administrator/Worldshaper
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Upgrade request analysis routing

Browse source
This commit is contained in:
Andraxion 2026-06-27 01:44:11 -04:00
parent 1cd446bae8
commit db3e080640
19 changed files with 1520 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

19
docs/kb/queue-workflow.md
View file

@ -15,13 +15,14 @@ Turn raw launcher submissions into structured request items that are:
## Recommended Pipeline
1. Read one pending submission.
2. Split it into candidate atomic requests.
2. Run a light routing pass that maps slang and broad language onto likely systems and tags.
3. Retrieve likely systems from `docs/kb/systems.json`.
4. Load the matching `docs/kb/systems/*.md` files.
5. Load the standardized request tags from `docs/kb/tags.json`.
6. Ask the local model for JSON that matches `docs/kb/request-analysis-schema.json`.
7. Validate the JSON.
8. Promote high-confidence items and hold low-confidence items for review.
4. Retrieve likely focused modules from `docs/kb/modules.json`.
5. Load only the matching `docs/kb/systems/*.md` and `docs/kb/modules/*.md` files.
6. Load the standardized request tags from `docs/kb/tags.json`.
7. Ask the local model for JSON that matches `docs/kb/request-analysis-schema.json`.
8. Validate the JSON.
9. Promote high-confidence items and hold low-confidence items for review.
## Suggested Confidence Rules
@ -41,7 +42,9 @@ Search `systems.json` using:
- aliases
- past tags from similar requests
If a submission touches multiple subsystems, feed the model the top two to four matching docs instead of the whole KB.
If a submission touches multiple subsystems, feed the model the top two to four matching system docs plus the smallest helpful focused modules instead of the whole KB.
Use `terminology.json` during the routing pass so phrases like "sprite editor", "painting tool", "recoloring", and "engine" still resolve to the intended Worldshaper concepts.
## Prompt Skeleton
@ -67,6 +70,7 @@ If you are unsure, lower confidence and use statusRecommendation = "needs_review
Then provide:
- the raw submission
- the routing summary
- the JSON schema
- the retrieved KB docs
@ -121,6 +125,7 @@ Behavior:
- high-confidence all-active results replace the pending submission with active request rows
- mixed or lower-confidence results stay on the pending submission as review metadata
- failures are stored as analysis errors instead of silently disappearing
- broad or ambiguous requests should still receive a useful interpretation, likely systems, and possible directions instead of a dead-end review
## What Not To Automate First