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/total-tokens.test.ts

@@ -258,6 +258,25 @@ describe("totalTokens field", () => {
 		}, 60000);
 	});
 
+	// =========================================================================
+	// Mistral
+	// =========================================================================
+
+	describe.skipIf(!process.env.MISTRAL_API_KEY)("Mistral", () => {
+		it("devstral-medium-latest - should return totalTokens equal to sum of components", async () => {
+			const llm = getModel("mistral", "devstral-medium-latest");
+
+			console.log(`\nMistral / ${llm.id}:`);
+			const { first, second } = await testTotalTokensWithCache(llm, { apiKey: process.env.MISTRAL_API_KEY });
+
+			logUsage("First request", first);
+			logUsage("Second request", second);
+
+			assertTotalTokensEqualsComponents(first);
+			assertTotalTokensEqualsComponents(second);
+		}, 60000);
+	});
+
 	// =========================================================================
 	// OpenRouter - Multiple backend providers
 	// =========================================================================