feat(desktop): configurable group chat round cap + model-aware limits + token budget guard

[beplee]

Summary

• Add group-chat-config.ts: config.yaml-driven group_chat.* settings + free-model detection
• Make GROUP_CHAT_MAX_ROUNDS config-aware: free models (:free suffix or free_models[] allowlist) get unlimited rounds up to HARD_CAP=20, paid models default to max_rounds: 3
• Add token-budget guard: cumulative room-log tokens exceeding group_chat.token_budget (default 80k chars) force exitKind='capped' independent of round count — the real safety net for pathological cascades
• Add getGroupChatConfig(), isFreeModel(), getEffectiveRoundCap(), getCurrentModelName() helpers
• Add config.yaml schema in cli-config.yaml.example under group_chat:

Why

Hardcoded 3-round cap is too tight for free-model rooms (where API cost is zero) and too loose for paid-model rooms (where each round burns real money). A single config block drives everything automatically.

Config

group_chat:
  max_rounds: 3              # paid models
  max_rounds_free: null      # null = unlimited (HARD_CAP=20 backstop)
  token_budget: 80000        # hard ceiling per drive (chars, ~20k tokens)
  free_models:               # quality-tier allowlist
    - upstage/solar-pro4
    - meituan/longcat-2.0
    - tencent/hy3
  hard_cap: 20               # absolute ceiling even for free models

Safety

• Token budget is the real backstop — fires regardless of model type or round count
• HARD_CAP=20 prevents unbounded free-model cascades (20 rounds × 6 bots = 120 messages max)
• Paid models always capped at max_rounds (default 3)
• exitKind='capped' logged to activity feed for every termination path

Test plan

• Paid model → 3-round cap fires
• Free model (allowlist) → 20-round cap fires
• Token budget exhaustion → mid-drive cap fires
• Model switch mid-drive → cap re-evaluates
• 6-bot free room → halts cleanly at token budget
• Empty free_models + :free suffix → allowlist is sole gate (no bypass)

Refs: #96726

[beplee]

The shared config module reads cleanly and the token-budget ceiling is the right backstop.

Closing this PR — #98616 (feat(desktop): drive Bot Mode room limits from config.yaml) already solves the same problem with a smaller change, actual tests (77 lines in group-rounds.test.ts), and the group_chat: block in cli-config.yaml.example. Rather than merge two mechanisms, I'm pointing at that one as the shared seam.

Credit for the model-aware free-model rounding idea — I'll carry that as a follow-up on top of #98616's schema.