mirror of
https://github.com/expo/explore.git
synced 2026-11-15 17:32:23 -10:00
Compare commits
8
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cf5e25e1df | ||
|
|
909ba65174 | ||
|
|
614a11d7ed | ||
|
|
65f20fad4c | ||
|
|
ed31b0c767 | ||
|
|
b1edd7ea81 | ||
|
|
50230b7f93 | ||
|
|
33f31da08e |
No files matched your search
@@ -67,9 +67,12 @@ jobs:
|
||||
shell: bash
|
||||
env:
|
||||
COMMENT_ID: ${{ steps.comment.outputs.id }}
|
||||
# How long an alias can keep serving the previous push: an EAS Hosting edge that served it keeps it for about
|
||||
# five minutes (FIXTURE_ALIAS_WAIT_MS in src/report/preview-deploy.ts).
|
||||
ALIAS_CATCH_UP: 5 minutes
|
||||
run: |
|
||||
set -euo pipefail
|
||||
jq -r --arg marker "$MARKER" --arg sha "${SHA:0:7}" --arg run "$RUN_URL" '
|
||||
jq -r --arg marker "$MARKER" --arg sha "${SHA:0:7}" --arg run "$RUN_URL" --arg catchup "$ALIAS_CATCH_UP" '
|
||||
.previewUrl as $url
|
||||
| ([.reports[] | select(.platform == "android")] + [.reports[] | select(.platform != "android")]) as $reports
|
||||
| ($reports[0].source // "") as $source
|
||||
@@ -85,6 +88,8 @@ jobs:
|
||||
| ((.label // (if .platform == "ios" then "iOS" else "Android" end)) | gsub("\\|"; "\\\\|")) as $name
|
||||
| "| \($name)\(if .device then " · \(.device)" else "" end) | \(.changes // "–") | [Map](\($url)?\($query)) · [Screens](\($url)?\($query)#/screens) · [Compare](\($url)?\($query)&view=compare) |"),
|
||||
"",
|
||||
# The alias still served the previous push when the deploy stopped waiting for it: say so, and link the new deployment.
|
||||
(if .aliasBehind then "> **Going live:** this link can take up to \($catchup) to show \($sha); until then it shows the previous push, or nothing on a new pull request. [This push'"'"'s deployment](\(.deploymentUrl)/p/\($url | split("/p/")[1])) is live now.\n" else empty end),
|
||||
"The link stays the same on every push. [Deploy run](\($run))"]
|
||||
| join("\n")' "$RUNNER_TEMP/preview.json" > "$RUNNER_TEMP/comment.md"
|
||||
if [[ -n "$COMMENT_ID" ]]; then
|
||||
|
||||
+4
-4
@@ -49,16 +49,16 @@ Each workflow starts with a `targets` job: it installs the pinned CLI and runs `
|
||||
| | checkout `app-base`, `app-head` | Checks out the exact base and head SHAs with full history and without persisted credentials. |
|
||||
| | Verify deterministic source planning | `source:verify` builds the capture plan from source alone in two fresh processes and compares the bytes. Runs before any build or simulator work and needs no credentials. |
|
||||
| | Install app dependencies | `npm ci --ignore-scripts` in both checkouts (`APP_INSTALL_DIR` for monorepos). |
|
||||
| | Find / Download optional exact-base evidence | `ci:find-baseline` looks for a successful `explore-baseline-<base sha>-<target>` artifact (target `ios` also accepts the older unsuffixed `explore-baseline-<base sha>`) from the baseline workflow on the default branch and downloads it as `EXPLORE_CAPTURE_CACHE`. Missing evidence is not an error. |
|
||||
| | Find / Download optional exact-base evidence | `ci:find-baseline` looks for a finished run's `explore-baseline-<base sha>-<target>` artifact (a run another target's baseline failed in counts: a baseline job uploads its artifact only after its own steps passed) (target `ios` also accepts the older unsuffixed `explore-baseline-<base sha>`) from the baseline workflow on the default branch and downloads it as `EXPLORE_CAPTURE_CACHE`. Missing evidence is not an error. |
|
||||
| | Capture review | `capture:review` (§3). `EXPO_TOKEN`, the provider key and the app's `{{secret:NAME}}` values reach only this step. The sticky PR comment is updated while it runs. It writes `preview=<hosting>` to the step outputs, which decides whether the deploy job runs. |
|
||||
| | Stop capture sessions and check the checkouts | `ci:after-capture`, whenever the PR was resolved, success or not: stops the EAS Simulator sessions named in `head-session` / `base-session`, nothing else, then fails with `CHECKOUT_MODIFIED` if capture modified an app checkout. |
|
||||
| | Upload captured review / diagnostics | `explore-capture-<run>-<attempt>-<target>` feeds the report job. On failure `explore-diagnostics-<run>-<attempt>-<target>` keeps plans, exports and agent diagnostics for 7 days. |
|
||||
| report (matrix: target) | Install Explore, download the capture | Runs without Expo or model credentials. |
|
||||
| report (matrix: target) | Download the capture, install Explore | Runs without Expo or model credentials, after every capture job, whether or not each succeeded (`!cancelled()`). Each leg downloads its own target's capture by an exact-name pattern: a target whose capture failed uploaded none, so its leg packages and publishes nothing, and the other targets' reports still reach the comment. |
|
||||
| | Package hosted review bundle | `ci:report` writes the report directory. |
|
||||
| | Upload hosted review bundle | `explore-review-<run>-<attempt>-<target>`, kept 30 days. |
|
||||
| | Publish current PR hosted links | `ci:publish` re-checks that the artifact belongs to this PR, then updates the sticky comment with **Open** (the hosted Viewer) and **zip**. The comment is rendered from one hidden record per target (`<!-- expo-explore-record:<target>:… -->`, plus one history line for earlier runs); each job folds its own record into the ones the comment already carries and re-renders the whole comment, so parallel targets do not overwrite each other. Rows, report links and validation columns are labelled with the target's label (`iOS` and `Android` without `targets:`) and follow config order. |
|
||||
| `deploy` (only when `report.preview` is set; after every report job) | Deploy the hosted preview | `ci:deploy --inputs --reports` downloads every target's capture and report artifacts, writes each report's manifest and screenshots as static files under the link's token, deploys them with the prebuilt preview Viewer to a dedicated EAS Hosting project (the only post-capture job holding `EXPO_TOKEN`), verifies that only `/p/<token>` answers, then updates the comment with **Explore report**. The link works as long as the EAS Hosting deployment. |
|
||||
| failure | Report failure only on the current PR | Downloads whichever diagnostics exist and posts the failure comment to this PR alone, replacing only the failed target's record when the run has several; the target is the id the failed job's diagnostics artifact name ends with, and its label comes from the record the capture job already posted. |
|
||||
| `deploy` (only when `report.preview` is set; after every report job, once any of them published) | Deploy the hosted preview | `ci:deploy --inputs --reports` downloads every capture and report artifact the run has (a target whose capture or report job failed has none and is left out), writes each report's manifest and screenshots as static files under the link's token, deploys them with the prebuilt preview Viewer to a dedicated EAS Hosting project (the only post-capture job holding `EXPO_TOKEN`), verifies that only `/p/<token>` answers, then updates the comment with **Explore report**. The link works as long as the EAS Hosting deployment. |
|
||||
| failure | Report failure only on the current PR | Downloads whichever diagnostics exist and posts the failure comment to this PR alone, replacing only each failed target's record when the run has several; the target is the id the failed job's diagnostics artifact name ends with (or, when download-artifact extracted a lone artifact without its directory, the `target` its `error.json` records), and its label comes from the record the capture job already posted. Once the other targets published, the comment shows their reports and this failure, with no new-run line. |
|
||||
|
||||
A reviewer downloads the report ZIP and drops it on the hosted Viewer; downloading needs read access to the repository.
|
||||
|
||||
|
||||
@@ -198,6 +198,41 @@ npx @expo/explore explore:session <session-id> --env-file path/.env.eas-simulato
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><strong>Take the same steps on every run and device</strong></summary>
|
||||
|
||||
A model picks its own path, so two runs (or an iPhone and an Android phone) can reach different screens. To get the same screens every time, write the steps down once, for example after a model run showed you the app, and pass them with `--replay`. No model login or API key is needed.
|
||||
|
||||
```sh
|
||||
npx @expo/explore explore:binary ./my-app.app --replay steps.json
|
||||
npx @expo/explore explore:session --replay steps.json # an iPhone Duo pose, or any session you set up by hand
|
||||
```
|
||||
|
||||
```json
|
||||
{
|
||||
"steps": [
|
||||
{ "capture": "Home" },
|
||||
{ "action": "tap", "label": "Settings" },
|
||||
{ "capture": "Settings" },
|
||||
{ "action": "tap", "label": "Dark" },
|
||||
{ "capture": "Settings", "state": "dark" },
|
||||
{ "action": "tap", "label": "Learn", "platforms": ["ios"] },
|
||||
{ "capture": "Learn", "platforms": ["ios"] },
|
||||
{ "action": "tap", "label": "Got it", "optional": true }
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
- An action is one of `tap` or `fill` (with `label` or `identifier`), `type`, `scroll` (`direction`), `wait` (`milliseconds`), `open` (`url`), `back`, and `dismiss-keyboard`, as in the model's own tools. The same safety rules apply: destructive or app-leaving taps are refused. A step takes only the fields listed here; any other field (a typo such as `platform`) is an error.
|
||||
- `{ "capture": "Title" }` photographs the current screen under that title; add `"state"` for another state of a screen already captured. A capture of a screen the plan already captured under another title is reported as looking the same, and the screen keeps its first title.
|
||||
- `"platforms": ["ios"]` limits a step to those platforms, for screens one platform does not have. `"optional": true` skips an action that fails (a one-time dialog) instead of stopping; the summary lists the steps it skipped.
|
||||
- A `fill` or `type` text can be a `{{secret:NAME}}`, as in `--hints`: Explore types the value of the environment variable `NAME`, and a variable that is not set fails before a device starts.
|
||||
- If a required action fails, the run stops there and the report still shows what was captured, with a gap naming the step and the screens it did not reach.
|
||||
- The screen and action budgets still apply. A plan with more captures or actions than they allow is refused before a device starts, as is one with no steps for the platform; raise `--max-screens` and `--max-actions` for a long plan. If a budget still runs out (each screen the plan reaches also counts), the gap names the planned screens not reached.
|
||||
- `--provider`, `--model` and `--hints` only steer a model, so they cannot be combined with `--replay`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><strong>What a run without source shows</strong></summary>
|
||||
|
||||
|
||||
Generated
+2
-2
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "@expo/explore",
|
||||
"version": "0.20.1",
|
||||
"version": "0.20.2",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "@expo/explore",
|
||||
"version": "0.20.1",
|
||||
"version": "0.20.2",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@expo/repack-app": "0.10.1",
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@expo/explore",
|
||||
"version": "0.20.1",
|
||||
"version": "0.20.2",
|
||||
"description": "Source-driven mobile app maps, deterministic CI capture, and visual reviews",
|
||||
"license": "MIT",
|
||||
"type": "module",
|
||||
|
||||
@@ -33,6 +33,10 @@ Platform, bundle id, app name and version are read from the archive; do not pass
|
||||
|
||||
Budgets default to 15 minutes, 40 screens, 150 actions (`--max-duration-minutes`, `--max-screens`, `--max-actions`). Steer the model with `--hints "focus on the onboarding and settings"`, skip onboarding with `--launch-url myapp://home`, and allow a specific risky control with `--allow-destructive "Clear cache"`.
