-
Notifications
You must be signed in to change notification settings - Fork 296
refactor: resolve 4 semantic function clustering findings #19799
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
pelikhan
merged 2 commits into
main
from
copilot/refactor-semantic-function-clustering-53b8f0b4-b41a-4962-835b-fb09f6ba3ea6
Mar 6, 2026
+273
−334
Merged
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| package cli | ||
|
|
||
| import ( | ||
| "regexp" | ||
| "strings" | ||
|
|
||
| "github.com/github/gh-aw/pkg/workflow" | ||
| ) | ||
|
|
||
| // ParseCopilotCodingAgentLogMetrics extracts metrics from GitHub Copilot coding agent logs | ||
| // This is different from Copilot CLI logs and requires specialized parsing | ||
| func ParseCopilotCodingAgentLogMetrics(logContent string, verbose bool) workflow.LogMetrics { | ||
| copilotCodingAgentLog.Printf("Parsing GitHub Copilot coding agent log metrics: %d bytes", len(logContent)) | ||
|
|
||
| var metrics workflow.LogMetrics | ||
| var maxTokenUsage int | ||
|
|
||
| lines := strings.Split(logContent, "\n") | ||
| toolCallMap := make(map[string]*workflow.ToolCallInfo) | ||
| var currentSequence []string | ||
| turns := 0 | ||
|
|
||
| // GitHub Copilot coding agent log patterns | ||
| // These patterns are designed to match the specific log format of the agent | ||
| turnPattern := regexp.MustCompile(`(?i)task.*iteration|agent.*turn|step.*\d+`) | ||
| toolCallPattern := regexp.MustCompile(`(?i)tool.*call|executing.*tool|calling.*(\w+)`) | ||
|
|
||
| for _, line := range lines { | ||
| // Skip empty lines | ||
| if strings.TrimSpace(line) == "" { | ||
| continue | ||
| } | ||
|
|
||
| // Count turns based on agent iteration patterns | ||
| if turnPattern.MatchString(line) { | ||
| turns++ | ||
| // Start of a new turn, save previous sequence if any | ||
| if len(currentSequence) > 0 { | ||
| metrics.ToolSequences = append(metrics.ToolSequences, currentSequence) | ||
| currentSequence = []string{} | ||
| } | ||
| } | ||
|
|
||
| // Extract tool calls from agent logs | ||
| if matches := toolCallPattern.FindStringSubmatch(line); len(matches) > 1 { | ||
| toolName := extractToolName(line) | ||
| if toolName != "" { | ||
| // Track tool call | ||
| if _, exists := toolCallMap[toolName]; !exists { | ||
| toolCallMap[toolName] = &workflow.ToolCallInfo{ | ||
| Name: toolName, | ||
| CallCount: 0, | ||
| } | ||
| } | ||
| toolCallMap[toolName].CallCount++ | ||
|
|
||
| // Add to current sequence | ||
| currentSequence = append(currentSequence, toolName) | ||
|
|
||
| if verbose { | ||
| copilotCodingAgentLog.Printf("Found tool call: %s", toolName) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| // Try to extract token usage from JSON format if available | ||
| jsonMetrics := workflow.ExtractJSONMetrics(line, verbose) | ||
| if jsonMetrics.TokenUsage > 0 || jsonMetrics.EstimatedCost > 0 { | ||
| if jsonMetrics.TokenUsage > maxTokenUsage { | ||
| maxTokenUsage = jsonMetrics.TokenUsage | ||
| } | ||
| if jsonMetrics.EstimatedCost > 0 { | ||
| metrics.EstimatedCost += jsonMetrics.EstimatedCost | ||
| } | ||
| } | ||
| } | ||
|
|
||
| // Add final sequence if any | ||
| if len(currentSequence) > 0 { | ||
| metrics.ToolSequences = append(metrics.ToolSequences, currentSequence) | ||
| } | ||
|
|
||
| // Convert tool call map to slice | ||
| for _, toolInfo := range toolCallMap { | ||
| metrics.ToolCalls = append(metrics.ToolCalls, *toolInfo) | ||
| } | ||
|
|
||
| metrics.TokenUsage = maxTokenUsage | ||
| metrics.Turns = turns | ||
|
|
||
| copilotCodingAgentLog.Printf("Parsed metrics: tokens=%d, cost=$%.4f, turns=%d", | ||
| metrics.TokenUsage, metrics.EstimatedCost, metrics.Turns) | ||
|
|
||
| return metrics | ||
| } | ||
|
|
||
| // extractToolName extracts a tool name from a log line | ||
| func extractToolName(line string) string { | ||
| // Try to extract tool name from various patterns | ||
| patterns := []*regexp.Regexp{ | ||
| regexp.MustCompile(`(?i)tool[:\s]+([a-zA-Z0-9_-]+)`), | ||
| regexp.MustCompile(`(?i)calling[:\s]+([a-zA-Z0-9_-]+)`), | ||
| regexp.MustCompile(`(?i)executing[:\s]+([a-zA-Z0-9_-]+)`), | ||
| regexp.MustCompile(`(?i)using[:\s]+tool[:\s]+([a-zA-Z0-9_-]+)`), | ||
| } | ||
|
|
||
| for _, pattern := range patterns { | ||
| if matches := pattern.FindStringSubmatch(line); len(matches) > 1 { | ||
| return strings.TrimSpace(matches[1]) | ||
| } | ||
| } | ||
|
|
||
| return "" | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
turnPatternandtoolCallPatternare compiled on every call toParseCopilotCodingAgentLogMetrics. Consider moving these regexes to package-levelvars (or initializing once) to avoid repeated compilation overhead when parsing many logs.This issue also appears on line 97 of the same file.