Add Mistral as AI provider

- Add Mistral to KnownProvider type and model generation
- Implement Mistral-specific compat handling in openai-completions:
  - requiresToolResultName: tool results need name field
  - requiresAssistantAfterToolResult: synthetic assistant message between tool/user
  - requiresThinkingAsText: thinking blocks as <thinking> text
  - requiresMistralToolIds: tool IDs must be exactly 9 alphanumeric chars
- Add MISTRAL_API_KEY environment variable support
- Add Mistral tests across all test files
- Update documentation (README, CHANGELOG) for both ai and coding-agent packages
- Remove client IDs from gemini.md, reference upstream source instead

Closes #165

packages/ai/test/tokens.test.ts

@@ -77,4 +77,12 @@ describe("Token Statistics on Abort", () => {
 			await testTokensOnAbort(llm, { thinkingEnabled: true, thinkingBudgetTokens: 2048 });
 		}, 10000);
 	});
+
+	describe.skipIf(!process.env.MISTRAL_API_KEY)("Mistral Provider", () => {
+		const llm = getModel("mistral", "devstral-medium-latest");
+
+		it("should include token stats when aborted mid-stream", async () => {
+			await testTokensOnAbort(llm);
+		}, 10000);
+	});
 });