1package tools
2
3import (
4 "bytes"
5 "context"
6 "encoding/json"
7 "fmt"
8 "io"
9 "net/http"
10 "strings"
11 "time"
12)
13
14type SourcegraphParams struct {
15 Query string `json:"query"`
16 Count int `json:"count,omitempty"`
17 ContextWindow int `json:"context_window,omitempty"`
18 Timeout int `json:"timeout,omitempty"`
19}
20
21type SourcegraphResponseMetadata struct {
22 NumberOfMatches int `json:"number_of_matches"`
23 Truncated bool `json:"truncated"`
24}
25
26type sourcegraphTool struct {
27 client *http.Client
28}
29
30const (
31 SourcegraphToolName = "sourcegraph"
32 sourcegraphToolDescription = `Search code across public repositories using Sourcegraph's GraphQL API.
33
34WHEN TO USE THIS TOOL:
35- Use when you need to find code examples or implementations across public repositories
36- Helpful for researching how others have solved similar problems
37- Useful for discovering patterns and best practices in open source code
38
39HOW TO USE:
40- Provide a search query using Sourcegraph's query syntax
41- Optionally specify the number of results to return (default: 10)
42- Optionally set a timeout for the request
43
44QUERY SYNTAX:
45- Basic search: "fmt.Println" searches for exact matches
46- File filters: "file:.go fmt.Println" limits to Go files
47- Repository filters: "repo:^github\.com/golang/go$ fmt.Println" limits to specific repos
48- Language filters: "lang:go fmt.Println" limits to Go code
49- Boolean operators: "fmt.Println AND log.Fatal" for combined terms
50- Regular expressions: "fmt\.(Print|Printf|Println)" for pattern matching
51- Quoted strings: "\"exact phrase\"" for exact phrase matching
52- Exclude filters: "-file:test" or "-repo:forks" to exclude matches
53
54ADVANCED FILTERS:
55- Repository filters:
56 * "repo:name" - Match repositories with name containing "name"
57 * "repo:^github\.com/org/repo$" - Exact repository match
58 * "repo:org/repo@branch" - Search specific branch
59 * "repo:org/repo rev:branch" - Alternative branch syntax
60 * "-repo:name" - Exclude repositories
61 * "fork:yes" or "fork:only" - Include or only show forks
62 * "archived:yes" or "archived:only" - Include or only show archived repos
63 * "visibility:public" or "visibility:private" - Filter by visibility
64
65- File filters:
66 * "file:\.js$" - Files with .js extension
67 * "file:internal/" - Files in internal directory
68 * "-file:test" - Exclude test files
69 * "file:has.content(Copyright)" - Files containing "Copyright"
70 * "file:has.contributor([email protected])" - Files with specific contributor
71
72- Content filters:
73 * "content:\"exact string\"" - Search for exact string
74 * "-content:\"unwanted\"" - Exclude files with unwanted content
75 * "case:yes" - Case-sensitive search
76
77- Type filters:
78 * "type:symbol" - Search for symbols (functions, classes, etc.)
79 * "type:file" - Search file content only
80 * "type:path" - Search filenames only
81 * "type:diff" - Search code changes
82 * "type:commit" - Search commit messages
83
84- Commit/diff search:
85 * "after:\"1 month ago\"" - Commits after date
86 * "before:\"2023-01-01\"" - Commits before date
87 * "author:name" - Commits by author
88 * "message:\"fix bug\"" - Commits with message
89
90- Result selection:
91 * "select:repo" - Show only repository names
92 * "select:file" - Show only file paths
93 * "select:content" - Show only matching content
94 * "select:symbol" - Show only matching symbols
95
96- Result control:
97 * "count:100" - Return up to 100 results
98 * "count:all" - Return all results
99 * "timeout:30s" - Set search timeout
100
101EXAMPLES:
102- "file:.go context.WithTimeout" - Find Go code using context.WithTimeout
103- "lang:typescript useState type:symbol" - Find TypeScript React useState hooks
104- "repo:^github\.com/kubernetes/kubernetes$ pod list type:file" - Find Kubernetes files related to pod listing
105- "repo:sourcegraph/sourcegraph$ after:\"3 months ago\" type:diff database" - Recent changes to database code
106- "file:Dockerfile (alpine OR ubuntu) -content:alpine:latest" - Dockerfiles with specific base images
107- "repo:has.path(\.py) file:requirements.txt tensorflow" - Python projects using TensorFlow
