thincoder 0.6.0 → 0.7.1

package/src/skills.mjs

@@ -28,13 +28,17 @@ export async function loadSkills(cwd) {
     try {
       const s = await stat(p)
       if (!s.isFile()) continue
-      // 提取描述（前 400 字符里第一段非空、非标题行）
+      // 提取描述（前 400 字符里第一段非空、非标题行）；文件带 frontmatter 时整块跳过，
+      // 否则会把 frontmatter 字段行（如 "name: x"）误当描述
       const head = await readFile(p, "utf8")
       const body = head.slice(0, 400).split("\n")
       let desc = ""
+      let inFrontmatter = false
       for (const line of body) {
         const t = line.trim()
-        if (t && !t.startsWith("#") && !t.startsWith("---")) {
+        if (t === "---") { inFrontmatter = !inFrontmatter; continue }
+        if (inFrontmatter) continue
+        if (t && !t.startsWith("#")) {
           desc = t.slice(0, 120)
           break
         }

package/src/tools/apply_patch.md

@@ -0,0 +1,11 @@
+Apply a unified diff to one or more files, atomically: if any hunk fails to apply, nothing is written.
+
+Parameters:
+- patch (required): Unified diff text. One `--- a/path` / `+++ b/path` header pair per file, then `@@ -old,count +new,count @@` hunks. Use `--- /dev/null` to create a new file.
+
+Notes:
+- Use this for multi-file changes (e.g. rename an interface + update all callers) — one call, all-or-nothing
+- Hunks are located by their context/removed lines, not line numbers — but the context must match the file EXACTLY. Read the files first and generate the patch from actual content
+- If a hunk's context matches multiple locations it is rejected — add more surrounding context lines
+- Deleting files is not supported — use the delete tool
+- For single-file small edits, edit is simpler; for full rewrites, write is simpler

package/src/tools/bash.md

@@ -4,10 +4,22 @@ Parameters:
 - command (required): Shell command to execute
 - timeout: Timeout in milliseconds (default 120000, max ~300000)
 
+Output format:
+```
+[stdout]:
+<standard output, or "(empty)">
+
+[stderr]:
+<standard error, only present if non-empty>
+
+(exit code N)
+```
+
 Notes:
 - There is NO TTY — editors, pagers (vim, less), and interactive prompts WILL hang. Always pass non-interactive flags: `git commit -m`, `git --no-pager`, `-y`/`--yes` where applicable
 - The environment sets GIT_PAGER=cat, PAGER=cat, EDITOR=true, TERM=dumb — but still always use non-interactive flags
-- Output is capped at ~50000 chars; if you need more, redirect to a file and read it
+- Output is capped at ~200K chars; if you need more, redirect to a file and read it. Truncated output ends with a `[... truncated: N chars omitted]` marker — the missing tail may contain errors.
+- Check `[stderr]` for error messages, warnings, and diagnostic output — it is separated from `[stdout]` so you can quickly identify problems.
 - On Windows, use Unix shell syntax inside bash commands (Git Bash): forward slashes, `/dev/null` not `NUL`
 - Never use bash to read, copy, or transmit secret files (.env, keys, tokens)
 - Do NOT run destructive commands (rm -rf, force-push, drop table) without explicit user confirmation

package/src/tools/checkpoint.md

@@ -0,0 +1,11 @@
+List, create, and restore workspace snapshots (checkpoints). Git repositories only.
+
+Parameters:
+- action (required): "list" | "create" | "rewind"
+- id: snapshot id (required for rewind)
+
+Notes:
+- A checkpoint is AUTO-CREATED before every user task. If uncommitted work was destroyed (by you, a git command, or a failed refactor), use action=list then action=rewind with the latest id to recover it
+- A checkpoint captures all uncommitted state: tracked-file changes (as a diff) plus copies of untracked files
+- Rewind first snapshots the current state, so rewinding is itself reversible
+- Create one manually before risky bulk operations

package/src/tools/grep.md

@@ -4,9 +4,12 @@ Parameters:
 - pattern (required): JavaScript regular expression
 - path: Directory or file to search (default cwd)
 - glob: Only search files matching this glob (e.g. '*.mjs')
+- before: Lines of context to show before each match (grep -B). Default 0
+- after: Lines of context to show after each match (grep -A). Default 0
 
 Notes:
 - Skips node_modules, .git, dist, build, .turbo, coverage
 - Results capped at 200 matches
 - Binary/unreadable files are silently skipped
 - Use this to find usages, definitions, patterns; use glob to find files by name
+- With before/after: matching lines use `:` separator, context lines use `-` (like ripgrep); overlapping context ranges in the same file are merged and de-duplicated

package/src/tools/insert_after.md

@@ -0,0 +1,13 @@
+Insert a line of text after a specific line in a file. Safer than `edit` for adding new content — no need to copy surrounding context for exact string matching.
+
+Parameters:
+- path (required): File path
+- content (required): Text to insert (will be placed as a new line after the target line)
+- after_line: Line number to insert after (1-based). Preferred when you know the exact line number from `read`.
+- after_regex: JavaScript regex to find the line to insert after. Must match exactly one line; if it matches multiple, the tool errors and shows the matching line numbers.
+
+Notes:
+- Either after_line or after_regex is required; if both are given, after_line wins.
+- Use this instead of `edit` when you're adding a new function, import, or block — no need to fabricate surrounding context for exact matching.
+- The inserted content becomes its own line; it's equivalent to `lines.splice(targetLine, 0, content)`.
+- Returns a diff of the change.

package/src/tools/question.md

@@ -8,3 +8,4 @@ Notes:
 - The agent loop pauses until the user answers
 - The answer is injected as the next user message
 - Use sparingly — prefer making reasonable decisions when possible
+- After receiving an answer about a design convention, tool preference, or recurring pattern: save it with memory_put. This prevents asking the same question in future sessions — the user shouldn't have to repeat their preferences.

package/src/tools/syntax_check.md

@@ -0,0 +1,10 @@
+Check a JavaScript file for syntax errors using `node --check`. Fast, offline, no dependencies — use after writing or editing .js/.mjs/.cjs files to catch parse errors before running tests.
+
+Parameters:
+- path (required): File path (.js, .mjs, or .cjs)
+
+Notes:
+- Only supports JavaScript-family files; for other languages, run the appropriate checker via `bash`.
+- Returns "Syntax OK" or the exact error message with line/column from Node.js.
+- This is NOT a test run — it only catches parse errors (missing brackets, invalid syntax), not logic bugs.
+- Use this right after `write` or `edit` to fail fast on trivial mistakes before investing time in a full test run.

package/src/tools/websearch.md

@@ -5,6 +5,7 @@ Parameters:
 - limit: Max results (default 8)
 
 Notes:
+- Before searching the web, call `memory_search` first — you may already know the answer from a previous session. Only reach for websearch if memory comes up empty.
 - Use this for information that is NOT in the local codebase — current docs, error messages, API references
 - Follow up with `fetch` to read full pages from the results
 - Results are scraped from Bing HTML — some formatting may be imperfect