Muhammad Zakir Ramadhan
2fa6ee247b
Tools, six built-in to fourteen: - read_many_files: up to 20 paths read concurrently, each with its own window. An unreadable path is reported in its own block instead of throwing. - multi_edit: several edits to one file, validated in memory first so a late failure cannot leave the file half-written. - list_dir: ignore-aware depth-limited tree. - git_status/diff/log/show/blame: read-only, spawned with a fixed argv rather than a shell string, which is what makes them safe to auto-approve. toolSets gates them. core is always on; edit-plus and git are optional. A disabled set reaches neither the wire nor the system prompt, since a prompt naming an absent tool teaches calls that cannot succeed. Interface: - Reasoning streams to a collapsed panel, ctrl-r expands, dropped when the turn ends: it is progress, not the answer. - The tool in flight is named from tool-input-start, before its arguments finish streaming, and cleared on its result. - Prompts typed mid-turn queue and drain in order. esc clears the queue as well as aborting. - @ opens a path picker fed by the ignore-aware walker. Prefix matches rank above substring matches, so @src/ means "under src/". The walk runs on the first @, not at startup. ctrl-c kills the command in flight and keeps the turn. The call throws rather than returning, so the model cannot read a killed command as one that ran and failed on its own terms. The kill takes the whole process tree: killing cmd /c alone left the real command holding both pipes open, so the read never returned and the interrupt did nothing for 19 seconds. Two pruning fixes: - A tool result whose tool call was pruned is now dropped with it. Pruning counts messages, so the cut landed between an assistant tool-call and the tool message answering it, producing 400 "No tool call found for function call output with call_id ...". The reverse pairing is left alone: a call awaiting its result is what a suspended approval looks like. - ignore.ts called statFs without importing it, so walk() crashed on the first symlink. 482 tests, up from 404. Docs synced across README, ROADMAP, TODO, and all of docs/: tool sets, the new tools, ctrl-c semantics, the tool-start event, and the two hand-maintained tool-name lists recorded as a known weakness.
30 lines
1.1 KiB
TypeScript
30 lines
1.1 KiB
TypeScript
import type { AppHooks } from '../src/ui/App';
|
|
|
|
/** Default AppHooks for UI tests; override only what a test cares about. */
|
|
export function testHooks(over: Partial<AppHooks> = {}): AppHooks {
|
|
return {
|
|
sessionId: 'test1234',
|
|
config: () => ({ provider: 'openai', model: 'gpt-5' }),
|
|
switchModel: (id) => `model is now ${id}`,
|
|
switchAgent: (name) => `agent is now ${name}`,
|
|
switchThinking: (level) => `thinking is now ${level}`,
|
|
agentName: () => 'default',
|
|
thinkingLevel: () => 'medium',
|
|
applyProvider: async () => 'configured',
|
|
listModels: async () => ({ models: [] }),
|
|
listSessions: async () => 'no saved sessions',
|
|
listSkills: () => 'no skills loaded',
|
|
listPlugins: () => 'no plugins active',
|
|
listMemory: async () => 'nothing remembered yet',
|
|
summarizeMemory: async () => 'nothing to compact',
|
|
resumeSession: async () => 'resumed',
|
|
saveSession: async () => 'saved',
|
|
instructionFiles: () => [],
|
|
listPaths: async () => [],
|
|
initPrompt: 'write AGENTS.md',
|
|
history: [],
|
|
recordPrompt: () => {},
|
|
...over,
|
|
};
|
|
}
|