|
||||
|
||||
## The same steps on every run: `--replay`
|
||||
|
||||
To compare runs, or an iPhone with an Android phone, screen for screen, pass `--replay steps.json` to `explore:binary` or `explore:session`: Explore takes the steps in the file instead of a model's, and no model access is needed. The format is in the README ("Take the same steps on every run and device"): `{ "steps": [{ "capture": "Home" }, { "action": "tap", "label": "Settings" }, { "capture": "Settings" }] }`, with `platforms` to limit a step and `optional` for an action that may fail. The plan is checked before a device starts: unknown fields, a plan with no steps for the platform, more captures or actions than `--max-screens` / `--max-actions`, and a `{{secret:NAME}}` in a `fill` or `type` whose variable is not set are all refused (`REPLAY_PLAN_INVALID`, `REPLAY_PLAN_EMPTY`, `REPLAY_PLAN_OVER_BUDGET`, `EXPLORATION_SECRET_MISSING`). `--provider`, `--model` and `--hints` cannot be combined with it (`REPLAY_OPTIONS_IGNORED`).
|
||||
|
||||
## Sign-in and other app state
|
||||
|
||||
Without help, the model treats a sign-in wall as the end of the road: it captures it and stops (`blocked`). Before running, read what you can about the app (its source if you have it, its first screens otherwise) and decide what it needs.
|
||||
|
||||
+29
-20
@@ -27,7 +27,7 @@ export type BlackBoxAction = CaptureSetupAction | { action: "back" } | { action:
|
||||
| { action: "tap"; frameId: string; x: number; y: number };
|
||||
|
||||
export type BlackBoxExplorerOptions = {
|
||||
session: CiAgentSession;
|
||||
session: Pick<CiAgentSession, "run">;
|
||||
store: ExploreStore;
|
||||
map: ExploreMap;
|
||||
app: { name: string; bundleId: string; platform: "ios" | "android"; version?: string };
|
||||
@@ -49,6 +49,8 @@ export type BlackBoxExplorerOptions = {
|
||||
appIcon?: Buffer;
|
||||
/** App-test inputs the operator hints reference as {{secret:NAME}}: the model and the map only ever hold the reference. */
|
||||
inputs?: ReturnType<typeof createExplorationInputs>;
|
||||
/** A sentence a budget stop's gap adds to its own, read once the session has stopped: a replay names the planned screens it did not reach. */
|
||||
budgetNote?: () => string | undefined;
|
||||
};
|
||||
|
||||
export type BlackBoxExplorerResult = {
|
||||
@@ -67,6 +69,12 @@ const EXTERNAL = /\b(open in|safari|chrome|browser|app store|play store|share|ma
|
||||
const VOLATILE = /\d|[:%$€£]|\b(am|pm)\b/gi;
|
||||
const INTERACTIVE = new Set(["button", "link", "cell", "switch", "tab", "menuitem", "textfield", "securetextfield", "searchfield", "textview", "edittext", "slider", "checkbox", "radiobutton", "segmentedcontrol", "toggle"]);
|
||||
|
||||
/** What the tools accept: their schemas, the checks on each call, and a replay plan checked before any device starts share these. */
|
||||
export const TOOL_LIMITS = { selector: 512, text: 2000, url: 2000, waitMs: 15_000, title: 80, state: 80, description: 500, summary: 4000, reason: 1000 } as const;
|
||||
|
||||
/** A screen seen after an action but never named keeps this title until the run ends and names it after the path to it. */
|
||||
export const isPlaceholderTitle = (title: string): boolean => /^Screen \d+$/.test(title);
|
||||
|
||||
const selectorProperties = {
|
||||
label: { type: "string", description: "Exact visible label of the target node, copied from the latest observation." },
|
||||
identifier: { type: "string", description: "Exact accessibility identifier of the target node, when it has one." },
|
||||
@@ -81,22 +89,22 @@ const tools: CiAgentTool[] = [
|
||||
inputSchema: { type: "object", properties: {
|
||||
action: { type: "string", enum: ["tap", "fill", "type", "scroll", "wait", "back", "dismiss-keyboard", "open"] },
|
||||
...selectorProperties,
|
||||
text: { type: "string", maxLength: 2000 }, url: { type: "string", maxLength: 2000 },
|
||||
text: { type: "string", maxLength: TOOL_LIMITS.text }, url: { type: "string", maxLength: TOOL_LIMITS.url },
|
||||
direction: { type: "string", enum: ["up", "down", "left", "right", "top", "bottom"] },
|
||||
milliseconds: { type: "integer", minimum: 1, maximum: 15_000 },
|
||||
milliseconds: { type: "integer", minimum: 1, maximum: TOOL_LIMITS.waitMs },
|
||||
frameId: { type: "string", description: "For a coordinate tap only: the latest observed frame." },
|
||||
x: { type: "number", minimum: 0, exclusiveMaximum: 1 }, y: { type: "number", minimum: 0, exclusiveMaximum: 1 },
|
||||
target: { type: "string", minLength: 1, maxLength: 80, description: "For a coordinate tap: what is being tapped, as a user would name it (\"search icon in the header\", \"first manga cover\")." },
|
||||
}, required: ["action"], additionalProperties: false } },
|
||||
{ name: "capture", description: "Name the latest observed frame (observe with includeImage) as a screen of the map, with a short human title. A screen is photographed the moment it first appears; capture gives it its title, and with state records another notable state of it.",
|
||||
inputSchema: { type: "object", properties: {
|
||||
frameId: { type: "string" }, title: { type: "string", minLength: 1, maxLength: 80 },
|
||||
description: { type: "string", maxLength: 500 }, state: { type: "string", maxLength: 80, description: "A variant of an already captured screen, such as 'empty' or 'menu open'." },
|
||||
frameId: { type: "string" }, title: { type: "string", minLength: 1, maxLength: TOOL_LIMITS.title },
|
||||
description: { type: "string", maxLength: TOOL_LIMITS.description }, state: { type: "string", maxLength: TOOL_LIMITS.state, description: "A variant of an already captured screen, such as 'empty' or 'menu open'." },
|
||||
}, required: ["frameId", "title"], additionalProperties: false } },
|
||||
{ name: "finish", description: "End the exploration when every reachable screen has been captured or the budget is nearly used. Include a summary of what the app does and what was not reached.",
|
||||
inputSchema: { type: "object", properties: { summary: { type: "string", minLength: 1, maxLength: 4000 } }, required: ["summary"], additionalProperties: false } },
|
||||
inputSchema: { type: "object", properties: { summary: { type: "string", minLength: 1, maxLength: TOOL_LIMITS.summary } }, required: ["summary"], additionalProperties: false } },
|
||||
{ name: "stop_blocked", description: "Stop because the app cannot be explored further (login wall without credentials, crash loop, permission prompt that cannot be dismissed). Keeps the evidence so far.",
|
||||
inputSchema: { type: "object", properties: { reason: { type: "string", minLength: 1, maxLength: 1000 } }, required: ["reason"], additionalProperties: false } },
|
||||
inputSchema: { type: "object", properties: { reason: { type: "string", minLength: 1, maxLength: TOOL_LIMITS.reason } }, required: ["reason"], additionalProperties: false } },
|
||||
];
|
||||
|
||||
const INSTRUCTIONS = `You are exploring a prebuilt mobile app on a remote simulator through accessibility and screenshots. Nobody gave you its source. Your job is to produce a map of its screens: visit every reachable screen, capture each one once with a clear title, and try each distinct kind of control so transitions are recorded.
|
||||
@@ -412,7 +420,7 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
}
|
||||
|
||||
/** Seen after an action but never named by the model (its screenshot was taken on arrival). */
|
||||
const isPlaceholder = (screen: Screen): boolean => /^Screen \d+$/.test(screen.title);
|
||||
const isPlaceholder = (screen: Screen): boolean => isPlaceholderTitle(screen.title);
|
||||
/** Fold an uncaptured placeholder into the screen the model says it is. */
|
||||
const mergeScreens = (from: Screen, into: Screen): void => {
|
||||
for (const item of map.actionAttempts) {
|
||||
@@ -491,7 +499,7 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
screen = { id: `scr_${key.slice(0, 16)}`, title: title ?? systemDialogTitle(frame.nodes) ?? `Screen ${map.screens.length + 1}`, start: map.screens.length === 0, terminal: false,
|
||||
depth, firstSeenAt: frame.capturedAt, lastSeenAt: frame.capturedAt, visits: 0, variantIds: [], observationIds: [], elementIds: [] };
|
||||
map.screens.push(screen); screensByKey.set(key, screen);
|
||||
} else if (title && /^Screen \d+$/.test(screen.title)) screen.title = title;
|
||||
} else if (title && isPlaceholderTitle(screen.title)) screen.title = title;
|
||||
screen.visits += 1; screen.lastSeenAt = frame.capturedAt;
|
||||
const seen = evidence.get(screen.id) ?? { parts: new Set<string>(), loadingOnly: true };
|
||||
for (const part of loose) seen.parts.add(part);
|
||||
@@ -625,7 +633,7 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
|
||||
const actionFor = (input: Record<string, unknown>): { action: BlackBoxAction; kind: ActionKind; label: string; risk: ActionRisk } => {
|
||||
const action = String(input.action);
|
||||
const selector = input.identifier !== undefined ? { identifier: text(input.identifier, "identifier", 512) } : input.label !== undefined ? { label: text(input.label, "label", 512) } : undefined;
|
||||
const selector = input.identifier !== undefined ? { identifier: text(input.identifier, "identifier", TOOL_LIMITS.selector) } : input.label !== undefined ? { label: text(input.label, "label", TOOL_LIMITS.selector) } : undefined;
|
||||
const label = selector ? ("identifier" in selector ? selector.identifier : selector.label) : action;
|
||||
const risk = selector ? riskOf(label, allow) : "safe";
|
||||
switch (action) {
|
||||
@@ -637,13 +645,13 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
}
|
||||
if (!selector) throw failure("AGENT_ACTION_INVALID", "tap needs a label, an identifier, or frame coordinates.");
|
||||
return { action: { action: "tap", ...selector } as BlackBoxAction, kind: "press", label, risk };
|
||||
case "fill": if (!selector) throw failure("AGENT_ACTION_INVALID", "fill needs a label or identifier."); return { action: { action: "fill", text: text(input.text, "text", 2000), ...selector } as BlackBoxAction, kind: "fill", label, risk };
|
||||
case "type": return { action: { action: "type", text: text(input.text, "text", 2000) }, kind: "fill", label: "type", risk: "safe" };
|
||||
case "fill": if (!selector) throw failure("AGENT_ACTION_INVALID", "fill needs a label or identifier."); return { action: { action: "fill", text: text(input.text, "text", TOOL_LIMITS.text), ...selector } as BlackBoxAction, kind: "fill", label, risk };
|
||||
case "type": return { action: { action: "type", text: text(input.text, "text", TOOL_LIMITS.text) }, kind: "fill", label: "type", risk: "safe" };
|
||||
case "scroll": return { action: { action: "scroll", direction: input.direction as "up" }, kind: "swipe", label: `scroll ${String(input.direction)}`, risk: "safe" };
|
||||
case "wait": return { action: { action: "wait", milliseconds: Number(input.milliseconds) || 1000 }, kind: "other", label: "wait", risk: "safe" };
|
||||
case "back": return { action: { action: "back" }, kind: "back", label: "back", risk: "safe" };
|
||||
