pi-eda 0.2.2 → 0.2.3

package/agents/naive-reader.md

@@ -15,8 +15,10 @@ cold, as if returning in 6 months having forgotten everything.
 - Comprehension only -- you never judge whether a choice was right, only
   whether it's explained.
 - Confirm every figure file passed to you is actually embedded in the
-  report -- an unreferenced figure is material-tier, since there isn't an
-  interpretation for it.
+  report. An unreferenced figure is material-tier, since there isn't an
+  interpretation for it. Intentional or deliberate omission is not an
+  exception. This holds unless the report itself documents that the
+  user explicitly said to exclude that figure.
 
 ## Severity rubric
 
@@ -25,7 +27,7 @@ cold, as if returning in 6 months having forgotten everything.
 | cosmetic | wording/labeling nit, doesn't change interpretation |
 | confusing | correct and complete, but too dense/jargon-heavy to parse easily |
 | clarifying | you can't tell why/what/how from the report alone. If you had to open the script to answer your own question, that's automatic clarifying-tier |
-| material | your conclusion contradicts what the report claims, or the claim isn't backed by anything shown |
+| material | your conclusion contradicts what the report claims, the claim isn't backed by anything shown, or a figure is omitted |
 
 Report every finding with its tier. Do not silently decide a fix for
 anything -- that's the calling agent's call, not yours.

package/extensions/show.ts

@@ -93,7 +93,7 @@ export default function (pi: ExtensionAPI) {
 				const text = result.content[0];
 				return new Text(text?.type === "text" ? text.text : "", 0, 0);
 			}
-			return new Image(details.base64, details.mediaType, theme, {
+			return new Image(details.base64, details.mediaType, { fallbackColor: (text: string) => theme.fg("muted", text) }, {
 				maxWidthCells: 80,
 				maxHeightCells: 36,
 			});

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-eda",
-  "version": "0.2.2",
+  "version": "0.2.3",
   "description": "Pi tooling for interactive exploratory data analysis.",
   "license": "MIT",
   "author": "Shivam V Verma",

package/skills/finishing-exploratory-data-analysis/SKILL.md

@@ -45,7 +45,9 @@ review doesn't count (see Common Mistakes).
        - *Data source(s) used*
        - *Questions*, grouped when closely related:
          - *Approach* in prose, with key equations if nontrivial
-         - *Results*, with the embedded figure(s)
+         - *Results*, with the embedded figure(s): all figures produced
+           during the EDA must be embedded; omitting one requires the
+           user's explicit consent.
        - *Conclusion*
 4. **Reread, then dispatch verification.** See `verification-dispatch.md`
    for the reread pass, the `naive-reader`/`critical-auditor` dispatch, and
@@ -68,3 +70,4 @@ review doesn't count (see Common Mistakes).
 | Silently patching a material-tier or `critical-auditor` finding before telling the user | Always surface these verbatim in the summary, even unresolved -- only cosmetic/confusing/non-fabricated-clarifying fixes get silently applied |
 | Treating a completed script/code review as satisfying this checkpoint's dispatch | Different gate, different artifact -- a code review checks the script, this checkpoint checks the written report. See `verification-dispatch.md` |
 | Saying an analysis is "done and reviewed" once code review passes, before the lock-in checkpoint has run | Say so explicitly ("script validated; report still needs the lock-in checkpoint") rather than a blanket "done" that could be read as covering sign-off too |
+| Omitting a figure without the user's explicit consent | Embed every figure; only skip one if the user explicitly says to |