kakan/codex-subagent-router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity

Release 2.0.0 with Sol-led escalation and evidence adjudication

Browse Source
This commit is contained in:
Codex
2026-09-15 21:17:41 +08:00
parent 7969489b7e
commit dc0360cefb
12 changed files with 300 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/behavior-scenarios.md
+17
View File
@@ -20,3 +20,20 @@ These are static review cases, not a record that a model executed them. Use them
| Local config says 8 threads, host gives 4 total slots | Follow actual host count, including parent if specified |
| Project requires Sol parent, current parent is Astra | Identify rule; no silent substitution based on model ranking |
| User says never delegate | Stay local even if a skill is selected implicitly |
## 2.0 escalation scenarios (manual forward evaluation)
These expectations are not recorded live-agent outcomes.
| Scenario | Expected behavior |
| --- | --- |
| Luna lacks the required input file | Diagnose input gap; do not consult Astra |
| Sol fails the same acceptance twice, then changes worker | Pause/reassess; preserve issue ID and count |
| Astra rejects a reproducible result without a counterexample | Check baseline and coverage; evidence decides, not model rank |
| A worker exposes a serious invariant violation on its first attempt | Suspend affected acceptance immediately |
| Requirements change after expert approval | Invalidate affected conclusion and verify the new baseline |
| Sol cannot explain the decisive expert reasoning | Do not accept or perform the dependent external action |
| Root cause is resolved and implementation is settled | Return remaining work to an adequate Terra/Luna route |
| Second expert consultation repeats the same question | Require new evidence or a specific prior omission |
For cost comparison use the same task baselines and acceptance checks across Sol alone, Astra planning plus Luna execution, and Sol-led four-model routing. Include sequential, decomposable and contract-heavy tasks; vary granularity and concurrency separately. Count failed attempts and parent integration in total tokens, actual cost and elapsed time. Repeat runs and report quality/failure distributions before claiming a winning route. Model requests without host identity remain unknown; synthetic packets do not substitute for measurements.