108
109BOOLEAN OPERATORS:
110- "term1 AND term2" - Results containing both terms
111- "term1 OR term2" - Results containing either term
112- "term1 NOT term2" - Results with term1 but not term2
113- "term1 and (term2 or term3)" - Grouping with parentheses
114
115LIMITATIONS:
116- Only searches public repositories
117- Rate limits may apply
118- Complex queries may take longer to execute
119- Maximum of 20 results per query
120
121TIPS:
122- Use specific file extensions to narrow results
123- Add repo: filters for more targeted searches
124- Use type:symbol to find function/method definitions
125- Use type:file to find relevant files`
126)
127
128func NewSourcegraphTool() BaseTool {
129 return &sourcegraphTool{
130 client: &http.Client{
131 Timeout: 30 * time.Second,
132 Transport: &http.Transport{
133 MaxIdleConns: 100,
134 MaxIdleConnsPerHost: 10,
135 IdleConnTimeout: 90 * time.Second,
136 },
137 },
138 }
139}
140
141func (t *sourcegraphTool) Info() ToolInfo {
142 return ToolInfo{
143 Name: SourcegraphToolName,
144 Description: sourcegraphToolDescription,
145 Parameters: map[string]any{
146 "query": map[string]any{
147 "type": "string",
148 "description": "The Sourcegraph search query",
149 },
150 "count": map[string]any{
151 "type": "number",
152 "description": "Optional number of results to return (default: 10, max: 20)",
153 },
154 "context_window": map[string]any{
155 "type": "number",
156 "description": "The context around the match to return (default: 10 lines)",
157 },
158 "timeout": map[string]any{
159 "type": "number",
160 "description": "Optional timeout in seconds (max 120)",
161 },
162 },
163 Required: []string{"query"},
164 }
165}
166
167func (t *sourcegraphTool) Run(ctx context.Context, call ToolCall) (ToolResponse, error) {
168 var params SourcegraphParams
169 if err := json.Unmarshal([]byte(call.Input), ¶ms); err != nil {
170 return NewTextErrorResponse("Failed to parse sourcegraph parameters: " + err.Error()), nil
171 }
172
173 if params.Query == "" {
174 return NewTextErrorResponse("Query parameter is required"), nil
175 }
176
177 if params.Count <= 0 {
178 params.Count = 10
179 } else if params.Count > 20 {
180 params.Count = 20 // Limit to 20 results
181 }
182
183 if params.ContextWindow <= 0 {
184 params.ContextWindow = 10 // Default context window
185 }
186
187 // Handle timeout with context
188 requestCtx := ctx
189 if params.Timeout > 0 {
190 maxTimeout := 120 // 2 minutes
191 if params.Timeout > maxTimeout {
192 params.Timeout = maxTimeout
193 }
194 var cancel context.CancelFunc
195 requestCtx, cancel = context.WithTimeout(ctx, time.Duration(params.Timeout)*time.Second)
196 defer cancel()
197 }
198
199 type graphqlRequest struct {
200 Query string `json:"query"`
201 Variables struct {
202 Query string `json:"query"`
203 } `json:"variables"`
204 }
205
206 request := graphqlRequest{
207 Query: "query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }",
208 }
209 request.Variables.Query = params.Query
210
211 graphqlQueryBytes, err := json.Marshal(request)
212 if err != nil {
213 return ToolResponse{}, fmt.Errorf("failed to marshal GraphQL request: %w", err)
214 }
215 graphqlQuery := string(graphqlQueryBytes)
216
217 req, err := http.NewRequestWithContext(
218 requestCtx,
219 "POST",
220 "https://sourcegraph.com/.api/graphql",
221 bytes.NewBuffer([]byte(graphqlQuery)),
222 )
223 if err != nil {
224 return ToolResponse{}, fmt.Errorf("failed to create request: %w", err)
225 }
226
227 req.Header.Set("Content-Type", "application/json")
228 req.Header.Set("User-Agent", "crush/1.0")
229
230 resp, err := t.client.Do(req)
231 if err != nil {
232 return ToolResponse{}, fmt.Errorf("failed to fetch URL: %w", err)
233 }
234 defer resp.Body.Close()
235
236 if resp.StatusCode != http.StatusOK {
237 body, _ := io.ReadAll(resp.Body)
238 if len(body) > 0 {
239 return NewTextErrorResponse(fmt.Sprintf("Request failed with status code: %d, response: %s", resp.StatusCode, string(body))), nil
240 }
241
242 return NewTextErrorResponse(fmt.Sprintf("Request failed with status code: %d", resp.StatusCode)), nil
243 }
244 body, err := io.ReadAll(resp.Body)
245 if err != nil {