case "dismiss-keyboard": return { action: { action: "dismiss-keyboard" }, kind: "dismiss", label: "dismiss keyboard", risk: "safe" };
|
||||
case "open": return { action: { action: "open", url: text(input.url, "url", 2000) }, kind: "deep-link", label: text(input.url, "url", 2000), risk: "unknown" };
|
||||
case "open": return { action: { action: "open", url: text(input.url, "url", TOOL_LIMITS.url) }, kind: "deep-link", label: text(input.url, "url", TOOL_LIMITS.url), risk: "unknown" };
|
||||
default: throw failure("AGENT_ACTION_INVALID", `Unknown action ${action}.`);
|
||||
}
|
||||
};
|
||||
@@ -749,10 +757,10 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
const frameId = text(input.frameId, "frameId", 256);
|
||||
if (!latest?.png && latest?.imageUnavailable?.code === "CAPTURE_SENSITIVE_INPUT") throw failure("CAPTURE_SENSITIVE_INPUT", latest.imageUnavailable.message, true);
|
||||
if (!latest?.png || latest.frameId !== frameId) throw failure("AGENT_FRAME_STALE", "Observe with an image first; capture must name the latest frame.", true);
|
||||
const title = text(input.title, "title", 80).trim();
|
||||
const title = text(input.title, "title", TOOL_LIMITS.title).trim();
|
||||
if (captures >= options.maxScreens) { stop("budget-screens"); abort.abort(failure("EXPLORATION_BUDGET_EXHAUSTED", "Screen budget exhausted.")); throw abort.signal.reason; }
|
||||
const { screen } = locate(latest, title);
|
||||
const state = str(input.state, 80);
|
||||
const state = str(input.state, TOOL_LIMITS.state);
|
||||
if (!state && map.observations.some(item => item.screenId === screen.id && item.screenshotArtifactId)) {
|
||||
if (title) screen.title = title;
|
||||
return toolResult({ ok: true, duplicate: true, screenId: screen.id, title: screen.title, message: "This screen is already captured (its title is updated); pass state to record a variant." });
|
||||
@@ -832,9 +840,9 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
await persist();
|
||||
return toolResult({ ok: !error, outcome, ...(error ? { error } : {}), ...view, ...progress().budget });
|
||||
}
|
||||
if (name === "finish") { stop("finished", text(input.summary, "summary", 4000)); abort.abort(new Error("finished")); return toolResult({ ok: true }); }
|
||||
if (name === "finish") { stop("finished", text(input.summary, "summary", TOOL_LIMITS.summary)); abort.abort(new Error("finished")); return toolResult({ ok: true }); }
|
||||
if (name === "stop_blocked") {
|
||||
const reason = text(input.reason, "reason", 1000);
|
||||
const reason = text(input.reason, "reason", TOOL_LIMITS.reason);
|
||||
map.gaps.push({ id: `gap_${randomUUID().slice(0, 8)}`, kind: "coverage", status: "open", message: reason, ...(currentScreenId ? { screenId: currentScreenId } : {}), createdAt: timestamp() });
|
||||
await persist();
|
||||
stop("blocked", reason); abort.abort(new Error("blocked")); return toolResult({ ok: true });
|
||||
@@ -856,8 +864,9 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
if (!result) stop(budget ? "budget-time" : "model-error", undefined, budget ? undefined : fatal ?? error);
|
||||
}
|
||||
if (result!.stopReason !== "finished" && result!.stopReason !== "blocked") {
|
||||
const note = result!.stopReason === "model-error" ? undefined : options.budgetNote?.();
|
||||
map.gaps.push({ id: `gap_${randomUUID().slice(0, 8)}`, kind: result!.stopReason === "model-error" ? "other" : "coverage", status: "open",
|
||||
message: result!.stopReason === "model-error" ? `The exploration stopped on an error: ${result!.error instanceof Error ? result!.error.message.slice(0, 300) : "unknown"}` : `The exploration stopped at its ${result!.stopReason.replace("budget-", "")} budget with ${map.frontier.filter(item => item.status === "pending").length} controls unexplored.`,
|
||||
message: result!.stopReason === "model-error" ? `The exploration stopped on an error: ${result!.error instanceof Error ? result!.error.message.slice(0, 300) : "unknown"}` : `The exploration stopped at its ${result!.stopReason.replace("budget-", "")} budget with ${map.frontier.filter(item => item.status === "pending").length} controls unexplored.${note ? ` ${note}` : ""}`,
|
||||
createdAt: timestamp() });
|
||||
}
|
||||
for (const item of map.frontier) if (item.status === "claimed") item.status = "pending";
|
||||
@@ -870,10 +879,10 @@ export async function runBlackBoxExploration(options: BlackBoxExplorerOptions):
|
||||
function nameUncapturedScreens(map: ExploreMap): void {
|
||||
const titles = new Map(map.screens.map(screen => [screen.id, screen.title]));
|
||||
for (const screen of map.screens) {
|
||||
if (!/^Screen \d+$/.test(screen.title)) continue;
|
||||
if (!isPlaceholderTitle(screen.title)) continue;
|
||||
const arrival = map.actionAttempts.find(attempt => attempt.targetScreenId === screen.id && attempt.outcome === "transition" && attempt.sourceScreenId !== screen.id);
|
||||
const from = arrival ? titles.get(arrival.sourceScreenId) : undefined;
|
||||
if (!arrival || !from || /^Screen \d+$/.test(from)) continue;
|
||||
if (!arrival || !from || isPlaceholderTitle(from)) continue;
|
||||
const step = arrival.action.input ? "typing" : arrival.action.label;
|
||||
screen.title = `${from} → ${step}`.slice(0, 80);
|
||||
titles.set(screen.id, screen.title);
|
||||
|
||||
@@ -0,0 +1,300 @@
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { CiError } from "../shared/ci-errors.js";
|
||||
import type { CiAgentSessionRunRequest, CiAgentSessionRunResult } from "../capture/agent/session.js";
|
||||
import { SETUP_SELECTOR_MAX, isSetupInput, isSetupSelector } from "../capture/setup-actions.js";
|
||||
import type { CaptureSetupAction } from "../config/explore-config.js";
|
||||
import { explorationSecretNames } from "../config/exploration-inputs.js";
|
||||
import { TOOL_LIMITS, isPlaceholderTitle } from "./explorer.js";
|
||||
|
||||
export type ReplayPlatform = "ios" | "android";
|
||||
type Selector = { label: string; identifier?: never } | { identifier: string; label?: never };
|
||||
type ReplayAction =
|
||||
| ({ action: "tap" } & Selector)
|
||||
| ({ action: "fill"; text: string } & Selector)
|
||||
| { action: "type"; text: string }
|
||||
| { action: "scroll"; direction: "up" | "down" | "left" | "right" | "top" | "bottom" }
|
||||
| { action: "wait"; milliseconds: number }
|
||||
| { action: "open"; url: string }
|
||||
| { action: "back" }
|
||||
| { action: "dismiss-keyboard" };
|
||||
type ReplayCapture = { capture: string; state?: string; description?: string };
|
||||
/** `platforms` limits a step to those platforms; an `optional` action that fails is skipped instead of ending the replay. */
|
||||
export type ReplayStep = (ReplayCapture & { platforms?: ReplayPlatform[] }) | (ReplayAction & { platforms?: ReplayPlatform[]; optional?: boolean });
|
||||
export type ReplayPlan = { steps: ReplayStep[] };
|
||||
|
||||
export type ReplaySession = {
|
||||
readonly provider: "replay";
|
||||
readonly model: string;
|
||||
preflight(): Promise<void>;
|
||||
run(request: CiAgentSessionRunRequest): Promise<CiAgentSessionRunResult>;
|
||||
/** After a budget stop, the planned screens the run did not reach, for the explorer's gap. */
|
||||
budgetNote(): string | undefined;
|
||||
};
|
||||
|
||||
const DIRECTIONS = new Set(["up", "down", "left", "right", "top", "bottom"]);
|
||||
/**
|
||||
* The fields each kind of step takes. Anything else is refused: a typo (`platform`, `optinal`) would otherwise do nothing,
|
||||
* and a field `act` reads another way (a coordinate tap's `frameId`, `x`, `y` and `target`) would change what is tapped.
|
||||
*/
|
||||
const FIELDS = new Map<string, readonly string[]>([
|
||||
["capture", ["capture", "state", "description", "platforms"]],
|
||||
["tap", ["action", "label", "identifier", "platforms", "optional"]],
|
||||
["fill", ["action", "label", "identifier", "text", "platforms", "optional"]],
|
||||
["type", ["action", "text", "platforms", "optional"]],
|
||||
["scroll", ["action", "direction", "platforms", "optional"]],
|
||||
["wait", ["action", "milliseconds", "platforms", "optional"]],
|
||||
["open", ["action", "url", "platforms", "optional"]],
|
||||
["back", ["action", "platforms", "optional"]],
|
||||
["dismiss-keyboard", ["action", "platforms", "optional"]],
|
||||
]);
|
||||
const ACTIONS = [...FIELDS.keys()].filter(kind => kind !== "capture");
|
||||
|
||||
function invalid(message: string): CiError {
|
||||
return new CiError({ code: "REPLAY_PLAN_INVALID", stage: "exploration", message, retryable: false,
|
||||
nextAction: "Fix the replay plan: a JSON object with a steps array of actions ({\"action\":\"tap\",\"label\":\"Settings\"}) and captures ({\"capture\":\"Settings\"})." });
|
||||
}
|
||||
|
||||
const nonEmpty = (value: unknown, max: number): value is string => typeof value === "string" && value.trim().length > 0 && value.length <= max;
|
||||
|
||||
function parseStep(step: unknown, at: string): ReplayStep {
|
||||
if (!step || typeof step !== "object" || Array.isArray(step)) throw invalid(`${at} is not an object.`);
|
||||
const entry = step as Record<string, unknown>;
|
||||
const kind = "capture" in entry ? "capture" : typeof entry.action === "string" && FIELDS.has(entry.action) ? entry.action : undefined;
|
||||
if (!kind) throw invalid(`${at} needs a capture title or an action (${ACTIONS.join(", ")}).`);
|
||||
const fields = FIELDS.get(kind)!;
|
||||
const unknown = Object.keys(entry).find(key => !fields.includes(key));
|
||||
if (unknown !== undefined) throw invalid(`${at} (${kind}) has a field ${JSON.stringify(unknown.slice(0, 40))} it does not take; a ${kind} step takes ${fields.join(", ")}.`);
|
||||
if (entry.platforms !== undefined && (!Array.isArray(entry.platforms) || !entry.platforms.length || entry.platforms.some(item => item !== "ios" && item !== "android"))) {
|
||||
throw invalid(`${at}: platforms must list ios and/or android.`);
|
||||
}
|
||||
if (entry.optional !== undefined && typeof entry.optional !== "boolean") throw invalid(`${at}: optional must be true or false.`);
|
||||
const extra = { ...(entry.platforms ? { platforms: [...entry.platforms] as ReplayPlatform[] } : {}), ...(entry.optional !== undefined ? { optional: entry.optional as boolean } : {}) };
|
||||
if (kind === "capture") {
|
||||
if (!nonEmpty(entry.capture, TOOL_LIMITS.title)) throw invalid(`${at}: capture must be a screen title of at most ${TOOL_LIMITS.title} characters.`);
|
||||
if (entry.state !== undefined && !nonEmpty(entry.state, TOOL_LIMITS.state)) throw invalid(`${at}: state must be a string of at most ${TOOL_LIMITS.state} characters.`);
|
||||
if (entry.description !== undefined && !nonEmpty(entry.description, TOOL_LIMITS.description)) throw invalid(`${at}: description must be a string of at most ${TOOL_LIMITS.description} characters.`);
|
||||
return { capture: entry.capture.trim(), ...(entry.state !== undefined ? { state: entry.state as string } : {}),
|
||||
...(entry.description !== undefined ? { description: entry.description as string } : {}), ...extra };
|
||||
}
|
||||
// The device selects by the setup executor's rules, which are stricter than what `act` itself accepts.
