emitFailureUsage writes a best-effort structured usage record to stderr when a review fails, so the outer caller still sees the cost of the failed att

ensureMessagesSuffix appends /v1/messages to base URLs that lack a versioned path.

estimateDiffFileTokens projects the input+output token cost of reviewing a single diff (PLAN + MAIN_TASK rounds). It mirrors scan.estimateFileTokens b

executeSubtask runs the scan pipeline for one file: 1. Optional PLAN_TASK: produce a JSON checklist of focus areas. 2. MAIN_TASK: review the file with

filterLargeDiffs drops diffs whose diff content alone consumes more than 80% of MaxTokens.

filterLargeScans drops items whose content exceeds 80% of MaxTokens.

finalizeManifest freezes the run's coverage builder and stores the immutable manifest on the session for persistence and CLI consumption. Nil-safe. A

firstLine returns the first non-empty trimmed line of git output, so a stray trailing newline or an unexpected second line never pollutes a resolved S

formatPlanGuidance parses the PLAN_TASK JSON output into a markdown snippet suitable for embedding in MAIN_TASK. On parse failure it returns the raw c

humanTokens formats a token count as e.g. "1.2M" / "850K" / "420".

humanTokens formats a token count as e.g. "1.2M" / "850K" / "420". Mirrors internal/scan/estimate.go; kept here so agent has no scan import.

isUserEditMsg reports whether msg represents user text input (typing or paste).

loadTestTemplate returns a validated default template for runtime tests.

maybeRunDedup, when the template has a DedupTask and the batch produced at least DedupMinComments comments, invokes the DEDUP_TASK LLM to merge near-d

maybeRunProjectSummary runs the post-batch PROJECT_SUMMARY_TASK over the union of all collected comments. Best-effort: any error / empty input no-temp

normalizeLine removes leading/trailing whitespace and strips any leading '+' or '-' diff marker.

partitionMessages divides messages into frozen, compress, and active zones. Frozen zone is always messages[0:2]. Active zone preserves the K most rece

reloadConfigAfterSaveFailure reloads on-disk config and refreshes derived provider TUI state so the UI matches persisted data after a failed save. Ret

reloadConfigAfterSaveFailure reloads on-disk config so in-memory state matches persisted data after a failed save. Returns false when reload could not

resolveRepoDir resolves the repo dir for `ocr rules check`. It delegates to resolveWorkingDir(requireGit=true) so it anchors at the git top-level just

resolveWorkingDirForSession accepts an explicit --repo flag value and falls back to the current working directory. Unlike resolveRepoDir it does not r

resolvedModel returns the model to persist, falling back to the in-session pick for the provider being finalized when result.model is empty.

transition moves a selected item to a terminal state through the single coverage entry point. Unknown item_id, an invalid failed classification, an em

valid reports whether c is one of the fixed item failure classes.

validateTimeoutSec converts a config-file timeout (in seconds) to time.Duration. Returns 0 for zero input (use default). Rejects negative values and o

writeCommit writes content to name, stages it, and commits with msg.

CallTool invokes a tool on the MCP server and returns the text result.

CollectPendingComments awaits any async comment-processing workers and returns the aggregated comments from the collector. Safe to call once per sessi

CompletionsWithCtx sends a Responses API request and maps the result back to the shared ChatResponse shape.

ComputeLineDiff returns a line-level diff between oldLines and newLines. Uses Myers-style LCS to find common subsequences, then emits context/added/de

ContentLogging returns true when content logging is enabled via OCR_CONTENT_LOGGING.

DisplayAddr rewrites a wildcard listen address (empty host, 0.0.0.0, or ::) to a localhost form so printed URLs are always openable in a browser. Non-

FinalManifest returns the frozen manifest stored for this run, or nil when the run produced none (legacy/scan, or a construction failure).

Get returns the diff text for path.

ListSessions returns lightweight summaries for all sessions in a repo subdir.

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

NewClient starts an MCP server subprocess (stdio transport), initializes the connection, and caches the list of available tools. The context governs t

NewToolCallMessage creates an assistant message with text content and tool invocations.

Of returns a checkpoint with data.

PrintToolCallStarted prints a line when a tool begins execution. Args are summarized as key-value pairs (path, search terms, etc.). Example: [ocr] ▶

RemoveByPathAndIndices removes comments for a given path whose per-path index (0-based position among all comments with that path) is in the indices s

Resolve returns the rule text for a given file path. Patterns with brace expansion like "*.{go,py}" are expanded into "*.go", "*.py". The first match

ResolveConfig builds the final Config by merging defaults, JSON config, and env vars. Precedence: defaults < config.json < environment variables.

SessionID returns the current scan's persisted session ID. It returns an empty string when no session file exists.

SessionID returns the persisted session identifier so callers can show it in JSON output or failure diagnostics. Returns "" when no session was create

SessionsDir returns the on-disk directory that holds JSONL session files for a given repository. It does not create the directory.

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

SetDiffMap replaces the diff snapshot. Must be called before concurrent access begins.

ShutdownWithTimeout creates a timeout context and calls Shutdown.

Snapshot returns the current count of stored comments. Pair with Since / ReplaceSince to operate on the comments added between two points in time (e.g

SubmitFor is Submit plus registration under key, so AwaitKey can wait for exactly the units submitted under that key instead of the whole pool. Calle

TotalOutputTokens returns the accumulated completion tokens from all LLM calls.

TotalTokensUsed / TotalInputTokens / ... delegate to the underlying runner.