c6c1364dd6
* Sync agent pipeline artifacts to 0.6.0. Add model routing defaults, L2 role updates, convoy telemetry, and manifest tracking without touching unrelated in-progress work. * Record tcg-vault interactive sync (kept local L1/L3 customizations). Update last_synced_at after reviewing behind/conflict artifacts; no overwrites applied. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(agent-pipeline): sync 0.6.0 — implementer Mode 2 fix pass + UI designer - role-implementer Mode 2 (fix pass) and role-reviewer hand-off - role-ui-designer + model-routing updates from upstream 783e2a3 - manifest last_synced_at bumped Co-authored-by: Cursor <cursoragent@cursor.com> * chore(agent-pipeline): sync v0.7.0 model routing Composer Standard for architect, Grok for audit fan-out, Sonnet 5 escalation path. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(agent-pipeline): finish 0.6.0/0.7.0 sync on branch Install security baseline, convoy planning, security-audit and ui-ux-pro-max skills; align PR template and metrics docs with convoy-metrics-gate; refresh manifest hashes while keeping tcg-vault-local L1/L3 customizations. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>
37 lines
1.9 KiB
Text
37 lines
1.9 KiB
Text
---
|
|
description: Model tier defaults for the agent pipeline — Composer Standard for architect; fast/Grok for build and audit; Sonnet 5 escalation
|
|
alwaysApply: true
|
|
---
|
|
|
|
# Model routing (cost-aware pipeline, v0.7)
|
|
|
|
Cursor subagent roles in `.cursor/agents/role-*.md` declare a `model:` in frontmatter. **Invoke roles from the Agents dropdown** (or a fresh chat pinned to that role) so the configured model applies. Parent chats on Opus that spawn Task subagents may override role models — see `docs/model-routing-policy.md` (or `docs/agent-context/model-routing-policy.md`).
|
|
|
|
## Default session model
|
|
|
|
- **Parent chat (ad hoc work):** `auto` or `composer-2.5-fast`.
|
|
- **Escalate to Sonnet 5** (`claude-sonnet-5-thinking-medium`) for failed implementer briefs or architect-flagged security/schema work.
|
|
- **Opus** (`claude-4.6-opus-high-thinking`) only when a brief sets `recommended_model: claude-4.6-opus-high-thinking`.
|
|
- **Never use Opus 4.7 / xhigh** for routine pipeline work.
|
|
|
|
## Per-role tiers (canonical, v0.7)
|
|
|
|
| Tier | Roles | Model |
|
|
| --- | --- | --- |
|
|
| Standard | architect | `composer-2.5` (Standard mode in picker) |
|
|
| Fast | conductor, ia-architect, ui-designer, ux-reviewer, implementer | `composer-2.5-fast` |
|
|
| Audit | reviewer, design-system-auditor, a11y-auditor | `cursor-grok-4.5-high` |
|
|
| Security | security-auditor | `gpt-5.6-terra-medium` |
|
|
| Auto | doc-writer | `auto` |
|
|
|
|
Read `model_policy:` from the convoy frontmatter when present; it overrides these defaults for that convoy.
|
|
|
|
## Context discipline (biggest cost lever)
|
|
|
|
- Implementers and auditors: read **only** the brief + files in `files:` — not the whole convoy, not `prisma/schema.prisma` unless listed.
|
|
- Audits: diff + brief only; no repo-wide grep sweeps.
|
|
- Stop and ask before any single chat exceeds ~5M tokens; start a fresh scoped chat instead.
|
|
|
|
## Metrics
|
|
|
|
After each role, log `model=` and `model_tier=` via `scripts/log-convoy-event.sh` (see each role's Metrics section).
|