|
||||
const selector = (): Selector => {
|
||||
const keys = (["label", "identifier"] as const).filter(key => entry[key] !== undefined);
|
||||
if (keys.length !== 1) throw invalid(`${at}: ${kind} needs exactly one of label or identifier.`);
|
||||
const key = keys[0]!, value = entry[key];
|
||||
if (!isSetupSelector(value) || value.length > TOOL_LIMITS.selector) throw invalid(`${at}: ${key} must be 1–${SETUP_SELECTOR_MAX} characters without control characters.`);
|
||||
return key === "label" ? { label: value } : { identifier: value };
|
||||
};
|
||||
const input = (): string => {
|
||||
if (!nonEmpty(entry.text, TOOL_LIMITS.text) || !isSetupInput(entry.text)) throw invalid(`${at}: ${kind} needs text: one line of at most ${TOOL_LIMITS.text} characters.`);
|
||||
try { explorationSecretNames(entry.text); }
|
||||
catch (error) { throw invalid(`${at}: ${error instanceof Error ? error.message : String(error)} Write each input as {{secret:NAME}} with an uppercase environment variable name that is not a provider, Expo, or CI credential.`); }
|
||||
return entry.text;
|
||||
};
|
||||
switch (kind) {
|
||||
case "tap": return { action: "tap", ...selector(), ...extra };
|
||||
case "fill": return { action: "fill", ...selector(), text: input(), ...extra };
|
||||
case "type": return { action: "type", text: input(), ...extra };
|
||||
case "scroll":
|
||||
if (typeof entry.direction !== "string" || !DIRECTIONS.has(entry.direction)) throw invalid(`${at}: scroll needs a direction (${[...DIRECTIONS].join(", ")}).`);
|
||||
return { action: "scroll", direction: entry.direction as "up", ...extra };
|
||||
case "wait":
|
||||
if (!(Number.isInteger(entry.milliseconds) && Number(entry.milliseconds) >= 1 && Number(entry.milliseconds) <= TOOL_LIMITS.waitMs)) {
|
||||
throw invalid(`${at}: wait needs milliseconds between 1 and ${TOOL_LIMITS.waitMs}.`);
|
||||
}
|
||||
return { action: "wait", milliseconds: entry.milliseconds as number, ...extra };
|
||||
case "open":
|
||||
if (!nonEmpty(entry.url, TOOL_LIMITS.url)) throw invalid(`${at}: open needs a url of at most ${TOOL_LIMITS.url} characters.`);
|
||||
return { action: "open", url: entry.url, ...extra };
|
||||
default: return { action: kind as "back" | "dismiss-keyboard", ...extra };
|
||||
}
|
||||
}
|
||||
|
||||
/** Checks a plan and keeps only the fields each step takes, so what reaches `act` is what the plan documents. */
|
||||
export function parseReplayPlan(value: unknown): ReplayPlan {
|
||||
if (!value || typeof value !== "object" || !Array.isArray((value as { steps?: unknown }).steps)) throw invalid("The replay plan has no steps array.");
|
||||
const unknown = Object.keys(value).find(key => key !== "steps");
|
||||
if (unknown !== undefined) throw invalid(`The replay plan has a field ${JSON.stringify(unknown.slice(0, 40))} it does not take; it takes only steps.`);
|
||||
const steps = (value as { steps: unknown[] }).steps;
|
||||
if (!steps.length) throw invalid("The replay plan has no steps.");
|
||||
return { steps: steps.map((step, index) => parseStep(step, `Step ${index + 1}`)) };
|
||||
}
|
||||
|
||||
export async function readReplayPlan(path: string): Promise<ReplayPlan> {
|
||||
let text: string;
|
||||
try { text = await readFile(path, "utf8"); }
|
||||
catch (error) { throw invalid(`The replay plan ${path} could not be read: ${error instanceof Error ? error.message : String(error)}`); }
|
||||
let value: unknown;
|
||||
try { value = JSON.parse(text); }
|
||||
catch (error) { throw invalid(`The replay plan ${path} is not JSON: ${error instanceof Error ? error.message : String(error)}`); }
|
||||
return parseReplayPlan(value);
|
||||
}
|
||||
|
||||
/** The plan's fill and type steps, whose {{secret:NAME}} inputs must be set before any device starts, as the hints' are. */
|
||||
export function replaySetup(plan: ReplayPlan): CaptureSetupAction[] {
|
||||
return plan.steps.flatMap(step => "action" in step && (step.action === "fill" || step.action === "type") ? [step as CaptureSetupAction] : []);
|
||||
}
|
||||
|
||||
const stepsFor = (plan: ReplayPlan, platform: ReplayPlatform) => plan.steps.map((step, index) => ({ step, number: index + 1 }))
|
||||
.filter(({ step }) => !step.platforms || step.platforms.includes(platform));
|
||||
|
||||
/**
|
||||
* Refuses, before any device starts, a plan with nothing to do on this platform or one the budgets cannot hold: a run that
|
||||
* would stop at its budget partway through the plan is better raised or shortened up front.
|
||||
*/
|
||||
export function assertReplayFits(plan: ReplayPlan, platform: ReplayPlatform, limits: { maxScreens: number; maxActions: number; maxTurns: number }): void {
|
||||
const steps = stepsFor(plan, platform);
|
||||
if (!steps.length) {
|
||||
throw new CiError({ code: "REPLAY_PLAN_EMPTY", stage: "exploration", message: `No step of the replay plan runs on ${platform}: each one is limited to ${platform === "ios" ? "android" : "ios"} by its platforms.`,
|
||||
nextAction: `Add steps for ${platform} to the plan, or run it on the platform it was written for.` });
|
||||
}
|
||||
const captures = steps.filter(({ step }) => "capture" in step).length;
|
||||
const actions = steps.filter(({ step }) => "action" in step && step.action !== "wait").length;
|
||||
// A screen counts against the budget when it is first photographed, on arrival, and a capture is refused once the budget
|
||||
// is used up, so the last capture needs one screen to spare.
|
||||
const over = [
|
||||
...(captures >= limits.maxScreens ? [{ text: `${captures} captures, which need a screen budget of at least ${captures + 1} (it is ${limits.maxScreens})`, flag: `--max-screens ${captures + 1}` }] : []),
|
||||
...(actions > limits.maxActions ? [{ text: `${actions} actions, more than the action budget of ${limits.maxActions}`, flag: `--max-actions ${actions}` }] : []),
|
||||
];
|
||||
if (over.length) {
|
||||
throw new CiError({ code: "REPLAY_PLAN_OVER_BUDGET", stage: "exploration", message: `On ${platform} the replay plan takes ${over.map(item => item.text).join(" and ")}.`,
|
||||
nextAction: `Pass ${over.map(item => item.flag).join(" ")} (or more: each screen the plan reaches without capturing it also counts), or shorten the plan.` });
|
||||
}
|
||||
// Each capture is an observe and a capture call, each action one act call, and the run ends with get_progress and finish.
|
||||
const turns = steps.length + captures + 2;
|
||||
if (turns > limits.maxTurns) {
|
||||
throw new CiError({ code: "REPLAY_PLAN_OVER_BUDGET", stage: "exploration", message: `On ${platform} the replay plan takes ${turns} tool calls, more than the ${limits.maxTurns} that the screen and action budgets allow.`,
|
||||
nextAction: "Raise --max-actions, or use fewer wait steps." });
|
||||
}
|
||||
}
|
||||
|
||||
function describeAction(step: ReplayAction): string {
|
||||
if ("label" in step && step.label) return `${step.action} "${step.label}"`;
|
||||
if ("identifier" in step && step.identifier) return `${step.action} #${step.identifier}`;
|
||||
if (step.action === "scroll") return `scroll ${step.direction}`;
|
||||
return step.action;
|
||||
}
|
||||
|
||||
/** Only the fields `act` documents for that action, whatever else the step object carries. */
|
||||
function actInput(step: ReplayAction): Record<string, unknown> {
|
||||
const selector = "label" in step && step.label !== undefined ? { label: step.label } : "identifier" in step && step.identifier !== undefined ? { identifier: step.identifier } : {};
|
||||
switch (step.action) {
|
||||
case "tap": return { action: "tap", ...selector };
|
||||
case "fill": return { action: "fill", ...selector, text: step.text };
|
||||
case "type": return { action: "type", text: step.text };
|
||||
case "scroll": return { action: "scroll", direction: step.direction };
|
||||
case "wait": return { action: "wait", milliseconds: step.milliseconds };
|
||||
case "open": return { action: "open", url: step.url };
|
||||
default: return { action: step.action };
|
||||
}
|
||||
}
|
||||
|
||||
/** As many names as fit in `room` characters, then "and N more"; a count of them when not even the first fits. */
|
||||
function listed(names: readonly string[], room: number, noun: string): string {
|
||||
let text = "";
|
||||
for (const [index, name] of names.entries()) {
|
||||
const next = text ? `${text}, ${name}` : name;
|
||||
const left = names.length - index - 1;
|
||||
if (next.length + (left ? ` and ${left} more`.length : 0) > room) return text ? `${text} and ${names.length - index} more` : `${names.length} ${noun}`;
|
||||
text = next;
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
const sameTitle = (left: string, right: string): boolean => left.toLowerCase() === right.toLowerCase();
|
||||
|
||||
/**
|
||||
* Runs a fixed plan through the explorer's own tools in place of a model: the same observe, act, and capture calls,
|
||||
* so the map and report are those of a model run, but every run takes the same steps. A step that fails does not
|
||||
* fail the run: the report keeps what was captured and names the screens that were not.
|
||||
*/
|
||||
export function createReplaySession(plan: ReplayPlan, platform: ReplayPlatform): ReplaySession {
|
||||
const steps = stepsFor(plan, platform);
|
||||
const title = (step: ReplayCapture) => step.state ? `${step.capture} (${step.state})` : step.capture;
|
||||
const missed: string[] = [];
|
||||
let position = 0;
|
||||
/** What the plan meant to capture and has not: the screens still ahead first, then the ones earlier steps missed. */
|
||||
const notCaptured = () => [...steps.slice(position).flatMap(({ step }) => "capture" in step ? [title(step)] : []), ...missed];
|
||||
return {
|
||||
provider: "replay",
|
||||
model: "replay plan",
|
||||
async preflight() {},
|
||||
budgetNote() {
|
||||
const names = notCaptured();
|
||||
return names.length ? `Not captured: ${listed(names, TOOL_LIMITS.reason, "planned screens")}.` : undefined;
|
||||
},
|
||||
async run(request) {
|
||||
const signal = request.signal ?? new AbortController().signal;
|
||||
const call = async (name: string, input: Record<string, unknown>) => {
|
||||
const result = await request.callTool(name, input, signal);
|
||||
const text = result.content.find(block => block.type === "text");
|
||||
const value = text && "text" in text ? JSON.parse(text.text) as Record<string, unknown> : {};
|
||||
return { failed: Boolean(result.isError) || value.ok === false, value };
|
||||
};
|
||||
const why = (value: Record<string, unknown>) => String(value.error ?? value.reason ?? value.message ?? "it failed");
|
||||
// A refused finish or stop_blocked would otherwise end the session with no result, which the explorer reports as a turn budget stop.
