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.

ResolveEndpoint resolves an endpoint without per-run overrides.

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

--- Provider-based resolution tests ---

NewCommentCollector creates an empty collector.

NewRegistry creates an empty, mutable registry.

Add appends a comment to the collector.

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 new Agent from the given arguments.

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

NewRetryCollector returns an empty collector.

NewRunner returns a Runner bound to the given dependencies.

NewTextMessage creates a message with simple string content.

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

Get returns the provider registered under name.

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

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

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

Freeze prevents further mutations. Call once setup is complete.

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

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

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

setTestHome redirects the user home resolved by os.UserHomeDir() to dir for the duration of the test. Setting HOME alone is NOT enough on Windows: os.

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

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

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

NewOpenAIClient creates a new OpenAI-compatible LLM client. ExtraHeaders are applied per request (not baked into the SDK client) so SessionKeyTemplate

setTestHome redirects the user home resolved by os.UserHomeDir() to dir for the duration of the test. Setting HOME alone is NOT enough on Windows: os.

Freeze builds the immutable report. It must be called once, after the run is done, and runID is the review session ID. The three return shapes are di

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.

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

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

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

Comments returns all collected comments.

Err returns the first error encountered while creating or writing the underlying file, or nil if none occurred. Text-mode rendering drops the per-writ

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

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

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

setTestHome redirects the user home resolved by os.UserHomeDir() to dir for the duration of the test. Setting HOME alone is NOT enough on Windows: os.

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

RunMainTask drives one MAIN_TASK conversation loop to its end. It sends messages with the configured tool definitions, executes any tool calls returne

--- Delete custom provider tests ---

metaCtx attaches identity the way the review path will in P4.

CompletionsWithCtx sends a chat completion request with context support for cancellation and timeout. The deferred finalizeRequest is the client boun

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

RecordReviewItemDone persists the file-level checkpoint used by resume.

newRawMiddleware builds the SDK middleware that captures raw request/response bodies into the writer held by holder. It sits inside the SDK retry loop

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().

resolveRuleEntries reads file references in each rule entry and replaces them with the file content. confineRoot is the canonical repo root for the un

Item returns a copy of the checkpoint for fingerprint.

NewAnthropicClient creates a new Anthropic Messages API client. The Anthropic API manages prompt-cache affinity server-side, so unlike the OpenAI clie

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

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.

Drive a poster method over a sequence of fake urlopen outcomes.