- Fix: Update tools to return structured JSON for native protocol (PR #9373 by @daniel-lxs)
- Fix: Include nativeArgs in tool repetition detection (PR #9377 by @daniel-lxs)
- Fix: Ensure no XML parsing when protocol is native (PR #9371 by @daniel-lxs)
- Fix: Gemini maxOutputTokens and reasoning config (PR #9375 by @hannesrudolph)
- Fix: Gemini thought signature validation and token counting errors (PR #9380 by @hannesrudolph)
- Fix: Exclude XML tool examples from MODES section when native protocol enabled (PR #9367 by @daniel-lxs)
- Retry eval tasks if API instability detected (PR #9365 by @cte)
- Add toolProtocol property to PostHog tool usage telemetry (PR #9374 by @app/roomote)
## [3.33.0] - 2025-11-18
![v3.33.0 Release - Twin Kangaroos and the Gemini Constellation](/releases/v3.33.0-release.png)
- Add Gemini 3 Pro Preview model (PR #9357 by @hannesrudolph)
- Improve Google Gemini defaults with better temperature and cost reporting (PR #9327 by @hannesrudolph)
- Enable native tool calling for openai-native provider (PR #9348 by @hannesrudolph)
- Add git status information to environment details (PR #9310 by @daniel-lxs)
- Add tool protocol selector to advanced settings (PR #9324 by @daniel-lxs)
- Implement dynamic tool protocol resolution with proper precedence hierarchy (PR #9286 by @daniel-lxs)
- Move Import/Export functionality to Modes view toolbar and cleanup Mode Edit view (PR #9077 by @hannesrudolph)
- Update cloud agent CTA to point to setup page (PR #9338 by @app/roomote)
- Fix: Prevent duplicate tool_result blocks in native tool protocol (PR #9248 by @daniel-lxs)
- Fix: Format tool responses properly for native protocol (PR #9270 by @daniel-lxs)
- Fix: Centralize toolProtocol configuration checks (PR #9279 by @daniel-lxs)
- Fix: Preserve tool blocks for native protocol in conversation history (PR #9319 by @daniel-lxs)
- Fix: Prevent infinite loop when task_done succeeds (PR #9325 by @daniel-lxs)
- Fix: Sync parser state with profile/model changes (PR #9355 by @daniel-lxs)
- Fix: Pass tool protocol parameter to lineCountTruncationError (PR #9358 by @daniel-lxs)
- Use VSCode theme color for outline button borders (PR #9336 by @app/roomote)
- Replace broken badgen.net badges with shields.io (PR #9318 by @app/roomote)
- Add max git status files setting to evals (PR #9322 by @mrubens)
- Roo Code Cloud Provider pricing page and changes elsewhere (PR #9195 by @brunobergher)
## [3.32.1] - 2025-11-14
![3.32.1 Release - Bug Fixes](/releases/3.32.1-release.png)
- Fix: Add abort controller for request cancellation in OpenAI native protocol (PR #9276 by @daniel-lxs)
- Fix: Resolve duplicate tool blocks causing 'tool has already been used' error in native protocol mode (PR #9275 by @daniel-lxs)
- Fix: Prevent duplicate tool_result blocks in native protocol mode for read_file (PR #9272 by @daniel-lxs)
- Fix: Correct OpenAI Native handling of encrypted reasoning blocks to prevent errors during condensing (PR #9263 by @hannesrudolph)
- Fix: Disable XML parser for native tool protocol to prevent parsing conflicts (PR #9277 by @daniel-lxs)
## [3.32.0] - 2025-11-14
![3.32.0 Release - GPT-5.1 models and OpenAI prompt caching](/releases/3.32.0-release.png)
- Feature: Add GPT-5.1 models to OpenAI provider (PR #9252 by @hannesrudolph)
- Feature: Support for OpenAI Responses 24 hour prompt caching (PR #9259 by @hannesrudolph)
- Fix: Repair the share button in the UI (PR #9253 by @hannesrudolph)
- Docs: Include PR numbers in the release guide to improve traceability (PR #9236 by @hannesrudolph)
## [3.31.3] - 2025-11-13
![3.31.3 Release - Kangaroo Decrypting a Message](/releases/3.31.3-release.png)
- Fix: OpenAI Native encrypted_content handling and remove gpt-5-chat-latest verbosity flag (#9225 by @politsin, PR by @hannesrudolph)
- Fix: Roo Code Cloud provider Anthropic input token normalization to avoid double-counting (thanks @hannesrudolph!)
- Refactor: Rename sliding-window to context-management and truncateConversationIfNeeded to manageContext (thanks @hannesrudolph!)
## [3.31.2] - 2025-11-12
- Fix: Apply updated API profile settings when provider/model unchanged (#9208 by @hannesrudolph, PR by @hannesrudolph)
- Migrate conversation continuity to plugin-side encrypted reasoning items using Responses API for improved reliability (thanks @hannesrudolph!)
- Fix: Include mcpServers in getState() for auto-approval (#9190 by @bozoweed, PR by @daniel-lxs)
- Batch settings updates from the webview to the extension host for improved performance (thanks @cte!)
- Fix: Replace rate-limited badges with badgen.net to improve README reliability (thanks @daniel-lxs!)
## [3.31.1] - 2025-11-11
![3.31.1 Release - Kangaroo Stuck in the Clouds](/releases/3.31.1-release.png)

16
README.md
View file

@ -1,7 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://badgen.net/vs-marketplace/v/RooVeterinaryInc.roo-cline?label=VS%20Code&color=007ACC" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://badgen.net/vs-marketplace/i/RooVeterinaryInc.roo-cline?label=Installs&color=007ACC" alt="Installs"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://badgen.net/vs-marketplace/rating/RooVeterinaryInc.roo-cline?label=Rating&color=007ACC" alt="Rating"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -37,7 +35,7 @@
- [简体中文](locales/zh-CN/README.md)
- [繁體中文](locales/zh-TW/README.md)
- ...
</details>
</details>
---
@ -169,16 +167,6 @@ We love community contributions! Get started by reading our [CONTRIBUTING.md](CO
---
## Contributors
Thanks to all our contributors who have helped make Roo Code better!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## License
[Apache 2.0 © 2025 Roo Code, Inc.](./LICENSE)

1
apps/web-roo-code/.env.example
View file

@ -1,7 +1,6 @@
# PostHog Analytics Configuration
# Replace these values with your actual PostHog API key and host
NEXT_PUBLIC_POSTHOG_KEY=your_posthog_api_key_here
NEXT_PUBLIC_POSTHOG_HOST=https://us.i.posthog.com
# Basin Form Endpoint for Static Form Submissions
# Replace this with your actual Basin form endpoint (e.g., https://usebasin.com/f/your-form-id)

120
apps/web-roo-code/src/app/pricing/page.tsx
View file

@ -1,4 +1,4 @@
import { Users, Building2, ArrowRight, Star, LucideIcon, Check, Cloud } from "lucide-react"
import { Users, Building2, ArrowRight, Star, LucideIcon, Check, Cloud, PlugZap } from "lucide-react"
import type { Metadata } from "next"
import Link from "next/link"
@ -64,7 +64,6 @@ interface PricingTier {
period?: string
creditPrice?: string
trial?: string
cancellation?: string
description: string
featuresIntro?: string
features: string[]
@ -80,13 +79,12 @@ const pricingTiers: PricingTier[] = [
name: "Cloud Free",
icon: Cloud,
price: "$0",
cancellation: "Cancel anytime",
description: "For folks just getting started",
features: [
"Token usage analytics",
"Access to the Roo Code Cloud Provider, including early access to free stealth models",
"Follow your tasks from anywhere",
"Share tasks with friends and co-workers",
"Early access to free AI Models",
"Community support",
],
cta: {
@ -95,18 +93,18 @@ const pricingTiers: PricingTier[] = [
},
},
{
name: "Pro",
name: "Cloud Pro",
icon: Star,
price: "$20",
period: "/mo",
trial: "Free 14-day trial · ",
trial: "Free for 14 days, then",
creditPrice: `$${PRICE_CREDITS}`,
cancellation: "Cancel anytime",
description: "For pro Roo coders",
featuresIntro: "Everything in Free +",
features: [
"Cloud Agents: PR Reviewer and more",
"Roomote Control: Start, stop and control tasks from anywhere",
"Cloud Agents: Coder, Explainer, Planner, Reviewer, Fixer and more",
"Start tasks from Slack",
"Roomote Control: Start, stop and control extension tasks from anywhere",
"Paid support",
],
cta: {
@ -115,13 +113,12 @@ const pricingTiers: PricingTier[] = [
},
},
{
name: "Team",
name: "Cloud Team",
icon: Users,
price: "$99",
period: "/mo",
creditPrice: `$${PRICE_CREDITS}`,
trial: "Free 14-day trial · ",
cancellation: "Cancel anytime",
trial: "Free for 14 days, then",
description: "For AI-forward teams",
featuresIntro: "Everything in Pro +",
features: ["Unlimited users (no per-seat cost)", "Shared configuration & policies", "Centralized billing"],
@ -151,12 +148,30 @@ export default function PricingPage() {
</div>
</section>
{/* Free Extension Notice */}
<div className="mx-auto max-w-6xl">
<div className="rounded-xl p-4 mb-8 text-center bg-gradient-to-r from-blue-500/10 via-cyan-500/10 to-purple-500/10 border border-blue-500/20 dark:border-white/20">
<div className="mx-6 md:mx-auto max-w-6xl">
<div className="rounded-xl p-4 mb-8 text-center bg-gradient-to-r from-blue-500/10 via-cyan-500/10 to-purple-500/10 border border-blue-500/20 dark:border-white/20 ">
<p className="text-center">
<strong className="font-semibold">The Roo Code extension is free! </strong>
Roo Code Cloud is an optional service which takes it to the next level.
<strong className="font-semibold">The Roo Code extension is totally free! </strong>
But Cloud takes you so much further.
</p>
</div>
</div>
<div className="mx-6 md:mx-auto max-w-6xl p-7 mb-4 relative flex flex-col justify-start bg-background border rounded-2xl transition-all shadow-none hover:shadow-lg">
<h3 className="text-xl font-semibold flex items-center gap-2 justify-between">
Roo Code Provider
<PlugZap className="size-6" />
</h3>
<div className="text-sm text-muted-foreground space-y-1 mt-2">
<p className="">
On any plan, you can bring your own provider key or use the built-in Roo Code Cloud provider.
</p>
<p className="text-sm text-muted-foreground">
We offer a select mix of tested state of the art closed and open weight LLMs for you to choose,
with no markup.
<Link href="/provider/pricing" className="underline hover:no-underline ml-1">
See detailed pricing
</Link>
</p>
</div>
</div>
@ -183,7 +198,7 @@ export default function PricingPage() {
<p className="text-sm text-muted-foreground font-light mb-2">
{tier.featuresIntro}&nbsp;
</p>
<ul className="space-y-3 my-0 h-[148px]">
<ul className="space-y-3 my-0 h-[168px]">
{tier.features.map((feature) => (
<li key={feature} className="flex items-start gap-2">
<Check className="mt-0.5 h-4 w-4 text-muted-foreground shrink-0" />
@ -193,20 +208,28 @@ export default function PricingPage() {
</ul>
</div>
<p className="text-2xl mt-0 mb-1 tracking-tight">
<strong>{tier.price}</strong>
{tier.period}
<p className="text-base font-light">{tier.trial}</p>
<p className="text-xl my-1 tracking-tight font-light">
<strong className="font-bold">{tier.price}</strong>
{tier.period} + prepaid credits
</p>
{tier.creditPrice && (
<p className="text-sm text-muted-foreground mb-1">
+ {tier.creditPrice}/hour for Cloud tasks
</p>
)}
<p className="text-xs text-muted-foreground mb-4">
{tier.trial}
{tier.cancellation}
<p className="text-sm text-muted-foreground mb-3">
{tier.creditPrice && (
<>
Cloud Agents: {tier.creditPrice}/hour if used
<br />
</>
)}
Inference:{" "}
<Link href="/provider/pricing" className="underline hover:no-underline">
Roo Provider pricing
</Link>{" "}
or{" "}
<abbr title="Bring Your Own Key" className="cursor-help">
BYOK
</abbr>
</p>
{tier.cta.isContactForm ? (
@ -249,7 +272,7 @@ export default function PricingPage() {
<h2 className="text-3xl font-bold tracking-tight sm:text-4xl">Frequently Asked Questions</h2>
</div>
<div className="mx-auto mt-12 grid max-w-5xl gap-8 md:grid-cols-2">
<div className="rounded-lg border border-border bg-card p-6">
<div className="rounded-xl border border-border bg-card p-6">
<h3 className="font-semibold">Wait, is Roo Code free or not?</h3>
<p className="mt-2 text-sm text-muted-foreground">
Yes! The Roo Code VS Code extension is open source and free forever. The extension acts
@ -257,7 +280,7 @@ export default function PricingPage() {
Code Cloud.
</p>
</div>
<div className="rounded-lg border border-border bg-card p-6">
<div className="rounded-xl border border-border bg-card p-6">
<h3 className="font-semibold">Is there a free trial?</h3>
<p className="mt-2 text-sm text-muted-foreground">
Yes, all paid plans come with a 14-day free trial to try out functionality.
@ -266,12 +289,25 @@ export default function PricingPage() {
To use Cloud Agents, you can buy credits.
</p>
</div>
<div className="rounded-lg border border-border bg-card p-6">
<h3 className="font-semibold">How do Cloud Agent credits work?</h3>
<div className="rounded-xl border border-border bg-card p-6">
<h3 className="font-semibold">How do credits work?</h3>
<p className="mt-2 text-sm text-muted-foreground">
Cloud Agents are a version of Roo running in the cloud without depending on your IDE.
You can run as many as you want, and bring your own inference provider key.
Roo Code Cloud credits can be used in two ways:
</p>
<ul className="mt-2 list-disc pl-5 text-sm text-muted-foreground">
<li>To pay for Cloud Agents running time (${PRICE_CREDITS}/hour)</li>
<li>
To pay for AI model inference costs (
<a
href="https://app.roocode.com/provider/pricing"
target="_blank"
rel="noopener noreferrer"
className="underline">
varies by model
</a>
)
</li>
</ul>
<p className="mt-2 text-sm text-muted-foreground">
To cover our infrastructure costs, we charge ${PRICE_CREDITS}/hour while the agent is
running (independent of inference costs).
@ -280,25 +316,25 @@ export default function PricingPage() {
There are no markups, no tiers, no dumbing-down of models to increase our profit.
</p>
</div>
<div className="rounded-lg border border-border bg-card p-6">
<div className="rounded-xl border border-border bg-card p-6">
<h3 className="font-semibold">Do I need a credit card for the free trial?</h3>
<p className="mt-2 text-sm text-muted-foreground">
Yes, but you won&apos;t be charged until your trial ends, except for credit purchases.
</p>
<p className="mt-2 text-sm text-muted-foreground">You can cancel anytime with one click.</p>
</div>
<div className="rounded-lg border border-border bg-card p-6">
<div className="rounded-xl border border-border bg-card p-6">
<h3 className="font-semibold">What payment methods do you accept?</h3>
<p className="mt-2 text-sm text-muted-foreground">
We accept all major credit cards, debit cards, and can arrange invoice billing for
Enterprise customers.
</p>
</div>
<div className="rounded-lg border border-border bg-card p-6">
<h3 className="font-semibold">Can I change plans anytime?</h3>
<div className="rounded-xl border border-border bg-card p-6">
<h3 className="font-semibold">Can I cancel or change plans?</h3>
<p className="mt-2 text-sm text-muted-foreground">
Yes, you can upgrade or downgrade your plan at any time. Changes will be reflected in
your next billing cycle.
Yes, you can upgrade, downgrade or cancel your plan at any time. Changes will be
reflected in your next billing cycle.
</p>
</div>
</div>

190
apps/web-roo-code/src/app/provider/pricing/components/model-card.tsx Normal file
View file

@ -0,0 +1,190 @@
import { ModelWithTotalPrice } from "@/lib/types/models"
import { formatCurrency, formatTokens } from "@/lib/formatters"
import {
ArrowLeftToLine,
ArrowRightToLine,
Building2,
Check,
Expand,
Gift,
HardDriveDownload,
HardDriveUpload,
RulerDimensionLine,
ChevronDown,
ChevronUp,
} from "lucide-react"
import { useState } from "react"
interface ModelCardProps {
model: ModelWithTotalPrice
}
export function ModelCard({ model }: ModelCardProps) {
// Prices are per token, multiply by 1M to get price per million tokens
const inputPrice = parseFloat(model.pricing.input) * 1_000_000
const outputPrice = parseFloat(model.pricing.output) * 1_000_000
const cacheReadPrice = parseFloat(model.pricing.input_cache_read || "0") * 1_000_000
const cacheWritePrice = parseFloat(model.pricing.input_cache_write || "0") * 1_000_000
const free = model.tags.includes("free")
// Filter tags to only show vision and reasoning
const displayTags = model.tags.filter((tag) => tag === "vision" || tag === "reasoning")
// Mobile collapsed/expanded state
const [expanded, setExpanded] = useState(false)
return (
<div
className={[
"relative cursor-default px-8 pt-7 pb-5 flex flex-col justify-start bg-background border rounded-3xl transition-all hover:shadow-xl",
// On mobile, visually hint at expandability
"sm:cursor-default",
].join(" ")}>
{/* Header: always visible */}
<div className="mb-4">
<h3 className="text-xl font-semibold tracking-tight mb-2 flex items-center gap-2 justify-between">
{model.name}
{free && (
<span className="inline-flex items-center text-sm font-medium text-green-500">
<Gift className="size-4 mr-1" />
Free!
</span>
)}
</h3>
<p
className={[
"text-sm text-muted-foreground",
// On mobile + collapsed: clamp description
"sm:line-clamp-none",
!expanded ? "line-clamp-2" : "",
]
.join(" ")
.trim()}>
{model.description}
</p>
</div>
{/* Content - pinned to bottom */}
<div className="overflow-x-auto mt-auto">
<table className="w-full text-xs">
<tbody>
{/* Provider: always visible if present */}
{model.owned_by && (
<tr className="border-b border-border">
<td className="py-1.5 font-medium text-muted-foreground">
<Building2 className="size-4 inline-block mr-1.5" />
Provider
</td>
<td className="py-1.5 text-right">{model.owned_by}</td>
</tr>
)}
{/* Context Window: always visible */}
<tr className="border-b border-border">
<td className="py-1.5 font-medium text-muted-foreground">
<RulerDimensionLine className="size-4 inline-block mr-1.5" />
Context Window
</td>
<td className="py-1.5 text-right font-mono">{formatTokens(model.context_window)}</td>
</tr>
{/* Max Output Tokens: always visible on >=sm, expandable on mobile */}
<tr
className={["border-b border-border", expanded ? "table-row" : "hidden sm:table-row"].join(
" ",
)}>
<td className="py-1.5 font-medium text-muted-foreground">
<Expand className="size-4 inline-block mr-1.5" />
Max Output Tokens
</td>
<td className="py-1.5 text-right font-mono">{formatTokens(model.max_tokens)}</td>
</tr>
{/* Input Price: always visible */}
<tr className="border-b border-border">
<td className="py-1.5 font-medium text-muted-foreground">
<ArrowRightToLine className="size-4 inline-block mr-1.5" />
Input Price
</td>
<td className="py-1.5 text-right">
{inputPrice === 0 ? "Free" : `${formatCurrency(inputPrice)}/1M tokens`}
</td>
</tr>
{/* Output Price: always visible */}
<tr
className={[
"border-b border-border",
// Add subtle separation from toggle on mobile
].join(" ")}>
<td className="py-1.5 font-medium text-muted-foreground">
<ArrowLeftToLine className="size-4 inline-block mr-1.5" />
Output Price
</td>
<td className="py-1.5 text-right">
{outputPrice === 0 ? "Free" : `${formatCurrency(outputPrice)}/1M tokens`}
</td>
</tr>
{/* Cache pricing: only visible on mobile when expanded, always visible on >=sm */}
{cacheReadPrice > 0 && (
<tr
className={[
"border-b border-border",
expanded ? "table-row" : "hidden sm:table-row",
].join(" ")}>
<td className="py-1.5 font-medium text-muted-foreground">
<HardDriveUpload className="size-4 inline-block mr-1.5" />
Cache Read
</td>
<td className="py-1.5 text-right">{formatCurrency(cacheReadPrice)}/1M tokens</td>
</tr>
)}
{cacheWritePrice > 0 && (
<tr
className={[
"border-b border-border",
expanded ? "table-row" : "hidden sm:table-row",
].join(" ")}>
<td className="py-1.5 font-medium text-muted-foreground">
<HardDriveDownload className="size-4 inline-block mr-1.5" />
Cache Write
</td>
<td className="py-1.5 text-right">{formatCurrency(cacheWritePrice)}/1M tokens</td>
</tr>
)}
{/* Tags row: only show if there are vision or reasoning tags */}
{displayTags.length > 0 && (
<tr className={[expanded ? "table-row" : "hidden sm:table-row"].join(" ")}>
<td className="py-1.5 font-medium text-muted-foreground align-top">Features</td>
<td className="py-1.5">
{displayTags.map((tag) => (
<span key={tag} className="flex justify-end items-center text-xs capitalize">
<Check className="size-3 m-1" />
{tag}
</span>
))}
</td>
</tr>
)}
{/* Mobile-only toggle row */}
<tr className="sm:hidden">
<td colSpan={2} className="pt-3">
<button
type="button"
onClick={() => setExpanded((v) => !v)}
className="w-full inline-flex items-center justify-center gap-1.5 text-xs font-medium text-primary">
{expanded ? "Less" : "More"}
{expanded ? <ChevronUp className="size-3" /> : <ChevronDown className="size-3" />}
</button>
</td>
</tr>
</tbody>
</table>
</div>
</div>
)
}

253
apps/web-roo-code/src/app/provider/pricing/page.tsx Normal file
View file

@ -0,0 +1,253 @@
"use client"
import { useEffect, useMemo, useState } from "react"
import { ModelCard } from "./components/model-card"
import { Model, ModelWithTotalPrice, ModelsResponse, SortOption } from "@/lib/types/models"
import Link from "next/link"
import { ChevronDown, CircleX, Loader, LoaderCircle, Search } from "lucide-react"
const API_URL = "https://api.roocode.com/proxy/v1/models?include_paid=true"
const faqs = [
{
question: "What are AI model providers?",
answer: "AI model providers offer various language models with different capabilities and pricing.",
},
{
question: "How is pricing calculated?",
answer: "Pricing is based on token usage for input and output, measured per million tokens, like pretty much any other provider out there.",
},
{
question: "What is the Roo Code Cloud Provider?",
answer: (
<>
<p>This is our very own model provider, optimized to work seamlessly with Roo Code Cloud.</p>
<p>
It offers a selection of state-of-the-art LLMs (both closed and open weight) we know work well with
Roo for you to choose, with no markup.
</p>
<p>
We also often feature 100% free models which labs share with us for the community to use and provide
feedback.
</p>
</>
),
},
{
question: "But how much does the Roo Code Cloud service cost?",
answer: (
<>
Our{" "}
<Link href="/pricing" className="underline hover:no-underline">
service pricing is here.
</Link>
</>
),
},
]
function calculateTotalPrice(model: Model): number {
return parseFloat(model.pricing.input) + parseFloat(model.pricing.output)
}
function enrichModelWithTotalPrice(model: Model): ModelWithTotalPrice {
return {
...model,
totalPrice: calculateTotalPrice(model),
}
}
export default function ProviderPricingPage() {
const [models, setModels] = useState<ModelWithTotalPrice[]>([])
const [loading, setLoading] = useState(true)
const [error, setError] = useState<string | null>(null)
const [searchQuery, setSearchQuery] = useState("")
const [sortOption, setSortOption] = useState<SortOption>("alphabetical")
useEffect(() => {
async function fetchModels() {
try {
setLoading(true)
setError(null)
const response = await fetch(API_URL)
if (!response.ok) {
throw new Error(`Failed to fetch models: ${response.statusText}`)
}
const data: ModelsResponse = await response.json()
const enrichedModels = data.data.map(enrichModelWithTotalPrice)
setModels(enrichedModels)
} catch (err) {
setError(err instanceof Error ? err.message : "An error occurred while fetching models")
} finally {
setLoading(false)
}
}
fetchModels()
}, [])
const filteredAndSortedModels = useMemo(() => {
// Filter out deprecated models
let filtered = models.filter((model) => !model.deprecated)
// Filter by search query
if (searchQuery.trim()) {
const query = searchQuery.toLowerCase()
filtered = filtered.filter((model) => {
return (
model.name.toLowerCase().includes(query) ||
model.owned_by?.toLowerCase().includes(query) ||
model.description.toLowerCase().includes(query)
)
})
}
// Sort filtered results
const sorted = [...filtered]
switch (sortOption) {
case "alphabetical":
sorted.sort((a, b) => a.name.localeCompare(b.name))
break
case "price-asc":
sorted.sort((a, b) => a.totalPrice - b.totalPrice)
break
case "price-desc":
sorted.sort((a, b) => b.totalPrice - a.totalPrice)
break
case "context-window-asc":
sorted.sort((a, b) => a.context_window - b.context_window)
break
case "context-window-desc":
sorted.sort((a, b) => b.context_window - a.context_window)
break
}
return sorted
}, [models, searchQuery, sortOption])
// Count non-deprecated models for the display
const nonDeprecatedCount = useMemo(() => models.filter((model) => !model.deprecated).length, [models])
return (
<>
<section className="relative overflow-hidden py-16">
<div className="container relative z-10 mx-auto px-4 sm:px-6 lg:px-8">
<div className="text-center">
<h1 className="text-4xl md:text-5xl font-bold tracking-tight">
Roo Code Cloud Provider Pricing
</h1>
<p className="mx-auto mt-4 max-w-2xl md:text-lg text-muted-foreground">
See pricing and features for all models we offer in our selection.
<br />
You can always bring your own key (
<Link href="#faq" className="underline hover:no-underline">
FAQ
</Link>
).
</p>
</div>
</div>
</section>
<section className="py-10 relative border-t border-b">
<div className="absolute inset-0 bg-gradient-to-br from-violet-500/0 via-violet-500/10 to-violet-500/0 dark:from-blue-500/10 dark:via-cyan-500/10 dark:to-purple-500/10" />
<div className="container mx-auto px-4 sm:px-6 lg:px-8">
<div className="mx-auto max-w-4xl">
<div className="flex flex-col gap-4 sm:flex-row sm:items-center sm:justify-between">
<div className="flex-1">
<div className="relative">
<Search className="absolute left-3 top-1/2 h-4 w-4 -translate-y-1/2 text-muted-foreground" />
<input
type="text"
placeholder="Search models..."
value={searchQuery}
onChange={(e) => setSearchQuery(e.target.value)}
className="w-full rounded-full border border-input bg-background px-10 py-2 text-base ring-offset-background placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2"
/>
<div className="text-sm cursor-default text-muted-foreground absolute bg-background right-0 top-0 m-0.5 px-3 py-2 rounded-full">
{filteredAndSortedModels.length} of {nonDeprecatedCount} models
</div>
</div>
</div>
<div className="flex-shrink-0">
<div className="flex items-center gap-2 relative">
<select
id="sort"
value={sortOption}
onChange={(e) => setSortOption(e.target.value as SortOption)}
className="rounded-full cursor-pointer border border-input bg-background hover:bg-muted pl-4 w-full md:w-auto pr-9 py-2.5 text-base ring-offset-background focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 relative appearance-none">
<option value="alphabetical">Alphabetical</option>
<option value="price-asc">Price: Low to High</option>
<option value="price-desc">Price: High to Low</option>
<option value="context-window-asc">Context Window: Small to Large</option>
<option value="context-window-desc">Context Window: Large to Small</option>
</select>
<ChevronDown className="size-4 absolute right-3" />
</div>
</div>
</div>
</div>
</div>
<div className="container mx-auto px-4 sm:px-6 lg:px-8 ">
<div className="mx-auto max-w-6xl">
{loading && (
<div className="text-center pt-12 space-y-2 mb-4">
<LoaderCircle className="size-8 text-muted-foreground mx-auto animate-spin" />
<p className="text-lg">Loading model list...</p>
</div>
)}
{error && (
<div className="text-center pt-12 space-y-2">
<CircleX className="size-8 text-muted-foreground mx-auto mb-4" />
<p className="text-lg">Oops, couldn&apos;t load the model list.</p>
<p className="text-muted-foreground">Try again in a bit please.</p>
</div>
)}
{!loading && !error && filteredAndSortedModels.length === 0 && (
<div className="text-center pt-12 space-y-2">
<Loader className="size-8 text-muted-foreground mx-auto mb-4" />
<p className="text-lg">No models match your search.</p>
<p className="text-muted-foreground">
Keep in mind we don&apos;t have every model under the sun – only the ones we think
are worth using.
<br />
You can always use a third-party provider to access a wider selection.
</p>
</div>
)}
{!loading && !error && filteredAndSortedModels.length > 0 && (
<div className="grid gap-4 pt-8 md:grid-cols-2 lg:grid-cols-3">
{filteredAndSortedModels.map((model) => (
<ModelCard key={model.id} model={model} />
))}
</div>
)}
</div>
</div>
</section>
{/* FAQ Section */}
<section className="bg-background my-16 relative z-50">
<a id="faq" />
<div className="container mx-auto px-4 sm:px-6 lg:px-8">
<div className="mx-auto max-w-3xl text-center">
<h2 className="text-3xl font-bold tracking-tight sm:text-4xl">Frequently Asked Questions</h2>
</div>
<div className="mx-auto mt-12 grid max-w-5xl gap-8 md:grid-cols-2">
{faqs.map((faq, index) => (
<div key={index} className="rounded-lg border border-border bg-card p-6">
<h3 className="font-semibold">{faq.question}</h3>
<p className="mt-2 text-sm text-muted-foreground">{faq.answer}</p>
</div>
))}
</div>
</div>
</section>
</>
)
}

11
apps/web-roo-code/src/components/providers/posthog-provider.tsx
View file

@ -32,7 +32,6 @@ export function PostHogProvider({ children }: { children: React.ReactNode }) {
// Initialize PostHog immediately on the client side
if (typeof window !== "undefined" && !posthog.__loaded) {
const posthogKey = process.env.NEXT_PUBLIC_POSTHOG_KEY
const posthogHost = process.env.NEXT_PUBLIC_POSTHOG_HOST
// Check if environment variables are set
if (!posthogKey) {
@ -43,19 +42,13 @@ export function PostHogProvider({ children }: { children: React.ReactNode }) {
return
}
if (!posthogHost) {
console.warn(
"PostHog host URL is missing. Using default host. " +
"Please set NEXT_PUBLIC_POSTHOG_HOST in your .env file.",
)
}
// Check if user has already consented to cookies
const userHasConsented = hasConsent()
// Initialize PostHog with appropriate persistence based on consent
posthog.init(posthogKey, {
api_host: posthogHost || "https://us.i.posthog.com",
api_host: "https://ph.roocode.com",
ui_host: "https://us.posthog.com",
capture_pageview: false, // We handle pageview tracking manually
loaded: (posthogInstance) => {
if (process.env.NODE_ENV === "development") {

