@c4a/context 0.7.29 → 0.7.30
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -127,8 +127,24 @@ assess the page with its non-text evidence.
|
|
|
127
127
|
|
|
128
128
|
## Image choices for a production task
|
|
129
129
|
|
|
130
|
+
Before capture, the Agent follows the document-capture Route procedure's task-wide
|
|
131
|
+
document threshold and image self-check, without asking for user confirmation.
|
|
132
|
+
Set `DOCUMENT_IMAGE_CAPTURE` in task instructions or workspace guidance to `ON`
|
|
133
|
+
(include images), `OFF` (references only), or a positive integer document threshold.
|
|
134
|
+
Omitting it uses `10`; exactly the threshold remains within normal acquisition.
|
|
135
|
+
Current-conversation instructions override workspace guidance for that task only.
|
|
136
|
+
For example, `DOCUMENT_IMAGE_CAPTURE: 20` skips image downloads when the task
|
|
137
|
+
contains more than 20 distinct documents. This is an Agent instruction, not an
|
|
138
|
+
environment variable, CLI flag or SDK field; no Bot configuration is required.
|
|
139
|
+
Above a numeric threshold, the default is body capture with image references,
|
|
140
|
+
unless the effective setting is overridden to `ON`. This workflow
|
|
141
|
+
choice uses the existing resource fields; it does not change SDK defaults or add
|
|
142
|
+
a CLI hard gate. Apply it before bulk capture or host prefetch, not after images
|
|
143
|
+
have already been downloaded.
|
|
144
|
+
|
|
130
145
|
The work-start report asks once when a task contains more than 30 distinct images
|
|
131
|
-
and has no explicit image policy.
|
|
146
|
+
that will be acquired and has no explicit image handling policy. Reuse the
|
|
147
|
+
current-conversation image instruction when it already settles this choice. The choices are intelligent conversion and
|
|
132
148
|
inclusion (recommended), include all as images with compression, or include none
|
|
133
149
|
with placeholders. Count the whole task, not each capture or writing batch.
|
|
134
150
|
Review reports show the resulting image handling and any fallbacks.
|