Merge token counter to master

[ultmaster]

No description provided.

[Copilot]

Pull Request Overview

This PR adds image token counting functionality and integrates token counts into the LSP server and VSCode panel, along with corresponding UI updates.

• Introduce estimateImageTokens util to compute image token usage for OpenAI vision models
• Integrate token computation in the LSP server (computeTokens) and return counts in preview responses
• Update VSCode panel UI and types to display per-message and total token counts

Reviewed Changes

Copilot reviewed 9 out of 10 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
packages/poml/util/tokenCounterImage.ts	New helper to estimate image tokens for vision models
packages/poml/util/image.ts	Utility to extract image dimensions using sharp
packages/poml/tests/tokenCounterImage.test.ts	Tests for image token estimator (patch & detail modes)
packages/poml-vscode/panel/types.ts	Extend preview types with returnTokenCounts
packages/poml-vscode/panel/panel.ts	Populate returnTokenCounts based on language model
packages/poml-vscode/panel/content.tsx	Render per-message and total token counts in UI
packages/poml-vscode/lsp/server.ts	Compute and cache token counts for text/image content
package.json	Add js-tiktoken dependency for token encoding
media/style.css	Styles for token count display

Comments suppressed due to low confidence (2)

packages/poml/tests/tokenCounterImage.test.ts:5

• Add test cases for the billable option in estimateImageTokens to verify that billed token counts (with billable: true) produce the correct rounded values.

  const cases: { w: number; h: number; model: VisionModel; detail?: DetailLevel; expected: number }[] = [

packages/poml-vscode/panel/types.ts:57

• Consider tightening the type of model here from string to VisionModel (or a union of supported model names) to prevent invalid model names at compile time.

  returnTokenCounts?: { model: string };

[Copilot]

[nitpick] The returnTokenCounts assignment is duplicated in two methods; extracting it into a helper (e.g. buildPreviewParams) would reduce repetition and simplify future updates.

Suggested change

	returnTokenCounts: { model: languageModelSettings.model },
	...this.buildPreviewParams(languageModelSettings),