pi-hashline-edit-pro 1.1.1 → 1.2.0

package/README.md

@@ -179,7 +179,7 @@ Each line is canonicalized (carriage returns stripped, trailing whitespace trimm
 
 The alphabet is sized for an LLM consumer: the model tokenizes rather than squinting at glyphs, so case and digits are all included. The URL-safe specials `-` and `_` are deliberately excluded — a hash starting with `-` is shape-identical to a diff-preview deletion row, and `-`/`_` at a line start are markdown-active, inviting mis-copying and false autocorrections.
 
-**Unique anchors by construction.** If a line's base hash collides with an already-assigned hash, the next free hash is allocated from a bitset (O(1) amortized). Every line in a file therefore gets a unique anchor — two byte-identical lines (repeated `}`, repeated `import` statements) never share one. The same guarantee sets the file size cap: at most 238,328 lines per file, beyond which `read` and `replace` reject with `[E_FILE_TOO_LARGE]` (use `write` for very large files).
+**Unique anchors by construction.** If a line's base hash collides with an already-assigned hash, the next free hash is allocated from a bitset by probing with a stride coprime to the hash space (O(1) amortized). The stride is `62² + 62 + 1`, so consecutive collisions — runs of blank lines, repeated `}` — land on anchors that differ in all three characters instead of sharing a prefix. Every line in a file therefore gets a unique anchor — two byte-identical lines (repeated `}`, repeated `import` statements) never share one. The same guarantee sets the file size cap: at most 238,328 lines per file, beyond which `read` and `replace` reject with `[E_FILE_TOO_LARGE]` (use `write` for very large files).
 
 ## Design decisions
 
@@ -193,13 +193,14 @@ The alphabet is sized for an LLM consumer: the model tokenizes rather than squin
 
 - **Stale anchors.** `[E_STALE_ANCHOR]` / `[E_AMBIGUOUS_ANCHOR]` mean the file changed since the anchors were read, or an earlier `read` never happened. Call `read` for fresh anchors and retry.
 - **Reset the hash store.** Anchors live in `~/.config/pi-hashline-edit-pro/hash-store.sqlite` (with `-wal`/`-shm` sidecars). Quit pi, delete those three files, and the store is rebuilt on the next session. Anchor history is lost, but no project files are touched.
+- **Upgrading.** A hash-allocation change clears the hash store once on the first run after upgrade — anchors are rebuilt on the next read and undo history is lost, but no project files are touched.
 - **Corrupt store.** If the store fails its health check it is renamed to `hash-store.sqlite.corrupt-<timestamp>` (plus `-wal`/`-shm` variants) and rebuilt automatically; the quarantined files can be deleted once a healthy store exists.
 - **Legacy migration.** On first run after upgrading from an older version, the previous `hash-store.json` is imported once and renamed to `hash-store.json.bak`, which can be deleted.
 - **`[E_UNDO_UNAVAILABLE]`.** The edit was refused because the undo record could not be written — check disk space and that the config directory is writable, then retry.
 
