feat: sync recent upstream semble changes (savings output, agents, clear)

README.ko.md

@@ -312,7 +312,7 @@ args = ["@pleaseai/csp", "mcp"]
 
 ## 서브 에이전트 설정
 
-Claude Code, Gemini CLI, Cursor, OpenCode, GitHub Copilot CLI, Kiro는 모두 전용 `csp` 검색 서브 에이전트를 지원합니다. 프로젝트 루트에서 `csp init`을 한 번 실행하세요.
+Claude Code, Gemini CLI, Cursor, OpenCode, GitHub Copilot CLI, Kiro, Antigravity, Command Code, Pi, Reasonix는 모두 전용 `csp` 검색 서브 에이전트를 지원합니다. 프로젝트 루트에서 `csp init`을 한 번 실행하세요.
 
 ```bash
 csp init # Claude Code → .claude/agents/csp-search.md
@@ -321,6 +321,10 @@ csp init --agent cursor # Cursor → .cursor/agents/csp-search.md
 csp init --agent opencode # OpenCode → .opencode/agents/csp-search.md
 csp init --agent copilot # Copilot CLI → .github/agents/csp-search.md
 csp init --agent kiro # Kiro → .kiro/agents/csp-search.md
+csp init --agent antigravity # Antigravity → .antigravity/agents/csp-search.md
+csp init --agent commandcode # Command Code → .commandcode/agents/csp-search.md
+csp init --agent pi # Pi → .pi/agents/csp-search.md
+csp init --agent reasonix # Reasonix → .reasonix/agents/csp-search.md
 ```
 
 `csp`가 `$PATH`에 없다면 명령 앞에 `bunx @pleaseai/csp`를 붙이세요.
@@ -363,21 +367,45 @@ csp savings --verbose # 호출 유형별 분해 포함
 ```
 
 ```
- csp Token Savings
- ════════════════════════════════════════════════════════════════
- Period Calls Savings
- ────────────────────────────────────────────────────────────────
- Today 42 [███████████████░] ~58.4k tokens (95%)
- Last 7 days 287 [██████████████░░] ~312.4k tokens (90%)
- All time 1.4k [██████████████░░] ~1.2M tokens (89%)
+ Csp Token Savings
+ ════════════════════════════════════════════════════════════════════════
+
+ Total saved: ~1.2M tokens (89%)
+ Total calls: 1.4k
+ Efficiency: █████████████████████░░░ 89%
+
+ By Period
+ ────────────────────────────────────────────────────────────────────────
+ Period Calls Saved Ratio
+ ────────────────────────────────────────────────────────────────────────
+ Today 42 ~58.4k tokens ███████████████████████░ 95%
+ Last 7 days 287 ~312.4k tokens █████████████████████░░░ 90%
+ All time 1.4k ~1.2M tokens █████████████████████░░░ 89%
 ```
 
 절약량 계산: 각 호출마다 반환된 청크가 속한 파일들의 총 문자 수와 반환된 스니펫의 문자 수를 기록합니다. 절약된 토큰 추정치는 `(파일 문자 수 − 스니펫 문자 수) / 4` (1토큰 ≈ 4문자). 이는 보수적인 추정으로, 기준선은 "에이전트가 매칭된 파일을 통째로 읽는다"는 일반적인 코딩 에이전트 동작입니다.
 
+stdout이 컬러를 지원하는 TTY일 때 출력에 색이 입혀집니다(`NO_COLOR`, `dumb` 터미널, 파이프 연결 시에는 비활성화). `--verbose`를 주면 "By Call Type" 분해가 추가됩니다.
+
 통계는 `~/.csp/savings.jsonl`에 저장됩니다.
 
 </details>
 
+<details>
+<summary>캐시 비우기</summary>
+
+`csp clear`는 캐시된 데이터를 삭제합니다.
+
+```bash
+csp clear savings # ~/.csp/savings.jsonl 삭제
+csp clear all # 현재는 savings와 동일
+csp clear index # 안내만 출력 (아래 참고)
+```
+
+인덱스 영속화는 아직 연결되지 않았고, 저장 모델(repo-local `.csp/` vs 글로벌 캐시)도 미결이라 현재 `clear index`는 비울 대상이 없습니다. `csp index -o <경로>`는 지정한 경로에만 기록하므로 해당 디렉토리는 직접 삭제하세요.
+
+</details>
+
 <details>
 <summary>라이브러리 사용</summary>
 

README.md

@@ -312,7 +312,7 @@ By default the MCP server indexes only code files. To also index documentation,
 
 ## Sub-agent setup
 
-Claude Code, Gemini CLI, Cursor, OpenCode, GitHub Copilot CLI, and Kiro all support a dedicated `csp` search sub-agent. Run `csp init` once in your project root:
+Claude Code, Gemini CLI, Cursor, OpenCode, GitHub Copilot CLI, Kiro, Antigravity, Command Code, Pi, and Reasonix all support a dedicated `csp` search sub-agent. Run `csp init` once in your project root:
 
