feat(ai-proxy): feat(agent): add AI integration with addAI customization method

[Scra3]

Summary

• Add Mistral AI as a new provider option alongside OpenAI
• Uses @langchain/mistralai for Mistral integration
• Converts messages between OpenAI and LangChain formats for compatibility
• Returns responses in OpenAI format for frontend compatibility

Changes

• Add MistralConfiguration type with provider: 'mistral'
• Add MistralUnprocessableError for Mistral-specific errors
• Implement dispatchMistral method in ProviderDispatcher
• Add message conversion utilities (OpenAI ↔ LangChain)
• Add comprehensive tests for Mistral provider

Usage

agent.addAI({
  provider: 'mistral',
  model: 'mistral-large-latest',
  apiKey: process.env.MISTRAL_API_KEY,
});

Test plan

• All existing tests pass
• New Mistral tests pass
• Build succeeds
• Lint passes

🤖 Generated with Claude Code

[qltysh]

2 new issues

Tool	Category	Rule	Count
qlty	Structure	Function with many parameters (count = 4): makeRoutes	1
qlty	Structure	Function with high complexity (count = 11): dispatch	1

[qltysh]

Coverage Impact

⬆️ Merging this pull request will increase total coverage on main by 0.01%.

Modified Files with Diff Coverage (3)

Rating	File	% Diff	Uncovered Line #s
	packages/agent/src/agent.ts	100.0%
	packages/agent/src/routes/index.ts	100.0%
	packages/agent/src/routes/ai/ai-proxy.ts	100.0%
	Total	100.0%

🚦 See full report on Qlty Cloud »

🛟 Help

• Diff Coverage: Coverage for added or modified lines of code (excludes deleted files). Learn more.

• Total Coverage: Coverage for the whole repository, calculated as the sum of all File Coverage. Learn more.

• File Coverage: Covered Lines divided by Covered Lines plus Missed Lines. (Excludes non-executable lines including blank lines and comments.)

  • Indirect Changes: Changes to File Coverage for files that were not modified in this PR. Learn more.

[Scra3]

Code review

Found 2 issues:

1. Missing null check for args.query when accessing args.query['tool-name']. The query parameter is typed as optional (query?: Query), so if undefined, this will throw a TypeError.

agent-nodejs/packages/ai-proxy/src/router.ts

Lines 63 to 67 in 2130789

	return await remoteTools.invokeTool(
	args.query['tool-name'],
	(args.body as InvokeRemoteToolBody).inputs,
	);
	}

2. Missing null check for args.body when accessing (args.body as InvokeRemoteToolBody).inputs. The body parameter is optional and can be undefined, which will throw a TypeError.

agent-nodejs/packages/ai-proxy/src/router.ts

Lines 63 to 67 in 2130789

	return await remoteTools.invokeTool(
	args.query['tool-name'],
	(args.body as InvokeRemoteToolBody).inputs,
	);
	}

Suggested fix for both issues:

if (args.route === 'invoke-remote-tool') {
  if (!args.query?.['tool-name']) {
    throw new AIUnprocessableError('Missing required query parameter: tool-name');
  }
  if (!args.body || !('inputs' in args.body)) {
    throw new AIUnprocessableError('Missing or invalid body for invoke-remote-tool');
  }
  return await remoteTools.invokeTool(
    args.query['tool-name'],
    (args.body as InvokeRemoteToolBody).inputs,
  );
}

🤖 Generated with Claude Code

_{- If this code review was useful, please react with 👍. Otherwise, react with 👎.}

[Scra3]

Auto code review

No issues found. Checked for bugs and CLAUDE.md compliance.

🤖 Generated with Claude Code