Implement tool result truncation with actionable notices (#134)

- read: actionable notices with offset for continuation
  - First line > 30KB: return empty + bash command suggestion
  - Hit limit: '[Showing lines X-Y of Z. Use offset=N to continue]'

- bash: tail truncation with temp file
  - Notice includes line range + temp file path
  - Edge case: last line > 30KB shows partial

- grep: pre-truncate match lines to 500 chars
  - '[... truncated]' suffix on long lines
  - Notice for match limit and line truncation

- find/ls: result/entry limit notices
  - '[N results limit reached. Use limit=M for more]'

- All notices now in text content (LLM sees them)
- TUI simplified (notices render as part of output)
- Never return partial lines (except bash edge case)

packages/ai/test/context-overflow.test.ts

@@ -118,7 +118,8 @@ describe("Context overflow error handling", () => {
 
 	describe.skipIf(!process.env.OPENAI_API_KEY)("OpenAI Completions", () => {
 		it("gpt-4o-mini - should detect overflow via isContextOverflow", async () => {
-			const model = getModel("openai", "gpt-4o-mini");
+			const model = { ...getModel("openai", "gpt-4o-mini") };
+			model.api = "openai-completions" as any;
 			const result = await testContextOverflow(model, process.env.OPENAI_API_KEY!);
 			logResult(result);