2
apps/web-roo-code/src/lib/constants.ts
View file

@ -26,7 +26,7 @@ export const EXTERNAL_LINKS = {
TESTIMONIALS: "https://roocode.com/#testimonials",
CLOUD_APP_LOGIN: "https://app.roocode.com/sign-in",
CLOUD_APP_SIGNUP: "https://app.roocode.com/sign-up",
CLOUD_APP_SIGNUP_PRO: "https://app.roocode.com/sign-up?redirect_url=/cloud-agents/welcome",
CLOUD_APP_SIGNUP_PRO: "https://app.roocode.com/sign-up?redirect_url=/cloud-agents/setup",
}
export const INTERNAL_LINKS = {

22
apps/web-roo-code/src/lib/formatters.ts Normal file
View file

@ -0,0 +1,22 @@
const formatter = new Intl.NumberFormat("en-US", {
style: "currency",
currency: "USD",
})
export const formatCurrency = (amount: number) => formatter.format(amount)
export const formatTokens = (tokens: number) => {
if (tokens < 1000) {
return tokens.toString()
}
if (tokens < 1000000) {
return `${(tokens / 1000).toFixed(1)}K`
}
if (tokens < 1000000000) {
return `${(tokens / 1000000).toFixed(1)}M`
}
return `${(tokens / 1000000000).toFixed(1)}B`
}

31
apps/web-roo-code/src/lib/types/models.ts Normal file
View file

@ -0,0 +1,31 @@
export interface ModelPricing {
input: string
output: string
input_cache_read: string
input_cache_write: string
}
export interface Model {
id: string
object: string
created: number
owned_by: string
name: string
description: string
context_window: number
max_tokens: number
type: string
tags: string[]
pricing: ModelPricing
deprecated?: boolean
}
export interface ModelsResponse {
data: Model[]
}
export interface ModelWithTotalPrice extends Model {
totalPrice: number
}
export type SortOption = "alphabetical" | "price-asc" | "price-desc" | "context-window-asc" | "context-window-desc"

12
locales/ca/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Ens encanten les contribucions de la comunitat! Comença llegint el nostre [CONT
---
## Col·laboradors
Gràcies a tots els nostres col·laboradors que han ajudat a millorar Roo Code!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Llicència
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/de/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Wir lieben Community-Beiträge! Lies unsere [CONTRIBUTING.md](CONTRIBUTING.md),
---
## Mitwirkende
Danke an alle unsere Mitwirkenden, die geholfen haben, Roo Code besser zu machen!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Lizenz
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/es/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Usamos [changesets](https://github.com/changesets/changesets) para el versionado
---
## Colaboradores
¡Gracias a todos nuestros colaboradores que han ayudado a mejorar Roo Code!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Licencia
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/fr/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Nous adorons les contributions de la communauté ! Commencez par lire notre [CON
---
## Contributeurs
Merci à tous nos contributeurs qui ont aidé à améliorer Roo Code !
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Licence
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/hi/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ pnpm install:vsix [-y] [--editor=<command>]
---
## योगदानकर्ता
हमारे सभी योगदानकर्ताओं को धन्यवाद जिन्होंने Roo Code को बेहतर बनाने में मदद की है!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## लाइसेंस
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/id/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Kami menyukai kontribusi komunitas! Mulailah dengan membaca [CONTRIBUTING.md](CO
---
## Kontributor
Terima kasih kepada semua kontributor kami yang telah membantu membuat Roo Code lebih baik!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Lisensi
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/it/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Adoriamo i contributi della community! Inizia leggendo il nostro [CONTRIBUTING.m
---
## Contributori
Grazie a tutti i nostri contributori che hanno aiutato a migliorare Roo Code!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Licenza
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/ja/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ VSIXパッケージを手動でインストールしたい場合：
---
## 貢献者
Roo Codeをより良くするために協力してくれたすべての貢献者に感謝します！
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## ライセンス
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/ko/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ VSIX 패키지를 수동으로 설치하려면:
---
## 기여자
Roo Code를 더 좋게 만드는 데 도움을 준 모든 기여자들에게 감사합니다!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## 라이선스
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/nl/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ We houden van bijdragen uit de community! Begin met het lezen van onze [CONTRIBU
---
## Bijdragers
Dank aan al onze bijdragers die hebben geholpen Roo Code beter te maken!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Licentie
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/pl/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Uwielbiamy wkłady społeczności! Zacznij od przeczytania naszego pliku [CONTRI
---
## Współtwórcy
Dziękujemy wszystkim naszym współtwórcom, którzy pomogli ulepszyć Roo Code!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Licencja
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/pt-BR/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Adoramos contribuições da comunidade! Comece lendo nosso [CONTRIBUTING.md](CON
---
## Contribuidores
Obrigado a todos os nossos contribuidores que ajudaram a tornar o Roo Code melhor!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Licença
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/ru/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ pnpm install:vsix [-y] [--editor=<command>]
---
## Участники
Спасибо всем нашим участникам, которые помогли сделать Roo Code лучше!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Лицензия
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/tr/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Topluluk katkılarını çok seviyoruz! [CONTRIBUTING.md](CONTRIBUTING.md) dosya
---
## Katkıda Bulunanlar
Roo Code'u daha iyi hale getirmemize yardımcı olan tüm katkıda bulunanlarımıza teşekkür ederiz!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Lisans
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/vi/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ Chúng tôi yêu thích những đóng góp của cộng đồng! Bắt đầu b
---
## Những người đóng góp
Cảm ơn tất cả những người đóng góp đã giúp Roo Code trở nên tốt hơn!
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## Giấy phép
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/zh-CN/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ pnpm install:vsix [-y] [--editor=<command>]
---
## 贡献者
感谢所有帮助改进 Roo Code 的贡献者！
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## 许可证
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

12
locales/zh-TW/README.md generated
View file

@ -1,5 +1,5 @@
<p align="center">
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/visual-studio-marketplace/v/RooVeterinaryInc.roo-cline.svg?label=VS%20Code&color=%23007ACC&style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code"></a>
<a href="https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline"><img src="https://img.shields.io/badge/VS_Code_Marketplace-007ACC?style=flat&logo=visualstudiocode&logoColor=white" alt="VS Code Marketplace"></a>
<a href="https://x.com/roocode"><img src="https://img.shields.io/badge/roocode-000000?style=flat&logo=x&logoColor=white" alt="X"></a>
<a href="https://youtube.com/@roocodeyt?feature=shared"><img src="https://img.shields.io/badge/YouTube-FF0000?style=flat&logo=youtube&logoColor=white" alt="YouTube"></a>
<a href="https://discord.gg/roocode"><img src="https://img.shields.io/badge/Join%20Discord-5865F2?style=flat&logo=discord&logoColor=white" alt="Join Discord"></a>
@ -167,16 +167,6 @@ pnpm install:vsix [-y] [--editor=<command>]
---
## 貢獻者
感謝所有幫助改進 Roo Code 的貢獻者！
<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->
[![Contributors](https://contrib.rocks/image?repo=RooCodeInc/roo-code&max=120&columns=12&cacheBust=0000000000)](https://github.com/RooCodeInc/roo-code/graphs/contributors)
<!-- END CONTRIBUTORS SECTION -->
## 授權
[Apache 2.0 © 2025 Roo Code, Inc.](../../LICENSE)

1
package.json
View file

@ -22,7 +22,6 @@
"install:vsix": "pnpm install --frozen-lockfile && pnpm clean && pnpm vsix && node scripts/install-vsix.js",
"changeset:version": "cp CHANGELOG.md src/CHANGELOG.md && changeset version && cp -vf src/CHANGELOG.md .",
"knip": "knip --include files",
"update-contributors": "node scripts/update-contributors.js",
"evals": "dotenvx run -f packages/evals/.env.development packages/evals/.env.local -- docker compose -f packages/evals/docker-compose.yml --profile server --profile runner up --build --scale runner=0",
"npm:publish:types": "pnpm --filter @roo-code/types npm:publish"
},

1
packages/build/src/types.ts
View file

@ -86,6 +86,7 @@ const configurationPropertySchema = z.object({
})
.optional(),
properties: z.record(z.string(), z.any()).optional(),
enum: z.array(z.any()).optional(),
default: z.any().optional(),
description: z.string(),
})

10
packages/cloud/src/CloudAPI.ts
View file

@ -134,4 +134,14 @@ export class CloudAPI {
.parse(data),
})
}
async creditBalance(): Promise<number> {
return this.request("/api/extension/credit-balance", {
method: "GET",
parseResponse: (data) => {
const result = z.object({ balance: z.number() }).parse(data)
return result.balance
},
})
}
}

96
packages/cloud/src/__tests__/CloudAPI.creditBalance.spec.ts Normal file
View file

@ -0,0 +1,96 @@
import { describe, it, expect, vi, beforeEach, type Mock } from "vitest"
import { CloudAPI } from "../CloudAPI.js"
import { AuthenticationError, CloudAPIError } from "../errors.js"
import type { AuthService } from "@roo-code/types"
// Mock the config module
vi.mock("../config.js", () => ({
getRooCodeApiUrl: () => "https://api.test.com",
}))
// Mock the utils module
vi.mock("../utils.js", () => ({
getUserAgent: () => "test-user-agent",
}))
describe("CloudAPI.creditBalance", () => {
let mockAuthService: {
getSessionToken: Mock<() => string | undefined>
}
let cloudAPI: CloudAPI
beforeEach(() => {
mockAuthService = {
getSessionToken: vi.fn(),
}
cloudAPI = new CloudAPI(mockAuthService as unknown as AuthService)
// Reset fetch mock
global.fetch = vi.fn()
})
it("should fetch credit balance successfully", async () => {
const mockBalance = 12.34
mockAuthService.getSessionToken.mockReturnValue("test-session-token")
global.fetch = vi.fn().mockResolvedValue({
ok: true,
json: async () => ({ balance: mockBalance }),
})
const balance = await cloudAPI.creditBalance()
expect(balance).toBe(mockBalance)
expect(global.fetch).toHaveBeenCalledWith(
"https://api.test.com/api/extension/credit-balance",
expect.objectContaining({
method: "GET",
headers: expect.objectContaining({
Authorization: "Bearer test-session-token",
"Content-Type": "application/json",
"User-Agent": "test-user-agent",
}),
}),
)
})
it("should throw AuthenticationError when session token is missing", async () => {
mockAuthService.getSessionToken.mockReturnValue(undefined)
await expect(cloudAPI.creditBalance()).rejects.toThrow(AuthenticationError)
})
it("should handle API errors", async () => {
mockAuthService.getSessionToken.mockReturnValue("test-session-token")
global.fetch = vi.fn().mockResolvedValue({
ok: false,
status: 500,
statusText: "Internal Server Error",
json: async () => ({ error: "Server error" }),
})
await expect(cloudAPI.creditBalance()).rejects.toThrow(CloudAPIError)
})
it("should handle network errors", async () => {
mockAuthService.getSessionToken.mockReturnValue("test-session-token")
global.fetch = vi.fn().mockRejectedValue(new TypeError("fetch failed"))
await expect(cloudAPI.creditBalance()).rejects.toThrow(
"Network error while calling /api/extension/credit-balance",
)
})
it("should handle invalid response format", async () => {
mockAuthService.getSessionToken.mockReturnValue("test-session-token")
global.fetch = vi.fn().mockResolvedValue({
ok: true,
json: async () => ({ invalid: "response" }),
})
await expect(cloudAPI.creditBalance()).rejects.toThrow()
})
})

16
packages/evals/src/cli/runTask.ts
View file

@ -217,11 +217,23 @@ export const runTask = async ({ run, task, publish, logger }: RunTaskOptions) =>
"diff_error",
"condense_context",
"condense_context_error",
"api_req_retry_delayed",
"api_req_retried",
]
let isApiUnstable = false
client.on(IpcMessageType.TaskEvent, async (taskEvent) => {
const { eventName, payload } = taskEvent
if (
eventName === RooCodeEventName.Message &&
payload[0].message.say &&
["api_req_retry_delayed", "api_req_retried"].includes(payload[0].message.say)
) {
isApiUnstable = true
}
// Publish all events except for these to Redis.
if (!ignoreEvents.broadcast.includes(eventName)) {
await publish({ ...taskEvent, taskId: task.id })
@ -388,4 +400,8 @@ export const runTask = async ({ run, task, publish, logger }: RunTaskOptions) =>
}
logger.close()
if (isApiUnstable) {
throw new Error("API is unstable, throwing to trigger a retry.")
}
}

2
packages/telemetry/src/PostHogTelemetryClient.ts
View file

@ -25,7 +25,7 @@ export class PostHogTelemetryClient extends BaseTelemetryClient {
debug,
)
this.client = new PostHog(process.env.POSTHOG_API_KEY || "", { host: "https://us.i.posthog.com" })
this.client = new PostHog(process.env.POSTHOG_API_KEY || "", { host: "https://ph.roocode.com" })
}
/**

4
packages/telemetry/src/TelemetryService.ts
View file

@ -98,8 +98,8 @@ export class TelemetryService {
this.captureEvent(TelemetryEventName.MODE_SWITCH, { taskId, newMode })
}
public captureToolUsage(taskId: string, tool: string): void {
this.captureEvent(TelemetryEventName.TOOL_USED, { taskId, tool })
public captureToolUsage(taskId: string, tool: string, toolProtocol: string): void {
this.captureEvent(TelemetryEventName.TOOL_USED, { taskId, tool, toolProtocol })
}
public captureCheckpointCreated(taskId: string): void {

2
packages/types/npm/package.metadata.json
View file

@ -1,6 +1,6 @@
{
"name": "@roo-code/types",
"version": "1.85.0",
"version": "1.86.0",
"description": "TypeScript type definitions for Roo Code.",
"publishConfig": {
"access": "public",

7
packages/types/src/global-settings.ts
View file

@ -103,6 +103,12 @@ export const globalSettingsSchema = z.object({
* @default true
*/
includeCurrentCost: z.boolean().optional(),
/**
* Maximum number of git status file entries to include in the environment details.
* Set to 0 to disable git status. The header (branch, commits) is always included when > 0.
* @default 0
*/
maxGitStatusFiles: z.number().optional(),
/**
* Whether to include diagnostic messages (errors, warnings) in tool outputs
@ -339,6 +345,7 @@ export const EVALS_SETTINGS: RooCodeSettings = {
rateLimitSeconds: 0,
maxOpenTabsContext: 20,
maxWorkspaceFiles: 200,
maxGitStatusFiles: 20,
showRooIgnoredFiles: true,
maxReadFileLine: -1, // -1 to enable full file reading.

1
packages/types/src/index.ts
View file

@ -20,6 +20,7 @@ export * from "./todo.js"
export * from "./telemetry.js"
export * from "./terminal.js"
export * from "./tool.js"
export * from "./tool-params.js"
export * from "./type-fu.js"
export * from "./vscode.js"

31
packages/types/src/model.ts
View file

@ -18,6 +18,22 @@ export const reasoningEffortWithMinimalSchema = z.union([reasoningEffortsSchema,
export type ReasoningEffortWithMinimal = z.infer<typeof reasoningEffortWithMinimalSchema>
/**
* Extended Reasoning Effort (includes "none" and "minimal")
* Note: "disable" is a UI/control value, not a value sent as effort
*/
export const reasoningEffortsExtended = ["none", "minimal", "low", "medium", "high"] as const
export const reasoningEffortExtendedSchema = z.enum(reasoningEffortsExtended)
export type ReasoningEffortExtended = z.infer<typeof reasoningEffortExtendedSchema>
/**
* Reasoning Effort user setting (includes "disable")
*/
export const reasoningEffortSettingValues = ["disable", "none", "minimal", "low", "medium", "high"] as const
export const reasoningEffortSettingSchema = z.enum(reasoningEffortSettingValues)
/**
* Verbosity
*/
@ -58,6 +74,10 @@ export const modelInfoSchema = z.object({
contextWindow: z.number(),
supportsImages: z.boolean().optional(),
supportsPromptCache: z.boolean(),
// Optional default prompt cache retention policy for providers that support it.
// When set to "24h", extended prompt caching will be requested; when omitted
// or set to "in_memory", the default in‑memory cache is used.
promptCacheRetention: z.enum(["in_memory", "24h"]).optional(),
// Capability flag to indicate whether the model supports an output verbosity parameter
supportsVerbosity: z.boolean().optional(),
supportsReasoningBudget: z.boolean().optional(),
@ -67,7 +87,9 @@ export const modelInfoSchema = z.object({
supportsTemperature: z.boolean().optional(),
defaultTemperature: z.number().optional(),
requiredReasoningBudget: z.boolean().optional(),
supportsReasoningEffort: z.boolean().optional(),
supportsReasoningEffort: z
.union([z.boolean(), z.array(z.enum(["disable", "none", "minimal", "low", "medium", "high"]))])
.optional(),
requiredReasoningEffort: z.boolean().optional(),
preserveReasoning: z.boolean().optional(),
supportedParameters: z.array(modelParametersSchema).optional(),
@ -76,7 +98,8 @@ export const modelInfoSchema = z.object({
cacheWritesPrice: z.number().optional(),
cacheReadsPrice: z.number().optional(),
description: z.string().optional(),
reasoningEffort: reasoningEffortsSchema.optional(),
// Default effort value for models that support reasoning effort
reasoningEffort: reasoningEffortExtendedSchema.optional(),
minTokensPerCachePoint: z.number().optional(),
maxCachePoints: z.number().optional(),
cachableFields: z.array(z.string()).optional(),
@ -84,6 +107,10 @@ export const modelInfoSchema = z.object({
deprecated: z.boolean().optional(),
// Flag to indicate if the model is free (no cost)
isFree: z.boolean().optional(),
// Flag to indicate if the model supports native tool calling (OpenAI-style function calling)
supportsNativeTools: z.boolean().optional(),
// Default tool protocol preferred by this model (if not specified, falls back to capability/provider defaults)
defaultToolProtocol: z.enum(["xml", "native"]).optional(),
/**
* Service tiers with pricing information.
* Each tier can have a name (for OpenAI service tiers) and pricing overrides.

7
packages/types/src/provider-settings.ts
View file

@ -1,6 +1,6 @@
import { z } from "zod"
import { modelInfoSchema, reasoningEffortWithMinimalSchema, verbosityLevelsSchema, serviceTierSchema } from "./model.js"
import { modelInfoSchema, reasoningEffortSettingSchema, verbosityLevelsSchema, serviceTierSchema } from "./model.js"
import { codebaseIndexProviderSchema } from "./codebase-index.js"
import {
anthropicModels,
@ -176,12 +176,15 @@ const baseProviderSettingsSchema = z.object({
// Model reasoning.
enableReasoningEffort: z.boolean().optional(),
reasoningEffort: reasoningEffortWithMinimalSchema.optional(),
reasoningEffort: reasoningEffortSettingSchema.optional(),
modelMaxTokens: z.number().optional(),
modelMaxThinkingTokens: z.number().optional(),
// Model verbosity.
verbosity: verbosityLevelsSchema.optional(),
// Tool protocol override for this profile.
toolProtocol: z.enum(["xml", "native"]).optional(),
})
// Several of the providers share common model config properties.

360
packages/types/src/providers/gemini.ts
View file

@ -3,140 +3,68 @@ import type { ModelInfo } from "../model.js"
// https://ai.google.dev/gemini-api/docs/models/gemini
export type GeminiModelId = keyof typeof geminiModels
export const geminiDefaultModelId: GeminiModelId = "gemini-2.0-flash-001"
export const geminiDefaultModelId: GeminiModelId = "gemini-2.5-pro"
export const geminiModels = {
// Latest models (pointing to the most recent stable versions)
"gemini-flash-latest": {
"gemini-3-pro-preview": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 0.3,
outputPrice: 2.5,
cacheReadsPrice: 0.075,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
supportsReasoningEffort: ["low", "high"],
reasoningEffort: "low",
supportsTemperature: true,
defaultTemperature: 1,
inputPrice: 4.0,
outputPrice: 18.0,
tiers: [
{
contextWindow: 200_000,
inputPrice: 2.0,
outputPrice: 12.0,
},
{
contextWindow: Infinity,
inputPrice: 4.0,
outputPrice: 18.0,
},
],
},
"gemini-flash-lite-latest": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
cacheWritesPrice: 1.0,
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
},
// 2.5 Flash models (09-2025 versions - most recent)
"gemini-2.5-flash-preview-09-2025": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.3,
outputPrice: 2.5,
cacheReadsPrice: 0.075,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
},
"gemini-2.5-flash-lite-preview-09-2025": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
cacheWritesPrice: 1.0,
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
},
// 2.5 Flash models (06-17 version)
"gemini-2.5-flash-lite-preview-06-17": {
maxTokens: 64_000,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
cacheWritesPrice: 1.0,
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
},
// 2.5 Flash models (05-20 versions)
"gemini-2.5-flash-preview-05-20:thinking": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.15,
outputPrice: 3.5,
cacheReadsPrice: 0.0375,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
},
"gemini-2.5-flash-preview-05-20": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.15,
outputPrice: 0.6,
cacheReadsPrice: 0.0375,
cacheWritesPrice: 1.0,
},
// 2.5 Flash models (04-17 versions)
"gemini-2.5-flash-preview-04-17:thinking": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 3.5,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
},
"gemini-2.5-flash-preview-04-17": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.6,
},
// 2.5 Flash stable
"gemini-2.5-flash": {
maxTokens: 64_000,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.3,
outputPrice: 2.5,
cacheReadsPrice: 0.075,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
},
// 2.5 Pro models
"gemini-2.5-pro": {
maxTokens: 64_000,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.625,
},
],
},
"gemini-2.5-pro-preview-06-05": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
@ -163,6 +91,7 @@ export const geminiModels = {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
@ -187,6 +116,7 @@ export const geminiModels = {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
@ -209,163 +139,73 @@ export const geminiModels = {
},
],
},
"gemini-2.5-pro-exp-03-25": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.5-pro": {
maxTokens: 64_000,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.625,
},
],
},
// 2.0 Flash models
"gemini-2.0-flash-lite-preview-02-05": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.0-flash-thinking-exp-01-21": {
// 2.5 Flash models
"gemini-flash-latest": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 0.3,
outputPrice: 2.5,
cacheReadsPrice: 0.075,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
},
"gemini-2.0-flash-thinking-exp-1219": {
maxTokens: 8192,
contextWindow: 32_767,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-2.0-flash-exp": {
maxTokens: 8192,
"gemini-2.5-flash-preview-09-2025": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 0.3,
outputPrice: 2.5,
cacheReadsPrice: 0.075,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
},
"gemini-2.0-flash-001": {
maxTokens: 8192,
"gemini-2.5-flash": {
maxTokens: 64_000,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 0.3,
outputPrice: 2.5,
cacheReadsPrice: 0.075,
cacheWritesPrice: 1.0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
},
// 2.5 Flash Lite models
"gemini-flash-lite-latest": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
cacheWritesPrice: 1.0,
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
},
// 2.0 Pro models
"gemini-2.0-pro-exp-02-05": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
// 1.5 Flash models
"gemini-1.5-flash-002": {
maxTokens: 8192,
"gemini-2.5-flash-lite-preview-09-2025": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsNativeTools: true,
supportsPromptCache: true,
inputPrice: 0.15, // This is the pricing for prompts above 128k tokens.
outputPrice: 0.6,
cacheReadsPrice: 0.0375,
inputPrice: 0.1,
outputPrice: 0.4,
cacheReadsPrice: 0.025,
cacheWritesPrice: 1.0,
tiers: [
{
contextWindow: 128_000,
inputPrice: 0.075,
outputPrice: 0.3,
cacheReadsPrice: 0.01875,
},
{
contextWindow: Infinity,
inputPrice: 0.15,
outputPrice: 0.6,
cacheReadsPrice: 0.0375,
},
],
},
"gemini-1.5-flash-exp-0827": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-1.5-flash-8b-exp-0827": {
maxTokens: 8192,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
// 1.5 Pro models
"gemini-1.5-pro-002": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
"gemini-1.5-pro-exp-0827": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
},
// Experimental models
"gemini-exp-1206": {
maxTokens: 8192,
contextWindow: 2_097_152,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
},
} as const satisfies Record<string, ModelInfo>

214
packages/types/src/providers/openai.ts
View file

@ -3,90 +3,144 @@ import type { ModelInfo } from "../model.js"
// https://openai.com/api/pricing/
export type OpenAiNativeModelId = keyof typeof openAiNativeModels
export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-5-2025-08-07"
export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-5.1"
export const openAiNativeModels = {
"gpt-5-chat-latest": {
"gpt-5.1": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: false,
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.13,
description: "GPT-5 Chat Latest: Optimized for conversational AI and non-reasoning tasks",
supportsVerbosity: true,
},
"gpt-5-2025-08-07": {
maxTokens: 128000,
contextWindow: 400000,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: true,
promptCacheRetention: "24h",
supportsReasoningEffort: ["none", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.13,
description: "GPT-5: The best model for coding and agentic tasks across domains",
// supportsVerbosity is a new capability; ensure ModelInfo includes it
cacheReadsPrice: 0.125,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 400000, inputPrice: 0.625, outputPrice: 5.0, cacheReadsPrice: 0.0625 },
{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
],
description: "GPT-5.1: The best model for coding and agentic tasks across domains",
},
"gpt-5-mini-2025-08-07": {
"gpt-5.1-codex": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: true,
promptCacheRetention: "24h",
supportsReasoningEffort: ["low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.125,
supportsTemperature: false,
tiers: [{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 }],
description: "GPT-5.1 Codex: A version of GPT-5.1 optimized for agentic coding in Codex",
},
"gpt-5.1-codex-mini": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
promptCacheRetention: "24h",
supportsReasoningEffort: ["low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 0.25,
outputPrice: 2.0,
cacheReadsPrice: 0.03,
description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
cacheReadsPrice: 0.025,
supportsTemperature: false,
description: "GPT-5.1 Codex mini: A version of GPT-5.1 optimized for agentic coding in Codex",
},
"gpt-5": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.125,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 400000, inputPrice: 0.625, outputPrice: 5.0, cacheReadsPrice: 0.0625 },
{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
],
description: "GPT-5: The best model for coding and agentic tasks across domains",
},
"gpt-5-mini": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 0.25,
outputPrice: 2.0,
cacheReadsPrice: 0.025,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 400000, inputPrice: 0.125, outputPrice: 1.0, cacheReadsPrice: 0.0125 },
{ name: "priority", contextWindow: 400000, inputPrice: 0.45, outputPrice: 3.6, cacheReadsPrice: 0.045 },
],
},
"gpt-5-nano-2025-08-07": {
maxTokens: 128000,
contextWindow: 400000,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: true,
reasoningEffort: "medium",
inputPrice: 0.05,
outputPrice: 0.4,
cacheReadsPrice: 0.01,
description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
supportsVerbosity: true,
supportsTemperature: false,
tiers: [{ name: "flex", contextWindow: 400000, inputPrice: 0.025, outputPrice: 0.2, cacheReadsPrice: 0.0025 }],
description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
},
"gpt-5-codex": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: true,
supportsReasoningEffort: ["low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.13,
cacheReadsPrice: 0.125,
supportsTemperature: false,
tiers: [{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 }],
description: "GPT-5-Codex: A version of GPT-5 optimized for agentic coding in Codex",
},
"gpt-5-nano": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 0.05,
outputPrice: 0.4,
cacheReadsPrice: 0.005,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [{ name: "flex", contextWindow: 400000, inputPrice: 0.025, outputPrice: 0.2, cacheReadsPrice: 0.0025 }],
description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
},
"gpt-5-chat-latest": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.125,
description: "GPT-5 Chat: Optimized for conversational AI and non-reasoning tasks",
},
"gpt-4.1": {
maxTokens: 32_768,
contextWindow: 1_047_576,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2,
@ -100,6 +154,7 @@ export const openAiNativeModels = {
"gpt-4.1-mini": {
maxTokens: 32_768,
contextWindow: 1_047_576,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.4,
@ -113,6 +168,7 @@ export const openAiNativeModels = {
"gpt-4.1-nano": {
maxTokens: 32_768,
contextWindow: 1_047_576,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.1,
@ -126,12 +182,13 @@ export const openAiNativeModels = {
o3: {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.0,
outputPrice: 8.0,
cacheReadsPrice: 0.5,
supportsReasoningEffort: true,
supportsReasoningEffort: ["low", "medium", "high"],
reasoningEffort: "medium",
supportsTemperature: false,
tiers: [
@ -142,6 +199,7 @@ export const openAiNativeModels = {
"o3-high": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.0,
@ -153,6 +211,7 @@ export const openAiNativeModels = {
"o3-low": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.0,
@ -164,12 +223,13 @@ export const openAiNativeModels = {
"o4-mini": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.275,
supportsReasoningEffort: true,
supportsReasoningEffort: ["low", "medium", "high"],
reasoningEffort: "medium",
supportsTemperature: false,
tiers: [
@ -180,6 +240,7 @@ export const openAiNativeModels = {
"o4-mini-high": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
@ -191,6 +252,7 @@ export const openAiNativeModels = {
"o4-mini-low": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
@ -202,18 +264,20 @@ export const openAiNativeModels = {
"o3-mini": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.1,
outputPrice: 4.4,
cacheReadsPrice: 0.55,
supportsReasoningEffort: true,
supportsReasoningEffort: ["low", "medium", "high"],
reasoningEffort: "medium",
supportsTemperature: false,
},
"o3-mini-high": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.1,
@ -225,6 +289,7 @@ export const openAiNativeModels = {
"o3-mini-low": {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.1,
@ -236,6 +301,7 @@ export const openAiNativeModels = {
o1: {
maxTokens: 100_000,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 15,
@ -246,6 +312,7 @@ export const openAiNativeModels = {
"o1-preview": {
maxTokens: 32_768,
contextWindow: 128_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 15,
@ -256,6 +323,7 @@ export const openAiNativeModels = {
"o1-mini": {
maxTokens: 65_536,
contextWindow: 128_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 1.1,
@ -266,6 +334,7 @@ export const openAiNativeModels = {
"gpt-4o": {
maxTokens: 16_384,
contextWindow: 128_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5,
@ -279,6 +348,7 @@ export const openAiNativeModels = {
"gpt-4o-mini": {
maxTokens: 16_384,
contextWindow: 128_000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0.15,
@ -292,15 +362,71 @@ export const openAiNativeModels = {
"codex-mini-latest": {
maxTokens: 16_384,
contextWindow: 200_000,
supportsNativeTools: true,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.5,
outputPrice: 6,
cacheReadsPrice: 0,
cacheReadsPrice: 0.375,
supportsTemperature: false,
description:
"Codex Mini: Cloud-based software engineering agent powered by codex-1, a version of o3 optimized for coding tasks. Trained with reinforcement learning to generate human-style code, adhere to instructions, and iteratively run tests.",
},
// Dated clones (snapshots) preserved for backward compatibility
"gpt-5-2025-08-07": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 1.25,
outputPrice: 10.0,
cacheReadsPrice: 0.125,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 400000, inputPrice: 0.625, outputPrice: 5.0, cacheReadsPrice: 0.0625 },
{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
],
description: "GPT-5: The best model for coding and agentic tasks across domains",
},
"gpt-5-mini-2025-08-07": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 0.25,
outputPrice: 2.0,
cacheReadsPrice: 0.025,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [
{ name: "flex", contextWindow: 400000, inputPrice: 0.125, outputPrice: 1.0, cacheReadsPrice: 0.0125 },
{ name: "priority", contextWindow: 400000, inputPrice: 0.45, outputPrice: 3.6, cacheReadsPrice: 0.045 },
],
description: "GPT-5 Mini: A faster, more cost-efficient version of GPT-5 for well-defined tasks",
},
"gpt-5-nano-2025-08-07": {
maxTokens: 128000,
contextWindow: 400000,
supportsNativeTools: true,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",
inputPrice: 0.05,
outputPrice: 0.4,
cacheReadsPrice: 0.005,
supportsVerbosity: true,
supportsTemperature: false,
tiers: [{ name: "flex", contextWindow: 400000, inputPrice: 0.025, outputPrice: 0.2, cacheReadsPrice: 0.0025 }],
description: "GPT-5 Nano: Fastest, most cost-efficient version of GPT-5",
},
} as const satisfies Record<string, ModelInfo>
export const openAiModelInfoSaneDefaults: ModelInfo = {
@ -310,6 +436,7 @@ export const openAiModelInfoSaneDefaults: ModelInfo = {
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
supportsNativeTools: true,
}
// https://learn.microsoft.com/en-us/azure/ai-services/openai/api-version-deprecation
@ -317,6 +444,5 @@ export const openAiModelInfoSaneDefaults: ModelInfo = {
export const azureOpenAiDefaultApiVersion = "2024-08-01-preview"
export const OPENAI_NATIVE_DEFAULT_TEMPERATURE = 0
export const GPT5_DEFAULT_TEMPERATURE = 1.0
export const OPENAI_AZURE_AI_INFERENCE_PATH = "/models/chat/completions"

