scanLines reads from r line by line, collecting at most maxLines lines starting from startLine (1-based), while counting the total number of lines. Th

shouldReview applies the filter algorithm via whyExcluded.

shouldSkipFile returns true if a git ls-files output path should be skipped. Keeps only widely useful files (those with recognizable extensions).

splitAndNormalize splits code text into lines and normalizes each one.

splitBindHost returns the host portion of a listen address as passed to http.Server.Addr. Empty input returns "".

stripEmptyPlanBlock removes the "### Review Plan …\n{{plan_guidance}}\n\n" wrapper from a MAIN_TASK user message when the plan phase produced no guida

stripThinkTags removes reasoning wrapper tags from content.

triggerAsyncCompression kicks off a background compression job for the conversation owning st. A no-op when a job is already pending — the check-and-s

等待至少一个仓库就绪（git 扩展异步扫描，首次可能为空）。

whyExcluded mirrors agent.whyExcluded but for ScanItem inputs.

writeGarbageExternalDiff writes a shell script that emits non-diff output and returns its path. When git invokes it via GIT_EXTERNAL_DIFF / diff.exter

AddToolResult appends a tool call result to this task record and writes a tool_call record to the JSONL stream.

ApplyLanguage injects a language directive into all system-role messages of this conversation.

BuildToolDefs converts toolsconfig.ToolConfigEntry slice into []llm.ToolDef, filtering by phase (planOnly=true for plan_task, false for main_task).

Complete returns a checkpoint signaling task completion.

EndSpan ends the span and records error status if present.

Eventf is like Event but includes a message attribute.

Fail returns a checkpoint signaling terminal task failure.

FormatDuration returns a human-readable duration string for console output.

GroupRules groups the given file paths by their resolved rule content. Files are placed in the same group only when their source, matched pattern, and

HomeConfigPath returns the default path to ~/.opencodereview/config.json.

initEmbeddedLoader configures tiktoken to use embedded BPE data instead of fetching from network. Call this once during application startup, before an

IsKnown reports whether the tool is not UNKNOWN.

LLMFailures returns the total number of LLM request failures recorded during this session.

LoadDefault parses the embedded task.json and returns the TEST_TASK conversation.

LoadFromJSON merges telemetry settings from a JSON config file if present. This has lower priority than environment variables.

MergeBase returns the computed merge-base commit hash for range mode.

Name returns the tool's identifier name.

NewCommentWorkerPool delegates to llmloop.NewCommentWorkerPool.

NewToolResultMessage creates a tool-role message with the given result. Uses the OpenAI Chat Completions format: role="tool" with tool_call_id and pla

ParseReviewMode returns the correct ReviewMode based on provided flag values.

PhaseEvent records a review phase completion with duration and optional error.

PrintToolCallError prints a line when a tool fails. Example: [ocr] ✘ file_read "internal/config/rules/loader.go" failed: permission denied

PrintToolCallFinished prints a line when a tool finishes successfully. Example: [ocr] ✔ file_read "internal/config/rules/loader.go" (12ms)

ProjectSummary returns the markdown project-level summary produced after all batches finish. Empty when SkipSummary is set, PROJECT_SUMMARY_TASK is ab

Quiet replaces stdout with io.Discard and returns a cleanup function. Usage: defer stdout.Quiet()() WARNING: Quiet must ONLY be called from the mai

RecordReviewItemReused records that this run reused a checkpoint from another session.

RefValue returns the git ref that should be used for reading file contents in range or commit mode. Returns ("", false) for workspace mode.

RuleGroupsMarkdown renders rule groups into a markdown section.

RunSplit executes a git command and returns stdout and stderr separately.

SessionsRoot returns the root directory where session JSONL files are stored.

StartToolSpan creates a span for a tool execution with standard attributes.

Stream acquires the semaphore, starts a git command, and passes its stdout as an io.Reader to consume. The semaphore is held for the full duration. co

ToolCalls extracts tool calls from the first choice.

ToolDefsByPhase returns the parsed tool definitions filtered by phase. planOnly=true returns only tools with plan_task:true. planOnly=false returns on

Warnings returns the warnings recorded by the LLM runner.

WriteSessionStart writes the initial session_start record.

Make a GitLab API request with retry on rate-limit and transient errors. Returns a dict:: {'success': bool, 'data': response or None,

Return the first present, non-empty field among several possible key names.

Case-insensitive header lookup. urllib normalizes response header keys to title-case (e.g. 'Retry-After'), but this defensive check also hand

addNextMessage extends the conversation with the assistant message and tool responses, applying three-zone compression at the soft (60%) and warning (

applyLanguage appends instruction to all system-role messages in conv.

beginManualTokenReplace is the manual-tab equivalent of beginAPIKeyReplace.

budgetAgentTestTemplate returns a minimal template sufficient to drive dispatchSubtasks without plan/dedup/summary phases.

buildBadge renders a compact "[category · severity]" tag for a finding. It returns an empty string when neither structured field is present, so text o

buildChangeFilesExcept returns a formatted list of changed files except the given path.

buildDedupCommentsJSON renders the batch comments as a JSON list with stable c-N ids that the LLM groups by. Only fields the LLM needs to judge simila

buildFilterCommentsJSON serializes comments into a JSON array with generated IDs.

buildMessageXML serializes msgs into the <message><content> form expected by the MEMORY_COMPRESSION_TASK prompt template.

buildSummaryCommentsList renders comments as a compact path-anchored markdown list suitable for embedding in the PROJECT_SUMMARY_TASK prompt. Format:

checkMetricErr intentionally ignores metric registration errors: telemetry is best-effort and must not interrupt the main flow.