pi-hashline-edit-pro 4.4.0 → 4.4.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-hashline-edit-pro",
-  "version": "4.4.0",
+  "version": "4.4.1",
   "type": "module",
   "description": "Hash-anchored read/replace/insert/grep tools for pi-coding-agent. Every line gets a unique 4-char tokenizer-friendly anchor that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.",
   "main": "index.ts",

package/prompts/insert.md

@@ -1 +1,3 @@
-Insert lines after or before one existing line in a text file, addressed by a bare anchor from any served anchor│content row. The anchor line is preserved: `lines` go after it with `direction: "after"` or before it with `direction: "before"`, one string per line, no anchor prefixes, no embedded newlines. Inserted lines are written exactly as given; nothing else in the file changes. Multiple `replace`/`insert` calls on the same file in one message form one batch per file: earlier calls reply `In batch N` and the last call shows the combined diff, with one undo for the whole batch.
+Insert lines after or before one existing line in a text file, addressed by a bare anchor from any served anchor│content row. The anchor line is preserved: `lines` go after it with `direction: "after"` or before it with `direction: "before"`, one string per line, no anchor prefixes, no embedded newlines. Inserted lines are written exactly as given; nothing else in the file changes.
+
+Same-file calls in one message batch: earlier calls reply `In batch N` and the last call shows the combined diff, with one undo for the whole batch.

package/prompts/read.md

@@ -1 +1 @@
-Read a text file and return it as `anchor│content` rows, one per line: a 4-character anchor (letters only), the `│` separator, then the line content. Target lines in replace and insert by anchor, never by content or line number. Page long files with `offset` and `limit`; when the output says truncated, continue with the hinted `offset/limit`. Images attach visually; binary, directory, and UTF-16/UTF-32 text are rejected; an empty file returns one empty row you can replace to seed content.
+Read a text file and return it as `anchor│content` rows, one per line: a 4-character anchor (letters only, case-sensitive), the `│` separator, then the line content. Target lines in replace and insert by anchor, never by content or line number. Page long files with `offset` and `limit`; when the output says truncated, continue with the hinted `offset/limit`. Images attach visually; binary, directory, and UTF-16/UTF-32 text are rejected; an empty file returns one empty row you can replace to seed content.

package/prompts/replace-guidelines.md

@@ -1,4 +1,6 @@
-- `replace`: edit with `replace`/`insert`, not `sed -i` or heredocs — anchor edits are verified against what was shown and undoable.
-- `replace`: `replacement_lines` `[""]` is one blank line; pasted `anchor│` prefixes are stripped automatically (single line: same anchor for `remove_from` and `remove_to`).
-- `replace`: never anchor on `-anchor│` rows of the post-edit diff, those anchors were freed by the edit. Check each batch diff before the next turn's edits on that file.
-- `replace`: same-file same-message batches must target disjoint ranges; an overlap or member failure aborts only that file's batch unwritten. Unresolvable calls stay solo and don't abort.
+- `replace`: `-anchor│` rows in a post-edit diff are dead anchors; only `+anchor│` and ` anchor│` rows are live. Check the post-edit diff before the next turn's edits on that file.
+- `replace`: same-file same-message calls batch: disjoint ranges, one undo. A call whose anchors resolve nowhere fails alone; its file's batch still commits.
+- `replace`: `[E_STALE_ANCHOR]` means the anchor is not owned in this session: call `read` on the file for fresh anchors. `[E_RANGE_STALE]` means a line in the range changed since it was shown, or was never shown: retry with the fresh anchors the error returns.
+- `replace`: `[E_BATCH_OVERLAP]` means two batch calls share lines: retry with disjoint ranges. `[E_OP_ABORTED]` means another batch call failed or the file changed: fix that call, then retry, or call `read` for fresh anchors.
+- `replace`: use `replace`/`insert`, not `sed -i` or heredocs — anchor edits are verified against what was shown and undoable.
+- `replace`: `replacement_lines`: one string per line, `[""]` is one blank line, `[]` deletes. Pasted `anchor│` prefixes are stripped. Single line: same anchor for `remove_from` and `remove_to`.

package/prompts/replace.md

@@ -1 +1,5 @@
-Replace a range of lines (or a single line) in a text file, targeted by 4-character anchors from any served anchor│content row. Give `remove_from` and `remove_to` as bare anchors marking the first and last line to remove, and `replacement_lines` as one string per new line with no anchor prefixes and no embedded newlines; `[]` deletes the range. Anchor follow-up edits on the `+anchor│` and ` anchor│` rows of the post-edit diff instead of re-reading. Multiple `replace`/`insert` calls on the same file in one message form one batch per file: earlier calls reply `In batch N` and the last call shows the combined diff, with one undo for the whole batch.
+Replace a range of lines (or a single line) in a text file, targeted by 4-character anchors from any served anchor│content row. Give `remove_from` and `remove_to` as bare anchors marking the first and last line to remove, and `replacement_lines` as one string per new line with no anchor prefixes and no embedded newlines; `[]` deletes the range.
+
+Same-file calls in one message batch: earlier calls reply `In batch N` and the last call shows the combined diff, with one undo for the whole batch.
+
+Example: read served `Hasu│old` and `arvm│old2`. Call { "remove_from": "Hasu", "remove_to": "arvm", "replacement_lines": ["new"] }. The post-edit diff shows `-Hasu│old`, `-arvm│old2`, `+Qwer│new`: the `-` rows are dead anchors now; the `+` and ` ` rows are live anchors for the next edit.