1
packages/types/src/providers/openrouter.ts
View file

@ -8,6 +8,7 @@ export const openRouterDefaultModelInfo: ModelInfo = {
contextWindow: 200_000,
supportsImages: true,
supportsPromptCache: true,
supportsNativeTools: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,

24
packages/types/src/providers/vertex.ts
View file

@ -6,6 +6,30 @@ export type VertexModelId = keyof typeof vertexModels
export const vertexDefaultModelId: VertexModelId = "claude-sonnet-4-5@20250929"
export const vertexModels = {
"gemini-3-pro-preview": {
maxTokens: 65_536,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["low", "high"],
reasoningEffort: "low",
supportsTemperature: true,
defaultTemperature: 1,
inputPrice: 4.0,
outputPrice: 18.0,
tiers: [
{
contextWindow: 200_000,
inputPrice: 2.0,
outputPrice: 12.0,
},
{
contextWindow: Infinity,
inputPrice: 4.0,
outputPrice: 18.0,
},
],
},
"gemini-2.5-flash-preview-05-20:thinking": {
maxTokens: 65_535,
contextWindow: 1_048_576,

37
packages/types/src/tool-params.ts Normal file
View file

@ -0,0 +1,37 @@
/**
* Tool parameter type definitions for native protocol
*/
export interface LineRange {
start: number
end: number
}
export interface FileEntry {
path: string
lineRanges?: LineRange[]
}
export interface Coordinate {
x: number
y: number
}
export interface Size {
width: number
height: number
}
export interface BrowserActionParams {
action: "launch" | "click" | "hover" | "type" | "scroll_down" | "scroll_up" | "resize" | "close"
url?: string
coordinate?: Coordinate
size?: Size
text?: string
}
export interface GenerateImageParams {
prompt: string
path: string
image?: string
}

21
packages/types/src/tool.ts
View file

@ -68,3 +68,24 @@ export const TOOL_PROTOCOL = {
* Derived from TOOL_PROTOCOL constants to ensure type safety
*/
export type ToolProtocol = (typeof TOOL_PROTOCOL)[keyof typeof TOOL_PROTOCOL]
/**
* Checks if the protocol is native (non-XML).
*
* @param protocol - The tool protocol to check
* @returns True if protocol is native
*/
export function isNativeProtocol(protocol: ToolProtocol): boolean {
return protocol === TOOL_PROTOCOL.NATIVE
}
/**
* Gets the effective protocol from settings or falls back to the default XML.
* This function is safe to use in webview-accessible code as it doesn't depend on vscode module.
*
* @param toolProtocol - Optional tool protocol from settings
* @returns The effective tool protocol (defaults to "xml")
*/
export function getEffectiveProtocol(toolProtocol?: ToolProtocol): ToolProtocol {
return toolProtocol || TOOL_PROTOCOL.XML
}

110
pnpm-lock.yaml generated
View file

@ -627,8 +627,8 @@ importers:
specifier: ^3.922.0
version: 3.922.0
'@google/genai':
specifier: ^1.0.0
version: 1.3.0(@modelcontextprotocol/sdk@1.12.0)
specifier: ^1.29.1
version: 1.29.1(@modelcontextprotocol/sdk@1.12.0)
'@lmstudio/sdk':
specifier: ^1.1.1
version: 1.2.0
@ -773,6 +773,9 @@ importers:
reconnecting-eventsource:
specifier: ^1.6.4
version: 1.6.4
safe-stable-stringify:
specifier: ^2.5.0
version: 2.5.0
sanitize-filename:
specifier: ^1.6.3
version: 1.6.3
@ -1914,11 +1917,14 @@ packages:
'@floating-ui/utils@0.2.9':
resolution: {integrity: sha512-MDWhGtE+eHw5JW7lq4qhc5yRLS11ERl1c7Z6Xd0a58DozHES6EnNNwUWbMiG4J9Cgj053Bhk8zvlhFYKVhULwg==}
'@google/genai@1.3.0':
resolution: {integrity: sha512-rrMzAELX4P902FUpuWy/W3NcQ7L3q/qtCzfCmGVqIce8yWpptTF9hkKsw744tvZpwqhuzD0URibcJA95wd8QFA==}
'@google/genai@1.29.1':
resolution: {integrity: sha512-Buywpq0A6xf9cOdhiWCi5KUiDBbZkjCH5xbl+xxNQRItoYQgd31p0OKyn5cUnT0YNzC/pAmszqXoOc7kncqfFQ==}
engines: {node: '>=20.0.0'}
peerDependencies:
'@modelcontextprotocol/sdk': ^1.11.0
'@modelcontextprotocol/sdk': ^1.20.1
peerDependenciesMeta:
'@modelcontextprotocol/sdk':
optional: true
'@hookform/resolvers@5.1.1':
resolution: {integrity: sha512-J/NVING3LMAEvexJkyTLjruSm7aOFx7QX21pzkiJfMoNG0wl5aFEjLTl7ay7IQb9EWY6AkrBy7tHL2Alijpdcg==}
@ -6208,10 +6214,18 @@ packages:
resolution: {integrity: sha512-LDODD4TMYx7XXdpwxAVRAIAuB0bzv0s+ywFonY46k126qzQHT9ygyoa9tncmOiQmmDrik65UYsEkv3lbfqQ3yQ==}
engines: {node: '>=14'}
gaxios@7.1.3:
resolution: {integrity: sha512-YGGyuEdVIjqxkxVH1pUTMY/XtmmsApXrCVv5EU25iX6inEPbV+VakJfLealkBtJN69AQmh1eGOdCl9Sm1UP6XQ==}
engines: {node: '>=18'}
gcp-metadata@6.1.1:
resolution: {integrity: sha512-a4tiq7E0/5fTjxPAaH4jpjkSv/uCaU2p5KC6HVGrvl0cDjA8iBZv4vv1gyzlmK0ZUKqwpOyQMKzZQe3lTit77A==}
engines: {node: '>=14'}
gcp-metadata@8.1.2:
resolution: {integrity: sha512-zV/5HKTfCeKWnxG0Dmrw51hEWFGfcF2xiXqcA3+J90WDuP0SvoiSO5ORvcBsifmx/FoIjgQN3oNOGaQ5PhLFkg==}
engines: {node: '>=18'}
gel@2.1.0:
resolution: {integrity: sha512-HCeRqInCt6BjbMmeghJ6BKeYwOj7WJT5Db6IWWAA3IMUUa7or7zJfTUEkUWCxiOtoXnwnm96sFK9Fr47Yh2hOA==}
engines: {node: '>= 18.0.0'}
@ -6328,6 +6342,10 @@ packages:
resolution: {integrity: sha512-jhIXaOzy1sb8IyocaruWSn1TjmnBVs8Ayhcy83rmxNJ8q2uWKCAj3CnJY+KpGSXCueAPc0i05kVvVKtP1t9S3g==}
engines: {node: '>=10'}
google-auth-library@10.5.0:
resolution: {integrity: sha512-7ABviyMOlX5hIVD60YOfHw4/CxOfBhyduaYB+wbFWCWoni4N7SLcV46hrVRktuBbZjFC9ONyqamZITN7q3n32w==}
engines: {node: '>=18'}
google-auth-library@9.15.1:
resolution: {integrity: sha512-Jb6Z0+nvECVz+2lzSMt9u98UsoakXxA2HGHMCxh+so3n90XgYWkq5dur19JAJV7ONiJY22yBTyJB1TSkvPq9Ng==}
engines: {node: '>=14'}
@ -6336,6 +6354,10 @@ packages:
resolution: {integrity: sha512-NEgUnEcBiP5HrPzufUkBzJOD/Sxsco3rLNo1F1TNf7ieU8ryUzBhqba8r756CjLX7rn3fHl6iLEwPYuqpoKgQQ==}
engines: {node: '>=14'}
google-logging-utils@1.1.3:
resolution: {integrity: sha512-eAmLkjDjAFCVXg7A1unxHsLf961m6y17QFqXqAXGj/gVkKFrEICfStRfwUlGNfeCEjNRa32JEWOUTlYXPyyKvA==}
engines: {node: '>=14'}
gopd@1.2.0:
resolution: {integrity: sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==}
engines: {node: '>= 0.4'}
@ -6354,6 +6376,10 @@ packages:
resolution: {integrity: sha512-pCcEwRi+TKpMlxAQObHDQ56KawURgyAf6jtIY046fJ5tIv3zDe/LEIubckAO8fj6JnAxLdmWkUfNyulQ2iKdEw==}
engines: {node: '>=14.0.0'}
gtoken@8.0.0:
resolution: {integrity: sha512-+CqsMbHPiSTdtSO14O51eMNlrp9N79gmeqmXeouJOhfucAedHw9noVe/n5uJk3tbKE6a+6ZCQg3RPhVhHByAIw==}
engines: {node: '>=18'}
hachure-fill@0.5.2:
resolution: {integrity: sha512-3GKBOn+m2LX9iq+JC1064cSFprJY4jL1jCXTcpnfER5HYE2l/4EfWSGzkPa/ZDBmYI0ZOEj5VHV/eKnPGkHuOg==}
@ -8750,6 +8776,10 @@ packages:
deprecated: Rimraf versions prior to v4 are no longer supported
hasBin: true
rimraf@5.0.10:
resolution: {integrity: sha512-l0OE8wL34P4nJH/H2ffoaniAokM2qSmrtXHmlpvYr5AVVX8msAyW0l8NVJFDxlSK4u3Uh/f41cQheDVdnYijwQ==}
hasBin: true
rimraf@6.0.1:
resolution: {integrity: sha512-9dkvaxAsk/xNXSJzMgFqqMCuFgt2+KsOFek3TMLfo8NCPfWpBmqwyNn5Y+NX56QUYfCtsyhF3ayiboEoUmJk/A==}
engines: {node: 20 || >=22}
@ -8804,6 +8834,10 @@ packages:
resolution: {integrity: sha512-x/+Cz4YrimQxQccJf5mKEbIa1NzeCRNI5Ecl/ekmlYaampdNLPalVyIcCZNNH3MvmqBugV5TMYZXv0ljslUlaw==}
engines: {node: '>= 0.4'}
safe-stable-stringify@2.5.0:
resolution: {integrity: sha512-b3rppTKm9T+PsVCBEOUR46GWI7fdOs00VKZ1+9c1EWDaDMvjQc6tUwuFyIprgGgTcWoVHSKrU8H31ZHA2e0RHA==}
engines: {node: '>=10'}
safer-buffer@2.1.2:
resolution: {integrity: sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==}
@ -11470,16 +11504,14 @@ snapshots:
'@floating-ui/utils@0.2.9': {}
'@google/genai@1.3.0(@modelcontextprotocol/sdk@1.12.0)':
'@google/genai@1.29.1(@modelcontextprotocol/sdk@1.12.0)':
dependencies:
google-auth-library: 10.5.0
ws: 8.18.3
optionalDependencies:
'@modelcontextprotocol/sdk': 1.12.0
google-auth-library: 9.15.1
ws: 8.18.2
zod: 3.25.76
zod-to-json-schema: 3.24.5(zod@3.25.76)
transitivePeerDependencies:
- bufferutil
- encoding
- supports-color
- utf-8-validate
@ -15110,8 +15142,7 @@ snapshots:
d3: 7.9.0
lodash-es: 4.17.21
data-uri-to-buffer@4.0.1:
optional: true
data-uri-to-buffer@4.0.1: {}
data-uri-to-buffer@6.0.2: {}
@ -15991,7 +16022,6 @@ snapshots:
dependencies:
node-domexception: 1.0.0
web-streams-polyfill: 3.3.3
optional: true
fflate@0.4.8: {}
@ -16085,7 +16115,6 @@ snapshots:
formdata-polyfill@4.0.10:
dependencies:
fetch-blob: 3.2.0
optional: true
forwarded@0.2.0: {}
@ -16170,6 +16199,15 @@ snapshots:
- encoding
- supports-color
gaxios@7.1.3:
dependencies:
extend: 3.0.2
https-proxy-agent: 7.0.6
node-fetch: 3.3.2
rimraf: 5.0.10
transitivePeerDependencies:
- supports-color
gcp-metadata@6.1.1:
dependencies:
gaxios: 6.7.1
@ -16179,6 +16217,14 @@ snapshots:
- encoding
- supports-color
gcp-metadata@8.1.2:
dependencies:
gaxios: 7.1.3
google-logging-utils: 1.1.3
json-bigint: 1.0.0
transitivePeerDependencies:
- supports-color
gel@2.1.0:
dependencies:
'@petamoriken/float16': 3.9.3
@ -16316,6 +16362,18 @@ snapshots:
merge2: 1.4.1
slash: 3.0.0
google-auth-library@10.5.0:
dependencies:
base64-js: 1.5.1
ecdsa-sig-formatter: 1.0.11
gaxios: 7.1.3
gcp-metadata: 8.1.2
google-logging-utils: 1.1.3
gtoken: 8.0.0
jws: 4.0.0
transitivePeerDependencies:
- supports-color
google-auth-library@9.15.1:
dependencies:
base64-js: 1.5.1
@ -16330,6 +16388,8 @@ snapshots:
google-logging-utils@0.0.2: {}
google-logging-utils@1.1.3: {}
gopd@1.2.0: {}
graceful-fs@4.2.11: {}
@ -16351,6 +16411,13 @@ snapshots:
- encoding
- supports-color
gtoken@8.0.0:
dependencies:
gaxios: 7.1.3
jws: 4.0.0
transitivePeerDependencies:
- supports-color
hachure-fill@0.5.2: {}
harmony-reflect@1.6.2: {}
@ -18141,7 +18208,6 @@ snapshots:
data-uri-to-buffer: 4.0.1
fetch-blob: 3.2.0
formdata-polyfill: 4.0.10
optional: true
node-ipc@12.0.0:
dependencies:
@ -19211,6 +19277,10 @@ snapshots:
dependencies:
glob: 7.2.3
rimraf@5.0.10:
dependencies:
glob: 10.4.5
rimraf@6.0.1:
dependencies:
glob: 11.0.3
@ -19298,6 +19368,8 @@ snapshots:
es-errors: 1.3.0
is-regex: 1.2.1
safe-stable-stringify@2.5.0: {}
safer-buffer@2.1.2: {}
sanitize-filename@1.6.3:
@ -20788,8 +20860,7 @@ snapshots:
web-namespaces@2.0.1: {}
web-streams-polyfill@3.3.3:
optional: true
web-streams-polyfill@3.3.3: {}
web-streams-polyfill@4.0.0-beta.3: {}
@ -20933,8 +21004,7 @@ snapshots:
ws@8.18.2: {}
ws@8.18.3:
optional: true
ws@8.18.3: {}
xml-name-validator@5.0.0: {}

BIN
releases/3.31.3-release.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 1.3 MiB

BIN
releases/3.32.0-release.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 1.1 MiB

BIN
releases/3.32.1-release.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 2 MiB

BIN
releases/3.33.1-release.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 2.1 MiB

BIN
releases/v3.33.0-release.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 1.4 MiB

384
scripts/update-contributors.js
View file

@ -1,384 +0,0 @@
#!/usr/bin/env node
/**
* This script fetches contributor data from GitHub and updates the README.md file
* with a contributors section showing avatars and usernames.
* It also updates all localized README files in the locales directory.
*/
const https = require("https")
const fs = require("fs")
const { promisify } = require("util")
const path = require("path")
// Promisify filesystem operations
const readFileAsync = promisify(fs.readFile)
const writeFileAsync = promisify(fs.writeFile)
// GitHub API URL for fetching contributors
const GITHUB_API_URL = "https://api.github.com/repos/RooCodeInc/Roo-Code/contributors?per_page=100"
const README_PATH = path.join(__dirname, "..", "README.md")
const LOCALES_DIR = path.join(__dirname, "..", "locales")
// Sentinel markers for contributors section
const START_MARKER = "<!-- START CONTRIBUTORS SECTION - AUTO-GENERATED, DO NOT EDIT MANUALLY -->"
const END_MARKER = "<!-- END CONTRIBUTORS SECTION -->"
// HTTP options for GitHub API request
const options = {
headers: {
"User-Agent": "Roo-Code-Contributors-Script",
},
}
// Add GitHub token for authentication if available
if (process.env.GITHUB_TOKEN) {
options.headers.Authorization = `token ${process.env.GITHUB_TOKEN}`
console.log("Using GitHub token from environment variable")
}
/**
* Parses the GitHub API Link header to extract pagination URLs
* Based on RFC 5988 format for the Link header
* @param {string} header The Link header from GitHub API response
* @returns {Object} Object containing URLs for next, prev, first, last pages (if available)
*/
function parseLinkHeader(header) {
// Return empty object if no header is provided
if (!header || header.trim() === "") return {}
// Initialize links object
const links = {}
// Split the header into individual link entries
// Example: <https://api.github.com/...?page=2>; rel="next", <https://api.github.com/...?page=5>; rel="last"
const entries = header.split(/,\s*/)
// Process each link entry
for (const entry of entries) {
// Extract the URL (between < and >) and the parameters (after >)
const segments = entry.split(";")
if (segments.length < 2) continue
// Extract URL from the first segment, removing < and >
const urlMatch = segments[0].match(/<(.+)>/)
if (!urlMatch) continue
const url = urlMatch[1]
// Find the rel="value" parameter
let rel = null
for (let i = 1; i < segments.length; i++) {
const relMatch = segments[i].match(/\s*rel\s*=\s*"?([^"]+)"?/)
if (relMatch) {
rel = relMatch[1]
break
}
}
// Only add to links if both URL and rel were found
if (rel) {
links[rel] = url
}
}
return links
}
/**
* Performs an HTTP GET request and returns the response
* @param {string} url The URL to fetch
* @param {Object} options Request options
* @returns {Promise<Object>} Response object with status, headers and body
*/
function httpGet(url, options) {
return new Promise((resolve, reject) => {
https
.get(url, options, (res) => {
let data = ""
res.on("data", (chunk) => {
data += chunk
})
res.on("end", () => {
resolve({
statusCode: res.statusCode,
headers: res.headers,
body: data,
})
})
})
.on("error", (error) => {
reject(error)
})
})
}
/**
* Fetches a single page of contributors from GitHub API
* @param {string} url The API URL to fetch
* @returns {Promise<Object>} Object containing contributors and pagination links
*/
async function fetchContributorsPage(url) {
try {
// Make the HTTP request
const response = await httpGet(url, options)
// Check for successful response
if (response.statusCode !== 200) {
throw new Error(`GitHub API request failed with status code: ${response.statusCode}`)
}
// Parse the Link header for pagination
const linkHeader = response.headers.link
const links = parseLinkHeader(linkHeader)
// Parse the JSON response
const contributors = JSON.parse(response.body)
return { contributors, links }
} catch (error) {
throw new Error(`Failed to fetch contributors page: ${error.message}`)
}
}
/**
* Fetches all contributors data from GitHub API (handling pagination)
* @returns {Promise<Array>} Array of all contributor objects
*/
async function fetchContributors() {
let allContributors = []
let currentUrl = GITHUB_API_URL
let pageCount = 1
// Loop through all pages of contributors
while (currentUrl) {
console.log(`Fetching contributors page ${pageCount}...`)
const { contributors, links } = await fetchContributorsPage(currentUrl)
allContributors = allContributors.concat(contributors)
// Move to the next page if it exists
currentUrl = links.next
pageCount++
}
console.log(`Fetched ${allContributors.length} contributors from ${pageCount - 1} pages`)
return allContributors
}
/**
* Reads the README.md file
* @returns {Promise<string>} README content
*/
async function readReadme() {
try {
return await readFileAsync(README_PATH, "utf8")
} catch (err) {
throw new Error(`Failed to read README.md: ${err.message}`)
}
}
/**
* Creates HTML for the contributors section
* @param {Array} contributors Array of contributor objects from GitHub API
* @returns {string} HTML for contributors section
*/
const EXCLUDED_LOGIN_SUBSTRINGS = ['[bot]', 'R00-B0T'];
const EXCLUDED_LOGIN_EXACTS = ['cursor', 'roomote'];
function formatContributorsSection(contributors) {
// Filter out GitHub Actions bot, cursor, and roomote
const filteredContributors = contributors.filter((c) =>
!EXCLUDED_LOGIN_SUBSTRINGS.some(sub => c.login.includes(sub)) &&
!EXCLUDED_LOGIN_EXACTS.includes(c.login)
)
// Start building with Markdown table format
let markdown = `${START_MARKER}
`
// Number of columns in the table
const COLUMNS = 6
// Create contributor cell HTML
const createCell = (contributor) => {
return `<a href="${contributor.html_url}"><img src="${contributor.avatar_url}" width="100" height="100" alt="${contributor.login}"/><br /><sub><b>${contributor.login}</b></sub></a>`
}
if (filteredContributors.length > 0) {
// Table header is the first row of contributors
const headerCells = filteredContributors.slice(0, COLUMNS).map(createCell)
// Fill any empty cells in header row
while (headerCells.length < COLUMNS) {
headerCells.push(" ")
}
// Add header row
markdown += `|${headerCells.join("|")}|\n`
// Add alignment row
markdown += "|"
for (let i = 0; i < COLUMNS; i++) {
markdown += ":---:|"
}
markdown += "\n"
// Add remaining contributor rows starting with the second batch
for (let i = COLUMNS; i < filteredContributors.length; i += COLUMNS) {
const rowContributors = filteredContributors.slice(i, i + COLUMNS)
// Create cells for each contributor in this row
const cells = rowContributors.map(createCell)
// Fill any empty cells to maintain table structure
while (cells.length < COLUMNS) {
cells.push(" ")
}
// Add row to the table
markdown += `|${cells.join("|")}|\n`
}
}
markdown += `${END_MARKER}`
return markdown
}
/**
* Updates the README.md file with contributors section
* @param {string} readmeContent Original README content
* @param {string} contributorsSection HTML for contributors section
* @returns {Promise<void>}
*/
async function updateReadme(readmeContent, contributorsSection) {
// Find existing contributors section markers
const startPos = readmeContent.indexOf(START_MARKER)
const endPos = readmeContent.indexOf(END_MARKER)
if (startPos === -1 || endPos === -1) {
console.warn("Warning: Could not find contributors section markers in README.md")
console.warn("Skipping update - please add markers to enable automatic updates.")
return
}
// Replace existing section, trimming whitespace at section boundaries
const beforeSection = readmeContent.substring(0, startPos).trimEnd()
const afterSection = readmeContent.substring(endPos + END_MARKER.length).trimStart()
// Ensure single newline separators between sections
const updatedContent = beforeSection + "\n\n" + contributorsSection.trim() + "\n\n" + afterSection
await writeReadme(updatedContent)
}
/**
* Writes updated content to README.md
* @param {string} content Updated README content
* @returns {Promise<void>}
*/
async function writeReadme(content) {
try {
await writeFileAsync(README_PATH, content, "utf8")
} catch (err) {
throw new Error(`Failed to write updated README.md: ${err.message}`)
}
}
/**
* Finds all localized README files in the locales directory
* @returns {Promise<string[]>} Array of README file paths
*/
async function findLocalizedReadmes() {
const readmeFiles = []
// Check if locales directory exists
if (!fs.existsSync(LOCALES_DIR)) {
// No localized READMEs found
return readmeFiles
}
// Get all language subdirectories
const languageDirs = fs
.readdirSync(LOCALES_DIR, { withFileTypes: true })
.filter((dirent) => dirent.isDirectory())
.map((dirent) => dirent.name)
// Add all localized READMEs to the list
for (const langDir of languageDirs) {
const readmePath = path.join(LOCALES_DIR, langDir, "README.md")
if (fs.existsSync(readmePath)) {
readmeFiles.push(readmePath)
}
}
return readmeFiles
}
/**
* Updates a localized README file with contributors section
* @param {string} filePath Path to the README file
* @param {string} contributorsSection HTML for contributors section
* @returns {Promise<void>}
*/
async function updateLocalizedReadme(filePath, contributorsSection) {
try {
// Read the file content
const readmeContent = await readFileAsync(filePath, "utf8")
// Find existing contributors section markers
const startPos = readmeContent.indexOf(START_MARKER)
const endPos = readmeContent.indexOf(END_MARKER)
if (startPos === -1 || endPos === -1) {
console.warn(`Warning: Could not find contributors section markers in ${filePath}`)
console.warn(`Skipping update for ${filePath}`)
return
}
// Replace existing section, trimming whitespace at section boundaries
const beforeSection = readmeContent.substring(0, startPos).trimEnd()
const afterSection = readmeContent.substring(endPos + END_MARKER.length).trimStart()
// Ensure single newline separators between sections
const updatedContent = beforeSection + "\n\n" + contributorsSection.trim() + "\n\n" + afterSection
// Write the updated content
await writeFileAsync(filePath, updatedContent, "utf8")
console.log(`Updated ${filePath}`)
} catch (err) {
console.warn(`Warning: Could not update ${filePath}: ${err.message}`)
}
}
/**
* Main function that orchestrates the update process
*/
async function main() {
try {
// Fetch contributors from GitHub (now handles pagination)
const contributors = await fetchContributors()
console.log(`Total contributors: ${contributors.length}`)
// Generate contributors section
const contributorsSection = formatContributorsSection(contributors)
// Update main README
const readmeContent = await readReadme()
await updateReadme(readmeContent, contributorsSection)
console.log(`Updated ${README_PATH}`)
// Find and update all localized README files
const localizedReadmes = await findLocalizedReadmes()
console.log(`Found ${localizedReadmes.length} localized README files`)
// Update each localized README
for (const readmePath of localizedReadmes) {
await updateLocalizedReadme(readmePath, contributorsSection)
}
console.log("Contributors section update complete")
} catch (error) {
console.error(`Error: ${error.message}`)
process.exit(1)
}
}
// Run the script
main()

27
src/api/index.ts
View file

@ -1,6 +1,7 @@
import { Anthropic } from "@anthropic-ai/sdk"
import OpenAI from "openai"
import type { ProviderSettings, ModelInfo } from "@roo-code/types"
import type { ProviderSettings, ModelInfo, ToolProtocol } from "@roo-code/types"
import { ApiStream } from "./transform/stream"
@ -63,6 +64,30 @@ export interface ApiHandlerCreateMessageMetadata {
* - Unbound: Sent in unbound_metadata
*/
mode?: string
suppressPreviousResponseId?: boolean
/**
* Controls whether the response should be stored for 30 days in OpenAI's Responses API.
* When true (default), responses are stored and can be referenced in future requests
* using the previous_response_id for efficient conversation continuity.
* Set to false to opt out of response storage for privacy or compliance reasons.
* @default true
*/
store?: boolean
/**
* Optional array of tool definitions to pass to the model.
* For OpenAI-compatible providers, these are ChatCompletionTool definitions.
*/
tools?: OpenAI.Chat.ChatCompletionTool[]
/**
* Controls which (if any) tool is called by the model.
* Can be "none", "auto", "required", or a specific tool choice.
*/
tool_choice?: OpenAI.Chat.ChatCompletionCreateParams["tool_choice"]
/**
* The tool protocol being used (XML or Native).
* Used by providers to determine whether to include native tool definitions.
*/
toolProtocol?: ToolProtocol
}
export interface ApiHandler {

