Bump node-llama-cpp from 3.0.0-beta.44 to 3.7.0

[dependabot]

Bumps node-llama-cpp from 3.0.0-beta.44 to 3.7.0.

Release notes

Sourced from node-llama-cpp's releases.

v3.7.0

3.7.0 (2025-03-28)

Features

• extract function calling syntax from a Jinja template (#444) (c070e81)
• Full support for Qwen and QwQ via QwenChatWrapper (#444) (c070e81)
• export a llama instance getter on a model instance (#444) (c070e81)

Bug Fixes

• better handling for function calling with empty parameters (#444) (c070e81)
• reranking edge case crash (#444) (c070e81)
• limit the context size by default in the node-typescript template (#444) (c070e81)
• adapt to breaking llama.cpp changes (#444) (c070e81)
• bump min nodejs version to 20 due to dependencies' requirements (#444) (c070e81)
• defineChatSessionFunction type (#444) (c070e81)

---

Shipped with llama.cpp release b4980

To use the latest llama.cpp release available, run npx -n node-llama-cpp source download --release latest. (learn more)

v3.6.0

✨ DeepSeek R1 is here! ✨

Read about the release in the blog post

---

3.6.0 (2025-02-21)

Features

• DeepSeek R1 support (#428) (ca6b901) (documentation: DeepSeek R1)
• chain of thought segmentation (#428) (ca6b901) (documentation: Stream Response Segments)
• pass a model to resolveChatWrapper (#428) (ca6b901)
• defineChatSessionFunction: improve params type (#428) (ca6b901)
• Electron template: show chain of thought (#428) (ca6b901) (documentation: DeepSeek R1)
• Electron template: add functions template (#428) (ca6b901)
• Electron template: new icon for the CI build (#428) (ca6b901)
• Electron template: update model message in a more stable manner (#428) (ca6b901)
• Electron template: more convenient completion (#428) (ca6b901)

... (truncated)

Commits

• c070e81 feat: extract function calling syntax from a Jinja template (#444)
• ee94403 docs: fix electron command (#442)
• 1d13c0e docs: fix cover images (#432)
• 599a161 fix: uncaught exception (#430)
• ca6b901 feat: DeepSeek R1 support (#428)
• 63a1066 chore: update modules (#425)
• 73454d9 feat: shorter model URIs (#421)
• 6e4bf3d fix: adapt to llama.cpp breaking changes (#424)
• 314d7e8 fix: metadata string encoding (#420)
• 86e1bee fix: ranking empty inputs (#415)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[0xdevalias]

Interesting that this upgrade was able to run the tests and merge successfully when it's been failing for so long prior.. I wonder what the root issue was, and what fixed it; as looking at the main commits in this repo, it doesn't look like the tests were fixed/etc at all.

Background context:

See my previous exploration/analysis into this build failure in the following comments:

• Bump node-llama-cpp from 3.0.0-beta.44 to 3.5.0 #301 (comment)
• Bump node-llama-cpp from 3.0.0-beta.44 to 3.5.0 #301 (comment)

The following links may be relevant for understanding if/what changes need to be made to the Gbnf grammar (or other ways to achieve similar):

• https://node-llama-cpp.withcat.ai/guide/grammar
  • https://node-llama-cpp.withcat.ai/guide/grammar#reducing-json-schema-hallucinations
• https://node-llama-cpp.withcat.ai/api/classes/Llama#getgrammarfor
• https://github.com/ggerganov/llama.cpp/tree/master/grammars
• https://node-llama-cpp.withcat.ai/guide/chat-session#response-json-schema
• https://node-llama-cpp.withcat.ai/guide/function-calling
• https://node-llama-cpp.withcat.ai/guide/chat-session#function-calling

Originally posted by @0xdevalias in #301 (comment)

---

Resolving this will likely also resolve the following from this issue:

• Remove/update deprecated/unsupported packages #52 (comment)

  • ⇒ npm install humanifyjs
    npm warn deprecated npmlog@6.0.2: This package is no longer supported.
    npm warn deprecated are-we-there-yet@3.0.1: This package is no longer supported.
    npm warn deprecated gauge@4.0.4: This package is no longer supported.

Originally posted by @0xdevalias in #337 (comment)

Actually.. cloning locally (7beba2d) and running npm test seems to fail with the same error as previously:

⇒ npm test

..snip..

> humanifyjs@2.2.2 test:e2e
> npm run build && find src -name '*.e2etest.ts' | xargs tsx --test --test-concurrency=1

..snip..

✖ failing tests:

test at src/test/local.e2etest.ts:1:468
✖ Unminifies an example file successfully (10744.814553ms)
  AssertionError [ERR_ASSERTION]: Expected "UNREADABLE" but got GOOD

  The function given performs a task that appears to split a given string (`e`) into chunks of a specified size (`t`)
      at expectStartsWith (/Users/devalias/dev/jehna/humanify/src/test/local.e2etest.ts:24:5)
      at TestContext.<anonymous> (/Users/devalias/dev/jehna/humanify/src/test/local.e2etest.ts:30:9)
      at async Test.run (node:internal/test_runner/test:866:9)
      at async Test.processPendingSubtests (node:internal/test_runner/test:574:7) {
    generatedMessage: false,
    code: 'ERR_ASSERTION',
    actual: false,
    expected: true,
    operator: '=='
  }

So this seems like it never should have passed and been able to be merged.. probably a race condition/similar bug in the automerge GitHub action that likely would be resolved by the improvements raised in:

• refactor automerge github action to be more efficient #346

---

Edit: I've opened a new issue to specifically track this failing test since it's in main now:

• failing test: src/test/local.e2etest.ts:1:468 - Unminifies an example file successfully - AssertionError [ERR_ASSERTION]: Expected "UNREADABLE" but got GOOD #384