package/src/anchor-registry.ts

@@ -568,6 +568,24 @@ export function ownerOf(anchor: string): OwnedAnchor | undefined {
   return current()?.owned.get(anchor);
 }
 
+export interface CaseFoldedOwner {
+  anchor: string;
+  path: string;
+}
+
+export function ownersDifferingOnlyByCase(anchor: string, paths?: ReadonlySet<string>): CaseFoldedOwner[] {
+  const state = current();
+  if (!state) return [];
+  const lower = anchor.toLowerCase();
+  const matches: CaseFoldedOwner[] = [];
+  for (const [owned, entry] of state.owned) {
+    if (owned === anchor || owned.toLowerCase() !== lower) continue;
+    if (paths && paths.size > 0 && !paths.has(entry.path)) continue;
+    matches.push({ anchor: owned, path: entry.path });
+  }
+  return matches;
+}
+
 export function ownersForPath(path: string): Map<string, string> {
   const claims = new Map<string, string>();
   const state = current();

package/src/auto-read-all.ts

@@ -27,7 +27,7 @@ const MAX_REPORTED_OMISSIONS = 50;
 export const AUTO_READ_ALL_CHUNK_BYTES = 48 * 1024;
 
 const HEADER =
-  "[hashline auto-read-all] Every non-ignored project file is attached below with live hashline anchors. Do not call read for files in [files complete: ...]. Edit directly from the attachment with replace and insert.";
+  "[hashline auto-read-all] Every non-ignored project file is attached below as `=== path ===` then `anchor│content` rows with live anchors.\nEdit directly from the attachment with replace and insert; do not call read for files in [files complete: ...].\nFiles listed as omitted or not attached can be read normally.\nAnchors are case-sensitive and stay valid until their line is edited.";
 
 const IMAGE_EXTENSIONS = new Set([
   ".avif",

package/src/edit-common.ts

@@ -1,7 +1,7 @@
 import { withFileMutationQueue } from "@earendil-works/pi-coding-agent";
 import { resolveInCwd } from "./fs-write";
 import { abortIf, makePrepareArguments } from "./utils";
-import { ownerOf } from "./anchor-registry";
+import { ownerOf, ownersDifferingOnlyByCase, type OwnedAnchor } from "./anchor-registry";
 import { parseHashRef, stripAnchorRow } from "./hashline";
 import { readConfig } from "./config";
 import { makeRenderCall, renderEditResult, type RPreview, type FgT } from "./replace-render";
@@ -37,7 +37,7 @@ export function withReplacePrompts(base: { description: string; snippet: string;
   const snippetParts = [base.snippet];
   let guidelines = [...base.guidelines];
   if (!flags.autoRead) {
-    description = description.replace(" Anchor follow-up edits on the `+anchor│` and ` anchor│` rows of the post-edit diff instead of re-reading.", "");
+    description = description.replace(/\n\nExample:[\s\S]*$/, "");
     guidelines = guidelines.filter((guideline) => !guideline.includes("post-edit diff"));
     description = description.replace("and the last call shows the combined diff,", "and the last call shows the combined result,");
   }
@@ -95,14 +95,27 @@ export function withUndoPrompts(base: { description: string; snippet: string; gu
   const guidelines = base.guidelines.map((guideline) => guideline.includes("bad diff") ? "`undo_last_change`: only the last `replace`/`insert` per file is undoable; a `write` clears it, so undo right after a bad edit — review what you're restoring." : guideline);
   return { description: base.description, snippet: base.snippet, guidelines };
 }
+
+function staleAnchorMessage(ref: string, hash: string, owners: Array<OwnedAnchor | undefined>): string {
+  const knownPaths = new Set<string>();
+  for (const owner of owners) {
+    if (owner) knownPaths.add(owner.path);
+  }
+  const folded = ownersDifferingOnlyByCase(hash, knownPaths);
+  const hint =
+    folded.length > 0
+      ? ` Anchors are case-sensitive; ${folded.map((match) => `"${match.anchor}"`).join(", ")} differs only in case.`
+      : "";
+  return `[E_STALE_ANCHOR] "${ref}" is not owned in this session.${hint} Call read() on the target file first.`;
+}
+
 export function resolveEditTarget(removeFrom: string, removeTo?: string): string {
   const refs = [removeFrom, removeTo].filter((value): value is string => typeof value === "string");
-  const owners = refs.map((ref) => ownerOf(parseHashRef(stripAnchorRow(ref.trim(), "anchor entry")).hash));
+  const hashes = refs.map((ref) => parseHashRef(stripAnchorRow(ref.trim(), "anchor entry")).hash);
+  const owners = hashes.map((hash) => ownerOf(hash));
   const missing = owners.findIndex((owner) => !owner);
   if (missing >= 0) {
-    throw new Error(
-      `[E_STALE_ANCHOR] "${refs[missing]!}" is not owned in this session. Call read() on the target file first.`,
-    );
+    throw new Error(staleAnchorMessage(refs[missing]!, hashes[missing]!, owners));
   }
   const paths = new Set(owners.map((owner) => owner!.path));
   if (paths.size > 1) {