|
||||
const end = async (name: "finish" | "stop_blocked", input: Record<string, unknown>) => {
|
||||
const ended = await call(name, input);
|
||||
if (!ended.failed) return;
|
||||
if (name === "finish") return end("stop_blocked", { reason: `The replay could not finish (${why(ended.value)}). ${String(input.summary)}`.slice(0, TOOL_LIMITS.reason) });
|
||||
throw new CiError({ code: "REPLAY_STOP_REFUSED", stage: "exploration", message: `The explorer refused the replay's ${name}: ${why(ended.value)}`.slice(0, 600),
|
||||
nextAction: "Report this with the replay plan; the screens captured so far are in the map." });
|
||||
};
|
||||
/** Screen id to the title the plan captured it under. */
|
||||
const planned = new Map<string, string>();
|
||||
const skipped: string[] = [];
|
||||
missed.length = 0;
|
||||
try {
|
||||
for (const [index, { step, number }] of steps.entries()) {
|
||||
position = index;
|
||||
if ("capture" in step) {
|
||||
const seen = await call("observe", { includeImage: true });
|
||||
const frameId = typeof seen.value.frameId === "string" ? seen.value.frameId : undefined;
|
||||
const known = typeof seen.value.screenId === "string" && !step.state ? planned.get(seen.value.screenId) : undefined;
|
||||
// The plan already captured this screen: a second capture would only rename it, so it is not made.
|
||||
if (known !== undefined) {
|
||||
if (!sameTitle(known, step.capture)) missed.push(`${title(step)} (looked the same as ${known})`);
|
||||
continue;
|
||||
}
|
||||
const captured = frameId && !seen.failed ? await call("capture", { frameId, title: step.capture,
|
||||
...(step.state ? { state: step.state } : {}), ...(step.description ? { description: step.description } : {}) }) : undefined;
|
||||
const screenId = typeof captured?.value.screenId === "string" ? captured.value.screenId : undefined;
|
||||
if (!captured || captured.failed || !screenId) missed.push(title(step));
|
||||
else if (!planned.has(screenId)) planned.set(screenId, step.capture);
|
||||
continue;
|
||||
}
|
||||
const acted = await call("act", actInput(step));
|
||||
if (!acted.failed) continue;
|
||||
if (step.optional) { skipped.push(`step ${number} (${describeAction(step)})`); continue; }
|
||||
const head = `Replay step ${number} (${describeAction(step)}) failed: ${why(acted.value)}`.slice(0, 600);
|
||||
const names = notCaptured();
|
||||
const lead = ". Not captured: ";
|
||||
await end("stop_blocked", { reason: head + (names.length ? `${lead}${listed(names, TOOL_LIMITS.reason - head.length - lead.length, "planned screens")}` : "") });
|
||||
return { inputTokens: 0, outputTokens: 0 };
|
||||
}
|
||||
position = steps.length;
|
||||
// The map as it stands: screens merged into others are gone, and each keeps its latest title. One reached but never
|
||||
// captured is still "Screen N" here and is named after the path to it only once the run ends, so it is counted.
|
||||
const progress = await call("get_progress", {});
|
||||
const screens = Array.isArray(progress.value.captured) ? progress.value.captured as Array<{ id?: unknown; title?: unknown }> : [];
|
||||
const unplanned = screens.filter(screen => typeof screen.id === "string" && !planned.has(screen.id)).map(screen => typeof screen.title === "string" ? screen.title : "");
|
||||
const named = unplanned.filter(name => name && !isPlaceholderTitle(name));
|
||||
const unnamed = unplanned.length - named.length;
|
||||
const reached = [...named, ...(unnamed ? [`${unnamed} unnamed screen${unnamed === 1 ? "" : "s"}`] : [])];
|
||||
const sections = ([["Not captured", missed, "planned screens"], ["Optional steps skipped because they failed", skipped, "steps"],
|
||||
["Also reached, not in the plan", reached, "screens"]] as const).filter(([, names]) => names.length);
|
||||
let summary = `Replayed ${steps.length} planned steps on ${platform}.${missed.length ? "" : " Every planned screen was captured."}`;
|
||||
for (const [index, [label, names, noun]] of sections.entries()) {
|
||||
// Each later section keeps room for its label and a count, so a long list of misses does not crowd out the rest.
|
||||
const reserve = sections.slice(index + 1).reduce((sum, [later]) => sum + later.length + 32, 0);
|
||||
const lead = ` ${label}: `;
|
||||
summary += `${lead}${listed(names, TOOL_LIMITS.summary - summary.length - lead.length - 1 - reserve, noun)}.`;
|
||||
}
|
||||
await end("finish", { summary });
|
||||
} catch (error) {
|
||||
if (signal.aborted) return { inputTokens: 0, outputTokens: 0 };
|
||||
throw error;
|
||||
}
|
||||
return { inputTokens: 0, outputTokens: 0 };
|
||||
},
|
||||
};
|
||||
}
|
||||
+45
-9
@@ -5,6 +5,7 @@ import { join } from "node:path";
|
||||
import { createCiAgentSession, type CiAgentSession, type CiAgentSessionConfig } from "../capture/agent/session.js";
|
||||
import { createLocalCiAgentSession } from "../capture/agent/session-local.js";
|
||||
import type { CiAgentProviderName } from "../capture/agent/provider.js";
|
||||
import { assertReplayFits, createReplaySession, parseReplayPlan, replaySetup, type ReplayPlan } from "./replay.js";
|
||||
import { CONTROLLER_SESSION, baseEnvironment, isRecord } from "../capture/common.js";
|
||||
import { controllerData, defaultRunner, openedSimulatorDevice } from "../capture/controller.js";
|
||||
import type { CommandRequest, CommandResult } from "../capture/run.js";
|
||||
@@ -57,6 +58,8 @@ export type BinaryExploreOptions = {
|
||||
simulator?: "eas" | "local";
|
||||
environment?: NodeJS.ProcessEnv;
|
||||
runner?: typeof defaultRunner;
|
||||
/** Fixed steps to take instead of a model's; no model access is needed. */
|
||||
replay?: ReplayPlan;
|
||||
createSession?: (config: CiAgentSessionConfig, options: { env: NodeJS.ProcessEnv; auth: ModelAuth }) => CiAgentSession;
|
||||
progress?: (message: string) => void;
|
||||
now?: () => number;
|
||||
@@ -68,7 +71,7 @@ export type BinaryExploreResult = {
|
||||
archive: Omit<InspectedArchive, "path"> & { path: string };
|
||||
session: { id: string; platform: Platform; device: string; owner: string; project: string };
|
||||
runtime: ActiveSimulatorRuntime;
|
||||
model: { provider: CiAgentProviderName; model: string; auth: "local-login" | "api-key" };
|
||||
model: { provider: CiAgentProviderName | "replay"; model: string; auth: "local-login" | "api-key" | "none" };
|
||||
exploration: BlackBoxExplorerResult;
|
||||
durationMs: number;
|
||||
};
|
||||
@@ -162,8 +165,8 @@ export function resolveSessionApp(runner: typeof defaultRunner, connection: Simu
|
||||
* App-test inputs: each {{secret:NAME}} in the hints names an environment variable whose value Explore types for the
|
||||
* model. Read before any session starts, so a missing one costs nothing.
|
||||
*/
|
||||
export function hintInputs(hints: string | undefined, environment: NodeJS.ProcessEnv): ReturnType<typeof createExplorationInputs> {
|
||||
try { return createExplorationInputs({ instructions: hints ?? "", environment }); }
|
||||
export function hintInputs(hints: string | undefined, environment: NodeJS.ProcessEnv, replay?: ReplayPlan): ReturnType<typeof createExplorationInputs> {
|
||||
try { return createExplorationInputs({ instructions: hints ?? "", ...(replay ? { setup: replaySetup(replay) } : {}), environment }); }
|
||||
catch (error) {
|
||||
if (!(error instanceof CiError) || !error.code.startsWith("EXPLORATION_SECRET_")) throw error;
|
||||
const name = typeof error.details?.secretName === "string" ? error.details.secretName : "NAME";
|
||||
@@ -194,6 +197,36 @@ function modelSession(provider: CiAgentProviderName, auth: ModelAuth, options: M
|
||||
return { session, provider, model: config.model, auth };
|
||||
}
|
||||
|
||||
/** The turns the model gets: three for each action and two for each screen, plus a few to look around and finish. */
|
||||
const turnBudget = (limits: { maxScreens: number; maxActions: number }): number => limits.maxActions * 3 + limits.maxScreens * 2 + 20;
|
||||
|
||||
/**
|
||||
* A replay plan is checked here as well as by the CLI, for callers that pass one directly. It takes the model's place, so
|
||||
* the options that only steer a model would do nothing; the plan's own fill and type steps name the secrets it types.
|
||||
*/
|
||||
function replayPlan(options: Pick<BinaryExploreOptions, "replay" | "provider" | "model" | "hints">): ReplayPlan | undefined {
|
||||
if (!options.replay) return undefined;
|
||||
const ignored = (["provider", "model", "hints"] as const).filter(name => options[name] !== undefined);
|
||||
if (ignored.length) {
|
||||
throw binaryError("REPLAY_OPTIONS_IGNORED", `--replay takes the model's place, so ${ignored.map(name => `--${name}`).join(" and ")} would do nothing.`,
|
||||
`Drop ${ignored.map(name => `--${name}`).join(" and ")}. A {{secret:NAME}} in the plan's fill and type steps is read from the environment, as one in --hints is.`);
|
||||
}
|
||||
const plan = parseReplayPlan(options.replay);
|
||||
for (const [index, step] of plan.steps.entries()) {
|
||||
if (!("action" in step) || step.action !== "open") continue;
|
||||
try { assertAppUrl(step.url); }
|
||||
catch (error) { throw new CiError({ code: "REPLAY_PLAN_INVALID", stage: "exploration", message: `Step ${index + 1}: ${error instanceof Error ? error.message : String(error)}`, nextAction: "Open only the app's own URLs in the replay plan." }); }
|
||||
}
|
||||
return plan;
|
||||
}
|
||||
|
||||
/** A replay plan takes the model's place: no model access is checked or used. */
|
||||
function replayModel(plan: ReplayPlan, platform: Platform, limits: { maxScreens: number; maxActions: number }) {
|
||||
assertReplayFits(plan, platform, { ...limits, maxTurns: turnBudget(limits) });
|
||||
const session = createReplaySession(plan, platform);
|
||||
return { session, budgetNote: session.budgetNote, provider: "replay" as const, model: "replay plan", auth: "none" as const };
|
||||
}
|
||||
|
||||
/** Local `claude`/`codex` login unless an API key is present; preflight proves access before a simulator is paid for. */
|
||||
export function selectModelSession(options: ModelSessionOptions, environment: NodeJS.ProcessEnv) {
|
||||
const provider: CiAgentProviderName = options.provider ?? (environment.OPENAI_API_KEY?.trim() && !environment.ANTHROPIC_API_KEY?.trim() ? "openai" : "anthropic");
|
||||
@@ -260,7 +293,7 @@ export type ConnectedSessionExploration = {
|
||||
limits: { maxDurationMinutes: number; maxScreens: number; maxActions: number };
|
||||
store: ExploreStore;
|
||||
map: ExploreMap;
|
||||
model: { session: CiAgentSession };
|
||||
model: { session: Pick<CiAgentSession, "run">; budgetNote?: () => string | undefined };
|
||||
/** `eas simulator:get --json` for the attached session; descriptive (OS version) only. */
|
||||
sessionJson: () => string;
|
||||
/** agent-device session name on the daemon; explore:session reuses the caller's session so the device is not "in use" by another. */
|
||||
@@ -444,7 +477,8 @@ export async function exploreConnectedSession(ctx: ConnectedSessionExploration):
|
||||
}
|
||||
const exploration = blockedAtLaunch ?? await runBlackBoxExploration({ session: model.session, store, map, app: { name: app.name, bundleId, platform, ...(app.version ? { version: app.version } : {}) },
|
||||
inputs, ...(hints ? { hints: hints } : {}), ...(launchUrl ? { launchUrl: launchUrl } : {}), ...(allowDestructive ? { allowDestructive: allowDestructive } : {}), ...(ctx.appIcon ? { appIcon: ctx.appIcon } : {}),
|
||||
deadlineMs, maxScreens: limits.maxScreens, maxActions: limits.maxActions, maxTurns: limits.maxActions * 3 + limits.maxScreens * 2 + 20, now, observe, progress: say,
|
||||
...(model.budgetNote ? { budgetNote: model.budgetNote } : {}),
|
||||
deadlineMs, maxScreens: limits.maxScreens, maxActions: limits.maxActions, maxTurns: turnBudget(limits), now, observe, progress: say,
|
||||
act: async action => {
|
||||
const perform = async () => {
|
||||
if (action.action === "tap" && "frameId" in action) {
|
||||
@@ -508,7 +542,8 @@ export async function runSessionExploration(options: SessionExploreOptions): Pro
|
||||
const environment = options.environment ?? process.env;
|
||||
const runner = options.runner ?? defaultRunner;
|
||||
const limits = validatedLimits(options);
|
||||
const inputs = hintInputs(options.hints, environment);
|
||||
const replay = replayPlan(options);
|
||||
const inputs = hintInputs(options.hints, environment, replay);
|
||||
if (options.bundleId !== undefined && !appIdPattern.test(options.bundleId)) throw binaryError("BUNDLE_ID_INVALID", `${options.bundleId} is not a bundle or package id.`, "Pass --bundle-id with the app's bundle identifier (iOS) or package name (Android).");
|
||||
let connection: SimulatorConnection;
|
||||
try { connection = await resolveAttachedSimulatorSession(environment, options.envFile, options.session); }
|
||||
@@ -572,7 +607,7 @@ export async function runSessionExploration(options: SessionExploreOptions): Pro
|
||||
map.run.environment = { deviceModel: device };
|
||||
session = { id: connection.sessionId, platform, device, name: info.name, ...(info.deviceRunSessionUrl ? { url: info.deviceRunSessionUrl } : {}) };
|
||||
|
||||
const model = await preflightModelSession(options, environment, say);
|
||||
const model = replay ? replayModel(replay, platform, limits) : await preflightModelSession(options, environment, say);
|
||||
const outputDirectory = await realpath(await mkdir(options.output, { recursive: true }).then(() => options.output));
|
||||
const store = new ExploreStore(outputDirectory);
|
||||
if (await store.exists()) throw binaryError("OUTPUT_NOT_EMPTY", `${outputDirectory} already holds an Explore map.`, "Pass an empty --output directory.");
|
||||
@@ -665,7 +700,8 @@ export async function runBinaryExploration(options: BinaryExploreOptions): Promi
|
||||
const environment = options.environment ?? process.env;
|
||||
const runner = options.runner ?? defaultRunner;
|
||||
const limits = validatedLimits(options);
|
||||
const inputs = hintInputs(options.hints, environment);
|
||||
const replay = replayPlan(options);
|
||||
const inputs = hintInputs(options.hints, environment, replay);
|
||||
const local = options.simulator === "local";
|
||||
// A local emulator runs this Mac's ABI (arm64-v8a on Apple silicon); EAS's runs x86_64.
