Run executes the full-scan pipeline: enumerate → filter → token-filter → dispatch one subtask per file → collect comments.

New creates a new SessionHistory with the given repo directory.

String renders a one-line human-readable estimate. Money is intentionally omitted — pricing varies per provider/model and we don't want to imply a pre

New creates a new Agent from the given arguments.

ResolveEndpoint reads from 4 strategy sources in priority order. Each strategy requires all three fields (URL, Token, Model) to be non-empty. Returns

NewCommentCollector creates an empty collector.

--- Provider-based resolution tests ---

NewRegistry creates an empty, mutable registry.

Execute runs the tool with the given arguments and returns the result string.

Add appends a comment to the collector.

NewResolver builds a Resolver with the following priority: 1. Custom rule file specified via --rule flag (first match wins) 2. Project-local .opencode

NewTextMessage creates a message with simple string content.

Writer returns the current stdout writer (real stdout or discard).

Finalize marks the session as complete, sets the end time, and persists the final summary record. When a frozen manifest was stored via SetFinalManife

New creates a Runner that allows at most maxConcurrent simultaneous git subprocesses. If maxConcurrent <= 0 the default (16) is used.

ResolveLineNumbers populates StartLine/EndLine on each comment by matching the ExistingCode against the corresponding file's diff hunks (primary), or

newBuilderWith registers a set of selected items on a fresh builder and sets a valid input mode so Finalize passes the mandatory-mode check.

mustFinalize finalizes and fails the test on an unexpected validation error.

Get returns the provider registered under name.

Run executes the full review pipeline: parse diffs -> plan per file -> LLM tool-loop -> collect comments.

MarkCompleted records that the item's subtask completed. Whether it produced comments does not affect completion.

NewAgent creates a scan Agent from the given args. The Session is auto-created (review_mode = full_scan) when not supplied.

emitRunResult is the post-LLM-run finalization shared by `ocr review` and `ocr scan`: resolves comment line numbers, records telemetry, restores stdou

GetOrCreateFileSession returns the FileSession for the given file path, creating one if it doesn't exist yet.

--- Delete custom provider tests ---

StartSpan creates a new span from the given context. When telemetry is not enabled, it returns a no-op span so callers can safely defer .End().

ExtractText returns the concatenated text content from a Message's Content field. Handles both plain string and content block array formats.

ListProviders returns all built-in providers sorted by provider name. Each returned Provider has its own copy of the Models slice in registry order.

NewRunner returns a Runner bound to the given dependencies.

One OCR comment as `ocr review --format json` emits it.

dispatchSubtasks runs the Plan + Main phases for each changed file concurrently.

parseReviewFlags provides test compatibility: parses args through a fresh cobra command instance and returns the resulting reviewOptions.

Comments returns all collected comments.

Content extracts the text content from the first choice, falling back to reasoning content.

LookupProvider returns the preset provider by name. The returned Provider has its own copy of the Models slice.

NewOpenAIResponsesClient creates a client for the OpenAI Responses API. URL normalization mirrors NewOpenAIClient: cfg.URL is forced to end in respons

One OCR comment as ``ocr review --format json`` emits it.

resolveRuleEntries scans each entry's Rule field. When the value looks like a file path, it reads the file content and replaces the Rule. Absolute pat

ReadLines returns a window of lines from the file plus the total line count. startLine is 1-based; maxLines is the maximum number of lines to collect.

Register adds a tool provider. Panics if the registry is frozen.

AppendTaskRecord adds a new task record to the file session for the given file path and task type. It auto-assigns the RequestNo based on existing rec

Since returns a copy of all comments stored at index ≥ start. Returns nil when no new comments have been added since the snapshot.

Drive post() over a sequence of fake urlopen outcomes. Each outcome is either bytes (a response body), an HTTPError (raised), or a Fa

runGitTest runs a git command in dir and fails the test on error.

IsEnabled returns true when telemetry has been initialized with exporters.

LoadSession fully parses a JSONL file into a ViewSession.

MarkFailed records that the item failed. class must be a valid, specific failure class — an empty or unknown-string class is rejected rather than down

stripANSI removes ANSI escape sequences from a string so tests can assert against plain text content.

Freeze prevents further mutations. Call once setup is complete.

Item returns a copy of the checkpoint for fingerprint.

SetError records an error for this task record, writes an llm_error entry to the JSONL stream, and increments the session-level LLM failure counter.

SetInput sets the frozen, resolved input identity (including the mandatory Mode). Finalize rejects an invalid or missing Mode.

Build an HTTPError suitable for mocking urlopen.

CompletedCount returns the number of reusable file-level checkpoints.

NewOpenAIClient creates a new OpenAI-compatible LLM client.

RunPerFile drives the main LLM conversation loop for a single file. It sends messages with the configured tool definitions, executes any tool calls re

ValidateOptions verifies that the requested review range matches the prior session.

Helper: run publish() with a Recorder and no-op sleep.