sorokin.oleg.edu/learnharness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

seam (master-approved): MODELS.pdfReader for the T2b pdf-reader sub-agent

Browse Source 
One key, master pre-approved content (2026-09 master sync): the pdf-reader
is of the teacher/researcher family — dense image→text extraction wants the
stronger multimodal; qwen/qwen3.8-flash stays specialized for visualMaker
(generation). Owner can override in one line after live testing.
This commit is contained in:
amosblomqvist
2026-09-19 15:00:10 +03:00
parent cab1632c74
commit bc2c02b865
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.ts
+5
View File
@@ -62,6 +62,11 @@ export const MODELS = {
demoBuilder: { model: "z-ai/glm-5.3-flash", effort: "low" },
/** Must be vision-capable: it looks at rendered SVGs. */
visualMaker: { model: "qwen/qwen3.8-flash", effort: "low" },
/** SEAM (master-approved 2026-09): the pdf-reader sub-agent. Must be
* vision-capable — it looks at rendered PDF pages; its briefs are text.
* The teacher/researcher family model (glm-5.3-flash accepts image input
* per pi's zai catalog); qwen stays specialized for visual GENERATION. */
pdfReader: { model: "z-ai/glm-5.3-flash", effort: "low" },
/** Extraction is judgment over given evidence — light thinking suffices. */
extractor: { model: "z-ai/glm-5.3-flash", effort: "low" },
/** The auditor verifies evidence exists; keep it cheap. */