37
src/api/providers/__tests__/gemini.spec.ts
View file

@ -7,7 +7,7 @@ import { type ModelInfo, geminiDefaultModelId } from "@roo-code/types"
import { t } from "i18next"
import { GeminiHandler } from "../gemini"
const GEMINI_20_FLASH_THINKING_NAME = "gemini-2.0-flash-thinking-exp-1219"
const GEMINI_MODEL_NAME = geminiDefaultModelId
describe("GeminiHandler", () => {
let handler: GeminiHandler
@ -20,7 +20,7 @@ describe("GeminiHandler", () => {
handler = new GeminiHandler({
apiKey: "test-key",
apiModelId: GEMINI_20_FLASH_THINKING_NAME,
apiModelId: GEMINI_MODEL_NAME,
geminiApiKey: "test-key",
})
@ -37,7 +37,7 @@ describe("GeminiHandler", () => {
describe("constructor", () => {
it("should initialize with provided config", () => {
expect(handler["options"].geminiApiKey).toBe("test-key")
expect(handler["options"].apiModelId).toBe(GEMINI_20_FLASH_THINKING_NAME)
expect(handler["options"].apiModelId).toBe(GEMINI_MODEL_NAME)
})
})
@ -76,14 +76,14 @@ describe("GeminiHandler", () => {
expect(chunks.length).toBe(3)
expect(chunks[0]).toEqual({ type: "text", text: "Hello" })
expect(chunks[1]).toEqual({ type: "text", text: " world!" })
expect(chunks[2]).toEqual({ type: "usage", inputTokens: 10, outputTokens: 5 })
expect(chunks[2]).toMatchObject({ type: "usage", inputTokens: 10, outputTokens: 5 })
// Verify the call to generateContentStream
expect(handler["client"].models.generateContentStream).toHaveBeenCalledWith(
expect.objectContaining({
model: GEMINI_20_FLASH_THINKING_NAME,
model: GEMINI_MODEL_NAME,
config: expect.objectContaining({
temperature: 0,
temperature: 1,
systemInstruction: systemPrompt,
}),
}),
@ -116,11 +116,11 @@ describe("GeminiHandler", () => {
// Verify the call to generateContent
expect(handler["client"].models.generateContent).toHaveBeenCalledWith({
model: GEMINI_20_FLASH_THINKING_NAME,
model: GEMINI_MODEL_NAME,
contents: [{ role: "user", parts: [{ text: "Test prompt" }] }],
config: {
httpOptions: undefined,
temperature: 0,
temperature: 1,
},
})
})
@ -148,10 +148,8 @@ describe("GeminiHandler", () => {
describe("getModel", () => {
it("should return correct model info", () => {
const modelInfo = handler.getModel()
expect(modelInfo.id).toBe(GEMINI_20_FLASH_THINKING_NAME)
expect(modelInfo.id).toBe(GEMINI_MODEL_NAME)
expect(modelInfo.info).toBeDefined()
expect(modelInfo.info.maxTokens).toBe(8192)
expect(modelInfo.info.contextWindow).toBe(32_767)
})
it("should return default model if invalid model specified", () => {
@ -208,23 +206,6 @@ describe("GeminiHandler", () => {
expect(handler.calculateCost({ info: mockInfo, inputTokens: 0, outputTokens })).toBeCloseTo(expectedCost)
})
it("should calculate cost with cache write tokens", () => {
const inputTokens = 10000
const outputTokens = 20000
const cacheWriteTokens = 5000
const CACHE_TTL = 5 // Match the constant in gemini.ts
// Added non-null assertions (!)
const expectedInputCost = (inputTokens / 1_000_000) * mockInfo.inputPrice!
const expectedOutputCost = (outputTokens / 1_000_000) * mockInfo.outputPrice!
const expectedCacheWriteCost =
mockInfo.cacheWritesPrice! * (cacheWriteTokens / 1_000_000) * (CACHE_TTL / 60)
const expectedCost = expectedInputCost + expectedOutputCost + expectedCacheWriteCost
const cost = handler.calculateCost({ info: mockInfo, inputTokens, outputTokens })
expect(cost).toBeCloseTo(expectedCost)
})
it("should calculate cost with cache read tokens", () => {
const inputTokens = 10000 // Total logical input
const outputTokens = 20000

45
src/api/providers/__tests__/openai-native-usage.spec.ts
View file

@ -344,6 +344,51 @@ describe("OpenAiNativeHandler - normalizeUsage", () => {
})
})
describe("OpenAiNativeHandler - prompt cache retention", () => {
let handler: OpenAiNativeHandler
beforeEach(() => {
handler = new OpenAiNativeHandler({
openAiNativeApiKey: "test-key",
})
})
const buildRequestBodyForModel = (modelId: string) => {
// Force the handler to use the requested model ID
;(handler as any).options.apiModelId = modelId
const model = handler.getModel()
// Minimal formatted input/systemPrompt/verbosity/metadata for building the body
return (handler as any).buildRequestBody(model, [], "", model.verbosity, undefined, undefined)
}
it("should set prompt_cache_retention=24h for gpt-5.1 models that support prompt caching", () => {
const body = buildRequestBodyForModel("gpt-5.1")
expect(body.prompt_cache_retention).toBe("24h")
const codexBody = buildRequestBodyForModel("gpt-5.1-codex")
expect(codexBody.prompt_cache_retention).toBe("24h")
const codexMiniBody = buildRequestBodyForModel("gpt-5.1-codex-mini")
expect(codexMiniBody.prompt_cache_retention).toBe("24h")
})
it("should not set prompt_cache_retention for non-gpt-5.1 models even if they support prompt caching", () => {
const body = buildRequestBodyForModel("gpt-5")
expect(body.prompt_cache_retention).toBeUndefined()
const fourOBody = buildRequestBodyForModel("gpt-4o")
expect(fourOBody.prompt_cache_retention).toBeUndefined()
})
it("should not set prompt_cache_retention when the model does not support prompt caching", () => {
const modelId = "codex-mini-latest"
expect(openAiNativeModels[modelId as keyof typeof openAiNativeModels].supportsPromptCache).toBe(false)
const body = buildRequestBodyForModel(modelId)
expect(body.prompt_cache_retention).toBeUndefined()
})
})
describe("cost calculation", () => {
it("should pass total input tokens to calculateApiCostOpenAI", () => {
const usage = {

78
src/api/providers/__tests__/openai-native.spec.ts
View file

@ -159,6 +159,9 @@ describe("OpenAiNativeHandler", () => {
},
],
}),
expect.objectContaining({
signal: expect.any(Object),
}),
)
})
@ -202,7 +205,7 @@ describe("OpenAiNativeHandler", () => {
openAiNativeApiKey: "test-api-key",
})
const modelInfo = handlerWithoutModel.getModel()
expect(modelInfo.id).toBe("gpt-5-2025-08-07") // Default model
expect(modelInfo.id).toBe("gpt-5.1") // Default model
expect(modelInfo.info).toBeDefined()
})
})
@ -247,7 +250,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
})
const stream = handler.createMessage(systemPrompt, messages)
@ -271,7 +274,7 @@ describe("OpenAiNativeHandler", () => {
)
const body1 = (mockFetch.mock.calls[0][1] as any).body as string
const parsedBody = JSON.parse(body1)
expect(parsedBody.model).toBe("gpt-5-2025-08-07")
expect(parsedBody.model).toBe("gpt-5.1")
expect(parsedBody.instructions).toBe("You are a helpful assistant.")
// Now using structured format with content arrays (no system prompt in input; it's provided via `instructions`)
expect(parsedBody.input).toEqual([
@ -399,7 +402,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
verbosity: "low", // Set verbosity through options
})
@ -442,7 +445,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
reasoningEffort: "minimal" as any, // GPT-5 supports minimal
})
@ -461,6 +464,44 @@ describe("OpenAiNativeHandler", () => {
)
})
it("should omit reasoning when selection is 'disable'", async () => {
// Mock fetch for Responses API
const mockFetch = vitest.fn().mockResolvedValue({
ok: true,
body: new ReadableStream({
start(controller) {
controller.enqueue(
new TextEncoder().encode(
'data: {"type":"response.output_item.added","item":{"type":"text","text":"No reasoning"}}\n\n',
),
)
controller.enqueue(new TextEncoder().encode("data: [DONE]\n\n"))
controller.close()
},
}),
})
global.fetch = mockFetch as any
// Mock SDK to fail
mockResponsesCreate.mockRejectedValue(new Error("SDK not available"))
const handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5.1",
reasoningEffort: "disable" as any,
})
const stream = handler.createMessage(systemPrompt, messages)
for await (const _ of stream) {
// drain
}
const bodyStr = (mockFetch.mock.calls[0][1] as any).body as string
const parsed = JSON.parse(bodyStr)
expect(parsed.reasoning).toBeUndefined()
expect(parsed.include).toBeUndefined()
})
it("should support low reasoning effort for GPT-5", async () => {
// Mock fetch for Responses API
const mockFetch = vitest.fn().mockResolvedValue({
@ -484,7 +525,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
reasoningEffort: "low",
})
@ -503,7 +544,7 @@ describe("OpenAiNativeHandler", () => {
)
const body2 = (mockFetch.mock.calls[0][1] as any).body as string
const parsedBody = JSON.parse(body2)
expect(parsedBody.model).toBe("gpt-5-2025-08-07")
expect(parsedBody.model).toBe("gpt-5.1")
expect(parsedBody.reasoning?.effort).toBe("low")
expect(parsedBody.reasoning?.summary).toBe("auto")
expect(parsedBody.text?.verbosity).toBe("medium")
@ -535,7 +576,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
verbosity: "high",
reasoningEffort: "minimal" as any,
})
@ -555,7 +596,7 @@ describe("OpenAiNativeHandler", () => {
)
const body3 = (mockFetch.mock.calls[0][1] as any).body as string
const parsedBody = JSON.parse(body3)
expect(parsedBody.model).toBe("gpt-5-2025-08-07")
expect(parsedBody.model).toBe("gpt-5.1")
expect(parsedBody.reasoning?.effort).toBe("minimal")
expect(parsedBody.reasoning?.summary).toBe("auto")
expect(parsedBody.text?.verbosity).toBe("high")
@ -613,7 +654,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
})
const stream = handler.createMessage(systemPrompt, messages)
@ -669,7 +710,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
})
const stream = handler.createMessage(systemPrompt, messages)
@ -714,7 +755,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
})
const stream = handler.createMessage(systemPrompt, messages)
@ -755,7 +796,7 @@ describe("OpenAiNativeHandler", () => {
const gpt5Handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
})
const stream = gpt5Handler.createMessage(systemPrompt, messages, {
@ -800,7 +841,7 @@ describe("OpenAiNativeHandler", () => {
handler = new OpenAiNativeHandler({
...mockOptions,
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
})
const stream = handler.createMessage(systemPrompt, messages)
@ -850,7 +891,7 @@ describe("GPT-5 streaming event coverage (additional)", () => {
mockResponsesCreate.mockRejectedValue(new Error("SDK not available"))
const handler = new OpenAiNativeHandler({
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
openAiNativeApiKey: "test-api-key",
})
@ -893,7 +934,7 @@ describe("GPT-5 streaming event coverage (additional)", () => {
mockResponsesCreate.mockRejectedValue(new Error("SDK not available"))
const handler = new OpenAiNativeHandler({
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
openAiNativeApiKey: "test-api-key",
})
@ -942,7 +983,7 @@ describe("GPT-5 streaming event coverage (additional)", () => {
mockResponsesCreate.mockRejectedValue(new Error("SDK not available"))
const handler = new OpenAiNativeHandler({
apiModelId: "gpt-5-2025-08-07",
apiModelId: "gpt-5.1",
openAiNativeApiKey: "test-api-key",
})
@ -1098,6 +1139,9 @@ describe("GPT-5 streaming event coverage (additional)", () => {
stream: false,
store: false,
}),
expect.objectContaining({
signal: expect.any(Object),
}),
)
})

210
src/api/providers/__tests__/openai.spec.ts
View file

@ -157,6 +157,55 @@ describe("OpenAiHandler", () => {
expect(usageChunk?.outputTokens).toBe(5)
})
it("should handle tool calls in non-streaming mode", async () => {
mockCreate.mockResolvedValueOnce({
choices: [
{
message: {
role: "assistant",
content: null,
tool_calls: [
{
id: "call_1",
type: "function",
function: {
name: "test_tool",
arguments: '{"arg":"value"}',
},
},
],
},
finish_reason: "tool_calls",
},
],
usage: {
prompt_tokens: 10,
completion_tokens: 5,
total_tokens: 15,
},
})
const handler = new OpenAiHandler({
...mockOptions,
openAiStreamingEnabled: false,
})
const stream = handler.createMessage(systemPrompt, messages)
const chunks: any[] = []
for await (const chunk of stream) {
chunks.push(chunk)
}
const toolCallChunks = chunks.filter((chunk) => chunk.type === "tool_call")
expect(toolCallChunks).toHaveLength(1)
expect(toolCallChunks[0]).toEqual({
type: "tool_call",
id: "call_1",
name: "test_tool",
arguments: '{"arg":"value"}',
})
})
it("should handle streaming responses", async () => {
const stream = handler.createMessage(systemPrompt, messages)
const chunks: any[] = []
@ -170,6 +219,66 @@ describe("OpenAiHandler", () => {
expect(textChunks[0].text).toBe("Test response")
})
it("should handle tool calls in streaming responses", async () => {
mockCreate.mockImplementation(async (options) => {
return {
[Symbol.asyncIterator]: async function* () {
yield {
choices: [
{
delta: {
tool_calls: [
{
index: 0,
id: "call_1",
function: { name: "test_tool", arguments: "" },
},
],
},
finish_reason: null,
},
],
}
yield {
choices: [
{
delta: {
tool_calls: [{ index: 0, function: { arguments: '{"arg":' } }],
},
finish_reason: null,
},
],
}
yield {
choices: [
{
delta: {
tool_calls: [{ index: 0, function: { arguments: '"value"}' } }],
},
finish_reason: "tool_calls",
},
],
}
},
}
})
const stream = handler.createMessage(systemPrompt, messages)
const chunks: any[] = []
for await (const chunk of stream) {
chunks.push(chunk)
}
const toolCallChunks = chunks.filter((chunk) => chunk.type === "tool_call")
expect(toolCallChunks).toHaveLength(1)
expect(toolCallChunks[0]).toEqual({
type: "tool_call",
id: "call_1",
name: "test_tool",
arguments: '{"arg":"value"}',
})
})
it("should include reasoning_effort when reasoning effort is enabled", async () => {
const reasoningOptions: ApiHandlerOptions = {
...mockOptions,
@ -618,6 +727,58 @@ describe("OpenAiHandler", () => {
)
})
it("should handle tool calls with O3 model in streaming mode", async () => {
const o3Handler = new OpenAiHandler(o3Options)
mockCreate.mockImplementation(async (options) => {
return {
[Symbol.asyncIterator]: async function* () {
yield {
choices: [
{
delta: {
tool_calls: [
{
index: 0,
id: "call_1",
function: { name: "test_tool", arguments: "" },
},
],
},
finish_reason: null,
},
],
}
yield {
choices: [
{
delta: {
tool_calls: [{ index: 0, function: { arguments: "{}" } }],
},
finish_reason: "tool_calls",
},
],
}
},
}
})
const stream = o3Handler.createMessage("system", [])
const chunks: any[] = []
for await (const chunk of stream) {
chunks.push(chunk)
}
const toolCallChunks = chunks.filter((chunk) => chunk.type === "tool_call")
expect(toolCallChunks).toHaveLength(1)
expect(toolCallChunks[0]).toEqual({
type: "tool_call",
id: "call_1",
name: "test_tool",
arguments: "{}",
})
})
it("should handle O3 model with streaming and exclude max_tokens when includeMaxTokens is false", async () => {
const o3Handler = new OpenAiHandler({
...o3Options,
@ -705,6 +866,55 @@ describe("OpenAiHandler", () => {
expect(callArgs).not.toHaveProperty("stream")
})
it("should handle tool calls with O3 model in non-streaming mode", async () => {
const o3Handler = new OpenAiHandler({
...o3Options,
openAiStreamingEnabled: false,
})
mockCreate.mockResolvedValueOnce({
choices: [
{
message: {
role: "assistant",
content: null,
tool_calls: [
{
id: "call_1",
type: "function",
function: {
name: "test_tool",
arguments: "{}",
},
},
],
},
finish_reason: "tool_calls",
},
],
usage: {
prompt_tokens: 10,
completion_tokens: 5,
total_tokens: 15,
},
})
const stream = o3Handler.createMessage("system", [])
const chunks: any[] = []
for await (const chunk of stream) {
chunks.push(chunk)
}
const toolCallChunks = chunks.filter((chunk) => chunk.type === "tool_call")
expect(toolCallChunks).toHaveLength(1)
expect(toolCallChunks[0]).toEqual({
type: "tool_call",
id: "call_1",
name: "test_tool",
arguments: "{}",
})
})
it("should use default temperature of 0 when not specified for O3 models", async () => {
const o3Handler = new OpenAiHandler({
...o3Options,

2
src/api/providers/__tests__/openrouter.spec.ts
View file

@ -33,6 +33,7 @@ vitest.mock("../fetchers/modelCache", () => ({
contextWindow: 200000,
supportsImages: true,
supportsPromptCache: true,
supportsNativeTools: true,
inputPrice: 3,
outputPrice: 15,
cacheWritesPrice: 3.75,
@ -97,6 +98,7 @@ describe("OpenRouterHandler", () => {
const result = await handler.fetchModel()
expect(result.id).toBe("anthropic/claude-sonnet-4.5")
expect(result.info.supportsPromptCache).toBe(true)
expect(result.info.supportsNativeTools).toBe(true)
})
it("honors custom maxTokens for thinking models", async () => {

2
src/api/providers/__tests__/vertex.spec.ts
View file

@ -95,7 +95,7 @@ describe("VertexHandler", () => {
model: expect.any(String),
contents: [{ role: "user", parts: [{ text: "Test prompt" }] }],
config: expect.objectContaining({
temperature: 0,
temperature: 1,
}),
}),
)

36
src/api/providers/base-openai-compatible-provider.ts
View file

@ -90,6 +90,8 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
messages: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
stream: true,
stream_options: { include_usage: true },
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
try {
@ -115,6 +117,8 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
}) as const,
)
const toolCallAccumulator = new Map<number, { id: string; name: string; arguments: string }>()
for await (const chunk of stream) {
// Check for provider-specific error responses (e.g., MiniMax base_resp)
const chunkAny = chunk as any
@ -125,6 +129,7 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
}
const delta = chunk.choices?.[0]?.delta
const finishReason = chunk.choices?.[0]?.finish_reason
if (delta?.content) {
for (const processedChunk of matcher.update(delta.content)) {
@ -139,6 +144,37 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
}
}
if (delta?.tool_calls) {
for (const toolCall of delta.tool_calls) {
const index = toolCall.index
const existing = toolCallAccumulator.get(index)
if (existing) {
if (toolCall.function?.arguments) {
existing.arguments += toolCall.function.arguments
}
} else {
toolCallAccumulator.set(index, {
id: toolCall.id || "",
name: toolCall.function?.name || "",
arguments: toolCall.function?.arguments || "",
})
}
}
}
if (finishReason === "tool_calls") {
for (const toolCall of toolCallAccumulator.values()) {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.name,
arguments: toolCall.arguments,
}
}
toolCallAccumulator.clear()
}
if (chunk.usage) {
yield {
type: "usage",

69
src/api/providers/base-provider.ts
View file

@ -18,6 +18,75 @@ export abstract class BaseProvider implements ApiHandler {
abstract getModel(): { id: string; info: ModelInfo }
/**
* Converts an array of tools to be compatible with OpenAI's strict mode.
* Filters for function tools and applies schema conversion to their parameters.
*/
protected convertToolsForOpenAI(tools: any[] | undefined): any[] | undefined {
if (!tools) {
return undefined
}
return tools.map((tool) =>
tool.type === "function"
? {
...tool,
function: {
...tool.function,
parameters: this.convertToolSchemaForOpenAI(tool.function.parameters),
},
}
: tool,
)
}
/**
* Converts tool schemas to be compatible with OpenAI's strict mode by:
* - Ensuring all properties are in the required array (strict mode requirement)
* - Converting nullable types (["type", "null"]) to non-nullable ("type")
* - Recursively processing nested objects and arrays
*
* This matches the behavior of ensureAllRequired in openai-native.ts
*/
protected convertToolSchemaForOpenAI(schema: any): any {
if (!schema || typeof schema !== "object" || schema.type !== "object") {
return schema
}
const result = { ...schema }
if (result.properties) {
const allKeys = Object.keys(result.properties)
// OpenAI strict mode requires ALL properties to be in required array
result.required = allKeys
// Recursively process nested objects and convert nullable types
const newProps = { ...result.properties }
for (const key of allKeys) {
const prop = newProps[key]
// Handle nullable types by removing null
if (prop && Array.isArray(prop.type) && prop.type.includes("null")) {
const nonNullTypes = prop.type.filter((t: string) => t !== "null")
prop.type = nonNullTypes.length === 1 ? nonNullTypes[0] : nonNullTypes
}
// Recursively process nested objects
if (prop && prop.type === "object") {
newProps[key] = this.convertToolSchemaForOpenAI(prop)
} else if (prop && prop.type === "array" && prop.items?.type === "object") {
newProps[key] = {
...prop,
items: this.convertToolSchemaForOpenAI(prop.items),
}
}
}
result.properties = newProps
}
return result
}
/**
* Default token counting implementation using tiktoken.
* Providers can override this to use their native token counting endpoints.

7
src/api/providers/featherless.ts
View file

@ -1,4 +1,9 @@
import { DEEP_SEEK_DEFAULT_TEMPERATURE, type FeatherlessModelId, featherlessDefaultModelId, featherlessModels } from "@roo-code/types"
import {
DEEP_SEEK_DEFAULT_TEMPERATURE,
type FeatherlessModelId,
featherlessDefaultModelId,
featherlessModels,
} from "@roo-code/types"
import { Anthropic } from "@anthropic-ai/sdk"
import OpenAI from "openai"

4
src/api/providers/fetchers/__tests__/openrouter.spec.ts
View file

@ -28,6 +28,7 @@ describe("OpenRouter API", () => {
description: expect.any(String),
supportsReasoningBudget: false,
supportsReasoningEffort: false,
supportsNativeTools: true,
supportedParameters: ["max_tokens", "temperature", "reasoning", "include_reasoning"],
})
@ -44,6 +45,7 @@ describe("OpenRouter API", () => {
supportsReasoningBudget: true,
requiredReasoningBudget: true,
supportsReasoningEffort: true,
supportsNativeTools: true,
supportedParameters: ["max_tokens", "temperature", "reasoning", "include_reasoning"],
})
@ -96,6 +98,7 @@ describe("OpenRouter API", () => {
cacheReadsPrice: 0.31,
description: undefined,
supportsReasoningEffort: undefined,
supportsNativeTools: undefined,
supportedParameters: undefined,
},
"google-ai-studio": {
@ -110,6 +113,7 @@ describe("OpenRouter API", () => {
cacheReadsPrice: 0.31,
description: undefined,
supportsReasoningEffort: undefined,
supportsNativeTools: undefined,
supportedParameters: undefined,
},
})

3
src/api/providers/fetchers/__tests__/roo.spec.ts
View file

@ -68,6 +68,7 @@ describe("getRooModels", () => {
supportsImages: true,
supportsReasoningEffort: true,
requiredReasoningEffort: false,
supportsNativeTools: false,
supportsPromptCache: true,
inputPrice: 100, // 0.0001 * 1_000_000
outputPrice: 200, // 0.0002 * 1_000_000
@ -116,6 +117,7 @@ describe("getRooModels", () => {
supportsImages: false,
supportsReasoningEffort: true,
requiredReasoningEffort: true,
supportsNativeTools: false,
supportsPromptCache: false,
inputPrice: 100, // 0.0001 * 1_000_000
outputPrice: 200, // 0.0002 * 1_000_000
@ -162,6 +164,7 @@ describe("getRooModels", () => {
supportsImages: false,
supportsReasoningEffort: false,
requiredReasoningEffort: false,
supportsNativeTools: false,
supportsPromptCache: false,
inputPrice: 100, // 0.0001 * 1_000_000
outputPrice: 200, // 0.0002 * 1_000_000

5
src/api/providers/fetchers/openrouter.ts
View file

@ -115,7 +115,7 @@ export async function getOpenRouterModels(options?: ApiHandlerOptions): Promise<
continue
}
models[id] = parseOpenRouterModel({
const parsedModel = parseOpenRouterModel({
id,
model,
inputModality: architecture?.input_modalities,
@ -123,6 +123,8 @@ export async function getOpenRouterModels(options?: ApiHandlerOptions): Promise<
maxTokens: top_provider?.max_completion_tokens,
supportedParameters: supported_parameters,
})
models[id] = parsedModel
}
} catch (error) {
console.error(
@ -216,6 +218,7 @@ export const parseOpenRouterModel = ({
cacheReadsPrice,
description: model.description,
supportsReasoningEffort: supportedParameters ? supportedParameters.includes("reasoning") : undefined,
supportsNativeTools: supportedParameters ? supportedParameters.includes("tools") : undefined,
supportedParameters: supportedParameters ? supportedParameters.filter(isModelParameter) : undefined,
}

9
src/api/providers/fetchers/roo.ts
View file

@ -92,18 +92,23 @@ export async function getRooModels(baseUrl: string, apiKey?: string): Promise<Mo
// Determine if the model requires reasoning effort based on tags
const requiredReasoningEffort = tags.includes("reasoning-required")
// Determine if the model supports native tool calling based on tags
const supportsNativeTools = tags.includes("tool-use")
// Parse pricing (API returns strings, convert to numbers)
const inputPrice = parseApiPrice(pricing.input)
const outputPrice = parseApiPrice(pricing.output)
const cacheReadPrice = pricing.input_cache_read ? parseApiPrice(pricing.input_cache_read) : undefined
const cacheWritePrice = pricing.input_cache_write ? parseApiPrice(pricing.input_cache_write) : undefined
models[modelId] = {
// Build the base model info from API response
const baseModelInfo = {
maxTokens,
contextWindow,
supportsImages,
supportsReasoningEffort,
requiredReasoningEffort,
supportsNativeTools,
supportsPromptCache: Boolean(cacheReadPrice !== undefined),
inputPrice,
outputPrice,
@ -113,6 +118,8 @@ export async function getRooModels(baseUrl: string, apiKey?: string): Promise<Mo
deprecated: model.deprecated || false,
isFree: tags.includes("free"),
}
models[modelId] = baseModelInfo
}
return models