246 return ToolResponse{}, fmt.Errorf("failed to read response body: %w", err)
247 }
248
249 var result map[string]any
250 if err = json.Unmarshal(body, &result); err != nil {
251 return ToolResponse{}, fmt.Errorf("failed to unmarshal response: %w", err)
252 }
253
254 formattedResults, err := formatSourcegraphResults(result, params.ContextWindow)
255 if err != nil {
256 return NewTextErrorResponse("Failed to format results: " + err.Error()), nil
257 }
258
259 return NewTextResponse(formattedResults), nil
260}
261
262func formatSourcegraphResults(result map[string]any, contextWindow int) (string, error) {
263 var buffer strings.Builder
264
265 if errors, ok := result["errors"].([]any); ok && len(errors) > 0 {
266 buffer.WriteString("## Sourcegraph API Error\n\n")
267 for _, err := range errors {
268 if errMap, ok := err.(map[string]any); ok {
269 if message, ok := errMap["message"].(string); ok {
270 buffer.WriteString(fmt.Sprintf("- %s\n", message))
271 }
272 }
273 }
274 return buffer.String(), nil
275 }
276
277 data, ok := result["data"].(map[string]any)
278 if !ok {
279 return "", fmt.Errorf("invalid response format: missing data field")
280 }
281
282 search, ok := data["search"].(map[string]any)
283 if !ok {
284 return "", fmt.Errorf("invalid response format: missing search field")
285 }
286
287 searchResults, ok := search["results"].(map[string]any)
288 if !ok {
289 return "", fmt.Errorf("invalid response format: missing results field")
290 }
291
292 matchCount, _ := searchResults["matchCount"].(float64)
293 resultCount, _ := searchResults["resultCount"].(float64)
294 limitHit, _ := searchResults["limitHit"].(bool)
295
296 buffer.WriteString("# Sourcegraph Search Results\n\n")
297 buffer.WriteString(fmt.Sprintf("Found %d matches across %d results\n", int(matchCount), int(resultCount)))
298
299 if limitHit {
300 buffer.WriteString("(Result limit reached, try a more specific query)\n")
301 }
302
303 buffer.WriteString("\n")
304
305 results, ok := searchResults["results"].([]any)
306 if !ok || len(results) == 0 {
307 buffer.WriteString("No results found. Try a different query.\n")
308 return buffer.String(), nil
309 }
310
311 maxResults := 10
312 if len(results) > maxResults {
313 results = results[:maxResults]
314 }
315
316 for i, res := range results {
317 fileMatch, ok := res.(map[string]any)
318 if !ok {
319 continue
320 }
321
322 typeName, _ := fileMatch["__typename"].(string)
323 if typeName != "FileMatch" {
324 continue
325 }
326
327 repo, _ := fileMatch["repository"].(map[string]any)
328 file, _ := fileMatch["file"].(map[string]any)
329 lineMatches, _ := fileMatch["lineMatches"].([]any)
330
331 if repo == nil || file == nil {
332 continue
333 }
334
335 repoName, _ := repo["name"].(string)
336 filePath, _ := file["path"].(string)
337 fileURL, _ := file["url"].(string)
338 fileContent, _ := file["content"].(string)
339
340 buffer.WriteString(fmt.Sprintf("## Result %d: %s/%s\n\n", i+1, repoName, filePath))
341
342 if fileURL != "" {
343 buffer.WriteString(fmt.Sprintf("URL: %s\n\n", fileURL))
344 }
345
346 if len(lineMatches) > 0 {
347 for _, lm := range lineMatches {
348 lineMatch, ok := lm.(map[string]any)
349 if !ok {
350 continue
351 }
352
353 lineNumber, _ := lineMatch["lineNumber"].(float64)
354 preview, _ := lineMatch["preview"].(string)
355
356 if fileContent != "" {
357 lines := strings.Split(fileContent, "\n")
358
359 buffer.WriteString("```\n")
360
361 startLine := max(1, int(lineNumber)-contextWindow)
362
363 for j := startLine - 1; j < int(lineNumber)-1 && j < len(lines); j++ {
364 if j >= 0 {
365 buffer.WriteString(fmt.Sprintf("%d| %s\n", j+1, lines[j]))
366 }
367 }
368
369 buffer.WriteString(fmt.Sprintf("%d| %s\n", int(lineNumber), preview))
370
371 endLine := int(lineNumber) + contextWindow
372
373 for j := int(lineNumber); j < endLine && j < len(lines); j++ {
374 if j < len(lines) {
375 buffer.WriteString(fmt.Sprintf("%d| %s\n", j+1, lines[j]))
376 }
377 }
378
379 buffer.WriteString("```\n\n")
380 } else {
381 buffer.WriteString("```\n")
382 buffer.WriteString(fmt.Sprintf("%d| %s\n", int(lineNumber), preview))
383 buffer.WriteString("```\n\n")
384 }
385 }
386 }
387 }
388
389 return buffer.String(), nil
390}