Develop 2.1.0 proactive Astra intervention and rolling fleet scheduling

This commit is contained in:
Codex committed 2026-09-15 23:51:54 +08:00
1 parent e2fbb211b6
commit e66dcc1810
13 files changed
+175 -24

No files matched your search

+6 -4
View File
@@ -5,7 +5,7 @@ description: Decide when Codex subagents help, route bounded work across Astra,
# Codex Subagent Router
Version 2.0.0. For new general engineering sessions recommend Sol / medium, with high when demonstrated reasoning needs justify it. Preserve the user's selected parent; installation does not switch it. Use Astra for bounded residual hard reasoning, rather than mandatory planning of every task.
Version 2.1.0. For new general engineering sessions recommend Sol / medium, with high when demonstrated reasoning needs justify it. Preserve the user's selected parent; installation does not switch it. Use Astra proactively for high-leverage difficult decisions, independent counterexample reviews and residual hard reasoning; neither failure nor a model quota is a prerequisite.
Make delegation useful, observable and bounded. Preserve the selected parent model. The parent owns the critical path, shared decisions, integration and final acceptance. This skill neither changes configuration nor grants external permissions.
@@ -13,8 +13,8 @@ Make delegation useful, observable and bounded. Preserve the selected parent mod
Classify the request before using child tools:
- **Audit or advice:** inspect rules, configuration and available tools; report findings without spawning or changing settings.
- **Authorized execution:** the user requested delegation, or an applicable instruction explicitly authorizes it. Within that scope, actively delegate independent useful slices while the parent advances other work.
- **Audit or advice without delegation authorization:** inspect rules, configuration and available tools; report findings without spawning or changing settings.
- **Authorized delegation:** the user requested delegation, or an applicable instruction explicitly authorizes it. This includes explicitly delegated read-only reviews; delegation does not grant edit permission. Within that scope, actively delegate independent useful slices while the parent advances other work.
- **No delegation authorization:** work locally. Automatic skill discovery, model availability, task complexity and a request to edit this skill do not grant permission to spawn.
Honor higher-priority host restrictions even when a lower-priority rule permits delegation. Do not request authorization repeatedly after it has been granted. Never turn a routing recommendation into a new user-owned task.
@@ -27,6 +27,8 @@ Before dispatch classify each candidate:
Spawn only P/C work with a concrete output and useful parent work available. Do not spawn for one command, ceremonial probes, duplicate reviews or a model quota. Batch homogeneous small work.
For authorized complex work, actively discover independent slices at intake and each readiness change. Dispatch ready work early and refill available capacity without waiting for a whole wave. Read [fleet scheduling](references/fleet.md) for rolling execution, Astra intervention and integration backpressure. Capacity is an upper bound, not a utilization target.
## Select a supported route explicitly
| Work shape | Initial route |
@@ -35,7 +37,7 @@ Spawn only P/C work with a concrete output and useful parent work available. Do
| Bounded classification, conversion, settled patch with fixed checks | Luna high |
| Everyday implementation, debugging, locating/correlating artifacts | Terra medium; high when needed |
| Bounded complex analysis, design or financial/security evidence | Sol medium; high when needed |
| Hardest independent synthesis across code, tools and research | Astra medium; high when needed |
| High-leverage difficult design, cross-system synthesis, independent high-impact counterexample review | Astra medium; high when needed |
| Shared decisions, integration and external/final gates | Current parent, serial |
These are starting heuristics, not measured cost rankings. Pick sufficient capability directly; do not escalate through every model. Missing access/data and tool failures need diagnosis, not a stronger model. After two same-class failures, pause that slice and return the evidence to the parent.