219
src/api/providers/gemini.ts
View file

@ -5,6 +5,8 @@ import {
type GenerateContentParameters,
type GenerateContentConfig,
type GroundingMetadata,
FunctionCallingConfigMode,
Content,
} from "@google/genai"
import type { JWTInput } from "google-auth-library"
@ -29,6 +31,8 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
protected options: ApiHandlerOptions
private client: GoogleGenAI
private lastThoughtSignature?: string
private lastResponseId?: string
constructor({ isVertex, ...options }: GeminiHandlerOptions) {
super()
@ -66,36 +70,143 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
metadata?: ApiHandlerCreateMessageMetadata,
): ApiStream {
const { id: model, info, reasoning: thinkingConfig, maxTokens } = this.getModel()
// Reset per-request metadata that we persist into apiConversationHistory.
this.lastThoughtSignature = undefined
this.lastResponseId = undefined
const contents = messages.map(convertAnthropicMessageToGemini)
// For hybrid/budget reasoning models (e.g. Gemini 2.5 Pro), respect user-configured
// modelMaxTokens so the ThinkingBudget slider can control the cap. For effort-only or
// standard models (like gemini-3-pro-preview), ignore any stale modelMaxTokens and
// default to the model's computed maxTokens from getModelMaxOutputTokens.
const isHybridReasoningModel = info.supportsReasoningBudget || info.requiredReasoningBudget
const maxOutputTokens = isHybridReasoningModel
? (this.options.modelMaxTokens ?? maxTokens ?? undefined)
: (maxTokens ?? undefined)
// Only forward encrypted reasoning continuations (thoughtSignature) when we are
// using reasoning (thinkingConfig is present). Both effort-based (thinkingLevel)
// and budget-based (thinkingBudget) models require this for active loops.
const includeThoughtSignatures = Boolean(thinkingConfig)
// The message list can include provider-specific meta entries such as
// `{ type: "reasoning", ... }` that are intended only for providers like
// openai-native. Gemini should never see those; they are not valid
// Anthropic.MessageParam values and will cause failures (e.g. missing
// `content` for the converter). Filter them out here.
type ReasoningMetaLike = { type?: string }
const geminiMessages = messages.filter((message): message is Anthropic.Messages.MessageParam => {
const meta = message as ReasoningMetaLike
if (meta.type === "reasoning") {
return false
}
return true
})
// Build a map of tool IDs to names from previous messages
// This is needed because Anthropic's tool_result blocks only contain the ID,
// but Gemini requires the name in functionResponse
const toolIdToName = new Map<string, string>()
for (const message of messages) {
if (Array.isArray(message.content)) {
for (const block of message.content) {
if (block.type === "tool_use") {
toolIdToName.set(block.id, block.name)
}
}
}
}
const contents = geminiMessages
.map((message) => convertAnthropicMessageToGemini(message, { includeThoughtSignatures, toolIdToName }))
.flat()
const tools: GenerateContentConfig["tools"] = []
if (this.options.enableUrlContext) {
tools.push({ urlContext: {} })
// Google built-in tools (Grounding, URL Context) are currently mutually exclusive
// with function declarations in the Gemini API. If native function calling is
// used (Agent tools), we must prioritize it and skip built-in tools to avoid
// "Tool use with function calling is unsupported" (HTTP 400) errors.
if (metadata?.tools && metadata.tools.length > 0) {
tools.push({
functionDeclarations: metadata.tools.map((tool) => ({
name: (tool as any).function.name,
description: (tool as any).function.description,
parametersJsonSchema: (tool as any).function.parameters,
})),
})
} else {
if (this.options.enableUrlContext) {
tools.push({ urlContext: {} })
}
if (this.options.enableGrounding) {
tools.push({ googleSearch: {} })
}
}
if (this.options.enableGrounding) {
tools.push({ googleSearch: {} })
}
// Determine temperature respecting model capabilities and defaults:
// - If supportsTemperature is explicitly false, ignore user overrides
// and pin to the model's defaultTemperature (or omit if undefined).
// - Otherwise, allow the user setting to override, falling back to model default,
// then to 1 for Gemini provider default.
const supportsTemperature = info.supportsTemperature !== false
const temperatureConfig: number | undefined = supportsTemperature
? (this.options.modelTemperature ?? info.defaultTemperature ?? 1)
: info.defaultTemperature
const config: GenerateContentConfig = {
systemInstruction,
httpOptions: this.options.googleGeminiBaseUrl ? { baseUrl: this.options.googleGeminiBaseUrl } : undefined,
thinkingConfig,
maxOutputTokens: this.options.modelMaxTokens ?? maxTokens ?? undefined,
temperature: this.options.modelTemperature ?? 0,
maxOutputTokens,
temperature: temperatureConfig,
...(tools.length > 0 ? { tools } : {}),
}
const params: GenerateContentParameters = { model, contents, config }
if (metadata?.tool_choice) {
const choice = metadata.tool_choice
let mode: FunctionCallingConfigMode
let allowedFunctionNames: string[] | undefined
if (choice === "auto") {
mode = FunctionCallingConfigMode.AUTO
} else if (choice === "none") {
mode = FunctionCallingConfigMode.NONE
} else if (choice === "required") {
// "required" means the model must call at least one tool; Gemini uses ANY for this.
mode = FunctionCallingConfigMode.ANY
} else if (typeof choice === "object" && "function" in choice && choice.type === "function") {
mode = FunctionCallingConfigMode.ANY
allowedFunctionNames = [choice.function.name]
} else {
// Fall back to AUTO for unknown values to avoid unintentionally broadening tool access.
mode = FunctionCallingConfigMode.AUTO
}
config.toolConfig = {
functionCallingConfig: {
mode,
...(allowedFunctionNames ? { allowedFunctionNames } : {}),
},
}
}
const params: GenerateContentParameters = { model, contents, config }
try {
const result = await this.client.models.generateContentStream(params)
let lastUsageMetadata: GenerateContentResponseUsageMetadata | undefined
let pendingGroundingMetadata: GroundingMetadata | undefined
let finalResponse: { responseId?: string } | undefined
let toolCallCounter = 0
for await (const chunk of result) {
// Track the final structured response (per SDK pattern: candidate.finishReason)
if (chunk.candidates && chunk.candidates[0]?.finishReason) {
finalResponse = chunk as { responseId?: string }
}
// Process candidates and their parts to separate thoughts from content
if (chunk.candidates && chunk.candidates.length > 0) {
const candidate = chunk.candidates[0]
@ -105,12 +216,33 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
}
if (candidate.content && candidate.content.parts) {
for (const part of candidate.content.parts) {
for (const part of candidate.content.parts as Array<{
thought?: boolean
text?: string
thoughtSignature?: string
functionCall?: { name: string; args: Record<string, unknown> }
}>) {
// Capture thought signatures so they can be persisted into API history.
const thoughtSignature = part.thoughtSignature
// Persist encrypted reasoning when using reasoning. Both effort-based
// and budget-based models require this for active loops.
if (thinkingConfig && thoughtSignature) {
this.lastThoughtSignature = thoughtSignature
}
if (part.thought) {
// This is a thinking/reasoning part
if (part.text) {
yield { type: "reasoning", text: part.text }
}
} else if (part.functionCall) {
const callId = `${part.functionCall.name}-${toolCallCounter++}`
yield {
type: "tool_call",
id: callId,
name: part.functionCall.name,
arguments: JSON.stringify(part.functionCall.args),
}
} else {
// This is regular content
if (part.text) {
@ -131,6 +263,12 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
}
}
if (finalResponse?.responseId) {
// Capture responseId so Task.addToApiConversationHistory can store it
// alongside the assistant message in api_history.json.
this.lastResponseId = finalResponse.responseId
}
if (pendingGroundingMetadata) {
const sources = this.extractGroundingSources(pendingGroundingMetadata)
if (sources.length > 0) {
@ -150,7 +288,13 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
outputTokens,
cacheReadTokens,
reasoningTokens,
totalCost: this.calculateCost({ info, inputTokens, outputTokens, cacheReadTokens }),
totalCost: this.calculateCost({
info,
inputTokens,
outputTokens,
cacheReadTokens,
reasoningTokens,
}),
}
}
} catch (error) {
@ -166,7 +310,14 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
const modelId = this.options.apiModelId
let id = modelId && modelId in geminiModels ? (modelId as GeminiModelId) : geminiDefaultModelId
let info: ModelInfo = geminiModels[id]
const params = getModelParams({ format: "gemini", modelId: id, model: info, settings: this.options })
const params = getModelParams({
format: "gemini",
modelId: id,
model: info,
settings: this.options,
defaultTemperature: info.defaultTemperature ?? 1,
})
// The `:thinking` suffix indicates that the model is a "Hybrid"
// reasoning model and that reasoning is required to be enabled.
@ -211,7 +362,7 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
async completePrompt(prompt: string): Promise<string> {
try {
const { id: model } = this.getModel()
const { id: model, info } = this.getModel()
const tools: GenerateContentConfig["tools"] = []
if (this.options.enableUrlContext) {
@ -220,19 +371,27 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
if (this.options.enableGrounding) {
tools.push({ googleSearch: {} })
}
const supportsTemperature = info.supportsTemperature !== false
const temperatureConfig: number | undefined = supportsTemperature
? (this.options.modelTemperature ?? info.defaultTemperature ?? 1)
: info.defaultTemperature
const promptConfig: GenerateContentConfig = {
httpOptions: this.options.googleGeminiBaseUrl
? { baseUrl: this.options.googleGeminiBaseUrl }
: undefined,
temperature: this.options.modelTemperature ?? 0,
temperature: temperatureConfig,
...(tools.length > 0 ? { tools } : {}),
}
const result = await this.client.models.generateContent({
const request = {
model,
contents: [{ role: "user", parts: [{ text: prompt }] }],
config: promptConfig,
})
}
const result = await this.client.models.generateContent(request)
let text = result.text ?? ""
@ -258,10 +417,13 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
try {
const { id: model } = this.getModel()
const response = await this.client.models.countTokens({
const countTokensRequest = {
model,
contents: convertAnthropicContentToGemini(content),
})
// Token counting does not need encrypted continuation; always drop thoughtSignature.
contents: convertAnthropicContentToGemini(content, { includeThoughtSignatures: false }),
}
const response = await this.client.models.countTokens(countTokensRequest)
if (response.totalTokens === undefined) {
console.warn("Gemini token counting returned undefined, using fallback")
@ -275,16 +437,26 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
}
}
public getThoughtSignature(): string | undefined {
return this.lastThoughtSignature
}
public getResponseId(): string | undefined {
return this.lastResponseId
}
public calculateCost({
info,
inputTokens,
outputTokens,
cacheReadTokens = 0,
reasoningTokens = 0,
}: {
info: ModelInfo
inputTokens: number
outputTokens: number
cacheReadTokens?: number
reasoningTokens?: number
}) {
// For models with tiered pricing, prices might only be defined in tiers
let inputPrice = info.inputPrice
@ -316,23 +488,24 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
// Subtract the cached input tokens from the total input tokens.
const uncachedInputTokens = inputTokens - cacheReadTokens
// Bill both completion and reasoning ("thoughts") tokens as output.
const billedOutputTokens = outputTokens + reasoningTokens
let cacheReadCost = cacheReadTokens > 0 ? cacheReadsPrice * (cacheReadTokens / 1_000_000) : 0
const inputTokensCost = inputPrice * (uncachedInputTokens / 1_000_000)
const outputTokensCost = outputPrice * (outputTokens / 1_000_000)
const outputTokensCost = outputPrice * (billedOutputTokens / 1_000_000)
const totalCost = inputTokensCost + outputTokensCost + cacheReadCost
const trace: Record<string, { price: number; tokens: number; cost: number }> = {
input: { price: inputPrice, tokens: uncachedInputTokens, cost: inputTokensCost },
output: { price: outputPrice, tokens: outputTokens, cost: outputTokensCost },
output: { price: outputPrice, tokens: billedOutputTokens, cost: outputTokensCost },
}
if (cacheReadTokens > 0) {
trace.cacheRead = { price: cacheReadsPrice, tokens: cacheReadTokens, cost: cacheReadCost }
}
// console.log(`[GeminiHandler] calculateCost -> ${totalCost}`, trace)
return totalCost
}
}

402
src/api/providers/openai-native.ts
View file

@ -7,10 +7,9 @@ import {
OpenAiNativeModelId,
openAiNativeModels,
OPENAI_NATIVE_DEFAULT_TEMPERATURE,
GPT5_DEFAULT_TEMPERATURE,
type ReasoningEffort,
type VerbosityLevel,
type ReasoningEffortWithMinimal,
type ReasoningEffortExtended,
type ServiceTier,
} from "@roo-code/types"
@ -26,11 +25,6 @@ import type { SingleCompletionHandler, ApiHandlerCreateMessageMetadata } from ".
export type OpenAiNativeModel = ReturnType<OpenAiNativeHandler["getModel"]>
// GPT-5 specific types
// Constants for model identification
const GPT5_MODEL_PREFIX = "gpt-5"
export class OpenAiNativeHandler extends BaseProvider implements SingleCompletionHandler {
protected options: ApiHandlerOptions
private client: OpenAI
@ -40,6 +34,10 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
private lastResponseOutput: any[] | undefined
// Last top-level response id from Responses API (for troubleshooting)
private lastResponseId: string | undefined
// Accumulate partial tool calls: call_id -> { name, arguments }
private currentToolCalls: Map<string, { name: string; arguments: string }> = new Map()
// Abort controller for cancelling ongoing requests
private abortController?: AbortController
// Event types handled by the shared event processor to avoid duplication
private readonly coreHandledEventTypes = new Set<string>([
@ -53,14 +51,19 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
"response.output_item.added",
"response.done",
"response.completed",
"response.tool_call_arguments.delta",
"response.function_call_arguments.delta",
"response.tool_call_arguments.done",
"response.function_call_arguments.done",
])
constructor(options: ApiHandlerOptions) {
super()
this.options = options
// Default to including reasoning.summary: "auto" for GPT‑5 unless explicitly disabled
if (this.options.enableGpt5ReasoningSummary === undefined) {
this.options.enableGpt5ReasoningSummary = true
// Default to including reasoning.summary: "auto" for models that support Responses API
// reasoning summaries unless explicitly disabled.
if (this.options.enableResponsesReasoningSummary === undefined) {
this.options.enableResponsesReasoningSummary = true
}
const apiKey = this.options.openAiNativeApiKey ?? "not-provided"
this.client = new OpenAI({ baseURL: this.options.openAiNativeBaseUrl, apiKey })
@ -150,6 +153,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
this.lastResponseOutput = undefined
// Reset last response id for this request
this.lastResponseId = undefined
// Reset tool call accumulator
this.currentToolCalls.clear()
// Use Responses API for ALL models
const { verbosity, reasoning } = this.getModel()
@ -170,9 +175,6 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
metadata,
)
// Temporary debug logging
// console.log("[OpenAI Native] Request body:", requestBody)
// Make the request (pass systemPrompt and messages for potential retry)
yield* this.executeRequest(requestBody, model, metadata, systemPrompt, messages)
}
@ -182,17 +184,49 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
formattedInput: any,
systemPrompt: string,
verbosity: any,
reasoningEffort: ReasoningEffortWithMinimal | undefined,
reasoningEffort: ReasoningEffortExtended | undefined,
metadata?: ApiHandlerCreateMessageMetadata,
): any {
// Build a request body
// Ensure we explicitly pass max_output_tokens for GPT‑5 based on Roo's reserved model response calculation
// Ensure all properties are in the required array for OpenAI's strict mode
// This recursively processes nested objects and array items
const ensureAllRequired = (schema: any): any => {
if (!schema || typeof schema !== "object" || schema.type !== "object") {
return schema
}
const result = { ...schema }
if (result.properties) {
const allKeys = Object.keys(result.properties)
result.required = allKeys
// Recursively process nested objects
const newProps = { ...result.properties }
for (const key of allKeys) {
const prop = newProps[key]
if (prop.type === "object") {
newProps[key] = ensureAllRequired(prop)
} else if (prop.type === "array" && prop.items?.type === "object") {
newProps[key] = {
...prop,
items: ensureAllRequired(prop.items),
}
}
}
result.properties = newProps
}
return result
}
// Build a request body for the OpenAI Responses API.
// Ensure we explicitly pass max_output_tokens based on Roo's reserved model response calculation
// so requests do not default to very large limits (e.g., 120k).
interface Gpt5RequestBody {
interface ResponsesRequestBody {
model: string
input: Array<{ role: "user" | "assistant"; content: any[] } | { type: string; content: string }>
stream: boolean
reasoning?: { effort?: ReasoningEffortWithMinimal; summary?: "auto" }
reasoning?: { effort?: ReasoningEffortExtended; summary?: "auto" }
text?: { verbosity: VerbosityLevel }
temperature?: number
max_output_tokens?: number
@ -200,13 +234,26 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
instructions?: string
service_tier?: ServiceTier
include?: string[]
/** Prompt cache retention policy: "in_memory" (default) or "24h" for extended caching */
prompt_cache_retention?: "in_memory" | "24h"
tools?: Array<{
type: "function"
name: string
description?: string
parameters?: any
strict?: boolean
}>
tool_choice?: any
}
// Validate requested tier against model support; if not supported, omit.
const requestedTier = (this.options.openAiNativeServiceTier as ServiceTier | undefined) || undefined
const allowedTierNames = new Set(model.info.tiers?.map((t) => t.name).filter(Boolean) || [])
const body: Gpt5RequestBody = {
// Decide whether to enable extended prompt cache retention for this request
const promptCacheRetention = this.getPromptCacheRetention(model)
const body: ResponsesRequestBody = {
model: model.id,
input: formattedInput,
stream: true,
@ -216,22 +263,19 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
// Unlike Chat Completions, system/developer roles in input have no special semantics here.
// The official way to set system behavior is the top-level `instructions` field.
instructions: systemPrompt,
include: ["reasoning.encrypted_content"],
// Only include encrypted reasoning content when reasoning effort is set
...(reasoningEffort ? { include: ["reasoning.encrypted_content"] } : {}),
...(reasoningEffort
? {
reasoning: {
...(reasoningEffort ? { effort: reasoningEffort } : {}),
...(this.options.enableGpt5ReasoningSummary ? { summary: "auto" as const } : {}),
...(this.options.enableResponsesReasoningSummary ? { summary: "auto" as const } : {}),
},
}
: {}),
// Only include temperature if the model supports it
...(model.info.supportsTemperature !== false && {
temperature:
this.options.modelTemperature ??
(model.id.startsWith(GPT5_MODEL_PREFIX)
? GPT5_DEFAULT_TEMPERATURE
: OPENAI_NATIVE_DEFAULT_TEMPERATURE),
temperature: this.options.modelTemperature ?? OPENAI_NATIVE_DEFAULT_TEMPERATURE,
}),
// Explicitly include the calculated max output tokens.
// Use the per-request reserved output computed by Roo (params.maxTokens from getModelParams).
@ -241,6 +285,21 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
(requestedTier === "default" || allowedTierNames.has(requestedTier)) && {
service_tier: requestedTier,
}),
// Enable extended prompt cache retention for models that support it.
// This uses the OpenAI Responses API `prompt_cache_retention` parameter.
...(promptCacheRetention ? { prompt_cache_retention: promptCacheRetention } : {}),
...(metadata?.tools && {
tools: metadata.tools
.filter((tool) => tool.type === "function")
.map((tool) => ({
type: "function",
name: tool.function.name,
description: tool.function.description,
parameters: ensureAllRequired(tool.function.parameters),
strict: true,
})),
}),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
// Include text.verbosity only when the model explicitly supports it
@ -258,9 +317,14 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
systemPrompt?: string,
messages?: Anthropic.Messages.MessageParam[],
): ApiStream {
// Create AbortController for cancellation
this.abortController = new AbortController()
try {
// Use the official SDK
const stream = (await (this.client as any).responses.create(requestBody)) as AsyncIterable<any>
const stream = (await (this.client as any).responses.create(requestBody, {
signal: this.abortController.signal,
})) as AsyncIterable<any>
if (typeof (stream as any)[Symbol.asyncIterator] !== "function") {
throw new Error(
@ -269,21 +333,27 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
}
for await (const event of stream) {
// Check if request was aborted
if (this.abortController.signal.aborted) {
break
}
for await (const outChunk of this.processEvent(event, model)) {
yield outChunk
}
}
} catch (sdkErr: any) {
// For errors, fallback to manual SSE via fetch
yield* this.makeGpt5ResponsesAPIRequest(requestBody, model, metadata, systemPrompt, messages)
yield* this.makeResponsesApiRequest(requestBody, model, metadata, systemPrompt, messages)
} finally {
this.abortController = undefined
}
}
private formatFullConversation(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): any {
// Format the entire conversation history for the Responses API using structured format
// This supports both text and images
// Messages already include reasoning items from API history, so we just need to format them
const formattedMessages: any[] = []
// The Responses API (like Realtime API) accepts a list of items, which can be messages, function calls, or function call outputs.
const formattedInput: any[] = []
// Do NOT embed the system prompt as a developer message in the Responses API input.
// The Responses API treats roles as free-form; use the top-level `instructions` field instead.
@ -293,48 +363,86 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
// Check if this is a reasoning item (already formatted in API history)
if ((message as any).type === "reasoning") {
// Pass through reasoning items as-is
formattedMessages.push(message)
formattedInput.push(message)
continue
}
const role = message.role === "user" ? "user" : "assistant"
const content: any[] = []
if (message.role === "user") {
const content: any[] = []
const toolResults: any[] = []
if (typeof message.content === "string") {
// For user messages, use input_text; for assistant messages, use output_text
if (role === "user") {
if (typeof message.content === "string") {
content.push({ type: "input_text", text: message.content })
} else {
content.push({ type: "output_text", text: message.content })
}
} else if (Array.isArray(message.content)) {
// For array content with potential images, format properly
for (const block of message.content) {
if (block.type === "text") {
// For user messages, use input_text; for assistant messages, use output_text
if (role === "user") {
content.push({ type: "input_text", text: (block as any).text })
} else {
content.push({ type: "output_text", text: (block as any).text })
} else if (Array.isArray(message.content)) {
for (const block of message.content) {
if (block.type === "text") {
content.push({ type: "input_text", text: block.text })
} else if (block.type === "image") {
const image = block as Anthropic.Messages.ImageBlockParam
const imageUrl = `data:${image.source.media_type};base64,${image.source.data}`
content.push({ type: "input_image", image_url: imageUrl })
} else if (block.type === "tool_result") {
// Map Anthropic tool_result to Responses API function_call_output item
const result =
typeof block.content === "string"
? block.content
: block.content?.map((c) => (c.type === "text" ? c.text : "")).join("") || ""
toolResults.push({
type: "function_call_output",
call_id: block.tool_use_id,
output: result,
})
}
} else if (block.type === "image") {
const image = block as Anthropic.Messages.ImageBlockParam
// Format image with proper data URL - images are always input_image
const imageUrl = `data:${image.source.media_type};base64,${image.source.data}`
content.push({ type: "input_image", image_url: imageUrl })
}
}
}
if (content.length > 0) {
formattedMessages.push({ role, content })
// Add user message first
if (content.length > 0) {
formattedInput.push({ role: "user", content })
}
// Add tool results as separate items
if (toolResults.length > 0) {
formattedInput.push(...toolResults)
}
} else if (message.role === "assistant") {
const content: any[] = []
const toolCalls: any[] = []
if (typeof message.content === "string") {
content.push({ type: "output_text", text: message.content })
} else if (Array.isArray(message.content)) {
for (const block of message.content) {
if (block.type === "text") {
content.push({ type: "output_text", text: block.text })
} else if (block.type === "tool_use") {
// Map Anthropic tool_use to Responses API function_call item
toolCalls.push({
type: "function_call",
call_id: block.id,
name: block.name,
arguments: JSON.stringify(block.input),
})
}
}
}
// Add assistant message if it has content
if (content.length > 0) {
formattedInput.push({ role: "assistant", content })
}
// Add tool calls as separate items
if (toolCalls.length > 0) {
formattedInput.push(...toolCalls)
}
}
}
return formattedMessages
return formattedInput
}
private async *makeGpt5ResponsesAPIRequest(
private async *makeResponsesApiRequest(
requestBody: any,
model: OpenAiNativeModel,
metadata?: ApiHandlerCreateMessageMetadata,
@ -345,6 +453,9 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
const baseUrl = this.options.openAiNativeBaseUrl || "https://api.openai.com"
const url = `${baseUrl}/v1/responses`
// Create AbortController for cancellation
this.abortController = new AbortController()
try {
const response = await fetch(url, {
method: "POST",
@ -354,12 +465,13 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
Accept: "text/event-stream",
},
body: JSON.stringify(requestBody),
signal: this.abortController.signal,
})
if (!response.ok) {
const errorText = await response.text()
let errorMessage = `GPT-5 API request failed (${response.status})`
let errorMessage = `OpenAI Responses API request failed (${response.status})`
let errorDetails = ""
// Try to parse error as JSON for better error messages
@ -429,6 +541,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
}
// Handle non-Error objects
throw new Error(`Unexpected error connecting to Responses API`)
} finally {
this.abortController = undefined
}
}
@ -449,6 +563,11 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
try {
while (true) {
// Check if request was aborted
if (this.abortController?.signal.aborted) {
break
}
const { done, value } = await reader.read()
if (done) break
@ -654,11 +773,16 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
// Output item completed
}
// Handle function/tool call events
else if (parsed.type === "response.function_call_arguments.delta") {
// Function call arguments streaming
// We could yield this as a special type if needed for tool usage
} else if (parsed.type === "response.function_call_arguments.done") {
// Function call completed
else if (
parsed.type === "response.function_call_arguments.delta" ||
parsed.type === "response.tool_call_arguments.delta" ||
parsed.type === "response.function_call_arguments.done" ||
parsed.type === "response.tool_call_arguments.done"
) {
// Delegated to processEvent (handles accumulation and completion)
for await (const outChunk of this.processEvent(parsed, model)) {
yield outChunk
}
}
// Handle MCP (Model Context Protocol) tool events
else if (parsed.type === "response.mcp_call_arguments.delta") {
@ -815,7 +939,7 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
}
}
// Usage for done/completed is already handled by processGpt5Event in SDK path.
// Usage for done/completed is already handled by processEvent in the SDK path.
// For SSE path, usage often arrives separately; avoid double-emitting here.
}
// These are structural or status events, we can just log them at a lower level or ignore.
@ -939,8 +1063,53 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
return
}
// Handle output item additions (SDK or Responses API alternative format)
if (event?.type === "response.output_item.added") {
// Handle tool/function call deltas and completion
if (
event?.type === "response.tool_call_arguments.delta" ||
event?.type === "response.function_call_arguments.delta"
) {
const callId = event.call_id || event.tool_call_id || event.id
if (callId) {
if (!this.currentToolCalls.has(callId)) {
this.currentToolCalls.set(callId, { name: "", arguments: "" })
}
const toolCall = this.currentToolCalls.get(callId)!
// Update name if present (usually in the first delta)
if (event.name || event.function_name) {
toolCall.name = event.name || event.function_name
}
// Append arguments delta
if (event.delta || event.arguments) {
toolCall.arguments += event.delta || event.arguments
}
}
return
}
if (
event?.type === "response.tool_call_arguments.done" ||
event?.type === "response.function_call_arguments.done"
) {
const callId = event.call_id || event.tool_call_id || event.id
if (callId && this.currentToolCalls.has(callId)) {
const toolCall = this.currentToolCalls.get(callId)!
// Yield the complete tool call
yield {
type: "tool_call",
id: callId,
name: toolCall.name,
arguments: toolCall.arguments,
}
// Remove from accumulator
this.currentToolCalls.delete(callId)
}
return
}
// Handle output item additions/completions (SDK or Responses API alternative format)
if (event?.type === "response.output_item.added" || event?.type === "response.output_item.done") {
const item = event?.item
if (item) {
if (item.type === "text" && item.text) {
@ -954,6 +1123,21 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
yield { type: "text", text: content.text }
}
}
} else if (
(item.type === "function_call" || item.type === "tool_call") &&
event.type === "response.output_item.done" // Only handle done events for tool calls to ensure arguments are complete
) {
// Handle complete tool/function call item
const callId = item.call_id || item.tool_call_id || item.id
if (callId && !this.currentToolCalls.has(callId)) {
const args = item.arguments || item.function?.arguments || item.function_arguments
yield {
type: "tool_call",
id: callId,
name: item.name || item.function?.name || item.function_name || "",
arguments: typeof args === "string" ? args : "{}",
}
}
}
}
return
@ -961,6 +1145,19 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
// Completion events that may carry usage
if (event?.type === "response.done" || event?.type === "response.completed") {
// Yield any pending tool calls that didn't get a 'done' event (fallback)
if (this.currentToolCalls.size > 0) {
for (const [callId, toolCall] of this.currentToolCalls) {
yield {
type: "tool_call",
id: callId,
name: toolCall.name,
arguments: toolCall.arguments || "{}",
}
}
this.currentToolCalls.clear()
}
const usage = event?.response?.usage || event?.usage || undefined
const usageData = this.normalizeUsage(usage, model)
if (usageData) {
@ -983,20 +1180,27 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
}
}
private getReasoningEffort(model: OpenAiNativeModel): ReasoningEffortWithMinimal | undefined {
const { reasoning, info } = model
private getReasoningEffort(model: OpenAiNativeModel): ReasoningEffortExtended | undefined {
// Single source of truth: user setting overrides, else model default (from types).
const selected = (this.options.reasoningEffort as any) ?? (model.info.reasoningEffort as any)
return selected && selected !== "disable" ? (selected as any) : undefined
}
// Check if reasoning effort is configured
if (reasoning && "reasoning_effort" in reasoning) {
const effort = reasoning.reasoning_effort as string
// Support all effort levels
if (effort === "minimal" || effort === "low" || effort === "medium" || effort === "high") {
return effort as ReasoningEffortWithMinimal
}
/**
* Returns the appropriate prompt cache retention policy for the given model, if any.
*
* The policy is driven by ModelInfo.promptCacheRetention so that model-specific details
* live in the shared types layer rather than this provider. When set to "24h" and the
* model supports prompt caching, extended prompt cache retention is requested.
*/
private getPromptCacheRetention(model: OpenAiNativeModel): "24h" | undefined {
if (!model.info.supportsPromptCache) return undefined
if (model.info.promptCacheRetention === "24h") {
return "24h"
}
// Use the model's default from types if available
return info.reasoningEffort as ReasoningEffortWithMinimal | undefined
return undefined
}
/**
@ -1034,19 +1238,11 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
modelId: id,
model: info,
settings: this.options,
defaultTemperature: id.startsWith(GPT5_MODEL_PREFIX)
? GPT5_DEFAULT_TEMPERATURE
: OPENAI_NATIVE_DEFAULT_TEMPERATURE,
defaultTemperature: OPENAI_NATIVE_DEFAULT_TEMPERATURE,
})
// For models using the Responses API, ensure we support reasoning effort
const effort =
(this.options.reasoningEffort as ReasoningEffortWithMinimal | undefined) ??
(info.reasoningEffort as ReasoningEffortWithMinimal | undefined)
if (effort) {
;(params.reasoning as any) = { reasoning_effort: effort }
}
// Reasoning effort inclusion is handled by getModelParams/getOpenAiReasoning.
// Do not re-compute or filter efforts here.
// The o3 models are named like "o3-mini-[reasoning-effort]", which are
// not valid model ids, so we need to strip the suffix.
@ -1080,6 +1276,9 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
}
async completePrompt(prompt: string): Promise<string> {
// Create AbortController for cancellation
this.abortController = new AbortController()
try {
const model = this.getModel()
const { verbosity, reasoning } = model
@ -1098,7 +1297,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
],
stream: false, // Non-streaming for completePrompt
store: false, // Don't store prompt completions
include: ["reasoning.encrypted_content"],
// Only include encrypted reasoning content when reasoning effort is set
...(reasoningEffort ? { include: ["reasoning.encrypted_content"] } : {}),
}
// Include service tier if selected and supported
@ -1112,17 +1312,13 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
if (reasoningEffort) {
requestBody.reasoning = {
effort: reasoningEffort,
...(this.options.enableGpt5ReasoningSummary ? { summary: "auto" as const } : {}),
...(this.options.enableResponsesReasoningSummary ? { summary: "auto" as const } : {}),
}
}
// Only include temperature if the model supports it
if (model.info.supportsTemperature !== false) {
requestBody.temperature =
this.options.modelTemperature ??
(model.id.startsWith(GPT5_MODEL_PREFIX)
? GPT5_DEFAULT_TEMPERATURE
: OPENAI_NATIVE_DEFAULT_TEMPERATURE)
requestBody.temperature = this.options.modelTemperature ?? OPENAI_NATIVE_DEFAULT_TEMPERATURE
}
// Include max_output_tokens if available
@ -1135,8 +1331,16 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
requestBody.text = { verbosity: (verbosity || "medium") as VerbosityLevel }
}
// Enable extended prompt cache retention for eligible models
const promptCacheRetention = this.getPromptCacheRetention(model)
if (promptCacheRetention) {
requestBody.prompt_cache_retention = promptCacheRetention
}
// Make the non-streaming request
const response = await (this.client as any).responses.create(requestBody)
const response = await (this.client as any).responses.create(requestBody, {
signal: this.abortController.signal,
})
// Extract text from the response
if (response?.output && Array.isArray(response.output)) {
@ -1162,6 +1366,8 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
throw new Error(`OpenAI Native completion error: ${error.message}`)
}
throw error
} finally {
this.abortController = undefined
}
}
}

123
src/api/providers/openai.ts
View file

@ -95,7 +95,7 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
const ark = modelUrl.includes(".volces.com")
if (modelId.includes("o1") || modelId.includes("o3") || modelId.includes("o4")) {
yield* this.handleO3FamilyMessage(modelId, systemPrompt, messages)
yield* this.handleO3FamilyMessage(modelId, systemPrompt, messages, metadata)
return
}
@ -164,6 +164,8 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
stream: true as const,
...(isGrokXAI ? {} : { stream_options: { include_usage: true } }),
...(reasoning && reasoning),
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
// Add max_tokens if needed
@ -189,9 +191,11 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
)
let lastUsage
const toolCallAccumulator = new Map<number, { id: string; name: string; arguments: string }>()
for await (const chunk of stream) {
const delta = chunk.choices?.[0]?.delta ?? {}
const finishReason = chunk.choices?.[0]?.finish_reason
if (delta.content) {
for (const chunk of matcher.update(delta.content)) {
@ -205,6 +209,38 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
text: (delta.reasoning_content as string | undefined) || "",
}
}
if (delta.tool_calls) {
for (const toolCall of delta.tool_calls) {
const index = toolCall.index
const existing = toolCallAccumulator.get(index)
if (existing) {
if (toolCall.function?.arguments) {
existing.arguments += toolCall.function.arguments
}
} else {
toolCallAccumulator.set(index, {
id: toolCall.id || "",
name: toolCall.function?.name || "",
arguments: toolCall.function?.arguments || "",
})
}
}
}
if (finishReason === "tool_calls") {
for (const toolCall of toolCallAccumulator.values()) {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.name,
arguments: toolCall.arguments,
}
}
toolCallAccumulator.clear()
}
if (chunk.usage) {
lastUsage = chunk.usage
}
@ -225,6 +261,8 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
: enabledLegacyFormat
? [systemMessage, ...convertToSimpleMessages(messages)]
: [systemMessage, ...convertToOpenAiMessages(messages)],
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
// Add max_tokens if needed
@ -240,9 +278,24 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
throw handleOpenAIError(error, this.providerName)
}
const message = response.choices?.[0]?.message
if (message?.tool_calls) {
for (const toolCall of message.tool_calls) {
if (toolCall.type === "function") {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.function.name,
arguments: toolCall.function.arguments,
}
}
}
}
yield {
type: "text",
text: response.choices?.[0]?.message.content || "",
text: message?.content || "",
}
yield this.processUsageMetrics(response.usage, modelInfo)
@ -304,6 +357,7 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
modelId: string,
systemPrompt: string,
messages: Anthropic.Messages.MessageParam[],
metadata?: ApiHandlerCreateMessageMetadata,
): ApiStream {
const modelInfo = this.getModel().info
const methodIsAzureAiInference = this._isAzureAiInference(this.options.openAiBaseUrl)
@ -324,6 +378,8 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
...(isGrokXAI ? {} : { stream_options: { include_usage: true } }),
reasoning_effort: modelInfo.reasoningEffort as "low" | "medium" | "high" | undefined,
temperature: undefined,
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
// O3 family models do not support the deprecated max_tokens parameter
@ -354,6 +410,8 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
],
reasoning_effort: modelInfo.reasoningEffort as "low" | "medium" | "high" | undefined,
temperature: undefined,
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
// O3 family models do not support the deprecated max_tokens parameter
@ -371,22 +429,73 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
throw handleOpenAIError(error, this.providerName)
}
const message = response.choices?.[0]?.message
if (message?.tool_calls) {
for (const toolCall of message.tool_calls) {
if (toolCall.type === "function") {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.function.name,
arguments: toolCall.function.arguments,
}
}
}
}
yield {
type: "text",
text: response.choices?.[0]?.message.content || "",
text: message?.content || "",
}
yield this.processUsageMetrics(response.usage)
}
}
private async *handleStreamResponse(stream: AsyncIterable<OpenAI.Chat.Completions.ChatCompletionChunk>): ApiStream {
const toolCallAccumulator = new Map<number, { id: string; name: string; arguments: string }>()
for await (const chunk of stream) {
const delta = chunk.choices?.[0]?.delta
if (delta?.content) {
yield {
type: "text",
text: delta.content,
const finishReason = chunk.choices?.[0]?.finish_reason
if (delta) {
if (delta.content) {
yield {
type: "text",
text: delta.content,
}
}
if (delta.tool_calls) {
for (const toolCall of delta.tool_calls) {
const index = toolCall.index
const existing = toolCallAccumulator.get(index)
if (existing) {
if (toolCall.function?.arguments) {
existing.arguments += toolCall.function.arguments
}
} else {
toolCallAccumulator.set(index, {
id: toolCall.id || "",
name: toolCall.function?.name || "",
arguments: toolCall.function?.arguments || "",
})
}
}
}
}
if (finishReason === "tool_calls") {
for (const toolCall of toolCallAccumulator.values()) {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.name,
arguments: toolCall.arguments,
}
}
toolCallAccumulator.clear()
}
if (chunk.usage) {

