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/context-overflow.test.ts

@@ -124,7 +124,7 @@ describe("Context overflow error handling", () => {
 			logResult(result);
 
 			expect(result.stopReason).toBe("error");
-			expect(result.errorMessage).toMatch(/exceeds the context window/i);
+			expect(result.errorMessage).toMatch(/maximum context length/i);
 			expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
 		}, 120000);
 	});
@@ -237,6 +237,22 @@ describe("Context overflow error handling", () => {
 		}, 120000);
 	});
 
+	// =============================================================================
+	// Mistral
+	// Expected pattern: TBD - need to test actual error message
+	// =============================================================================
+
+	describe.skipIf(!process.env.MISTRAL_API_KEY)("Mistral", () => {
+		it("devstral-medium-latest - should detect overflow via isContextOverflow", async () => {
+			const model = getModel("mistral", "devstral-medium-latest");
+			const result = await testContextOverflow(model, process.env.MISTRAL_API_KEY!);
+			logResult(result);
+
+			expect(result.stopReason).toBe("error");
+			expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
+		}, 120000);
+	});
+
 	// =============================================================================
 	// OpenRouter - Multiple backend providers
 	// Expected pattern: "maximum context length is X tokens"