docs: add TASKS.md agent-column schema to AGENTS.md (canonical reference)

AGENTS.md

@@ -53,3 +53,28 @@ pnpm typecheck && pnpm lint && pnpm format:check  # Quality gates
 - ESM everywhere (`"type": "module"`, `.js` extensions in imports)
 - NodeNext module resolution in all tsconfigs
 - Scratchpads are mandatory for non-trivial tasks
+
+## docs/TASKS.md — Schema (CANONICAL)
+
+The `agent` column specifies the required model for each task. **This is set at task creation by the orchestrator and must not be changed by workers.**
+
+| Value    | When to use                                                 | Budget                     |
+| -------- | ----------------------------------------------------------- | -------------------------- |
+| `codex`  | All coding tasks (default for implementation)               | OpenAI credits — preferred |
+| `glm-5`  | Cost-sensitive coding where Codex is unavailable            | Z.ai credits               |
+| `haiku`  | Review gates, verify tasks, status checks, docs-only        | Cheapest Claude tier       |
+| `sonnet` | Complex planning, multi-file reasoning, architecture review | Claude quota               |
+| `opus`   | Major cross-cutting architecture decisions ONLY             | Most expensive — minimize  |
+| `—`      | No preference / auto-select cheapest capable                | Pipeline decides           |
+
+Pipeline crons read this column and spawn accordingly. Workers never modify `docs/TASKS.md` — only the orchestrator writes it.
+
+**Full schema:**
+
+```
+| id | status | description | issue | agent | repo | branch | depends_on | estimate | notes |
+```
+
+- `status`: `not-started` | `in-progress` | `done` | `failed` | `blocked` | `needs-qa`
+- `agent`: model value from table above (set before spawning)
+- `estimate`: token budget e.g. `8K`, `25K`