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

writeRangeResumeSession persists a range-mode session with the given completed file checkpoints and returns its ID. HOME must already point at a temp

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

ApplyEffort overwrites the effort-controlled template scalars.

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

BedrockContext reports the AWS region and profile a Bedrock client resolved, so callers can show what a request actually used. ok is false for every o

BudgetExceeded reports whether the aggregate token budget gate stopped dispatch before every file was reviewed. Diagnostic only: scan still returns it

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.

IsTransition reports whether the resume changed provider or model, which is the condition that required an explicit flag to be accepted.

ItemID is the single, canonical derivation of a manifest item_id. It is content-independent: it is derived from the operation, the input mode and the

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.

Name returns the tool's identifier name.

NewAnthropicBedrockClient creates a client for Anthropic models served by AWS Bedrock. The wire format is the Messages API, so this reuses AnthropicC

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

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

PlanRequired reports whether a group warrants the plan phase based on its churn profile. Two thresholds cooperate: PlanModeLineThreshold gates on the

Preset returns the knob set for e.

Preview loads diffs and applies the filter algorithm, returning structured preview data without dispatching any LLM calls. It builds none of the revi

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

ReasoningContent extracts the reasoning content of the first choice, if any.

RemoteIdentity returns a stable, credential-free identity string for the repository's "origin" remote, suitable for hashing into the run manifest's re

ReviewRounds returns the effective per-group round count, never below 1.

RuleGroupsMarkdown renders rule groups into a markdown section.

RunManifest returns the immutable coverage snapshot produced for this review, or nil when manifest construction failed. The scan path deliberately ret

Sealed reports whether the selected set has been sealed.

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.

Single GitLab API attempt. Returns a rich result dict (no retry).

Make a GitLab API request with retry on rate-limit and transient errors. Used for reads and note writes (discussions go through the idempotency-a

Compute a retry delay (seconds) for a failed attempt, or None if not retryable. Order: Retry-After header -> wait-until-reset (primary limit exha

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

Case-insensitive header lookup.

Collapse whitespace and cap length so log lines stay readable.

addColorFlags registers the color control. It is persistent on the root command so every subcommand inherits identical behavior, and so `ocr --color=n

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

addOutputPathFlag registers --output/-o: write results to a UTF-8 file instead of stdout. "" or "-" keeps stdout; a real path is created lazily on the

apiKeyCmdForStep returns the api_key_cmd already configured for the provider the API-key step is editing, reading the same config entry loadExistingAP

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

attemptCounts snapshots the per-file real HTTP attempt counts.

beginManualTokenReplace is the manual-tab equivalent of beginAPIKeyReplace.

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