55 lines
3.5 KiB
Markdown
55 lines
3.5 KiB
Markdown
# Conclusion: How tai should handle models of CAP agents
|
|
|
|
## Metadata
|
|
|
|
| Field | Value |
|
|
|---|---|
|
|
| Institute | Molodetz Institute — Research & Retrieval Division |
|
|
| Subject | cap-protocol |
|
|
| Document type | Conclusion |
|
|
| Tier | N/A |
|
|
| Date decided | 2026-10-25 (recommendation only, retoor has not yet decided) |
|
|
| Decided by | tai (agent, Claude Sonnet 5) as a recommendation, pending retoor |
|
|
| Status | Active |
|
|
| Confidence | Medium |
|
|
|
|
## Question / problem statement
|
|
|
|
What do CAP and the neighboring protocols say about models and their usage, and what should tai's CAP side do about discovery, selection, precedence, cost and budgets.
|
|
|
|
## Conclusion
|
|
|
|
Treat a model as session configuration attached to an agent, resolved by an explicit precedence, never as agent-private knowledge. (1) Discovery order: the live `model`-category config option from ACP session setup for `acp_stdio` agents, then the manifest `[models]` list, then the `--cap-models` probe (CAP itself has no model list). (2) Selection: the caller passes a name or substring hint and the side that owns the catalog resolves it (MCP sampling hints, Claude Code aliases), which tai's fuzzy matcher already does. (3) Precedence for a delegated call: per-call model, then the agent's configured model, then a global default, then the parent's model; document it, because Claude Code's own order changed between releases. (4) Pass the model through `model_arg`; when an agent has none, warn instead of failing (already done). (5) Count cost from `cap.usage` (`model_id`, tokens, `cost_usd_estimate`) and enforce budgets in the orchestrator, never in the agent. (6) Expect delegation to cost a multiple of chat tokens (Anthropic reports about 15x) and cap it.
|
|
|
|
## Supporting sources
|
|
|
|
- [cap-core-v1](../cap-core-v1.md): `model` in session config, `model_arg`, `cap.usage`, orchestrator-enforced budgets (forward-corrected in this pass).
|
|
- [cap-profile-coding-v1](../cap-profile-coding-v1.md): no model or cost fields; per-agent permission and scope settings.
|
|
- [agentclientprotocol-session-config-options](../agentclientprotocol-session-config-options.md): live model options, defaults, ordering.
|
|
- [modelcontextprotocol-sampling-model-preferences](../modelcontextprotocol-sampling-model-preferences.md): hints plus priorities, owner decides.
|
|
- [claude-code-sub-agents-docs](../claude-code-sub-agents-docs.md): per-worker model and precedence.
|
|
- [anthropic-multi-agent-research-system](../anthropic-multi-agent-research-system.md): token multiple and model-tier results.
|
|
- [lmsys-routellm-blog](../lmsys-routellm-blog.md): two-tier routing savings.
|
|
|
|
## Alternatives considered and rejected
|
|
|
|
- Wait for CAP to standardize a model list: CAP's own STATUS marks no such work, and tai needs it now.
|
|
- A trained router (RouteLLM style): needs training data and a dependency; the calling model or the user already knows when a task is hard.
|
|
- Per-agent hard-coded model tables in tai: stale within weeks as providers rename models.
|
|
|
|
## Risks / open questions
|
|
|
|
- ACP discovery is not implemented in tai's CAP code; only the manifest list and probe exist.
|
|
- The precedence order is a recommendation, not something users have been asked about.
|
|
- Cost fields depend on agents reporting `cost.metered`; unmetered agents give no budget signal.
|
|
|
|
## Action taken
|
|
|
|
Nothing built beyond what already exists (manifest list, probe, fuzzy resolution). ACP discovery and the precedence rule are specified here only.
|
|
|
|
## Changelog
|
|
|
|
| Date | Change |
|
|
|---|---|
|
|
| 2026-10-25 | Initial conclusion recorded as a recommendation. |
|