refactor(hashline-edit): align tool payload to op/pos/end/lines

Unify hashline_edit input with replace/append/prepend + pos/end/lines semantics so callers use a single stable shape. Add normalization coverage and refresh tool guidance/tests to reduce schema confusion and stale legacy payload usage.
This commit is contained in:
minpeter
2026-02-24 03:00:38 +09:00
parent 1cf918362d
commit 9eda19bf7b
5 changed files with 210 additions and 189 deletions
+19 -20
View File
@@ -8,10 +8,11 @@ WORKFLOW:
5. Use anchors as "LINE#ID" only (never include trailing ":content").
VALIDATION:
Payload shape: { "filePath": string, "edits": [...], "delete"?: boolean, "rename"?: string }
Each edit must be one of: set_line, replace_lines, insert_after, insert_before, insert_between, replace, append, prepend
text/new_text must contain plain replacement text only (no LINE#ID prefixes, no diff + markers)
CRITICAL: all operations validate against the same pre-edit file snapshot and apply bottom-up. Refs/tags are interpreted against the last-read version of the file.
Payload shape: { "filePath": string, "edits": [...], "delete"?: boolean, "rename"?: string }
Each edit must be one of: replace, append, prepend
Edit shape: { "op": "replace"|"append"|"prepend", "pos"?: "LINE#ID", "end"?: "LINE#ID", "lines"?: string|string[]|null }
lines must contain plain replacement text only (no LINE#ID prefixes, no diff + markers)
CRITICAL: all operations validate against the same pre-edit file snapshot and apply bottom-up. Refs/tags are interpreted against the last-read version of the file.
LINE#ID FORMAT (CRITICAL):
Each line reference must be in "LINE#ID" format where:
@@ -23,22 +24,21 @@ FILE MODES:
rename moves final content to a new path and removes old path
CONTENT FORMAT:
text/new_text can be a string (single line) or string[] (multi-line, preferred).
If you pass a multi-line string, it is split by real newline characters.
Literal "\\n" is preserved as text.
lines can be a string (single line) or string[] (multi-line, preferred).
If you pass a multi-line string, it is split by real newline characters.
Literal "\\n" is preserved as text.
FILE CREATION:
append: adds content at EOF. If file does not exist, creates it.
prepend: adds content at BOF. If file does not exist, creates it.
CRITICAL: append/prepend are the only operations that work without an existing file.
append without anchors adds content at EOF. If file does not exist, creates it.
prepend without anchors adds content at BOF. If file does not exist, creates it.
CRITICAL: only unanchored append/prepend can create a missing file.
OPERATION CHOICE:
One line wrong -> set_line
Adjacent block rewrite or swap/move -> replace_lines (prefer one range op over many single-line ops)
Both boundaries known -> insert_between (ALWAYS prefer over insert_after/insert_before)
One boundary known -> insert_after or insert_before
New file or EOF/BOF addition -> append or prepend
No LINE#ID available -> replace (last resort)
replace with pos only -> replace one line at pos
replace with pos+end -> replace range pos..end
append with pos/end anchor -> insert after that anchor
prepend with pos/end anchor -> insert before that anchor
append/prepend without anchors -> EOF/BOF insertion
RULES (CRITICAL):
1. Minimize scope: one logical mutation site per operation.
@@ -53,10 +53,9 @@ RULES (CRITICAL):
TAG CHOICE (ALWAYS):
- Copy tags exactly from read output or >>> mismatch output.
- NEVER guess tags.
- Prefer insert_between over insert_after/insert_before when both boundaries are known.
- Anchor to structural lines (function/class/brace), NEVER blank lines.
- Anti-pattern warning: blank/whitespace anchors are fragile.
- Re-read after each successful edit call before issuing another on the same file.
- Anchor to structural lines (function/class/brace), NEVER blank lines.
- Anti-pattern warning: blank/whitespace anchors are fragile.
- Re-read after each successful edit call before issuing another on the same file.
AUTOCORRECT (built-in - you do NOT need to handle these):
Merged lines are auto-expanded back to original line count.