 ```bash
 csp init # Claude Code → .claude/agents/csp-search.md
@@ -321,6 +321,10 @@ csp init --agent cursor # Cursor → .cursor/agents/csp-search.md
 csp init --agent opencode # OpenCode → .opencode/agents/csp-search.md
 csp init --agent copilot # Copilot CLI → .github/agents/csp-search.md
 csp init --agent kiro # Kiro → .kiro/agents/csp-search.md
+csp init --agent antigravity # Antigravity → .antigravity/agents/csp-search.md
+csp init --agent commandcode # Command Code → .commandcode/agents/csp-search.md
+csp init --agent pi # Pi → .pi/agents/csp-search.md
+csp init --agent reasonix # Reasonix → .reasonix/agents/csp-search.md
 ```
 
 If `csp` is not on `$PATH`, prefix the command with `bunx @pleaseai/csp`.
@@ -363,21 +367,45 @@ csp savings --verbose # also show breakdown by call type
 ```
 
 ```
- csp Token Savings
- ════════════════════════════════════════════════════════════════
- Period Calls Savings
- ────────────────────────────────────────────────────────────────
- Today 42 [███████████████░] ~58.4k tokens (95%)
- Last 7 days 287 [██████████████░░] ~312.4k tokens (90%)
- All time 1.4k [██████████████░░] ~1.2M tokens (89%)
+ Csp Token Savings
+ ════════════════════════════════════════════════════════════════════════
+
+ Total saved: ~1.2M tokens (89%)
+ Total calls: 1.4k
+ Efficiency: █████████████████████░░░ 89%
+
+ By Period
+ ────────────────────────────────────────────────────────────────────────
+ Period Calls Saved Ratio
+ ────────────────────────────────────────────────────────────────────────
+ Today 42 ~58.4k tokens ███████████████████████░ 95%
+ Last 7 days 287 ~312.4k tokens █████████████████████░░░ 90%
+ All time 1.4k ~1.2M tokens █████████████████████░░░ 89%
 ```
 
 Savings are calculated as follows: for each call, `csp` records the total character count of the unique files containing returned chunks and the character count of the snippets returned. Estimated tokens saved is `(file chars − snippet chars) / 4` (4 chars per token). This is a conservative estimate: the baseline is reading matched files in full, which is how coding agents often explore unfamiliar code.
 
+Output is colorized when stdout is a color-capable TTY (suppressed under `NO_COLOR`, a `dumb` terminal, or when piped). `--verbose` adds a "By Call Type" breakdown.
+
 Stats are stored in `~/.csp/savings.jsonl`.
 