80
src/api/providers/openrouter.ts
View file

@ -24,7 +24,7 @@ import { getModelEndpoints } from "./fetchers/modelEndpointCache"
import { DEFAULT_HEADERS } from "./constants"
import { BaseProvider } from "./base-provider"
import type { SingleCompletionHandler } from "../index"
import type { ApiHandlerCreateMessageMetadata, SingleCompletionHandler } from "../index"
import { handleOpenAIError } from "./utils/openai-error-handler"
// Image generation types
@ -96,11 +96,38 @@ export class OpenRouterHandler extends BaseProvider implements SingleCompletionH
const apiKey = this.options.openRouterApiKey ?? "not-provided"
this.client = new OpenAI({ baseURL, apiKey, defaultHeaders: DEFAULT_HEADERS })
// Load models asynchronously to populate cache before getModel() is called
this.loadDynamicModels().catch((error) => {
console.error("[OpenRouterHandler] Failed to load dynamic models:", error)
})
}
private async loadDynamicModels(): Promise<void> {
try {
const [models, endpoints] = await Promise.all([
getModels({ provider: "openrouter" }),
getModelEndpoints({
router: "openrouter",
modelId: this.options.openRouterModelId,
endpoint: this.options.openRouterSpecificProvider,
}),
])
this.models = models
this.endpoints = endpoints
} catch (error) {
console.error("[OpenRouterHandler] Error loading dynamic models:", {
error: error instanceof Error ? error.message : String(error),
stack: error instanceof Error ? error.stack : undefined,
})
}
}
override async *createMessage(
systemPrompt: string,
messages: Anthropic.Messages.MessageParam[],
metadata?: ApiHandlerCreateMessageMetadata,
): AsyncGenerator<ApiStreamChunk> {
const model = await this.fetchModel()
@ -159,8 +186,11 @@ export class OpenRouterHandler extends BaseProvider implements SingleCompletionH
allow_fallbacks: false,
},
}),
parallel_tool_calls: false, // Ensure only one tool call at a time
...(transforms && { transforms }),
...(reasoning && { reasoning }),
...(metadata?.tools && { tools: metadata.tools }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
let stream
@ -171,6 +201,7 @@ export class OpenRouterHandler extends BaseProvider implements SingleCompletionH
}
let lastUsage: CompletionUsage | undefined = undefined
const toolCallAccumulator = new Map<number, { id: string; name: string; arguments: string }>()
for await (const chunk of stream) {
// OpenRouter returns an error object instead of the OpenAI SDK throwing an error.
@ -181,13 +212,52 @@ export class OpenRouterHandler extends BaseProvider implements SingleCompletionH
}
const delta = chunk.choices[0]?.delta
const finishReason = chunk.choices[0]?.finish_reason
if ("reasoning" in delta && delta.reasoning && typeof delta.reasoning === "string") {
yield { type: "reasoning", text: delta.reasoning }
if (delta) {
if ("reasoning" in delta && delta.reasoning && typeof delta.reasoning === "string") {
yield { type: "reasoning", text: delta.reasoning }
}
// Check for tool calls in delta
if ("tool_calls" in delta && Array.isArray(delta.tool_calls)) {
for (const toolCall of delta.tool_calls) {
const index = toolCall.index
const existing = toolCallAccumulator.get(index)
if (existing) {
// Accumulate arguments for existing tool call
if (toolCall.function?.arguments) {
existing.arguments += toolCall.function.arguments
}
} else {
// Start new tool call accumulation
toolCallAccumulator.set(index, {
id: toolCall.id || "",
name: toolCall.function?.name || "",
arguments: toolCall.function?.arguments || "",
})
}
}
}
if (delta.content) {
yield { type: "text", text: delta.content }
}
}
if (delta?.content) {
yield { type: "text", text: delta.content }
// When finish_reason is 'tool_calls', yield all accumulated tool calls
if (finishReason === "tool_calls" && toolCallAccumulator.size > 0) {
for (const toolCall of toolCallAccumulator.values()) {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.name,
arguments: toolCall.arguments,
}
}
// Clear accumulator after yielding
toolCallAccumulator.clear()
}
if (chunk.usage) {

20
src/api/providers/requesty.ts
View file

@ -28,6 +28,16 @@ interface RequestyUsage extends OpenAI.CompletionUsage {
total_cost?: number
}
type RequestyChatCompletionParamsStreaming = OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming & {
requesty?: {
trace_id?: string
extra?: {
mode?: string
}
}
thinking?: AnthropicReasoningParams
}
type RequestyChatCompletionParams = OpenAI.Chat.ChatCompletionCreateParams & {
requesty?: {
trace_id?: string
@ -118,12 +128,17 @@ export class RequestyHandler extends BaseProvider implements SingleCompletionHan
...convertToOpenAiMessages(messages),
]
const completionParams: RequestyChatCompletionParams = {
// Map extended efforts to OpenAI Chat Completions-accepted values (omit unsupported)
const allowedEffort = (["low", "medium", "high"] as const).includes(reasoning_effort as any)
? (reasoning_effort as OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming["reasoning_effort"])
: undefined
const completionParams: RequestyChatCompletionParamsStreaming = {
messages: openAiMessages,
model,
max_tokens,
temperature,
...(reasoning_effort && reasoning_effort !== "minimal" && { reasoning_effort }),
...(allowedEffort && { reasoning_effort: allowedEffort }),
...(thinking && { thinking }),
stream: true,
stream_options: { include_usage: true },
@ -132,6 +147,7 @@ export class RequestyHandler extends BaseProvider implements SingleCompletionHan
let stream
try {
// With streaming params type, SDK returns an async iterable stream
stream = await this.client.chat.completions.create(completionParams)
} catch (error) {
throw handleOpenAIError(error, this.providerName)

84
src/api/providers/roo.ts
View file

@ -1,7 +1,7 @@
import { Anthropic } from "@anthropic-ai/sdk"
import OpenAI from "openai"
import { rooDefaultModelId } from "@roo-code/types"
import { rooDefaultModelId, getApiProtocol } from "@roo-code/types"
import { CloudService } from "@roo-code/cloud"
import type { ApiHandlerOptions, ModelRecord } from "../../shared/api"
@ -100,6 +100,8 @@ export class RooHandler extends BaseOpenAiCompatibleProvider<string> {
stream: true,
stream_options: { include_usage: true },
...(reasoning && { reasoning }),
...(metadata?.tools && { tools: metadata.tools }),
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
}
try {
@ -124,9 +126,12 @@ export class RooHandler extends BaseOpenAiCompatibleProvider<string> {
)
let lastUsage: RooUsage | undefined = undefined
// Accumulate tool calls by index - similar to how reasoning accumulates
const toolCallAccumulator = new Map<number, { id: string; name: string; arguments: string }>()
for await (const chunk of stream) {
const delta = chunk.choices[0]?.delta
const finishReason = chunk.choices[0]?.finish_reason
if (delta) {
// Check for reasoning content (similar to OpenRouter)
@ -145,6 +150,28 @@ export class RooHandler extends BaseOpenAiCompatibleProvider<string> {
}
}
// Check for tool calls in delta
if ("tool_calls" in delta && Array.isArray(delta.tool_calls)) {
for (const toolCall of delta.tool_calls) {
const index = toolCall.index
const existing = toolCallAccumulator.get(index)
if (existing) {
// Accumulate arguments for existing tool call
if (toolCall.function?.arguments) {
existing.arguments += toolCall.function.arguments
}
} else {
// Start new tool call accumulation
toolCallAccumulator.set(index, {
id: toolCall.id || "",
name: toolCall.function?.name || "",
arguments: toolCall.function?.arguments || "",
})
}
}
}
if (delta.content) {
yield {
type: "text",
@ -153,6 +180,20 @@ export class RooHandler extends BaseOpenAiCompatibleProvider<string> {
}
}
// When finish_reason is 'tool_calls', yield all accumulated tool calls
if (finishReason === "tool_calls" && toolCallAccumulator.size > 0) {
for (const [index, toolCall] of toolCallAccumulator.entries()) {
yield {
type: "tool_call",
id: toolCall.id,
name: toolCall.name,
arguments: toolCall.arguments,
}
}
// Clear accumulator after yielding
toolCallAccumulator.clear()
}
if (chunk.usage) {
lastUsage = chunk.usage as RooUsage
}
@ -163,12 +204,25 @@ export class RooHandler extends BaseOpenAiCompatibleProvider<string> {
const model = this.getModel()
const isFreeModel = model.info.isFree ?? false
// Normalize input tokens based on protocol expectations:
// - OpenAI protocol expects TOTAL input tokens (cached + non-cached)
// - Anthropic protocol expects NON-CACHED input tokens (caches passed separately)
const modelId = model.id
const apiProtocol = getApiProtocol("roo", modelId)
const promptTokens = lastUsage.prompt_tokens || 0
const cacheWrite = lastUsage.cache_creation_input_tokens || 0
const cacheRead = lastUsage.prompt_tokens_details?.cached_tokens || 0
const nonCached = Math.max(0, promptTokens - cacheWrite - cacheRead)
const inputTokensForDownstream = apiProtocol === "anthropic" ? nonCached : promptTokens
yield {
type: "usage",
inputTokens: lastUsage.prompt_tokens || 0,
inputTokens: inputTokensForDownstream,
outputTokens: lastUsage.completion_tokens || 0,
cacheWriteTokens: lastUsage.cache_creation_input_tokens,
cacheReadTokens: lastUsage.prompt_tokens_details?.cached_tokens,
cacheWriteTokens: cacheWrite,
cacheReadTokens: cacheRead,
totalCost: isFreeModel ? 0 : (lastUsage.cost ?? 0),
}
}
@ -220,17 +274,21 @@ export class RooHandler extends BaseOpenAiCompatibleProvider<string> {
}
// Return the requested model ID even if not found, with fallback info.
const fallbackInfo = {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: false,
supportsReasoningEffort: false,
supportsPromptCache: true,
supportsNativeTools: false,
inputPrice: 0,
outputPrice: 0,
isFree: false,
}
return {
id: modelId,
info: {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: false,
supportsReasoningEffort: false,
supportsPromptCache: true,
inputPrice: 0,
outputPrice: 0,
},
info: fallbackInfo,
}
}
}

3
src/api/providers/utils/timeout-config.ts
View file

@ -1,4 +1,5 @@
import * as vscode from "vscode"
import { Package } from "../../../shared/package"
/**
* Gets the API request timeout from VSCode configuration with validation.
@ -7,7 +8,7 @@ import * as vscode from "vscode"
*/
export function getApiRequestTimeout(): number {
// Get timeout with validation to ensure it's a valid non-negative number
const configTimeout = vscode.workspace.getConfiguration("roo-cline").get<number>("apiRequestTimeout", 600)
const configTimeout = vscode.workspace.getConfiguration(Package.name).get<number>("apiRequestTimeout", 600)
// Validate that it's actually a number and not NaN
if (typeof configTimeout !== "number" || isNaN(configTimeout)) {

300
src/api/transform/__tests__/gemini-format.spec.ts
View file

@ -13,10 +13,12 @@ describe("convertAnthropicMessageToGemini", () => {
const result = convertAnthropicMessageToGemini(anthropicMessage)
expect(result).toEqual({
role: "user",
parts: [{ text: "Hello, world!" }],
})
expect(result).toEqual([
{
role: "user",
parts: [{ text: "Hello, world!" }],
},
])
})
it("should convert assistant role to model role", () => {
@ -27,10 +29,12 @@ describe("convertAnthropicMessageToGemini", () => {
const result = convertAnthropicMessageToGemini(anthropicMessage)
expect(result).toEqual({
role: "model",
parts: [{ text: "I'm an assistant" }],
})
expect(result).toEqual([
{
role: "model",
parts: [{ text: "I'm an assistant" }],
},
])
})
it("should convert a message with text blocks", () => {
@ -44,10 +48,12 @@ describe("convertAnthropicMessageToGemini", () => {
const result = convertAnthropicMessageToGemini(anthropicMessage)
expect(result).toEqual({
role: "user",
parts: [{ text: "First paragraph" }, { text: "Second paragraph" }],
})
expect(result).toEqual([
{
role: "user",
parts: [{ text: "First paragraph" }, { text: "Second paragraph" }],
},
])
})
it("should convert a message with an image", () => {
@ -68,18 +74,20 @@ describe("convertAnthropicMessageToGemini", () => {
const result = convertAnthropicMessageToGemini(anthropicMessage)
expect(result).toEqual({
role: "user",
parts: [
{ text: "Check out this image:" },
{
inlineData: {
data: "base64encodeddata",
mimeType: "image/jpeg",
expect(result).toEqual([
{
role: "user",
parts: [
{ text: "Check out this image:" },
{
inlineData: {
data: "base64encodeddata",
mimeType: "image/jpeg",
},
},
},
],
})
],
},
])
})
it("should throw an error for unsupported image source type", () => {
@ -115,21 +123,27 @@ describe("convertAnthropicMessageToGemini", () => {
const result = convertAnthropicMessageToGemini(anthropicMessage)
expect(result).toEqual({
role: "model",
parts: [
{ text: "Let me calculate that for you." },
{
functionCall: {
name: "calculator",
args: { operation: "add", numbers: [2, 3] },
expect(result).toEqual([
{
role: "model",
parts: [
{ text: "Let me calculate that for you." },
{
functionCall: {
name: "calculator",
args: { operation: "add", numbers: [2, 3] },
},
thoughtSignature: "skip_thought_signature_validator",
},
},
],
})
],
},
])
})
it("should convert a message with tool result as string", () => {
const toolIdToName = new Map<string, string>()
toolIdToName.set("calculator-123", "calculator")
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
@ -142,23 +156,25 @@ describe("convertAnthropicMessageToGemini", () => {
],
}
const result = convertAnthropicMessageToGemini(anthropicMessage)
const result = convertAnthropicMessageToGemini(anthropicMessage, { toolIdToName })
expect(result).toEqual({
role: "user",
parts: [
{ text: "Here's the result:" },
{
functionResponse: {
name: "calculator",
response: {
expect(result).toEqual([
{
role: "user",
parts: [
{ text: "Here's the result:" },
{
functionResponse: {
name: "calculator",
content: "The result is 5",
response: {
name: "calculator",
content: "The result is 5",
},
},
},
},
],
})
],
},
])
})
it("should handle empty tool result content", () => {
@ -176,13 +192,13 @@ describe("convertAnthropicMessageToGemini", () => {
const result = convertAnthropicMessageToGemini(anthropicMessage)
// Should skip the empty tool result
expect(result).toEqual({
role: "user",
parts: [],
})
expect(result).toEqual([])
})
it("should convert a message with tool result as array with text only", () => {
const toolIdToName = new Map<string, string>()
toolIdToName.set("search-123", "search")
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
@ -197,25 +213,30 @@ describe("convertAnthropicMessageToGemini", () => {
],
}
const result = convertAnthropicMessageToGemini(anthropicMessage)
const result = convertAnthropicMessageToGemini(anthropicMessage, { toolIdToName })
expect(result).toEqual({
role: "user",
parts: [
{
functionResponse: {
name: "search",
response: {
expect(result).toEqual([
{
role: "user",
parts: [
{
functionResponse: {
name: "search",
content: "First result\n\nSecond result",
response: {
name: "search",
content: "First result\n\nSecond result",
},
},
},
},
],
})
],
},
])
})
it("should convert a message with tool result as array with text and images", () => {
const toolIdToName = new Map<string, string>()
toolIdToName.set("search-123", "search")
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
@ -245,37 +266,42 @@ describe("convertAnthropicMessageToGemini", () => {
],
}
const result = convertAnthropicMessageToGemini(anthropicMessage)
const result = convertAnthropicMessageToGemini(anthropicMessage, { toolIdToName })
expect(result).toEqual({
role: "user",
parts: [
{
functionResponse: {
name: "search",
response: {
expect(result).toEqual([
{
role: "user",
parts: [
{
functionResponse: {
name: "search",
content: "Search results:\n\n(See next part for image)",
response: {
name: "search",
content: "Search results:\n\n(See next part for image)",
},
},
},
},
{
inlineData: {
data: "image1data",
mimeType: "image/png",
{
inlineData: {
data: "image1data",
mimeType: "image/png",
},
},
},
{
inlineData: {
data: "image2data",
mimeType: "image/jpeg",
{
inlineData: {
data: "image2data",
mimeType: "image/jpeg",
},
},
},
],
})
],
},
])
})
it("should convert a message with tool result containing only images", () => {
const toolIdToName = new Map<string, string>()
toolIdToName.set("imagesearch-123", "imagesearch")
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
@ -296,28 +322,102 @@ describe("convertAnthropicMessageToGemini", () => {
],
}
const result = convertAnthropicMessageToGemini(anthropicMessage)
const result = convertAnthropicMessageToGemini(anthropicMessage, { toolIdToName })
expect(result).toEqual({
role: "user",
parts: [
{
functionResponse: {
name: "imagesearch",
response: {
expect(result).toEqual([
{
role: "user",
parts: [
{
functionResponse: {
name: "imagesearch",
content: "\n\n(See next part for image)",
response: {
name: "imagesearch",
content: "\n\n(See next part for image)",
},
},
},
},
{
inlineData: {
data: "onlyimagedata",
mimeType: "image/png",
{
inlineData: {
data: "onlyimagedata",
mimeType: "image/png",
},
},
],
},
])
})
it("should handle tool names with hyphens using toolIdToName map", () => {
const toolIdToName = new Map<string, string>()
toolIdToName.set("search-files-123", "search-files")
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
{
type: "tool_result",
tool_use_id: "search-files-123",
content: "found files",
},
],
})
}
const result = convertAnthropicMessageToGemini(anthropicMessage, { toolIdToName })
expect(result).toEqual([
{
role: "user",
parts: [
{
functionResponse: {
name: "search-files",
response: {
name: "search-files",
content: "found files",
},
},
},
],
},
])
})
it("should throw error when toolIdToName map is not provided", () => {
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
{
type: "tool_result",
tool_use_id: "calculator-123",
content: "result is 5",
},
],
}
expect(() => convertAnthropicMessageToGemini(anthropicMessage)).toThrow(
'Unable to find tool name for tool_use_id "calculator-123"',
)
})
it("should throw error when tool_use_id is not in the map", () => {
const toolIdToName = new Map<string, string>()
toolIdToName.set("other-tool-456", "other-tool")
const anthropicMessage: Anthropic.Messages.MessageParam = {
role: "user",
content: [
{
type: "tool_result",
tool_use_id: "calculator-123",
content: "result is 5",
},
],
}
expect(() => convertAnthropicMessageToGemini(anthropicMessage, { toolIdToName })).toThrow(
'Unable to find tool name for tool_use_id "calculator-123"',
)
})
it("should throw an error for unsupported content block type", () => {

73
src/api/transform/__tests__/model-params.spec.ts
View file

@ -545,6 +545,79 @@ describe("getModelParams", () => {
expect(result.reasoning).toEqual({ effort: "medium" })
})
it("should include 'minimal' effort for openai format", () => {
const model: ModelInfo = {
...baseModel,
// Array capability explicitly includes minimal
supportsReasoningEffort: ["minimal", "low", "medium", "high"] as any,
}
const result = getModelParams({
...openaiParams,
settings: { reasoningEffort: "minimal" as any },
model,
})
expect(result.reasoningEffort).toBe("minimal")
expect(result.reasoning).toEqual({ reasoning_effort: "minimal" })
})
it("should include 'none' effort for openai format", () => {
const model: ModelInfo = {
...baseModel,
// Array capability explicitly includes none
supportsReasoningEffort: ["none", "low", "medium", "high"] as any,
}
const result = getModelParams({
...openaiParams,
settings: { reasoningEffort: "none" as any },
model,
})
expect(result.reasoningEffort).toBe("none")
expect(result.reasoning).toEqual({ reasoning_effort: "none" })
})
it("should omit reasoning for 'disable' selection", () => {
const model: ModelInfo = {
...baseModel,
supportsReasoningEffort: true,
}
const result = getModelParams({
...openaiParams,
settings: { reasoningEffort: "disable" as any },
model,
})
expect(result.reasoningEffort).toBeUndefined()
expect(result.reasoning).toBeUndefined()
})
it("should include 'minimal' and 'none' for openrouter format", () => {
const model: ModelInfo = {
...baseModel,
// Array capability explicitly includes both
supportsReasoningEffort: ["none", "minimal", "low", "medium", "high"] as any,
}
const minimalRes = getModelParams({
...openrouterParams,
settings: { reasoningEffort: "minimal" as any },
model,
})
expect(minimalRes.reasoningEffort).toBe("minimal")
expect(minimalRes.reasoning).toEqual({ effort: "minimal" })
const noneRes = getModelParams({
...openrouterParams,
settings: { reasoningEffort: "none" as any },
model,
})
expect(noneRes.reasoningEffort).toBe("none")
expect(noneRes.reasoning).toEqual({ effort: "none" })
})
it("should not use reasoning effort for anthropic format", () => {
const model: ModelInfo = {
...baseModel,

61
src/api/transform/__tests__/reasoning.spec.ts
View file

@ -7,11 +7,13 @@ import {
getAnthropicReasoning,
getOpenAiReasoning,
getRooReasoning,
getGeminiReasoning,
GetModelReasoningOptions,
OpenRouterReasoningParams,
AnthropicReasoningParams,
OpenAiReasoningParams,
RooReasoningParams,
GeminiReasoningParams,
} from "../reasoning"
describe("reasoning.ts", () => {
@ -529,7 +531,7 @@ describe("reasoning.ts", () => {
const result = getOpenAiReasoning(optionsWithoutEffort)
expect(result).toEqual({ reasoning_effort: undefined })
expect(result).toBeUndefined()
})
it("should handle all reasoning effort values", () => {
@ -587,6 +589,61 @@ describe("reasoning.ts", () => {
})
})
describe("Gemini reasoning (effort models)", () => {
it("should return thinkingLevel when effort is set to low or high and budget is not used", () => {
const geminiModel: ModelInfo = {
...baseModel,
// Effort-only reasoning model (no budget fields)
supportsReasoningEffort: ["low", "high"] as ModelInfo["supportsReasoningEffort"],
reasoningEffort: "low",
}
const settings: ProviderSettings = {
apiProvider: "gemini",
enableReasoningEffort: true,
reasoningEffort: "high",
}
const options: GetModelReasoningOptions = {
model: geminiModel,
reasoningBudget: 2048,
reasoningEffort: "high",
settings,
}
const result = getGeminiReasoning(options) as GeminiReasoningParams | undefined
// Budget should not be used for effort-only models
expect(result).toEqual({ thinkingLevel: "high", includeThoughts: true })
})
it("should still return thinkingLevel when enableReasoningEffort is false but effort is explicitly set", () => {
const geminiModel: ModelInfo = {
...baseModel,
// Effort-only reasoning model
supportsReasoningEffort: ["low", "high"] as ModelInfo["supportsReasoningEffort"],
reasoningEffort: "low",
}
const settings: ProviderSettings = {
apiProvider: "gemini",
// Even with this flag false, an explicit effort selection should win
enableReasoningEffort: false,
reasoningEffort: "high",
}
const options: GetModelReasoningOptions = {
model: geminiModel,
reasoningBudget: 2048,
reasoningEffort: "high",
settings,
}
const result = getGeminiReasoning(options) as GeminiReasoningParams | undefined
expect(result).toEqual({ thinkingLevel: "high", includeThoughts: true })
})
})
describe("Integration scenarios", () => {
it("should handle model with requiredReasoningBudget across all providers", () => {
const modelWithRequired: ModelInfo = {
@ -829,7 +886,7 @@ describe("reasoning.ts", () => {
expect(result).toEqual({ enabled: false })
})
it("should not return reasoning params for minimal effort", () => {
it("should omit reasoning params for minimal effort", () => {
const modelWithSupported: ModelInfo = {
...baseModel,
supportsReasoningEffort: true,

87
src/api/transform/gemini-format.ts
View file

@ -1,12 +1,60 @@
import { Anthropic } from "@anthropic-ai/sdk"
import { Content, Part } from "@google/genai"
export function convertAnthropicContentToGemini(content: string | Anthropic.ContentBlockParam[]): Part[] {
type ThoughtSignatureContentBlock = {
type: "thoughtSignature"
thoughtSignature?: string
}
type ExtendedContentBlockParam = Anthropic.ContentBlockParam | ThoughtSignatureContentBlock
type ExtendedAnthropicContent = string | ExtendedContentBlockParam[]
function isThoughtSignatureContentBlock(block: ExtendedContentBlockParam): block is ThoughtSignatureContentBlock {
return block.type === "thoughtSignature"
}
export function convertAnthropicContentToGemini(
content: ExtendedAnthropicContent,
options?: { includeThoughtSignatures?: boolean; toolIdToName?: Map<string, string> },
): Part[] {
const includeThoughtSignatures = options?.includeThoughtSignatures ?? true
const toolIdToName = options?.toolIdToName
// First pass: find thoughtSignature if it exists in the content blocks
let activeThoughtSignature: string | undefined
if (Array.isArray(content)) {
const sigBlock = content.find((block) => isThoughtSignatureContentBlock(block)) as ThoughtSignatureContentBlock
if (sigBlock?.thoughtSignature) {
activeThoughtSignature = sigBlock.thoughtSignature
}
}
// Determine the signature to attach to function calls.
// If we're in a mode that expects signatures (includeThoughtSignatures is true):
// 1. Use the actual signature if we found one in the history/content.
// 2. Fallback to "skip_thought_signature_validator" if missing (e.g. cross-model history).
let functionCallSignature: string | undefined
if (includeThoughtSignatures) {
functionCallSignature = activeThoughtSignature || "skip_thought_signature_validator"
}
if (typeof content === "string") {
return [{ text: content }]
}
return content.flatMap((block): Part | Part[] => {
// Handle thoughtSignature blocks first
if (isThoughtSignatureContentBlock(block)) {
if (includeThoughtSignatures && typeof block.thoughtSignature === "string") {
// The Google GenAI SDK currently exposes thoughtSignature as an
// extension field on Part; model it structurally without widening
// the upstream type.
return { thoughtSignature: block.thoughtSignature } as Part
}
// Explicitly omit thoughtSignature when not including it.
return []
}
switch (block.type) {
case "text":
return { text: block.text }
@ -22,14 +70,26 @@ export function convertAnthropicContentToGemini(content: string | Anthropic.Cont
name: block.name,
args: block.input as Record<string, unknown>,
},
}
// Inject the thoughtSignature into the functionCall part if required.
// This is necessary for Gemini 2.5/3+ thinking models to validate the tool call.
...(functionCallSignature ? { thoughtSignature: functionCallSignature } : {}),
} as Part
case "tool_result": {
if (!block.content) {
return []
}
// Extract tool name from tool_use_id (e.g., "calculator-123" -> "calculator")
const toolName = block.tool_use_id.split("-")[0]
// Get tool name from the map (built from tool_use blocks in message history).
// The map must contain the tool name - if it doesn't, this indicates a bug
// where the conversation history is incomplete or tool_use blocks are missing.
const toolName = toolIdToName?.get(block.tool_use_id)
if (!toolName) {
throw new Error(
`Unable to find tool name for tool_use_id "${block.tool_use_id}". ` +
`This indicates the conversation history is missing the corresponding tool_use block. ` +
`Available tool IDs: ${Array.from(toolIdToName?.keys() ?? []).join(", ") || "none"}`,
)
}
if (typeof block.content === "string") {
return {
@ -70,9 +130,20 @@ export function convertAnthropicContentToGemini(content: string | Anthropic.Cont
})
}
export function convertAnthropicMessageToGemini(message: Anthropic.Messages.MessageParam): Content {
return {
role: message.role === "assistant" ? "model" : "user",
parts: convertAnthropicContentToGemini(message.content),
export function convertAnthropicMessageToGemini(
message: Anthropic.Messages.MessageParam,
options?: { includeThoughtSignatures?: boolean; toolIdToName?: Map<string, string> },
): Content[] {
const parts = convertAnthropicContentToGemini(message.content, options)
if (parts.length === 0) {
return []
}
return [
{
role: message.role === "assistant" ? "model" : "user",
parts,
},
]
}

