…rt list (#13809)

### What this PR does

Before this PR:
- `PDF_NATIVE_PROVIDER_TYPES` included `'openai'`, `'new-api'`, and
`'gateway'` types, assuming all OpenAI-compatible providers support
native PDF file input via the `file` part type.
- Sending a PDF to providers like Moonshot/Kimi (which have `type:
'openai'`) resulted in a 400 error: `"invalid part type: file"`.
- A special-case `isCherryAI` check was needed because CherryAI also has
`type: 'openai'` but doesn't support native PDF.

After this PR:
- Only first-party provider protocols (`openai-response`, `anthropic`,
`gemini`, `azure-openai`, `vertexai`, `aws-bedrock`, `vertex-anthropic`)
are in `PDF_NATIVE_PROVIDER_TYPES`.
- All `type: 'openai'` providers (Moonshot, DeepSeek, Groq, CherryAI,
cherryin, etc.) correctly have PDFs converted to text before sending.
- The CherryAI special-case check is removed as it's no longer needed.

### Why we need it and why it was done in this way

The following tradeoffs were made:
- Removed `'openai'` entirely from the native set rather than adding
per-provider ID exceptions, because the actual OpenAI provider uses
`type: 'openai-response'` (not `'openai'`), and the vast majority of
`type: 'openai'` providers are third-party APIs that don't support
`file` parts.
- Also removed `'new-api'` and `'gateway'` aggregator types, since these
route to various backends — it's safer to convert PDFs to text and let
specific backends handle text rather than risk `file` part errors.

The following alternatives were considered:
- Adding individual provider IDs (like `moonshot`) to a blocklist —
rejected as it's whack-a-mole; new OpenAI-compatible providers would
keep hitting the same bug.
- Keeping `'openai'` in the set and adding more ID-based exceptions —
rejected for the same reason.

Links to places where the discussion took place:
- PR #13641 introduced the `pdfCompatibilityPlugin` with the overly
broad provider type set
- PR #13777 added the CherryAI special case as a point fix

### Breaking changes

None. Providers that previously had PDFs silently fail with 400 errors
will now correctly receive extracted text content instead.

### Special notes for your reviewer

- The actual OpenAI provider uses `type: 'openai-response'`, which
remains in the native set — real OpenAI API users are unaffected.
- All existing tests updated to match new behavior. Test suite passes
fully (3811 tests).
- The `isCherryAI` special case from PR #13777 is removed since CherryAI
(`type: 'openai'`) is now naturally handled by the conversion path.

### Checklist

- [x] PR: The PR description is expressive enough and will help future
contributors
- [x] Code: [Write code that humans can
understand](https://en.wikiquote.org/wiki/Martin_Fowler#code-for-humans)
and [Keep it simple](https://en.wikipedia.org/wiki/KISS_principle)
- [x] Refactor: You have [left the code cleaner than you found it (Boy
Scout
Rule)](https://learning.oreilly.com/library/view/97-things-every/9780596809515/ch08.html)
- [x] Upgrade: Impact of this change on upgrade flows was considered and
addressed if required
- [ ] Documentation: A [user-guide update](https://docs.cherry-ai.com)
was considered and is present (link) or not required. Check this only
when the PR introduces or changes a user-facing feature or behavior.
- [x] Self-review: I have reviewed my own code (e.g., via
[`/gh-pr-review`](/.claude/skills/gh-pr-review/SKILL.md), `gh pr diff`,
or GitHub UI) before requesting review from others

### Release note

```release-note
Fixed PDF file upload failing with "invalid part type: file" error for OpenAI-compatible providers (Moonshot, DeepSeek, Groq, etc.). PDFs are now correctly converted to text for these providers.
```

---------

Signed-off-by: suyao <[email protected]>
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Phantom <[email protected]>

…are (#13777)

### What this PR does

Before this PR:
1. CherryAI provider was incorrectly treated as supporting native PDF
input because its provider type matches `PDF_NATIVE_PROVIDER_TYPES`,
causing PDF files not being converted to text
2. PDF text extraction failed in production Electron builds with error:
`Cannot find module '.../pdf.worker.mjs'` because `pdf-parse` was in
devDependencies instead of dependencies

After this PR:
1. Added explicit check to exclude CherryAI provider from native PDF
handling
2. Moved `pdf-parse` from devDependencies to dependencies so it's
bundled correctly in Electron production builds

Fixes # N/A

### Why we need it and why it was done in this way

**Issue 1 - CherryAI provider:**
CherryAI is a proxy provider that doesn't actually support native PDF
input like the underlying providers (Anthropic, Google) do. The
middleware needs to convert PDFs to text before sending to CherryAI.

**Issue 2 - pdf-parse not found:**
In Electron apps, only `dependencies` are bundled into the production
build (`app.asar`), while `devDependencies` are excluded. Since
`pdf-parse` is required at runtime for PDF text extraction, it must be
in `dependencies`.

The following tradeoffs were made:
- Used provider ID check (`provider.id === 'cherryai'`) rather than
modifying the provider type set, as this is more explicit and
maintainable

The following alternatives were considered:
- Removing CherryAI's provider type from `PDF_NATIVE_PROVIDER_TYPES` -
rejected because CherryAI can proxy to multiple provider types

### Breaking changes

None

### Special notes for your reviewer

This is a bug fix that doesn't change Redux data models or IndexedDB
schemas.

### Checklist

- [x] PR: The PR description is expressive enough and will help future
contributors
- [x] Code: Write code that humans can understand and Keep it simple
- [x] Refactor: You have left the code cleaner than you found it (Boy
Scout Rule)
- [x] Upgrade: Impact of this change on upgrade flows was considered and
addressed if required
- [x] Documentation: A user-guide update was considered and is not
required
- [x] Self-review: I have reviewed my own code before requesting review
from others

### Release note

```release-note
fix: CherryAI provider now correctly converts PDF files to text instead of attempting native PDF input
fix: PDF text extraction now works in production builds (moved pdf-parse to dependencies)
```