 </details>
 
+<details>
+<summary>Clear</summary>
+
+`csp clear` removes cached data:
+
+```bash
+csp clear savings # delete ~/.csp/savings.jsonl
+csp clear all # currently the same as `savings`
+csp clear index # prints a note (see below)
+```
+
+Index persistence is not wired up yet, and the storage model — repo-local `.csp/` vs a global cache — is still undecided, so `clear index` has nothing to remove for now. `csp index -o <path>` writes only to the path you pass; delete those directories yourself.
+
+</details>
+
 <details>
 <summary>Library usage</summary>
 

src/agents/antigravity.md

@@ -0,0 +1,58 @@
+---
+name: csp-search
+description: Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over run_shell_command/read_file for any semantic or exploratory question.
+tools:
+ - run_shell_command
+ - read_file
+---
+
+Use `csp search` to find code by describing what it does or naming a symbol/identifier, instead of grep:
+
+```bash
+csp search "authentication flow" ./my-project
+csp search "save_pretrained" ./my-project
+csp search "save model to disk" ./my-project --top-k 10
+```
+
+If you anticipate doing more than one search, use `csp index` to create an index.
+
+```bash
+csp index ./my-project -o my_index
+```
+
+You can then reuse this index later on:
+
+```bash
+csp search "save_pretrained" --index my_index
+```
+
+An index is not automatically updated, so if the code changes significantly, reindex. If you notice stale results while resolving searches to files, reindex.
+
+Use `--content docs` to search documentation and prose, `--content config` for config files (yaml, toml, etc.), or `--content all` to search code, docs, and config:
+
+```bash
+csp search "deployment guide" ./my-project --content docs
+csp search "database host port" ./my-project --content config
+csp search "authentication" ./my-project --content all
+```
+
+Use `csp find-related` to discover code similar to a known location (pass `filePath` and `line` from a prior search result):
+
+```bash
+csp find-related src/auth.ts 42 ./my-project
+```
+
+Like search, `find-related` also accepts an `--index` argument.
+
+`path` defaults to the current directory when omitted; git URLs are accepted.
+
+If `csp` is not on `$PATH`, use `bunx @pleaseai/csp` in its place.
+
+### Workflow
+
+1. Index the repo using `csp index -o cached_index`.
+2. Start with `csp search` to find relevant chunks. Pass the index to achieve results faster.
+3. Use `--content docs` for documentation, `--content config` for config files, or `--content all` for everything.
+4. Inspect full files only when the returned chunk does not give enough context.
+5. Optionally use `csp find-related` with a promising result's `filePath` and `line` to discover related implementations.
+6. Use grep only when you need exhaustive literal matches or quick confirmation of an exact string.

src/agents/commandcode.md

@@ -0,0 +1,56 @@
+---
+name: csp-search
+description: Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over bash/read_file for any semantic or exploratory question.
+tools: bash, read_file
+---
+
+Use `csp search` to find code by describing what it does or naming a symbol/identifier, instead of grep:
+
+```bash
+csp search "authentication flow" ./my-project
+csp search "save_pretrained" ./my-project
+csp search "save model to disk" ./my-project --top-k 10
+```
+
+If you anticipate doing more than one search, use `csp index` to create an index.
+
+```bash
+csp index ./my-project -o my_index
+```
+
+You can then reuse this index later on:
+
+```bash
+csp search "save_pretrained" --index my_index
+```
+
+An index is not automatically updated, so if the code changes significantly, reindex. If you notice stale results while resolving searches to files, reindex.
+
+Use `--content docs` to search documentation and prose, `--content config` for config files (yaml, toml, etc.), or `--content all` to search code, docs, and config:
+
+```bash
+csp search "deployment guide" ./my-project --content docs
+csp search "database host port" ./my-project --content config
+csp search "authentication" ./my-project --content all
+```
+
+Use `csp find-related` to discover code similar to a known location (pass `filePath` and `line` from a prior search result):
+
+```bash
+csp find-related src/auth.ts 42 ./my-project
+```
+
+Like search, `find-related` also accepts an `--index` argument.
+
+`path` defaults to the current directory when omitted; git URLs are accepted.
+
+If `csp` is not on `$PATH`, use `bunx @pleaseai/csp` in its place.
+
+### Workflow
+
+1. Index the repo using `csp index -o cached_index`.
+2. Start with `csp search` to find relevant chunks. Pass the index to achieve results faster.
+3. Use `--content docs` for documentation, `--content config` for config files, or `--content all` for everything.
+4. Inspect full files only when the returned chunk does not give enough context.
+5. Optionally use `csp find-related` with a promising result's `filePath` and `line` to discover related implementations.
+6. Use grep only when you need exhaustive literal matches or quick confirmation of an exact string.