18
src/api/transform/model-params.ts
View file

@ -2,7 +2,7 @@ import {
type ModelInfo,
type ProviderSettings,
type VerbosityLevel,
type ReasoningEffortWithMinimal,
type ReasoningEffortExtended,
ANTHROPIC_DEFAULT_MAX_TOKENS,
} from "@roo-code/types"
@ -39,9 +39,10 @@ type GetModelParamsOptions<T extends Format> = {
type BaseModelParams = {
maxTokens: number | undefined
temperature: number | undefined
reasoningEffort: ReasoningEffortWithMinimal | undefined
reasoningEffort: ReasoningEffortExtended | undefined
reasoningBudget: number | undefined
verbosity: VerbosityLevel | undefined
tools?: boolean
}
type AnthropicModelParams = {
@ -129,8 +130,16 @@ export function getModelParams({
temperature = 1.0
} else if (shouldUseReasoningEffort({ model, settings })) {
// "Traditional" reasoning models use the `reasoningEffort` parameter.
const effort = customReasoningEffort ?? model.reasoningEffort
reasoningEffort = effort as ReasoningEffortWithMinimal
const effort = (customReasoningEffort ?? model.reasoningEffort) as
| ReasoningEffortExtended
| "disable"
| undefined
// Capability and settings checks are handled by shouldUseReasoningEffort.
// Here we simply propagate the resolved effort into the params, while
// still treating "disable" as an omission.
if (effort && effort !== "disable") {
reasoningEffort = effort as ReasoningEffortExtended
}
}
const params: BaseModelParams = { maxTokens, temperature, reasoningEffort, reasoningBudget, verbosity }
@ -152,6 +161,7 @@ export function getModelParams({
format,
...params,
reasoning: getOpenAiReasoning({ model, reasoningBudget, reasoningEffort, settings }),
tools: model.supportsNativeTools,
}
} else if (format === "gemini") {
return {

98
src/api/transform/reasoning.ts
View file

@ -2,31 +2,33 @@ import { BetaThinkingConfigParam } from "@anthropic-ai/sdk/resources/beta"
import OpenAI from "openai"
import type { GenerateContentConfig } from "@google/genai"
import type { ModelInfo, ProviderSettings, ReasoningEffortWithMinimal } from "@roo-code/types"
import type { ModelInfo, ProviderSettings, ReasoningEffortExtended } from "@roo-code/types"
import { shouldUseReasoningBudget, shouldUseReasoningEffort } from "../../shared/api"
export type OpenRouterReasoningParams = {
effort?: ReasoningEffortWithMinimal
effort?: ReasoningEffortExtended
max_tokens?: number
exclude?: boolean
}
export type RooReasoningParams = {
enabled?: boolean
effort?: ReasoningEffortWithMinimal
effort?: ReasoningEffortExtended
}
export type AnthropicReasoningParams = BetaThinkingConfigParam
export type OpenAiReasoningParams = { reasoning_effort: OpenAI.Chat.ChatCompletionCreateParams["reasoning_effort"] }
export type GeminiReasoningParams = GenerateContentConfig["thinkingConfig"]
export type GeminiReasoningParams = GenerateContentConfig["thinkingConfig"] & {
thinkingLevel?: "low" | "high"
}
export type GetModelReasoningOptions = {
model: ModelInfo
reasoningBudget: number | undefined
reasoningEffort: ReasoningEffortWithMinimal | undefined
reasoningEffort: ReasoningEffortExtended | "disable" | undefined
settings: ProviderSettings
}
@ -39,8 +41,8 @@ export const getOpenRouterReasoning = ({
shouldUseReasoningBudget({ model, settings })
? { max_tokens: reasoningBudget }
: shouldUseReasoningEffort({ model, settings })
? reasoningEffort
? { effort: reasoningEffort }
? reasoningEffort && reasoningEffort !== "disable"
? { effort: reasoningEffort as ReasoningEffortExtended }
: undefined
: undefined
@ -50,28 +52,36 @@ export const getRooReasoning = ({
settings,
}: GetModelReasoningOptions): RooReasoningParams | undefined => {
// Check if model supports reasoning effort
if (!model.supportsReasoningEffort) {
return undefined
}
if (!model.supportsReasoningEffort) return undefined
// If enableReasoningEffort is explicitly false, return enabled: false
// Explicit off switch from settings: always send disabled for back-compat and to
// prevent automatic reasoning when the toggle is turned off.
if (settings.enableReasoningEffort === false) {
return { enabled: false }
}
// If reasoning effort is provided, return it with enabled: true
if (reasoningEffort && reasoningEffort !== "minimal") {
return { enabled: true, effort: reasoningEffort }
}
// If reasoningEffort is explicitly undefined (None selected), disable reasoning
// This ensures we explicitly tell the backend not to use reasoning
if (reasoningEffort === undefined) {
// For Roo models that support reasoning effort, absence of a selection should be
// treated as an explicit "off" signal so that the backend does not auto-enable
// reasoning. This aligns with the default behavior in tests.
if (!reasoningEffort) {
return { enabled: false }
}
// Default: no reasoning parameter (reasoning not enabled)
return undefined
// "disable" is a legacy sentinel that means "omit the reasoning field entirely"
// and let the server decide any defaults.
if (reasoningEffort === "disable") {
return undefined
}
// For Roo, "minimal" is treated as "none" for effort-based reasoning – we omit
// the reasoning field entirely instead of sending an explicit effort.
if (reasoningEffort === "minimal") {
return undefined
}
// When an effort is provided (e.g. "low" | "medium" | "high" | "none"), enable
// with the selected effort.
return { enabled: true, effort: reasoningEffort as ReasoningEffortExtended }
}
export const getAnthropicReasoning = ({
@ -86,24 +96,44 @@ export const getOpenAiReasoning = ({
reasoningEffort,
settings,
}: GetModelReasoningOptions): OpenAiReasoningParams | undefined => {
if (!shouldUseReasoningEffort({ model, settings })) {
return undefined
}
if (!shouldUseReasoningEffort({ model, settings })) return undefined
if (reasoningEffort === "disable" || !reasoningEffort) return undefined
// If model has reasoning effort capability, return object even if effort is undefined
// This preserves the reasoning_effort field in the API call
if (reasoningEffort === "minimal") {
return undefined
// Include "none" | "minimal" | "low" | "medium" | "high" literally
return {
reasoning_effort: reasoningEffort as OpenAI.Chat.ChatCompletionCreateParams["reasoning_effort"],
}
return { reasoning_effort: reasoningEffort }
}
export const getGeminiReasoning = ({
model,
reasoningBudget,
reasoningEffort,
settings,
}: GetModelReasoningOptions): GeminiReasoningParams | undefined =>
shouldUseReasoningBudget({ model, settings })
? { thinkingBudget: reasoningBudget!, includeThoughts: true }
: undefined
}: GetModelReasoningOptions): GeminiReasoningParams | undefined => {
// Budget-based (2.5) models: use thinkingBudget, not thinkingLevel.
if (shouldUseReasoningBudget({ model, settings })) {
return { thinkingBudget: reasoningBudget!, includeThoughts: true }
}
// For effort-based Gemini models, rely directly on the selected effort value.
// We intentionally ignore enableReasoningEffort here so that explicitly chosen
// efforts in the UI (e.g. "High" for gemini-3-pro-preview) always translate
// into a thinkingConfig, regardless of legacy boolean flags.
const selectedEffort = (settings.reasoningEffort ?? model.reasoningEffort) as
| ReasoningEffortExtended
| "disable"
| undefined
// Respect “off” / unset semantics from the effort selector itself.
if (!selectedEffort || selectedEffort === "disable") {
return undefined
}
// Effort-based models on Google GenAI currently support only explicit low/high levels.
if (selectedEffort !== "low" && selectedEffort !== "high") {
return undefined
}
return { thinkingLevel: selectedEffort, includeThoughts: true }
}

8
src/api/transform/stream.ts
View file

@ -5,6 +5,7 @@ export type ApiStreamChunk =
| ApiStreamUsageChunk
| ApiStreamReasoningChunk
| ApiStreamGroundingChunk
| ApiStreamToolCallChunk
| ApiStreamError
export interface ApiStreamError {
@ -38,6 +39,13 @@ export interface ApiStreamGroundingChunk {
sources: GroundingSource[]
}
export interface ApiStreamToolCallChunk {
type: "tool_call"
id: string
name: string
arguments: string
}
export interface GroundingSource {
title: string
url: string

312
src/core/assistant-message/NativeToolCallParser.ts Normal file
View file

@ -0,0 +1,312 @@
import { type ToolName, toolNames, type FileEntry } from "@roo-code/types"
import { type ToolUse, type ToolParamName, toolParamNames, type NativeToolArgs } from "../../shared/tools"
/**
* Helper type to extract properly typed native arguments for a given tool.
* Returns the type from NativeToolArgs if the tool is defined there, otherwise never.
*/
type NativeArgsFor<TName extends ToolName> = TName extends keyof NativeToolArgs ? NativeToolArgs[TName] : never
/**
* Parser for native tool calls (OpenAI-style function calling).
* Converts native tool call format to ToolUse format for compatibility
* with existing tool execution infrastructure.
*
* For tools with refactored parsers (e.g., read_file), this parser provides
* typed arguments via nativeArgs. Tool-specific handlers should consume
* nativeArgs directly rather than relying on synthesized legacy params.
*/
export class NativeToolCallParser {
/**
* Convert a native tool call chunk to a ToolUse object.
*
* @param toolCall - The native tool call from the API stream
* @returns A properly typed ToolUse object
*/
public static parseToolCall<TName extends ToolName>(toolCall: {
id: string
name: TName
arguments: string
}): ToolUse<TName> | null {
// Check if this is a dynamic MCP tool (mcp_serverName_toolName)
if (typeof toolCall.name === "string" && toolCall.name.startsWith("mcp_")) {
return this.parseDynamicMcpTool(toolCall) as ToolUse<TName> | null
}
// Validate tool name
if (!toolNames.includes(toolCall.name as ToolName)) {
console.error(`Invalid tool name: ${toolCall.name}`)
console.error(`Valid tool names:`, toolNames)
return null
}
try {
// Parse the arguments JSON string
const args = JSON.parse(toolCall.arguments)
// Build legacy params object for backward compatibility with XML protocol and UI.
// Native execution path uses nativeArgs instead, which has proper typing.
const params: Partial<Record<ToolParamName, string>> = {}
for (const [key, value] of Object.entries(args)) {
// Skip complex parameters that have been migrated to nativeArgs.
// For read_file, the 'files' parameter is a FileEntry[] array that can't be
// meaningfully stringified. The properly typed data is in nativeArgs instead.
if (toolCall.name === "read_file" && key === "files") {
continue
}
// Validate parameter name
if (!toolParamNames.includes(key as ToolParamName)) {
console.warn(`Unknown parameter '${key}' for tool '${toolCall.name}'`)
console.warn(`Valid param names:`, toolParamNames)
continue
}
// Convert to string for legacy params format
const stringValue = typeof value === "string" ? value : JSON.stringify(value)
params[key as ToolParamName] = stringValue
}
// Build typed nativeArgs for tools that support it.
// This switch statement serves two purposes:
// 1. Validation: Ensures required parameters are present before constructing nativeArgs
// 2. Transformation: Converts raw JSON to properly typed structures
//
// Each case validates the minimum required parameters and constructs a properly typed
// nativeArgs object. If validation fails, nativeArgs remains undefined and the tool
// will fall back to legacy parameter parsing if supported.
let nativeArgs: NativeArgsFor<TName> | undefined = undefined
switch (toolCall.name) {
case "read_file":
if (args.files && Array.isArray(args.files)) {
nativeArgs = { files: args.files } as NativeArgsFor<TName>
}
break
case "attempt_completion":
if (args.result) {
nativeArgs = { result: args.result } as NativeArgsFor<TName>
}
break
case "execute_command":
if (args.command) {
nativeArgs = {
command: args.command,
cwd: args.cwd,
} as NativeArgsFor<TName>
}
break
case "insert_content":
if (args.path !== undefined && args.line !== undefined && args.content !== undefined) {
nativeArgs = {
path: args.path,
line: typeof args.line === "number" ? args.line : parseInt(String(args.line), 10),
content: args.content,
} as NativeArgsFor<TName>
}
break
case "apply_diff":
if (args.path !== undefined && args.diff !== undefined) {
nativeArgs = {
path: args.path,
diff: args.diff,
} as NativeArgsFor<TName>
}
break
case "ask_followup_question":
if (args.question !== undefined && args.follow_up !== undefined) {
nativeArgs = {
question: args.question,
follow_up: args.follow_up,
} as NativeArgsFor<TName>
}
break
case "browser_action":
if (args.action !== undefined) {
nativeArgs = {
action: args.action,
url: args.url,
coordinate: args.coordinate,
size: args.size,
text: args.text,
} as NativeArgsFor<TName>
}
break
case "codebase_search":
if (args.query !== undefined) {
nativeArgs = {
query: args.query,
path: args.path,
} as NativeArgsFor<TName>
}
break
case "fetch_instructions":
if (args.task !== undefined) {
nativeArgs = {
task: args.task,
} as NativeArgsFor<TName>
}
break
case "generate_image":
if (args.prompt !== undefined && args.path !== undefined) {
nativeArgs = {
prompt: args.prompt,
path: args.path,
image: args.image,
} as NativeArgsFor<TName>
}
break
case "list_code_definition_names":
if (args.path !== undefined) {
nativeArgs = {
path: args.path,
} as NativeArgsFor<TName>
}
break
case "run_slash_command":
if (args.command !== undefined) {
nativeArgs = {
command: args.command,
args: args.args,
} as NativeArgsFor<TName>
}
break
case "search_files":
if (args.path !== undefined && args.regex !== undefined) {
nativeArgs = {
path: args.path,
regex: args.regex,
file_pattern: args.file_pattern,
} as NativeArgsFor<TName>
}
break
case "switch_mode":
if (args.mode_slug !== undefined && args.reason !== undefined) {
nativeArgs = {
mode_slug: args.mode_slug,
reason: args.reason,
} as NativeArgsFor<TName>
}
break
case "update_todo_list":
if (args.todos !== undefined) {
nativeArgs = {
todos: args.todos,
} as NativeArgsFor<TName>
}
break
case "write_to_file":
if (args.path !== undefined && args.content !== undefined && args.line_count !== undefined) {
nativeArgs = {
path: args.path,
content: args.content,
line_count:
typeof args.line_count === "number"
? args.line_count
: parseInt(String(args.line_count), 10),
} as NativeArgsFor<TName>
}
break
case "use_mcp_tool":
if (args.server_name !== undefined && args.tool_name !== undefined) {
nativeArgs = {
server_name: args.server_name,
tool_name: args.tool_name,
arguments: args.arguments,
} as NativeArgsFor<TName>
}
break
default:
break
}
const result: ToolUse<TName> = {
type: "tool_use" as const,
name: toolCall.name,
params,
partial: false, // Native tool calls are always complete when yielded
nativeArgs,
}
return result
} catch (error) {
console.error(`Failed to parse tool call arguments:`, error)
console.error(`Error details:`, error instanceof Error ? error.message : String(error))
return null
}
}
/**
* Parse dynamic MCP tools (named mcp_serverName_toolName).
* These are generated dynamically by getMcpServerTools() and need to be
* converted back to use_mcp_tool format.
*/
private static parseDynamicMcpTool(toolCall: {
id: string
name: string
arguments: string
}): ToolUse<"use_mcp_tool"> | null {
try {
const args = JSON.parse(toolCall.arguments)
// Extract server_name and tool_name from the arguments
// The dynamic tool schema includes these as const properties
const serverName = args.server_name
const toolName = args.tool_name
const toolInputProps = args.toolInputProps
if (!serverName || !toolName) {
console.error(`Missing server_name or tool_name in dynamic MCP tool`)
return null
}
// Build params for backward compatibility with XML protocol
const params: Partial<Record<string, string>> = {
server_name: serverName,
tool_name: toolName,
}
if (toolInputProps) {
params.arguments = JSON.stringify(toolInputProps)
}
// Build nativeArgs with properly typed structure
const nativeArgs: NativeToolArgs["use_mcp_tool"] = {
server_name: serverName,
tool_name: toolName,
arguments: toolInputProps,
}
const result: ToolUse<"use_mcp_tool"> = {
type: "tool_use" as const,
name: "use_mcp_tool",
params,
partial: false,
nativeArgs,
}
return result
} catch (error) {
console.error(`Failed to parse dynamic MCP tool:`, error)
return null
}
}
}

205
src/core/assistant-message/__tests__/presentAssistantMessage-images.spec.ts Normal file
View file

@ -0,0 +1,205 @@
// npx vitest src/core/assistant-message/__tests__/presentAssistantMessage-images.spec.ts
import { describe, it, expect, beforeEach, vi } from "vitest"
import { Anthropic } from "@anthropic-ai/sdk"
import { presentAssistantMessage } from "../presentAssistantMessage"
import { Task } from "../../task/Task"
import { TOOL_PROTOCOL } from "@roo-code/types"
// Mock dependencies
vi.mock("../../task/Task")
vi.mock("../../tools/validateToolUse", () => ({
validateToolUse: vi.fn(),
}))
vi.mock("@roo-code/telemetry", () => ({
TelemetryService: {
instance: {
captureToolUsage: vi.fn(),
captureConsecutiveMistakeError: vi.fn(),
},
},
}))
describe("presentAssistantMessage - Image Handling in Native Tool Calls", () => {
let mockTask: any
beforeEach(() => {
// Create a mock Task with minimal properties needed for testing
mockTask = {
taskId: "test-task-id",
instanceId: "test-instance",
abort: false,
presentAssistantMessageLocked: false,
presentAssistantMessageHasPendingUpdates: false,
currentStreamingContentIndex: 0,
assistantMessageContent: [],
userMessageContent: [],
didCompleteReadingStream: false,
didRejectTool: false,
didAlreadyUseTool: false,
diffEnabled: false,
consecutiveMistakeCount: 0,
api: {
getModel: () => ({ id: "test-model", info: {} }),
},
browserSession: {
closeBrowser: vi.fn().mockResolvedValue(undefined),
},
recordToolUsage: vi.fn(),
toolRepetitionDetector: {
check: vi.fn().mockReturnValue({ allowExecution: true }),
},
providerRef: {
deref: () => ({
getState: vi.fn().mockResolvedValue({
mode: "code",
customModes: [],
}),
}),
},
say: vi.fn().mockResolvedValue(undefined),
ask: vi.fn().mockResolvedValue({ response: "yesButtonClicked" }),
}
})
it("should preserve images in tool_result for native protocol", async () => {
// Set up a tool_use block with an ID (indicates native protocol)
const toolCallId = "tool_call_123"
mockTask.assistantMessageContent = [
{
type: "tool_use",
id: toolCallId, // ID indicates native protocol
name: "ask_followup_question",
params: { question: "What do you see?" },
},
]
// Create a mock askApproval that includes images in the response
const imageBlock: Anthropic.ImageBlockParam = {
type: "image",
source: {
type: "base64",
media_type: "image/png",
data: "base64ImageData",
},
}
mockTask.ask = vi.fn().mockResolvedValue({
response: "yesButtonClicked",
text: "I see a cat",
images: ["data:image/png;base64,base64ImageData"],
})
// Execute presentAssistantMessage
await presentAssistantMessage(mockTask)
// Verify that userMessageContent was populated
expect(mockTask.userMessageContent.length).toBeGreaterThan(0)
// Find the tool_result block
const toolResult = mockTask.userMessageContent.find(
(item: any) => item.type === "tool_result" && item.tool_use_id === toolCallId,
)
expect(toolResult).toBeDefined()
expect(toolResult.tool_use_id).toBe(toolCallId)
// For native protocol, tool_result content should be a string (text only)
expect(typeof toolResult.content).toBe("string")
expect(toolResult.content).toContain("I see a cat")
// Images should be added as separate blocks AFTER the tool_result
const imageBlocks = mockTask.userMessageContent.filter((item: any) => item.type === "image")
expect(imageBlocks.length).toBeGreaterThan(0)
expect(imageBlocks[0].source.data).toBe("base64ImageData")
})
it("should convert to string when no images are present (native protocol)", async () => {
// Set up a tool_use block with an ID (indicates native protocol)
const toolCallId = "tool_call_456"
mockTask.assistantMessageContent = [
{
type: "tool_use",
id: toolCallId,
name: "ask_followup_question",
params: { question: "What is your name?" },
},
]
// Response with text but NO images
mockTask.ask = vi.fn().mockResolvedValue({
response: "yesButtonClicked",
text: "My name is Alice",
images: undefined,
})
await presentAssistantMessage(mockTask)
const toolResult = mockTask.userMessageContent.find(
(item: any) => item.type === "tool_result" && item.tool_use_id === toolCallId,
)
expect(toolResult).toBeDefined()
// When no images, content should be a string
expect(typeof toolResult.content).toBe("string")
})
it("should preserve images in content array for XML protocol (existing behavior)", async () => {
// Set up a tool_use block WITHOUT an ID (indicates XML protocol)
mockTask.assistantMessageContent = [
{
type: "tool_use",
// No ID = XML protocol
name: "ask_followup_question",
params: { question: "What do you see?" },
},
]
mockTask.ask = vi.fn().mockResolvedValue({
response: "yesButtonClicked",
text: "I see a dog",
images: ["data:image/png;base64,dogImageData"],
})
await presentAssistantMessage(mockTask)
// For XML protocol, content is added as separate blocks
// Check that both text and image blocks were added
const hasTextBlock = mockTask.userMessageContent.some((item: any) => item.type === "text")
const hasImageBlock = mockTask.userMessageContent.some((item: any) => item.type === "image")
expect(hasTextBlock).toBe(true)
// XML protocol preserves images as separate blocks in userMessageContent
expect(hasImageBlock).toBe(true)
})
it("should handle empty tool result gracefully", async () => {
const toolCallId = "tool_call_789"
mockTask.assistantMessageContent = [
{
type: "tool_use",
id: toolCallId,
name: "attempt_completion",
params: { result: "Task completed" },
},
]
// Empty response
mockTask.ask = vi.fn().mockResolvedValue({
response: "yesButtonClicked",
text: undefined,
images: undefined,
})
await presentAssistantMessage(mockTask)
const toolResult = mockTask.userMessageContent.find(
(item: any) => item.type === "tool_result" && item.tool_use_id === toolCallId,
)
expect(toolResult).toBeDefined()
// Should have fallback text
expect(toolResult.content).toBeTruthy()
})
})

355
src/core/assistant-message/presentAssistantMessage.ts
View file

@ -1,41 +1,45 @@
import cloneDeep from "clone-deep"
import { serializeError } from "serialize-error"
import { Anthropic } from "@anthropic-ai/sdk"
import type { ToolName, ClineAsk, ToolProgressStatus } from "@roo-code/types"
import { TelemetryService } from "@roo-code/telemetry"
import { defaultModeSlug, getModeBySlug } from "../../shared/modes"
import type { ToolParamName, ToolResponse } from "../../shared/tools"
import type { ToolParamName, ToolResponse, ToolUse } from "../../shared/tools"
import { Package } from "../../shared/package"
import { fetchInstructionsTool } from "../tools/fetchInstructionsTool"
import { listFilesTool } from "../tools/listFilesTool"
import { getReadFileToolDescription, readFileTool } from "../tools/readFileTool"
import { fetchInstructionsTool } from "../tools/FetchInstructionsTool"
import { listFilesTool } from "../tools/ListFilesTool"
import { readFileTool } from "../tools/ReadFileTool"
import { getSimpleReadFileToolDescription, simpleReadFileTool } from "../tools/simpleReadFileTool"
import { shouldUseSingleFileRead } from "@roo-code/types"
import { writeToFileTool } from "../tools/writeToFileTool"
import { applyDiffTool } from "../tools/multiApplyDiffTool"
import { insertContentTool } from "../tools/insertContentTool"
import { listCodeDefinitionNamesTool } from "../tools/listCodeDefinitionNamesTool"
import { searchFilesTool } from "../tools/searchFilesTool"
import { browserActionTool } from "../tools/browserActionTool"
import { executeCommandTool } from "../tools/executeCommandTool"
import { useMcpToolTool } from "../tools/useMcpToolTool"
import { shouldUseSingleFileRead, TOOL_PROTOCOL } from "@roo-code/types"
import { writeToFileTool } from "../tools/WriteToFileTool"
import { applyDiffTool } from "../tools/MultiApplyDiffTool"
import { insertContentTool } from "../tools/InsertContentTool"
import { listCodeDefinitionNamesTool } from "../tools/ListCodeDefinitionNamesTool"
import { searchFilesTool } from "../tools/SearchFilesTool"
import { browserActionTool } from "../tools/BrowserActionTool"
import { executeCommandTool } from "../tools/ExecuteCommandTool"
import { useMcpToolTool } from "../tools/UseMcpToolTool"
import { accessMcpResourceTool } from "../tools/accessMcpResourceTool"
import { askFollowupQuestionTool } from "../tools/askFollowupQuestionTool"
import { switchModeTool } from "../tools/switchModeTool"
import { attemptCompletionTool } from "../tools/attemptCompletionTool"
import { newTaskTool } from "../tools/newTaskTool"
import { askFollowupQuestionTool } from "../tools/AskFollowupQuestionTool"
import { switchModeTool } from "../tools/SwitchModeTool"
import { attemptCompletionTool, AttemptCompletionCallbacks } from "../tools/AttemptCompletionTool"
import { newTaskTool } from "../tools/NewTaskTool"
import { updateTodoListTool } from "../tools/updateTodoListTool"
import { runSlashCommandTool } from "../tools/runSlashCommandTool"
import { generateImageTool } from "../tools/generateImageTool"
import { updateTodoListTool } from "../tools/UpdateTodoListTool"
import { runSlashCommandTool } from "../tools/RunSlashCommandTool"
import { generateImageTool } from "../tools/GenerateImageTool"
import { formatResponse } from "../prompts/responses"
import { validateToolUse } from "../tools/validateToolUse"
import { Task } from "../task/Task"
import { codebaseSearchTool } from "../tools/codebaseSearchTool"
import { codebaseSearchTool } from "../tools/CodebaseSearchTool"
import { experiments, EXPERIMENT_IDS } from "../../shared/experiments"
import { applyDiffToolLegacy } from "../tools/applyDiffTool"
import { applyDiffTool as applyDiffToolClass } from "../tools/ApplyDiffTool"
import { isNativeProtocol } from "@roo-code/types"
import { resolveToolProtocol } from "../../utils/resolveToolProtocol"
/**
* Processes and presents assistant message content to the user interface.
@ -80,7 +84,18 @@ export async function presentAssistantMessage(cline: Task) {
return
}
const block = cloneDeep(cline.assistantMessageContent[cline.currentStreamingContentIndex]) // need to create copy bc while stream is updating the array, it could be updating the reference block properties too
let block: any
try {
block = cloneDeep(cline.assistantMessageContent[cline.currentStreamingContentIndex]) // need to create copy bc while stream is updating the array, it could be updating the reference block properties too
} catch (error) {
console.error(`ERROR cloning block:`, error)
console.error(
`Block content:`,
JSON.stringify(cline.assistantMessageContent[cline.currentStreamingContentIndex], null, 2),
)
cline.presentAssistantMessageLocked = false
return
}
switch (block.type) {
case "text": {
@ -163,7 +178,12 @@ export async function presentAssistantMessage(cline: Task) {
if (shouldUseSingleFileRead(modelId)) {
return getSimpleReadFileToolDescription(block.name, block.params)
} else {
return getReadFileToolDescription(block.name, block.params)
// Prefer native typed args when available; fall back to legacy params
// Check if nativeArgs exists (native protocol)
if (block.nativeArgs) {
return readFileTool.getReadFileToolDescription(block.name, block.nativeArgs)
}
return readFileTool.getReadFileToolDescription(block.name, block.params)
}
case "fetch_instructions":
return `[${block.name} for '${block.params.task}']`
@ -224,6 +244,8 @@ export async function presentAssistantMessage(cline: Task) {
return `[${block.name} for '${block.params.command}'${block.params.args ? ` with args: ${block.params.args}` : ""}]`
case "generate_image":
return `[${block.name} for '${block.params.path}']`
default:
return `[${block.name}]`
}
}
@ -255,13 +277,68 @@ export async function presentAssistantMessage(cline: Task) {
break
}
const pushToolResult = (content: ToolResponse) => {
cline.userMessageContent.push({ type: "text", text: `${toolDescription()} Result:` })
// Track if we've already pushed a tool result for this tool call (native protocol only)
let hasToolResult = false
if (typeof content === "string") {
cline.userMessageContent.push({ type: "text", text: content || "(tool did not return anything)" })
// Determine protocol by checking if this tool call has an ID.
// Native protocol tool calls ALWAYS have an ID (set when parsed from tool_call chunks).
// XML protocol tool calls NEVER have an ID (parsed from XML text).
const toolCallId = (block as any).id
const toolProtocol = toolCallId ? TOOL_PROTOCOL.NATIVE : TOOL_PROTOCOL.XML
const pushToolResult = (content: ToolResponse) => {
if (toolProtocol === TOOL_PROTOCOL.NATIVE) {
// For native protocol, only allow ONE tool_result per tool call
if (hasToolResult) {
console.warn(
`[presentAssistantMessage] Skipping duplicate tool_result for tool_use_id: ${toolCallId}`,
)
return
}
// For native protocol, tool_result content must be a string
// Images are added as separate blocks in the user message
let resultContent: string
let imageBlocks: Anthropic.ImageBlockParam[] = []
if (typeof content === "string") {
resultContent = content || "(tool did not return anything)"
} else {
// Separate text and image blocks
const textBlocks = content.filter((item) => item.type === "text")
imageBlocks = content.filter((item) => item.type === "image") as Anthropic.ImageBlockParam[]
// Convert text blocks to string for tool_result
resultContent =
textBlocks.map((item) => (item as Anthropic.TextBlockParam).text).join("\n") ||
"(tool did not return anything)"
}
// Add tool_result with text content only
cline.userMessageContent.push({
type: "tool_result",
tool_use_id: toolCallId,
content: resultContent,
} as Anthropic.ToolResultBlockParam)
// Add image blocks separately after tool_result
if (imageBlocks.length > 0) {
cline.userMessageContent.push(...imageBlocks)
}
hasToolResult = true
} else {
cline.userMessageContent.push(...content)
// For XML protocol, add as text blocks (legacy behavior)
cline.userMessageContent.push({ type: "text", text: `${toolDescription()} Result:` })
if (typeof content === "string") {
cline.userMessageContent.push({
type: "text",
text: content || "(tool did not return anything)",
})
} else {
cline.userMessageContent.push(...content)
}
}
// Once a tool result has been collected, ignore all other tool
@ -288,9 +365,14 @@ export async function presentAssistantMessage(cline: Task) {
// Handle both messageResponse and noButtonClicked with text.
if (text) {
await cline.say("user_feedback", text, images)
pushToolResult(formatResponse.toolResult(formatResponse.toolDeniedWithFeedback(text), images))
pushToolResult(
formatResponse.toolResult(
formatResponse.toolDeniedWithFeedback(text, toolProtocol),
images,
),
)
} else {
pushToolResult(formatResponse.toolDenied())
pushToolResult(formatResponse.toolDenied(toolProtocol))
}
cline.didRejectTool = true
return false
@ -299,7 +381,9 @@ export async function presentAssistantMessage(cline: Task) {
// Handle yesButtonClicked with text.
if (text) {
await cline.say("user_feedback", text, images)
pushToolResult(formatResponse.toolResult(formatResponse.toolApprovedWithFeedback(text), images))
pushToolResult(
formatResponse.toolResult(formatResponse.toolApprovedWithFeedback(text, toolProtocol), images),
)
}
return true
@ -322,7 +406,7 @@ export async function presentAssistantMessage(cline: Task) {
`Error ${action}:\n${error.message ?? JSON.stringify(serializeError(error), null, 2)}`,
)
pushToolResult(formatResponse.toolError(errorString))
pushToolResult(formatResponse.toolError(errorString, toolProtocol))
}
// If block is partial, remove partial closing tag so its not
@ -358,7 +442,7 @@ export async function presentAssistantMessage(cline: Task) {
if (!block.partial) {
cline.recordToolUsage(block.name)
TelemetryService.instance.captureToolUsage(cline.taskId, block.name)
TelemetryService.instance.captureToolUsage(cline.taskId, block.name, toolProtocol)
}
// Validate tool use before execution.
@ -374,7 +458,7 @@ export async function presentAssistantMessage(cline: Task) {
)
} catch (error) {
cline.consecutiveMistakeCount++
pushToolResult(formatResponse.toolError(error.message))
pushToolResult(formatResponse.toolError(error.message, toolProtocol))
break
}
@ -413,6 +497,7 @@ export async function presentAssistantMessage(cline: Task) {
pushToolResult(
formatResponse.toolError(
`Tool call repetition limit reached for ${block.name}. Please try a different approach.`,
toolProtocol,
),
)
break
@ -422,12 +507,39 @@ export async function presentAssistantMessage(cline: Task) {
switch (block.name) {
case "write_to_file":
await checkpointSaveAndMark(cline)
await writeToFileTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await writeToFileTool.handle(cline, block as ToolUse<"write_to_file">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "update_todo_list":
await updateTodoListTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await updateTodoListTool.handle(cline, block as ToolUse<"update_todo_list">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "apply_diff": {
await checkpointSaveAndMark(cline)
// Check if this tool call came from native protocol by checking for ID
// Native calls always have IDs, XML calls never do
if (toolProtocol === TOOL_PROTOCOL.NATIVE) {
await applyDiffToolClass.handle(cline, block as ToolUse<"apply_diff">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
}
// Get the provider and state to check experiment settings
const provider = cline.providerRef.deref()
let isMultiFileApplyDiffEnabled = false
@ -441,24 +553,27 @@ export async function presentAssistantMessage(cline: Task) {
}
if (isMultiFileApplyDiffEnabled) {
await checkpointSaveAndMark(cline)
await applyDiffTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
} else {
await checkpointSaveAndMark(cline)
await applyDiffToolLegacy(
cline,
block,
await applyDiffToolClass.handle(cline, block as ToolUse<"apply_diff">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
)
toolProtocol,
})
}
break
}
case "insert_content":
await checkpointSaveAndMark(cline)
await insertContentTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await insertContentTool.handle(cline, block as ToolUse<"insert_content">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "read_file":
// Check if this model should use the simplified single-file read tool
@ -471,41 +586,90 @@ export async function presentAssistantMessage(cline: Task) {
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
)
} else {
await readFileTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
// Type assertion is safe here because we're in the "read_file" case
await readFileTool.handle(cline, block as ToolUse<"read_file">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
}
break
case "fetch_instructions":
await fetchInstructionsTool(cline, block, askApproval, handleError, pushToolResult)
break
case "list_files":
await listFilesTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
break
case "codebase_search":
await codebaseSearchTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
break
case "list_code_definition_names":
await listCodeDefinitionNamesTool(
cline,
block,
await fetchInstructionsTool.handle(cline, block as ToolUse<"fetch_instructions">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
)
toolProtocol,
})
break
case "list_files":
await listFilesTool.handle(cline, block as ToolUse<"list_files">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "codebase_search":
await codebaseSearchTool.handle(cline, block as ToolUse<"codebase_search">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "list_code_definition_names":
await listCodeDefinitionNamesTool.handle(cline, block as ToolUse<"list_code_definition_names">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "search_files":
await searchFilesTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await searchFilesTool.handle(cline, block as ToolUse<"search_files">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "browser_action":
await browserActionTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await browserActionTool.handle(cline, block as ToolUse<"browser_action">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "execute_command":
await executeCommandTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await executeCommandTool.handle(cline, block as ToolUse<"execute_command">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "use_mcp_tool":
await useMcpToolTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await useMcpToolTool.handle(cline, block as ToolUse<"use_mcp_tool">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "access_mcp_resource":
await accessMcpResourceTool(
@ -518,38 +682,67 @@ export async function presentAssistantMessage(cline: Task) {
)
break
case "ask_followup_question":
await askFollowupQuestionTool(
cline,
block,
await askFollowupQuestionTool.handle(cline, block as ToolUse<"ask_followup_question">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
)
toolProtocol,
})
break
case "switch_mode":
await switchModeTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
break
case "new_task":
await newTaskTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
break
case "attempt_completion":
await attemptCompletionTool(
cline,
block,
await switchModeTool.handle(cline, block as ToolUse<"switch_mode">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "new_task":
await newTaskTool.handle(cline, block as ToolUse<"new_task">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "attempt_completion": {
const completionCallbacks: AttemptCompletionCallbacks = {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolDescription,
askFinishSubTaskApproval,
toolDescription,
toolProtocol,
}
await attemptCompletionTool.handle(
cline,
block as ToolUse<"attempt_completion">,
completionCallbacks,
)
break
}
case "run_slash_command":
await runSlashCommandTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await runSlashCommandTool.handle(cline, block as ToolUse<"run_slash_command">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
case "generate_image":
await generateImageTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag)
await checkpointSaveAndMark(cline)
await generateImageTool.handle(cline, block as ToolUse<"generate_image">, {
askApproval,
handleError,
pushToolResult,
removeClosingTag,
toolProtocol,
})
break
}
@ -596,6 +789,12 @@ export async function presentAssistantMessage(cline: Task) {
// this function ourselves.
presentAssistantMessage(cline)
return
} else {
// CRITICAL FIX: If we're out of bounds and the stream is complete, set userMessageContentReady
// This handles the case where assistantMessageContent is empty or becomes empty after processing
if (cline.didCompleteReadingStream) {
cline.userMessageContentReady = true
}
}
}