|
||||
const emulatorAbi = local ? hostEmulatorAbi() : "x86_64";
|
||||
@@ -682,7 +718,7 @@ export async function runBinaryExploration(options: BinaryExploreOptions): Promi
|
||||
say(`${archive.appName} ${archive.version ?? ""} (${bundleId}, ${platform}, ${(archive.bytes / 1048576).toFixed(0)} MB, sha256 ${archive.sha256.slice(0, 12)})`);
|
||||
if (archive.missingLibs?.length && emulatorAbi === "x86_64") say(`warning: lib/x86_64 lacks ${archive.missingLibs.slice(0, 4).join(", ")}${archive.missingLibs.length > 4 ? ` and ${archive.missingLibs.length - 4} more` : ""} that another ABI ships; the app may stop with UnsatisfiedLinkError on the emulator`);
|
||||
|
||||
const model = await preflightModelSession(options, environment, say);
|
||||
const model = replay ? replayModel(replay, platform, limits) : await preflightModelSession(options, environment, say);
|
||||
|
||||
const outputDirectory = await realpath(await mkdir(options.output, { recursive: true }).then(() => options.output));
|
||||
const store = new ExploreStore(outputDirectory);
|
||||
|
||||
@@ -216,6 +216,21 @@ const KEYBOARD_DISMISS_LABELS = ["Hide keyboard", "Dismiss keyboard", "Done"];
|
||||
const KEYBOARD_TOP = 0.4;
|
||||
const ALERT_PREFERRED_BUTTONS = ["Open", "OK", "Allow", "Allow While Using App", "Continue"];
|
||||
const READ_TOOLS = new Set(["ui-tree", "list-devices", "screenshot", "foreground-app", "await-screen-idle", "describe"]);
|
||||
/**
|
||||
* Argent 0.29's answer when a service a tool depends on (the device's simulator-server, its accessibility service) did
|
||||
* not start: the registry resolves a tool's services before it calls the tool, and wraps a start failure as
|
||||
* "[Tool:<id>] Service dependency failed: …", so the tool itself never ran and resending it is safe, a UI action too.
|
||||
* The tools the bridge sends that resolve a service while they run (keyboard, fill, restart-app, screen-recording-start)
|
||||
* resolve it before they act, and run-sequence answers a step's failure in its result rather than raising it. A failed
|
||||
* start leaves the service in the registry's ERROR state, so the next call starts it afresh.
|
||||
*/
|
||||
const SERVICE_DEPENDENCY_FAILED = "Service dependency failed:";
|
||||
/**
|
||||
* In brentvatne/euxy#172 (review run 39348956443) capture restarted SpringBoard and folded the iPhone Duo open again 8 s
|
||||
* later; that fold's simulator-server did not become ready within Argent's 30 s, and the whole target failed. The resend
|
||||
* comes after a pause, so a device still coming back from the restart has the time it needs.
|
||||
*/
|
||||
const DEPENDENCY_RETRY_DELAYS_MS = [3_000, 6_000] as const;
|
||||
const SPRINGBOARD = "com.apple.springboard";
|
||||
const ANDROID_SYSTEM_UI = "com.android.systemui";
|
||||
const OPEN_IN_APP_PROMPT = /^Open in “.+”\?$/;
|
||||
@@ -299,14 +314,23 @@ export async function runBridgeCommand(argv: readonly string[], context: ArgentB
|
||||
const { positional, flags } = parseCommand(rest);
|
||||
const bundleFlag = typeof flags["bundle-id"] === "string" ? flags["bundle-id"] : context.bundleId;
|
||||
|
||||
/** Reads are resent after a transport failure (they change nothing); a UI action is sent once, after a health check. */
|
||||
/**
|
||||
* Reads are resent after a transport failure (they change nothing); a UI action is sent once, after a health check.
|
||||
* Any tool, a UI action too, is resent when Argent could not start a service it depends on, which it raises before
|
||||
* the tool runs (see SERVICE_DEPENDENCY_FAILED).
|
||||
*/
|
||||
const call = async (tool: string, args: Record<string, unknown> = {}, options?: { out?: string }): Promise<Record<string, unknown>> => {
|
||||
// Tools that name devices their own way (or none) take no udid.
|
||||
const withDevice = tool === "list-devices" || tool === "stop-all-simulator-servers" ? args : { udid: state.udid, ...args };
|
||||
for (let attempt = 0; ; attempt++) {
|
||||
for (let readRetry = 0, dependencyRetry = 0; ;) {
|
||||
try { return record(await context.call(tool, withDevice, options)); }
|
||||
catch (error) {
|
||||
if (READ_TOOLS.has(tool) && attempt < 2) { await context.sleep(1_000 * (attempt + 1)); continue; }
|
||||
if (error instanceof ArgentCallError && error.message.includes(`[Tool:${tool}] ${SERVICE_DEPENDENCY_FAILED}`)
|
||||
&& dependencyRetry < DEPENDENCY_RETRY_DELAYS_MS.length) {
|
||||
await context.sleep(DEPENDENCY_RETRY_DELAYS_MS[dependencyRetry++]!);
|
||||
continue;
|
||||
}
|
||||
if (READ_TOOLS.has(tool) && readRetry < 2) { await context.sleep(1_000 * ++readRetry); continue; }
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
+10
-6
@@ -454,6 +454,8 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
// `eas simulator:control` names the session by id, from the session's own project directory.
|
||||
const sessionEas: EasCommand = (args, commandOptions) => runner({ command: options.easCommand, args, cwd: simulatorProject, environment: easEnvironment,
|
||||
timeoutMs: commandOptions?.timeoutMs ?? 5 * 60_000, ...(commandOptions?.allowFailure ? { allowFailure: true } : {}) });
|
||||
// A failed simulator:control action is sent again after a pause, which a test's clock replaces.
|
||||
const controlOptions = { sleep: options.sleep };
|
||||
// What the EAS session's host can do through simulator:control (iOS sessions on serve-sim 0.10.0 or later).
|
||||
let controlActions = new Set<string>();
|
||||
const configResult = eas(["config", "--platform", options.platform, "--profile", options.easProfile, "--json", "--non-interactive"]);
|
||||
@@ -785,7 +787,7 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
"--platform", options.platform, "--json"], cwd: simulatorProject, environment: controllerEnvironment, timeoutMs: 15 * 60_000 });
|
||||
// Before any link opens, as a local capture does with simctl: the app's own links then open without the prompt.
|
||||
if (sessionId && scheme) {
|
||||
const approved = approveSessionUrlSchemes(sessionEas, sessionId, controlActions, options.bundleId, [scheme]);
|
||||
const approved = approveSessionUrlSchemes(sessionEas, sessionId, controlActions, options.bundleId, [scheme], controlOptions);
|
||||
if (approved.length) say(`approved ${approved.map(item => `${item}://`).join(", ")} links on session ${sessionId}`);
|
||||
}
|
||||
}
|
||||
@@ -796,8 +798,10 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
const target = deviceArgs({ platform: options.platform, deviceModel: options.device, ...(localDevice() ? { provider: "local-simulator" as const, controllerDeviceId: localDevice()! } : {}) });
|
||||
// agent-device reads the hinge back after folding and fails to (locally and on EAS); its display is checked instead.
|
||||
const easAgentDevice = !!sessionId && controller === "agent-device";
|
||||
// Argent's bridge sends a fold again, twice, when the simulator-server it needs did not start within Argent's 30 s,
|
||||
// so a fold can take three of those waits and the panel checks after it: 4 minutes covers that.
|
||||
const fold = () => runner({ command: controllerCommand, args: ["fold", options.devicePose!, "--session", CONTROLLER_SESSION, ...target, "--platform", options.platform, "--json"],
|
||||
cwd: simulatorProject, environment: controllerEnvironment, timeoutMs: 2 * 60_000, ...(localSimulator || easAgentDevice ? { allowFailure: true } : {}) });
|
||||
cwd: simulatorProject, environment: controllerEnvironment, timeoutMs: 4 * 60_000, ...(localSimulator || easAgentDevice ? { allowFailure: true } : {}) });
|
||||
const pause = options.sleep ?? (milliseconds => { Atomics.wait(new Int32Array(new SharedArrayBuffer(4)), 0, 0, milliseconds); });
|
||||
if (localSimulator && controller === "argent") {
|
||||
// Argent folds without a session and checks the fold against its own reader; this machine also checks the display.