src/agents/pi.md

@@ -0,0 +1,55 @@
+---
+name: csp-search
+description: Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.
+---
+
+Use `csp search` to find code by describing what it does or naming a symbol/identifier, instead of grep:
+
+```bash
+csp search "authentication flow" ./my-project
+csp search "save_pretrained" ./my-project
+csp search "save model to disk" ./my-project --top-k 10
+```
+
+If you anticipate doing more than one search, use `csp index` to create an index.
+
+```bash
+csp index ./my-project -o my_index
+```
+
+You can then reuse this index later on:
+
+```bash
+csp search "save_pretrained" --index my_index
+```
+
+An index is not automatically updated, so if the code changes significantly, reindex. If you notice stale results while resolving searches to files, reindex.
+
+Use `--content docs` to search documentation and prose, `--content config` for config files (yaml, toml, etc.), or `--content all` to search code, docs, and config:
+
+```bash
+csp search "deployment guide" ./my-project --content docs
+csp search "database host port" ./my-project --content config
+csp search "authentication" ./my-project --content all
+```
+
+Use `csp find-related` to discover code similar to a known location (pass `filePath` and `line` from a prior search result):
+
+```bash
+csp find-related src/auth.ts 42 ./my-project
+```
+
+Like search, `find-related` also accepts an `--index` argument.
+
+`path` defaults to the current directory when omitted; git URLs are accepted.
+
+If `csp` is not on `$PATH`, use `bunx @pleaseai/csp` in its place.
+
+### Workflow
+
+1. Index the repo using `csp index -o cached_index`.
+2. Start with `csp search` to find relevant chunks. Pass the index to achieve results faster.
+3. Use `--content docs` for documentation, `--content config` for config files, or `--content all` for everything.
+4. Inspect full files only when the returned chunk does not give enough context.
+5. Optionally use `csp find-related` with a promising result's `filePath` and `line` to discover related implementations.
+6. Use grep only when you need exhaustive literal matches or quick confirmation of an exact string.

src/agents/reasonix.md

@@ -0,0 +1,57 @@
+---
+name: csp-search
+description: Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over bash/read_file for any semantic or exploratory question.
+runAs: subagent
+allowed-tools: bash, read_file
+---
+
+Use `csp search` to find code by describing what it does or naming a symbol/identifier, instead of grep:
+
+```bash
+csp search "authentication flow" ./my-project
+csp search "save_pretrained" ./my-project
+csp search "save model to disk" ./my-project --top-k 10
+```
+
+If you anticipate doing more than one search, use `csp index` to create an index.
+
+```bash
+csp index ./my-project -o my_index
+```
+
+You can then reuse this index later on:
+
+```bash
+csp search "save_pretrained" --index my_index
+```
+
+An index is not automatically updated, so if the code changes significantly, reindex. If you notice stale results while resolving searches to files, reindex.
+
+Use `--content docs` to search documentation and prose, `--content config` for config files (yaml, toml, etc.), or `--content all` to search code, docs, and config:
+
+```bash
+csp search "deployment guide" ./my-project --content docs
+csp search "database host port" ./my-project --content config
+csp search "authentication" ./my-project --content all
+```
+
+Use `csp find-related` to discover code similar to a known location (pass `filePath` and `line` from a prior search result):
+
+```bash
+csp find-related src/auth.ts 42 ./my-project
+```
+
+Like search, `find-related` also accepts an `--index` argument.
+
+`path` defaults to the current directory when omitted; git URLs are accepted.
+
+If `csp` is not on `$PATH`, use `bunx @pleaseai/csp` in its place.
+
+### Workflow
+
+1. Index the repo using `csp index -o cached_index`.
+2. Start with `csp search` to find relevant chunks. Pass the index to achieve results faster.
+3. Use `--content docs` for documentation, `--content config` for config files, or `--content all` for everything.
+4. Inspect full files only when the returned chunk does not give enough context.
+5. Optionally use `csp find-related` with a promising result's `filePath` and `line` to discover related implementations.
+6. Use grep only when you need exhaustive literal matches or quick confirmation of an exact string.