fix(ai): bump planner maxTokens 1024→4096 + teach prompt about the loop

Debug log from a "tag 4 notes" mission showed the planner's second-round
response truncated mid-step: it was proposing one add_tag_to_note per
listed note but ran out of tokens halfway through note #2. Parser
rejected the malformed JSON → loop exited with 0 staged, user saw
nothing to approve.

Raising maxTokens to 4096 fits ~15-20 step objects, which covers the
batch-tagging / batch-save pattern the reasoning loop is designed for.

Also updating the system prompt so the planner actually knows about
the loop it's running inside: read-only tools are announced as
auto-executing with outputs visible next turn, and a new rule makes
explicit that batch jobs must emit all write-steps in one plan (because
staging a propose-tool ends the turn). Step count raised 1-5 → 1-10.

Prompt snapshot tests still pass (they check structure, not text).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

apps/mana/apps/web/src/lib/llm-tasks/ai-plan.ts

@@ -45,7 +45,12 @@ export const aiPlanTask: LlmTask<AiPlanInput, AiPlanOutput> = {
 				{ role: 'user', content: user },
 			],
 			temperature: 0.3,
-			maxTokens: 1024,
+			// 1024 truncates mid-response when the planner proposes 3+ steps with
+			// rich rationales — the reasoning loop amplifies this because a
+			// single round can legitimately stage one step per listed item
+			// (e.g. 10 notes → 10 add_tag_to_note calls). 4096 fits ~15-20
+			// step objects while still fast on browser tier.
+			maxTokens: 4096,
 		});
 
 		// Always populate debug payload (cheap — strings already in memory).