|
||||
@@ -844,7 +848,7 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
if (!controlActions.has("springboard.restart")) throw new CiError({ code: "CONTROLLER_FOLD_UNVERIFIED", stage: "session",
|
||||
message: `${options.device} did not show the ${options.devicePose} display after folding.`, nextAction: "Rerun the capture on a new session." });
|
||||
say(`${options.device} did not draw the ${options.devicePose} display after the fold; restarting SpringBoard and folding ${options.devicePose} again`);
|
||||
simulatorControl(sessionEas, sessionId, "springboard.restart");
|
||||
simulatorControl(sessionEas, sessionId, "springboard.restart", [], controlOptions);
|
||||
pause(8_000);
|
||||
open(true);
|
||||
fold();
|
||||
@@ -859,7 +863,7 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
catch (error) {
|
||||
if (toCiError(error).code !== "CONTROLLER_FOLD_UNVERIFIED") throw error;
|
||||
say(`Argent kept reading the other panel after the fold; restarting SpringBoard and folding ${options.devicePose} again`);
|
||||
simulatorControl(sessionEas, sessionId, "springboard.restart");
|
||||
simulatorControl(sessionEas, sessionId, "springboard.restart", [], controlOptions);
|
||||
pause(8_000);
|
||||
try { fold(); }
|
||||
catch (retry) {
|
||||
@@ -892,7 +896,7 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
nextAction: "Rerun the capture; if it keeps happening, report it to Explore: this session's Argent tool-server needs a restart that EAS cannot do yet.", cause: error });
|
||||
if (recovery === 1) {
|
||||
say("Argent still did not read the app; restarting SpringBoard, then resetting Argent's device helpers and opening the app again");
|
||||
simulatorControl(sessionEas, sessionId, "springboard.restart");
|
||||
simulatorControl(sessionEas, sessionId, "springboard.restart", [], controlOptions);
|
||||
// SpringBoard takes a moment to come back, and sends the app to the background; the next open brings it back.
|
||||
(options.sleep ?? (milliseconds => { Atomics.wait(new Int32Array(new SharedArrayBuffer(4)), 0, 0, milliseconds); }))(8_000);
|
||||
} else say("Argent did not read the app after starting it; resetting Argent's device helpers and opening the app again");
|
||||
@@ -944,7 +948,7 @@ async function executeCiMap(options: CiMapOptions, setStage: (stage: string) =>
|
||||
// machine and serve-sim on an EAS iOS session; elsewhere its single pass runs as the device starts.
|
||||
if (controller !== "argent") runner({ command: controllerCommand, args: [...appearanceArgs(colorScheme), "--session", CONTROLLER_SESSION, ...deviceArgs(runtime), "--platform", options.platform],
|
||||
cwd: simulatorProject, environment: controllerEnvironment, timeoutMs: 60_000 });
|
||||
else if (sessionId && controlActions.has("appearance.set")) simulatorControl(sessionEas, sessionId, "appearance.set", [colorScheme]);
|
||||
else if (sessionId && controlActions.has("appearance.set")) simulatorControl(sessionEas, sessionId, "appearance.set", [colorScheme], controlOptions);
|
||||
else if (localSimulator) setLocalSimulatorAppearance({ runner, udid: localSimulator, scheme: colorScheme, cwd: simulatorProject, environment: restrictedEnvironment });
|
||||
else if (localEmulator) setLocalEmulatorAppearance({ runner, serial: localEmulator, scheme: colorScheme, cwd: simulatorProject, environment: restrictedEnvironment });
|
||||
// A scheme change recreates the Android activity in place, and the sheets it re-presents lose their inset; a
|
||||
|
||||
@@ -98,13 +98,24 @@ function failure(code: string, message: string, details?: Record<string, unknown
|
||||
...(details ? { details } : {}) });
|
||||
}
|
||||
|
||||
export const SETUP_SELECTOR_MAX = 256;
|
||||
|
||||
/** A label or identifier the executor can select by; a replay plan's selectors are checked against it before any device starts. */
|
||||
export function isSetupSelector(value: unknown): value is string {
|
||||
return typeof value === "string" && value.trim().length > 0 && value.length <= SETUP_SELECTOR_MAX && !/[\u0000-\u001f\u007f]/.test(value);
|
||||
}
|
||||
|
||||
/** Text the executor can fill or type: one line of at most 4,096 characters. */
|
||||
export function isSetupInput(value: unknown): value is string {
|
||||
return typeof value === "string" && value.length <= 4_096 && !/[\u0000\r\n]/.test(value);
|
||||
}
|
||||
|
||||
function selectorValue(selector: CaptureSetupSelector): { key: "label" | "identifier"; value: string } {
|
||||
const hasLabel = typeof selector.label === "string";
|
||||
const hasIdentifier = typeof selector.identifier === "string";
|
||||
const key = hasLabel ? "label" : "identifier";
|
||||
const value = selector[key];
|
||||
if (hasLabel === hasIdentifier || typeof value !== "string" || !value.trim()
|
||||
|| value.length > 256 || /[\u0000-\u001f\u007f]/.test(value)) {
|
||||
if (hasLabel === hasIdentifier || !isSetupSelector(value)) {
|
||||
throw failure("SETUP_SELECTOR_INVALID", "A UI selector must contain exactly one nonempty label or identifier.");
|
||||
}
|
||||
return { key, value };
|
||||
@@ -274,8 +285,7 @@ export async function executeCaptureSetup(actions: readonly CaptureSetupAction[]
|
||||
case "tap":
|
||||
case "fill": {
|
||||
selectorValue(action);
|
||||
if (action.action === "fill" && (typeof action.text !== "string" || action.text.length > 4_096
|
||||
|| /[\u0000\r\n]/.test(action.text))) {
|
||||
if (action.action === "fill" && !isSetupInput(action.text)) {
|
||||
throw failure("SETUP_INPUT_INVALID", "A UI fill input must be a single line of at most 4,096 characters.");
|
||||
}
|
||||
let resolved = false;
|
||||
@@ -330,7 +340,7 @@ export async function executeCaptureSetup(actions: readonly CaptureSetupAction[]
|
||||
break;
|
||||
}
|
||||
case "type": {
|
||||
if (typeof action.text !== "string" || !action.text || action.text.length > 4_096 || /[\u0000\r\n]/.test(action.text)) {
|
||||
if (!isSetupInput(action.text) || !action.text) {
|
||||
throw failure("SETUP_INPUT_INVALID", "A UI type input must be a nonempty single line of at most 4,096 characters.");
|
||||
}
|
||||
let ready = false;
|
||||
|
||||
@@ -20,23 +20,53 @@ export function simulatorControlActions(eas: EasCommand, sessionId: string): Set
|
||||
} catch { return new Set(); }
|
||||
}
|
||||
|
||||
/** Runs one `eas simulator:control` action on the session; eas-cli fills in the device. Throws with EAS's reason. */
|
||||
export function simulatorControl(eas: EasCommand, sessionId: string, action: string, values: readonly string[] = []): void {
|
||||
/**
|
||||
* Pauses before each resend of a failed action. Every action Explore runs is idempotent, and the session's host can fail
|
||||
* one once: in brentvatne/euxy's baseline run 39348933440, `app.approveUrlScheme` failed in its `simctl spawn … defaults
|
||||
* write`, which failed the dark-appearance session and with it the target's whole baseline.
|
||||
*/
|
||||
const SIMULATOR_CONTROL_RETRY_DELAYS_MS = [3_000, 6_000] as const;
|
||||
|
||||
/** Lets a test replace the pause between resends of a failed action. */
|
||||
export type SimulatorControlOptions = { sleep?: ((milliseconds: number) => void) | undefined };
|
||||
|
||||
/**
|
||||
* Runs one `eas simulator:control` action on the session; eas-cli fills in the device. A failed action is sent again
|
||||
* after a pause; one that still fails throws with EAS's reason.
|
||||
*/
|
||||
export function simulatorControl(eas: EasCommand, sessionId: string, action: string, values: readonly string[] = [], options: SimulatorControlOptions = {}): void {
|
||||
const sleep = options.sleep ?? (milliseconds => { Atomics.wait(new Int32Array(new SharedArrayBuffer(4)), 0, 0, milliseconds); });
|
||||
// Values follow `--` so one that starts with a dash is never read as a flag.
|
||||
eas(["simulator:control", action, "--id", sessionId, "--json", "--non-interactive", "--", ...values], { timeoutMs: 2 * 60_000 });
|
||||
const args = ["simulator:control", action, "--id", sessionId, "--json", "--non-interactive", "--", ...values];
|
||||
for (let retry = 0; ; retry += 1) {
|
||||
try { eas(args, { timeoutMs: 2 * 60_000 }); return; }
|
||||
catch (error) {
|
||||
const delayMs = SIMULATOR_CONTROL_RETRY_DELAYS_MS[retry];
|
||||
if (delayMs === undefined) throw error;
|
||||
// A resend that succeeds would otherwise leave no trace of the failure in the job log.
|
||||
process.stderr.write(`simulator:control ${action} failed (${firstLine(error)}); sending it again in ${delayMs / 1000} s\n`);
|
||||
sleep(delayMs);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Lets the app open its own links without iOS asking "Open in “App”?" first, like local captures do with simctl. A
|
||||
* session without the action keeps the controllers' prompt handling; http and https never prompt and are skipped.
|
||||
*/
|
||||
export function approveSessionUrlSchemes(eas: EasCommand, sessionId: string, actions: ReadonlySet<string>, bundleId: string, schemes: readonly string[]): string[] {
|
||||
export function approveSessionUrlSchemes(eas: EasCommand, sessionId: string, actions: ReadonlySet<string>, bundleId: string, schemes: readonly string[],
|
||||
options: SimulatorControlOptions = {}): string[] {
|
||||
if (!actions.has("app.approveUrlScheme")) return [];
|
||||
const approved: string[] = [];
|
||||
for (const scheme of new Set(schemes.map(value => value.toLowerCase()))) {
|
||||
if (scheme === "http" || scheme === "https" || !/^[a-z][a-z0-9+.-]*$/.test(scheme)) continue;
|
||||
simulatorControl(eas, sessionId, "app.approveUrlScheme", [bundleId, scheme]);
|
||||
simulatorControl(eas, sessionId, "app.approveUrlScheme", [bundleId, scheme], options);
|
||||
approved.push(scheme);
|
||||
}
|
||||
return approved;
|
||||
}
|
||||
|
||||
/** The first line of a failure, for a log line. */
|
||||
function firstLine(error: unknown): string {
|
||||
return (error instanceof Error ? error.message : String(error)).split("\n", 1)[0]!.slice(0, 300);
|
||||
}
|
||||
@@ -106,8 +106,11 @@ type GithubArtifact = { id: number; expired: boolean; workflow_run?: { id?: numb
|
||||
type GithubRun = { conclusion: string | null; workflow_id: number; head_sha: string; head_branch: string; event: string; head_repository?: { full_name?: string } };
|
||||
|
||||
/**
|
||||
* `ci:find-baseline`: the newest successful baseline-workflow artifact of exactly this commit, uploaded from the
|
||||
* default branch of this repository. Its id and run go to the step outputs for actions/download-artifact.
|
||||
* `ci:find-baseline`: the newest baseline-workflow artifact of exactly this commit, uploaded from the default branch of
|
||||
* this repository by a finished run. Its id and run go to the step outputs for actions/download-artifact. A run that
|
||||
* failed counts: a target's baseline job uploads its artifact only after every step before it passed, so another
|
||||
* target's failure (one flaky simulator session, as in brentvatne/euxy#172) does not make this target's baseline
|
||||
* unusable. A run still in progress or cancelled does not.