71
src/core/sliding-window/__tests__/sliding-window.spec.ts → src/core/context-management/__tests__/context-management.spec.ts
View file

@ -1,4 +1,4 @@
// npx vitest src/core/sliding-window/__tests__/sliding-window.spec.ts
// cd src && npx vitest run core/context-management/__tests__/context-management.spec.ts
import { Anthropic } from "@anthropic-ai/sdk"
@ -9,12 +9,7 @@ import { BaseProvider } from "../../../api/providers/base-provider"
import { ApiMessage } from "../../task-persistence/apiMessages"
import * as condenseModule from "../../condense"
import {
TOKEN_BUFFER_PERCENTAGE,
estimateTokenCount,
truncateConversation,
truncateConversationIfNeeded,
} from "../index"
import { TOKEN_BUFFER_PERCENTAGE, estimateTokenCount, truncateConversation, manageContext } from "../index"
// Create a mock ApiHandler for testing
class MockApiHandler extends BaseProvider {
@ -49,7 +44,7 @@ class MockApiHandler extends BaseProvider {
const mockApiHandler = new MockApiHandler()
const taskId = "test-task-id"
describe("Sliding Window", () => {
describe("Context Management", () => {
beforeEach(() => {
if (!TelemetryService.hasInstance()) {
TelemetryService.createInstance([])
@ -234,9 +229,9 @@ describe("Sliding Window", () => {
})
/**
* Tests for the truncateConversationIfNeeded function
* Tests for the manageContext function
*/
describe("truncateConversationIfNeeded", () => {
describe("manageContext", () => {
const createModelInfo = (contextWindow: number, maxTokens?: number): ModelInfo => ({
contextWindow,
supportsPromptCache: true,
@ -261,7 +256,7 @@ describe("Sliding Window", () => {
{ ...messages[messages.length - 1], content: "" },
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow: modelInfo.contextWindow,
@ -302,7 +297,7 @@ describe("Sliding Window", () => {
messagesWithSmallContent[4],
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow: modelInfo.contextWindow,
@ -337,7 +332,7 @@ describe("Sliding Window", () => {
// Test below threshold
const belowThreshold = 69999
const result1 = await truncateConversationIfNeeded({
const result1 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: belowThreshold,
contextWindow: modelInfo1.contextWindow,
@ -351,7 +346,7 @@ describe("Sliding Window", () => {
currentProfileId: "default",
})
const result2 = await truncateConversationIfNeeded({
const result2 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: belowThreshold,
contextWindow: modelInfo2.contextWindow,
@ -372,7 +367,7 @@ describe("Sliding Window", () => {
// Test above threshold
const aboveThreshold = 70001
const result3 = await truncateConversationIfNeeded({
const result3 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: aboveThreshold,
contextWindow: modelInfo1.contextWindow,
@ -386,7 +381,7 @@ describe("Sliding Window", () => {
currentProfileId: "default",
})
const result4 = await truncateConversationIfNeeded({
const result4 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: aboveThreshold,
contextWindow: modelInfo2.contextWindow,
@ -422,7 +417,7 @@ describe("Sliding Window", () => {
// Set base tokens so total is well below threshold + buffer even with small content added
const dynamicBuffer = modelInfo.contextWindow * TOKEN_BUFFER_PERCENTAGE
const baseTokensForSmall = availableTokens - smallContentTokens - dynamicBuffer - 10
const resultWithSmall = await truncateConversationIfNeeded({
const resultWithSmall = await manageContext({
messages: messagesWithSmallContent,
totalTokens: baseTokensForSmall,
contextWindow: modelInfo.contextWindow,
@ -457,7 +452,7 @@ describe("Sliding Window", () => {
// Set base tokens so we're just below threshold without content, but over with content
const baseTokensForLarge = availableTokens - Math.floor(largeContentTokens / 2)
const resultWithLarge = await truncateConversationIfNeeded({
const resultWithLarge = await manageContext({
messages: messagesWithLargeContent,
totalTokens: baseTokensForLarge,
contextWindow: modelInfo.contextWindow,
@ -485,7 +480,7 @@ describe("Sliding Window", () => {
// Set base tokens so we're just below threshold without content
const baseTokensForVeryLarge = availableTokens - Math.floor(veryLargeContentTokens / 2)
const resultWithVeryLarge = await truncateConversationIfNeeded({
const resultWithVeryLarge = await manageContext({
messages: messagesWithVeryLargeContent,
totalTokens: baseTokensForVeryLarge,
contextWindow: modelInfo.contextWindow,
@ -523,7 +518,7 @@ describe("Sliding Window", () => {
messagesWithSmallContent[4],
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow: modelInfo.contextWindow,
@ -570,7 +565,7 @@ describe("Sliding Window", () => {
{ ...messages[messages.length - 1], content: "" },
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow: modelInfo.contextWindow,
@ -637,7 +632,7 @@ describe("Sliding Window", () => {
messagesWithSmallContent[4],
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow: modelInfo.contextWindow,
@ -684,7 +679,7 @@ describe("Sliding Window", () => {
messagesWithSmallContent[4],
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow: modelInfo.contextWindow,
@ -741,7 +736,7 @@ describe("Sliding Window", () => {
{ ...messages[messages.length - 1], content: "" },
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow,
@ -793,7 +788,7 @@ describe("Sliding Window", () => {
{ ...messages[messages.length - 1], content: "" },
]
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow,
@ -880,7 +875,7 @@ describe("Sliding Window", () => {
.spyOn(condenseModule, "summarizeConversation")
.mockResolvedValue(mockSummarizeResponse)
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow,
@ -946,7 +941,7 @@ describe("Sliding Window", () => {
.spyOn(condenseModule, "summarizeConversation")
.mockResolvedValue(mockSummarizeResponse)
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow,
@ -1000,7 +995,7 @@ describe("Sliding Window", () => {
vi.clearAllMocks()
const summarizeSpy = vi.spyOn(condenseModule, "summarizeConversation")
const result = await truncateConversationIfNeeded({
const result = await manageContext({
messages: messagesWithSmallContent,
totalTokens,
contextWindow,
@ -1030,10 +1025,10 @@ describe("Sliding Window", () => {
})
/**
* Tests for the getMaxTokens function (private but tested through truncateConversationIfNeeded)
* Tests for the getMaxTokens function (private but tested through manageContext)
*/
describe("getMaxTokens", () => {
// We'll test this indirectly through truncateConversationIfNeeded
// We'll test this indirectly through manageContext
const createModelInfo = (contextWindow: number, maxTokens?: number): ModelInfo => ({
contextWindow,
supportsPromptCache: true, // Not relevant for getMaxTokens
@ -1061,7 +1056,7 @@ describe("Sliding Window", () => {
// Account for the dynamic buffer which is 10% of context window (10,000 tokens)
// Below max tokens and buffer - no truncation
const result1 = await truncateConversationIfNeeded({
const result1 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 39999, // Well below threshold + dynamic buffer
contextWindow: modelInfo.contextWindow,
@ -1082,7 +1077,7 @@ describe("Sliding Window", () => {
})
// Above max tokens - truncate
const result2 = await truncateConversationIfNeeded({
const result2 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 50001, // Above threshold
contextWindow: modelInfo.contextWindow,
@ -1114,7 +1109,7 @@ describe("Sliding Window", () => {
// Account for the dynamic buffer which is 10% of context window (10,000 tokens)
// Below max tokens and buffer - no truncation
const result1 = await truncateConversationIfNeeded({
const result1 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 81807, // Well below threshold + dynamic buffer (91808 - 10000 = 81808)
contextWindow: modelInfo.contextWindow,
@ -1135,7 +1130,7 @@ describe("Sliding Window", () => {
})
// Above max tokens - truncate
const result2 = await truncateConversationIfNeeded({
const result2 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 81809, // Above threshold (81808)
contextWindow: modelInfo.contextWindow,
@ -1166,7 +1161,7 @@ describe("Sliding Window", () => {
]
// Below max tokens and buffer - no truncation
const result1 = await truncateConversationIfNeeded({
const result1 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 34999, // Well below threshold + buffer
contextWindow: modelInfo.contextWindow,
@ -1182,7 +1177,7 @@ describe("Sliding Window", () => {
expect(result1.messages).toEqual(messagesWithSmallContent)
// Above max tokens - truncate
const result2 = await truncateConversationIfNeeded({
const result2 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 40001, // Above threshold
contextWindow: modelInfo.contextWindow,
@ -1211,7 +1206,7 @@ describe("Sliding Window", () => {
// Account for the dynamic buffer which is 10% of context window (20,000 tokens for this test)
// Below max tokens and buffer - no truncation
const result1 = await truncateConversationIfNeeded({
const result1 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 149999, // Well below threshold + dynamic buffer
contextWindow: modelInfo.contextWindow,
@ -1227,7 +1222,7 @@ describe("Sliding Window", () => {
expect(result1.messages).toEqual(messagesWithSmallContent)
// Above max tokens - truncate
const result2 = await truncateConversationIfNeeded({
const result2 = await manageContext({
messages: messagesWithSmallContent,
totalTokens: 170001, // Above threshold
contextWindow: modelInfo.contextWindow,

46
src/core/sliding-window/index.ts → src/core/context-management/index.ts
View file

@ -8,7 +8,18 @@ import { ApiMessage } from "../task-persistence/apiMessages"
import { ANTHROPIC_DEFAULT_MAX_TOKENS } from "@roo-code/types"
/**
* Default percentage of the context window to use as a buffer when deciding when to truncate
* Context Management
*
* This module provides Context Management for conversations, combining:
* - Intelligent condensation of prior messages when approaching configured thresholds
* - Sliding window truncation as a fallback when necessary
*
* Behavior and exports are preserved exactly from the previous sliding-window implementation.
*/
/**
* Default percentage of the context window to use as a buffer when deciding when to truncate.
* Used by Context Management to determine when to trigger condensation or (fallback) sliding window truncation.
*/
export const TOKEN_BUFFER_PERCENTAGE = 0.1
@ -33,6 +44,8 @@ export async function estimateTokenCount(
* The first message is always retained, and a specified fraction (rounded to an even number)
* of messages from the beginning (excluding the first) is removed.
*
* This implements the sliding window truncation behavior.
*
* @param {ApiMessage[]} messages - The conversation messages.
* @param {number} fracToRemove - The fraction (between 0 and 1) of messages (excluding the first) to remove.
* @param {string} taskId - The task ID for the conversation, used for telemetry
@ -50,20 +63,16 @@ export function truncateConversation(messages: ApiMessage[], fracToRemove: numbe
}
/**
* Conditionally truncates the conversation messages if the total token count
* exceeds the model's limit, considering the size of incoming content.
* Context Management: Conditionally manages the conversation context when approaching limits.
*
* @param {ApiMessage[]} messages - The conversation messages.
* @param {number} totalTokens - The total number of tokens in the conversation (excluding the last user message).
* @param {number} contextWindow - The context window size.
* @param {number} maxTokens - The maximum number of tokens allowed.
* @param {ApiHandler} apiHandler - The API handler to use for token counting.
* @param {boolean} autoCondenseContext - Whether to use LLM summarization or sliding window implementation
* @param {string} systemPrompt - The system prompt, used for estimating the new context size after summarizing.
* @returns {ApiMessage[]} The original or truncated conversation messages.
* Attempts intelligent condensation of prior messages when thresholds are reached.
* Falls back to sliding window truncation if condensation is unavailable or fails.
*
* @param {ContextManagementOptions} options - The options for truncation/condensation
* @returns {Promise<ApiMessage[]>} The original, condensed, or truncated conversation messages.
*/
type TruncateOptions = {
export type ContextManagementOptions = {
messages: ApiMessage[]
totalTokens: number
contextWindow: number
@ -79,16 +88,15 @@ type TruncateOptions = {
currentProfileId: string
}
type TruncateResponse = SummarizeResponse & { prevContextTokens: number }
export type ContextManagementResult = SummarizeResponse & { prevContextTokens: number }
/**
* Conditionally truncates the conversation messages if the total token count
* exceeds the model's limit, considering the size of incoming content.
* Conditionally manages conversation context (condense and fallback truncation).
*
* @param {TruncateOptions} options - The options for truncation
* @returns {Promise<ApiMessage[]>} The original or truncated conversation messages.
* @param {ContextManagementOptions} options - The options for truncation/condensation
* @returns {Promise<ApiMessage[]>} The original, condensed, or truncated conversation messages.
*/
export async function truncateConversationIfNeeded({
export async function manageContext({
messages,
totalTokens,
contextWindow,
@ -102,7 +110,7 @@ export async function truncateConversationIfNeeded({
condensingApiHandler,
profileThresholds,
currentProfileId,
}: TruncateOptions): Promise<TruncateResponse> {
}: ContextManagementOptions): Promise<ContextManagementResult> {
let error: string | undefined
let cost = 0
// Calculate the maximum tokens reserved for response

70
src/core/environment/__tests__/getEnvironmentDetails.spec.ts
View file

@ -17,6 +17,7 @@ import { ApiHandler } from "../../../api/index"
import { ClineProvider } from "../../webview/ClineProvider"
import { RooIgnoreController } from "../../ignore/RooIgnoreController"
import { formatResponse } from "../../prompts/responses"
import { getGitStatus } from "../../../utils/git"
import { Task } from "../../task/Task"
vi.mock("vscode", () => ({
@ -48,6 +49,7 @@ vi.mock("../../../services/glob/list-files")
vi.mock("../../../integrations/terminal/TerminalRegistry")
vi.mock("../../../integrations/terminal/Terminal")
vi.mock("../../../utils/path")
vi.mock("../../../utils/git")
vi.mock("../../prompts/responses")
describe("getEnvironmentDetails", () => {
@ -134,6 +136,7 @@ describe("getEnvironmentDetails", () => {
;(TerminalRegistry.getBackgroundTerminals as Mock).mockReturnValue([])
;(TerminalRegistry.isProcessHot as Mock).mockReturnValue(false)
;(TerminalRegistry.getUnretrievedOutput as Mock).mockReturnValue("")
;(getGitStatus as Mock).mockResolvedValue("## main")
vi.mocked(pWaitFor).mockResolvedValue(undefined)
vi.mocked(delay).mockResolvedValue(undefined)
})
@ -143,9 +146,9 @@ describe("getEnvironmentDetails", () => {
expect(result).toContain("<environment_details>")
expect(result).toContain("</environment_details>")
expect(result).toContain("# VSCode Visible Files")
expect(result).toContain("# VSCode Open Tabs")
// Visible Files and Open Tabs headers only appear when there's content
expect(result).toContain("# Current Time")
expect(result).not.toContain("# Git Status") // Git status is disabled by default (maxGitStatusFiles = 0)
expect(result).toContain("# Current Cost")
expect(result).toContain("# Current Mode")
expect(result).toContain("<model>test-model</model>")
@ -390,4 +393,67 @@ describe("getEnvironmentDetails", () => {
const result = await getEnvironmentDetails(cline as Task)
expect(result).toContain("REMINDERS")
})
it("should include git status when maxGitStatusFiles > 0", async () => {
;(getGitStatus as Mock).mockResolvedValue("## main\nM file1.ts")
mockProvider.getState.mockResolvedValue({
...mockState,
maxGitStatusFiles: 10,
})
const result = await getEnvironmentDetails(mockCline as Task)
expect(result).toContain("# Git Status")
expect(result).toContain("## main")
expect(getGitStatus).toHaveBeenCalledWith(mockCwd, 10)
})
it("should NOT include git status when maxGitStatusFiles is 0", async () => {
mockProvider.getState.mockResolvedValue({
...mockState,
maxGitStatusFiles: 0,
})
const result = await getEnvironmentDetails(mockCline as Task)
expect(result).not.toContain("# Git Status")
expect(getGitStatus).not.toHaveBeenCalled()
})
it("should NOT include git status when maxGitStatusFiles is undefined (defaults to 0)", async () => {
mockProvider.getState.mockResolvedValue({
...mockState,
maxGitStatusFiles: undefined,
})
const result = await getEnvironmentDetails(mockCline as Task)
expect(result).not.toContain("# Git Status")
expect(getGitStatus).not.toHaveBeenCalled()
})
it("should handle git status returning null gracefully when enabled", async () => {
;(getGitStatus as Mock).mockResolvedValue(null)
mockProvider.getState.mockResolvedValue({
...mockState,
maxGitStatusFiles: 10,
})
const result = await getEnvironmentDetails(mockCline as Task)
expect(result).not.toContain("# Git Status")
expect(getGitStatus).toHaveBeenCalledWith(mockCwd, 10)
})
it("should pass maxFiles parameter to getGitStatus", async () => {
;(getGitStatus as Mock).mockResolvedValue("## main")
mockProvider.getState.mockResolvedValue({
...mockState,
maxGitStatusFiles: 5,
})
await getEnvironmentDetails(mockCline as Task)
expect(getGitStatus).toHaveBeenCalledWith(mockCwd, 5)
})
})

20
src/core/environment/getEnvironmentDetails.ts
View file

@ -17,6 +17,7 @@ import { TerminalRegistry } from "../../integrations/terminal/TerminalRegistry"
import { Terminal } from "../../integrations/terminal/Terminal"
import { arePathsEqual } from "../../utils/path"
import { formatResponse } from "../prompts/responses"
import { getGitStatus } from "../../utils/git"
import { Task } from "../task/Task"
import { formatReminderSection } from "./reminder"
@ -34,8 +35,6 @@ export async function getEnvironmentDetails(cline: Task, includeFileDetails: boo
// It could be useful for cline to know if the user went from one or no
// file to another between messages, so we always include this context.
details += "\n\n# VSCode Visible Files"
const visibleFilePaths = vscode.window.visibleTextEditors
?.map((editor) => editor.document?.uri?.fsPath)
.filter(Boolean)
@ -48,12 +47,10 @@ export async function getEnvironmentDetails(cline: Task, includeFileDetails: boo
: visibleFilePaths.map((p) => p.toPosix()).join("\n")
if (allowedVisibleFiles) {
details += "\n\n# VSCode Visible Files"
details += `\n${allowedVisibleFiles}`
} else {
details += "\n(No visible files)"
}
details += "\n\n# VSCode Open Tabs"
const { maxOpenTabsContext } = state ?? {}
const maxTabs = maxOpenTabsContext ?? 20
const openTabPaths = vscode.window.tabGroups.all
@ -70,9 +67,8 @@ export async function getEnvironmentDetails(cline: Task, includeFileDetails: boo
: openTabPaths.map((p) => p.toPosix()).join("\n")
if (allowedOpenTabs) {
details += "\n\n# VSCode Open Tabs"
details += `\n${allowedOpenTabs}`
} else {
details += "\n(No open tabs)"
}
// Get task-specific and background terminals.
@ -191,7 +187,7 @@ export async function getEnvironmentDetails(cline: Task, includeFileDetails: boo
}
// Get settings for time and cost display
const { includeCurrentTime = true, includeCurrentCost = true } = state ?? {}
const { includeCurrentTime = true, includeCurrentCost = true, maxGitStatusFiles = 0 } = state ?? {}
// Add current time information with timezone (if enabled).
if (includeCurrentTime) {
@ -205,6 +201,14 @@ export async function getEnvironmentDetails(cline: Task, includeFileDetails: boo
details += `\n\n# Current Time\nCurrent time in ISO 8601 UTC format: ${now.toISOString()}\nUser time zone: ${timeZone}, UTC${timeZoneOffsetStr}`
}
// Add git status information (if enabled with maxGitStatusFiles > 0).
if (maxGitStatusFiles > 0) {
const gitStatus = await getGitStatus(cline.cwd, maxGitStatusFiles)
if (gitStatus) {
details += `\n\n# Git Status\n${gitStatus}`
}
}
// Add context tokens information (if enabled).
if (includeCurrentCost) {
const { totalCost } = getApiMetrics(cline.clineMessages)

5
src/core/prompts/__tests__/__snapshots__/add-custom-instructions/architect-mode-prompt.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -409,7 +409,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -429,6 +429,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

12
src/core/prompts/__tests__/__snapshots__/add-custom-instructions/ask-mode-prompt.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, a knowledgeable technical assistant focused on answering questions
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -342,7 +342,6 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -360,12 +359,9 @@ RULES
- You cannot `cd` into a different directory to complete a task. You are stuck operating from '/test/path', so be sure to pass in the correct 'path' parameter when using tools that require a path.
- Do not use the ~ character or $HOME to refer to the home directory.
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.
- When using the write_to_file tool to modify a file, use the tool directly with the desired content. You do not need to display the content before using the tool. ALWAYS provide the COMPLETE file content in your response. This is NON-NEGOTIABLE. Partial updates or placeholders like '// rest of code unchanged' are STRICTLY FORBIDDEN. You MUST include ALL parts of the file, even if they haven't been modified. Failure to do so will result in incomplete or broken code, severely impacting the user's project.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches.
- Some modes have restrictions on which files they can edit. If you attempt to edit a restricted file, the operation will be rejected with a FileRestrictionError that will specify which file patterns are allowed for the current mode.
- Be sure to consider the type of project (e.g. Python, JavaScript, web application) when determining the appropriate structure and files to include. Also consider what files may be most relevant to accomplishing the task, for example looking at a project's manifest file would help you understand the project's dependencies, which you could incorporate into any code you write.
* For example, in architect mode trying to edit app.js would be rejected because architect mode can only edit files matching "\.md$"

5
src/core/prompts/__tests__/__snapshots__/add-custom-instructions/mcp-server-creation-disabled.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -408,7 +408,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -428,6 +428,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/add-custom-instructions/mcp-server-creation-enabled.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -475,7 +475,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
- You have access to MCP servers that may provide additional tools and resources. Each server may provide different capabilities that you can use to accomplish tasks more effectively.
@ -497,6 +497,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/add-custom-instructions/partial-reads-enabled.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -414,7 +414,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -434,6 +434,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/consistent-system-prompt.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -409,7 +409,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -429,6 +429,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/with-computer-use-support.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -462,7 +462,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
- You can use the browser_action tool to interact with websites (including html files and locally running development servers) through a Puppeteer-controlled browser when you feel it is necessary in accomplishing the user's task. This tool is particularly useful for web development tasks as it allows you to launch a browser, navigate to pages, interact with elements through clicks and keyboard input, and capture the results through screenshots and console logs. This tool may be useful at key stages of web development tasks-such as after implementing new features, making substantial changes, when troubleshooting issues, or to verify the result of your work. You can analyze the provided screenshots to ensure correct rendering or identify errors, and review console logs for runtime issues.
- For example, if asked to add a component to a react website, you might create the necessary files, use execute_command to run the site locally, then use browser_action to launch the browser, navigate to the local server, and verify the component renders & functions correctly before closing the browser.
@ -484,6 +484,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/with-diff-enabled-false.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -409,7 +409,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -429,6 +429,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/with-diff-enabled-true.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -497,7 +497,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the apply_diff or write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the apply_diff, write_to_file, or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -517,6 +517,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using apply_diff or write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: apply_diff (for surgical edits - targeted changes to specific lines or functions), write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/with-diff-enabled-undefined.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -409,7 +409,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -429,6 +429,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/with-different-viewport-size.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -409,7 +409,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
====
@ -429,6 +429,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

5
src/core/prompts/__tests__/__snapshots__/system-prompt/with-mcp-hub-provided.snap generated
View file

@ -4,7 +4,7 @@ You are Roo, an experienced technical leader who is inquisitive and an excellent
MARKDOWN RULES
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in <attempt_completion>
ALL responses MUST show ANY `language construct` OR filename reference as clickable, exactly as [`filename OR language.declaration()`](relative/file/path.ext:line); line is required for `syntax` and optional for filename links. This applies to ALL markdown responses and ALSO those in attempt_completion
====
@ -475,7 +475,7 @@ CAPABILITIES
- When the user initially gives you a task, a recursive list of all filepaths in the current workspace directory ('/test/path') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current workspace directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
- You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file or insert_content tool to apply the changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
- You have access to MCP servers that may provide additional tools and resources. Each server may provide different capabilities that you can use to accomplish tasks more effectively.
@ -497,6 +497,7 @@ RULES
- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '/test/path', and if so prepend with `cd`'ing into that directory && then executing the command (as one command since you are stuck operating from '/test/path'). For example, if you needed to run `npm install` in a project outside of '/test/path', you would need to prepend with a `cd` i.e. pseudocode for this would be `cd (path to project) && (command, in this case npm install)`.
- When using the search_files tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the search_files tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using write_to_file to make informed changes.
- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when writing files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
- For editing files, you have access to these tools: write_to_file (for creating new files or complete file rewrites), insert_content (for adding lines to files).
- The insert_content tool adds lines of text to files at a specific line number, such as adding a new function to a JavaScript file or inserting a new route in a Python file. Use line number 0 to append at the end of the file, or any positive number to insert before that line.
- You should always prefer using other editing tools over write_to_file when making changes to existing files since write_to_file is much slower and cannot handle large files.

Some files were not shown because too many files have changed in this diff Show more