 ## Development
 
-Requires [Node.js](https://nodejs.org) ≥ 22.13 and npm.
+Requires [Node.js](https://nodejs.org) ≥ 22.19 and npm.
 
 ```bash
 npm install

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-hashline-edit-pro",
-  "version": "1.1.1",
+  "version": "1.2.0",
   "type": "module",
   "description": "Strict hashline read/replace tool for pi-coding-agent with hash-anchored edits (3-char, 62-symbol, perfect hashing)",
   "main": "index.ts",
@@ -34,15 +34,15 @@
   "dependencies": {
     "diff": "^8.0.2",
     "file-type": "^21.3.0",
-    "typebox": "^1.1.24",
+    "typebox": "^1.3.7",
     "xxhash-wasm": "^1.1.0"
   },
   "peerDependencies": {
-    "@earendil-works/pi-coding-agent": ">=0.74.0",
+    "@earendil-works/pi-coding-agent": ">=0.75.0",
     "@earendil-works/pi-tui": "*"
   },
   "engines": {
-    "node": ">=22.13.0"
+    "node": ">=22.19.0"
   },
   "scripts": {
     "test": "vitest run",
@@ -52,7 +52,7 @@
     "typecheck": "tsc --noEmit"
   },
   "devDependencies": {
-    "@earendil-works/pi-coding-agent": "^0.74.0",
+    "@earendil-works/pi-coding-agent": "^0.84.0",
     "@eslint/js": "^10.0.1",
     "@types/node": "^24.0.0",
     "@vitest/coverage-v8": "^4.1.10",

package/src/constants.ts

@@ -4,7 +4,7 @@ export const MAX_BYTES = 100 * 1024 * 1024;
 export const MAX_READ_LINE_BYTES = 200 * 1024;
 
 export const HASH_STORE_BUSY_TIMEOUT = 1000;
-export const HASH_STORE_VERSION = 4;
+export const HASH_STORE_VERSION = 5;
 export const CONTENT_LINES_NOT_STRING_MSG =
   `[E_BAD_SHAPE] "content_lines" must be a native JSON array of strings, not a JSON string.`
   + ` Do not serialize the array (e.g. '["line1", "line2"]') — pass it as a proper JSON array: ["line1", "line2"].`;

package/src/hashline/hash.ts

@@ -22,6 +22,8 @@ export const HASH_CLASS = `[${ALPH_SAFE}]{${HASH_LEN}}`;
 export const HASH_SPACE = ALPH.length ** HASH_LEN;
 export const MAX_HASH_LINES = HASH_SPACE;
 
+export const HASH_PROBE_STRIDE = ALPH.length ** 2 + ALPH.length + 1;
+
 function idxToHash(idx: number): string {
   let out = "";
   for (let j = 0; j < HASH_LEN; j++) {
@@ -66,44 +68,13 @@ function setBit(bits: Uint32Array, idx: number): void {
 }
 
 function nextZeroBit(bits: Uint32Array, start: number): number {
-  const totalWords = bits.length;
   const totalBits = HASH_SPACE;
-  const lastWordBits = HASH_SPACE - (totalWords - 1) * 32;
-
-  if (start >= totalBits) start = 0;
-
-  const wordIdx = start >>> 5;
-  const bitOffset = start & 31;
-  const wordBits = (w: number): number => (w === totalWords - 1 ? lastWordBits : 32);
-
-  let word = bits[wordIdx];
-  for (let b = bitOffset; b < wordBits(wordIdx); b++) {
-    if ((word >>> b & 1) === 0) return wordIdx * 32 + b;
-  }
-
-  for (let w = wordIdx + 1; w < totalWords; w++) {
-    word = bits[w];
-    if (~word !== 0) {
-      for (let b = 0; b < wordBits(w); b++) {
-        if ((word >>> b & 1) === 0) return w * 32 + b;
-      }
-    }
+  let idx = start % totalBits;
+  for (let i = 0; i < totalBits; i++) {
+    if (!getBit(bits, idx)) return idx;
+    idx += HASH_PROBE_STRIDE;
+    if (idx >= totalBits) idx -= totalBits;
   }
-
-  for (let w = 0; w < wordIdx; w++) {
-    word = bits[w];
-    if (~word !== 0) {
-      for (let b = 0; b < wordBits(w); b++) {
-        if ((word >>> b & 1) === 0) return w * 32 + b;
-      }
-    }
-  }
-
-  word = bits[wordIdx];
-  for (let b = 0; b < bitOffset; b++) {
-    if ((word >>> b & 1) === 0) return wordIdx * 32 + b;
-  }
-
   throw new Error(
     `[E_FILE_TOO_LARGE] Cannot allocate a unique hash anchor: the file exceeds the ${HASH_SPACE}-line limit for ${HASH_LEN}-char hashline anchors. For very large files use write or a non-line-based approach.`,
   );
@@ -112,13 +83,12 @@ function nextZeroBit(bits: Uint32Array, start: number): number {
 function assignHash(used: Uint32Array, baseIdx: number, hint: { value: number }): string {
   if (!getBit(used, baseIdx)) {
     setBit(used, baseIdx);
-    hint.value = baseIdx + 1;
+    hint.value = baseIdx + HASH_PROBE_STRIDE;
     return hashAt(baseIdx);
   }
-  const start = hint.value > baseIdx + 1 ? hint.value : baseIdx + 1;
-  const nextIdx = nextZeroBit(used, start);
+  const nextIdx = nextZeroBit(used, hint.value);
   setBit(used, nextIdx);
-  hint.value = nextIdx + 1;
+  hint.value = nextIdx + HASH_PROBE_STRIDE;
   return hashAt(nextIdx);
 }
 
@@ -277,7 +247,7 @@ function mapStableHashes(
     const idx = hashToIndex(hash);
     if (idx >= 0) {
       setBit(used, idx);
-      if (idx + 1 > hint.value) hint.value = idx + 1;
+      if (idx + HASH_PROBE_STRIDE > hint.value) hint.value = idx + HASH_PROBE_STRIDE;
     }
   };
 

package/src/hashline/index.ts

@@ -4,6 +4,7 @@ export {
 	HASH_SEP,
 	HASH_CLASS,
 	HASH_SPACE,
+	HASH_PROBE_STRIDE,
 	MAX_HASH_LINES,
 	HL_PREFIX_PLUS_RE,
 	HL_PREFIX_MINUS_RE,