|
||||
*/
|
||||
export async function findBaselineArtifact(options: { sha: string; target?: string;
|
||||
/** What callers from before targets pass: a platform is the id of its default target. */ platform?: string; environment?: Environment; transport?: typeof fetch }): Promise<{ id: number; run: number } | undefined> {
|
||||
@@ -131,7 +134,7 @@ export async function findBaselineArtifact(options: { sha: string; target?: stri
|
||||
for (const artifact of artifacts.filter(candidate => !candidate.expired).sort((a, b) => b.id - a.id)) {
|
||||
if (!artifact.workflow_run?.id) continue;
|
||||
const run = await githubGet<GithubRun>(`repos/${context.repository}/actions/runs/${artifact.workflow_run.id}`, context, transport);
|
||||
if (!run || run.conclusion !== "success" || run.workflow_id !== workflow.id || run.head_sha !== options.sha
|
||||
if (!run || (run.conclusion !== "success" && run.conclusion !== "failure") || run.workflow_id !== workflow.id || run.head_sha !== options.sha
|
||||
|| run.head_branch !== repository.default_branch || !["push", "workflow_dispatch"].includes(run.event)
|
||||
|| run.head_repository?.full_name !== context.repository) continue;
|
||||
return { id: artifact.id, run: artifact.workflow_run.id };
|
||||
|
||||
@@ -5,6 +5,7 @@ import { resolve } from "node:path";
|
||||
import { ExploreStore } from "./map/store.js";
|
||||
import { QUERY_CONTRACT } from "./types.js";
|
||||
import { EXPLORE_VERSION } from "./shared/package-paths.js";
|
||||
import { isTargetId } from "./config/explore-config.js";
|
||||
import { command, resultContract, argumentError, validateCommandArguments, flag, has, setStore } from "./cli/args.js";
|
||||
import { help } from "./cli/help.js";
|
||||
import { listScreens, getScreen, listElements, listObservations, getObservation, nextFrontier, listAttempts, getAttempt, listTransitions, getTransition, neighbors, pathQuery, listJourneys, getJourney, listFrontier, listGaps, summary, search, status, validate, exportArtifacts } from "./cli/map-commands.js";
|
||||
@@ -81,8 +82,11 @@ try {
|
||||
await handler();
|
||||
} catch (error) {
|
||||
if (command.startsWith("capture:") || command.startsWith("source:") || command.startsWith("ci:") || command.startsWith("config:")) {
|
||||
// The failure comment names the target from this: a capture, report or publication of one matrix target.
|
||||
const target = (() => { try { return flag("target"); } catch { return undefined; } })();
|
||||
const diagnostic = await reportCiError(ciErrorForCommand(error, command), {
|
||||
...(process.env.RUNNER_TEMP ? { diagnosticsPath: resolve(process.env.RUNNER_TEMP, "explore-diagnostics", "error.json") } : {}),
|
||||
...(isTargetId(target) ? { target } : {}),
|
||||
...(has("json") ? { write: (line: string) => { if (process.env.GITHUB_ACTIONS === "true") console.log(line); } } : {}),
|
||||
});
|
||||
if (has("json")) console.error(JSON.stringify({ contract: resultContract, command, ok: false, error: diagnostic.message, diagnostic }));
|
||||
|
||||
+2
-2
@@ -90,10 +90,10 @@ const flagKinds: Record<string, Record<string, "value" | "boolean">> = {
|
||||
|
||||
|
||||
|
||||
"explore:binary": { archive:"value", output:"value", platform:"value", controller:"value", simulator:"value", device:"value", "bundle-id":"value", "launch-url":"value", hints:"value", "allow-destructive":"value",
|
||||
"explore:binary": { replay:"value", archive:"value", output:"value", platform:"value", controller:"value", simulator:"value", device:"value", "bundle-id":"value", "launch-url":"value", hints:"value", "allow-destructive":"value",
|
||||
"max-duration-minutes":"value", "max-screens":"value", "max-actions":"value", provider:"value", model:"value", owner:"value", project:"value",
|
||||
upload:"boolean", "no-upload":"boolean", "expires-in":"value", alias:"value", "no-open":"boolean", port:"value" },
|
||||
"explore:session": { session:"value", "env-file":"value", "bundle-id":"value", "app-name":"value", "app-version":"value", output:"value", platform:"value", controller:"value", device:"value", "launch-url":"value", hints:"value",
|
||||
"explore:session": { replay:"value", session:"value", "env-file":"value", "bundle-id":"value", "app-name":"value", "app-version":"value", output:"value", platform:"value", controller:"value", device:"value", "launch-url":"value", hints:"value",
|
||||
"allow-destructive":"value", "max-duration-minutes":"value", "max-screens":"value", "max-actions":"value", provider:"value", model:"value", owner:"value", project:"value",
|
||||
upload:"boolean", "expires-in":"value", alias:"value", "no-open":"boolean", port:"value" },
|
||||
"ci:report": { input:"value", output:"value", target:"value", platform:"value" },
|
||||
|
||||
@@ -7,6 +7,7 @@ import { assertHostingExport, deployExplorationReport, zipReportDirectory } from
|
||||
import { keepReports } from "./report-commands.js";
|
||||
import { warnIgnoredExpiry } from "../config/explore-config.js";
|
||||
import { argumentError, flag, flags, has, nonNegativeInteger, oneOf, output, positional, positiveInteger } from "./args.js";
|
||||
import { readReplayPlan } from "../binary/replay.js";
|
||||
|
||||
|
||||
/** `--alias NAME` plus a fixed token from EXPLORE_PREVIEW_TOKEN: the hosted link stays the same from one run to the next (validated by the deploy). */
|
||||
@@ -49,6 +50,7 @@ export async function exploreBinary(): Promise<void> {
|
||||
...(flag("max-duration-minutes") ? { maxDurationMinutes: positiveInteger("max-duration-minutes") } : {}),
|
||||
...(flag("max-screens") ? { maxScreens: positiveInteger("max-screens") } : {}),
|
||||
...(flag("max-actions") ? { maxActions: positiveInteger("max-actions") } : {}),
|
||||
...(flag("replay") ? { replay: await readReplayPlan(resolve(process.cwd(), flag("replay")!)) } : {}),
|
||||
});
|
||||
say(`exploration ${result.exploration.stopReason}: ${result.exploration.screens} screens, ${result.exploration.observations} captures, ${result.exploration.actions} actions`);
|
||||
const report = await writeExplorationReport(result, join(outputDirectory, "report"));
|
||||
@@ -113,6 +115,7 @@ export async function exploreSession(): Promise<void> {
|
||||
...(flag("max-duration-minutes") ? { maxDurationMinutes: positiveInteger("max-duration-minutes") } : {}),
|
||||
...(flag("max-screens") ? { maxScreens: positiveInteger("max-screens") } : {}),
|
||||
...(flag("max-actions") ? { maxActions: positiveInteger("max-actions") } : {}),
|
||||
...(flag("replay") ? { replay: await readReplayPlan(resolve(process.cwd(), flag("replay")!)) } : {}),
|
||||
});
|
||||
say(`exploration ${result.exploration.stopReason}: ${result.exploration.screens} screens, ${result.exploration.observations} captures, ${result.exploration.actions} actions`);
|
||||
const report = await writeExplorationReport(result, join(outputDirectory, "report"));
|
||||
|
||||
@@ -56,6 +56,7 @@ const BINARY = `Prebuilt apps (no source needed; runs with your local claude or
|
||||
and the model and the report only see the reference)
|
||||
--max-duration-minutes N --max-screens N --max-actions N --provider anthropic|openai --model ID
|
||||
--owner ACCOUNT --project SLUG --allow-destructive "Label,Other label"
|
||||
--replay FILE (takes the steps in FILE instead of a model's, so every run and device takes the same path; no model access needed, and not with --provider, --model or --hints)
|
||||
--alias NAME (one EAS Hosting host per app that always serves the newest run; with EXPLORE_PREVIEW_TOKEN
|
||||
set to a fixed 32-character token, the hosted link is the same every run)
|
||||
(iOS needs a simulator build; a device .ipa and Android .aab are rejected before any device starts)
|
||||
|
||||
+11
-3
@@ -8,6 +8,7 @@ import { compareTitleMarkdown, projectReviewPresentation, type CompareReviewPres
|
||||
import { renderPublicComment, platformSectionMerge, reviewChangeCount, type PublicCommentState } from "./pr-comment-body.js";
|
||||
import { isTargetId, type ExplorePlatform } from "../config/explore-config.js";
|
||||
import { upsertStickyComment } from "./pr-comment.js";
|
||||
import { retryGitHubLookup } from "./github-lookup.js";
|
||||
import { previewLinks, viewerLinks } from "./viewer-links.js";
|
||||
import type { PublicReview } from "../contracts/capture.js";
|
||||
import { CiError, toCiError } from "../shared/ci-errors.js";
|
||||
@@ -136,6 +137,8 @@ export async function publishCiReportComment(options: {
|
||||
preview?: { url: string; expiresAt: number | null };
|
||||
/** Set by `ci:deploy` when the hosted preview failed: the comment falls back to the central Viewer and the ZIP. */
|
||||
previewFailed?: boolean;
|
||||
/** Pause between GitHub lookups that may succeed later; tests replace it so retries take no real time. */
|
||||
sleep?: (milliseconds: number) => Promise<void>;
|
||||
}) {
|
||||
const environment = options.environment ?? process.env; const transport = options.transport ?? fetch;
|
||||
const input = await readInput(options.inputPath); const review = input.publicReview; const pr = review.pullRequest;
|
||||
@@ -186,16 +189,21 @@ export async function publishCiReportComment(options: {
|
||||
catch (error) { throw new CiError({ code: "GITHUB_RESPONSE_INVALID", stage: "publication",
|
||||
message: "GitHub returned invalid report metadata.", nextAction: "Rerun publication; if the response remains invalid, inspect the GitHub metadata request.", cause: error }); }
|
||||
};
|
||||
const artifact = await api(`actions/artifacts/${new URL(options.artifactUrl).pathname.split("/").at(-1)}`);
|
||||
// A lookup is made again when GitHub may answer it later: no answer, a 5xx, or a 404 from the Actions API, which may
|
||||
// not list a just-uploaded artifact yet. A bad token, a missing permission or a rate limit fails at once, as before.
|
||||
const lookup = (path: string) => retryGitHubLookup(() => api(path), error => error instanceof CiError
|
||||
&& (error.code === "GITHUB_NETWORK_FAILED" || error.code === "GITHUB_REQUEST_FAILED" && error.retryable
|
||||
|| error.code === "GITHUB_RESOURCE_NOT_FOUND" && path.startsWith("actions/")), options.sleep);
|
||||
const artifact = await lookup(`actions/artifacts/${new URL(options.artifactUrl).pathname.split("/").at(-1)}`);
|
||||
if (artifact.expired || artifact.name !== `explore-review-${review.runId}-${review.runAttempt}${target ? `-${target}` : ""}` || String(artifact.workflow_run?.id) !== review.runId) {
|
||||
throw new CiError({ code: artifact.expired ? "REPORT_ARTIFACT_EXPIRED" : "REPORT_ARTIFACT_MISMATCH", stage: "publication",
|
||||
message: "The uploaded report artifact is unavailable or belongs to another run",
|
||||
nextAction: artifact.expired ? "Rerun Explore to upload a fresh report artifact." : "Pass the final report artifact from this workflow run and attempt." });
|
||||
}
|
||||
const attempt = await api(`actions/runs/${review.runId}/attempts/${review.runAttempt}`);
|
||||
const attempt = await lookup(`actions/runs/${review.runId}/attempts/${review.runAttempt}`);
|
||||
if (String(attempt.id) !== review.runId || String(attempt.run_attempt) !== review.runAttempt) throw new CiError({ code: "REPORT_RUN_MISMATCH", stage: "publication",
|
||||
message: "Report run attempt mismatch", nextAction: "Publish the artifact and report input from the same current workflow attempt." });
|
||||
const current = await api(`pulls/${pr.number}`);
|
||||
const current = await lookup(`pulls/${pr.number}`);
|
||||
if (current.state !== "open" || current.head?.repo?.full_name !== pr.repository || current.head?.ref !== pr.head.ref) {
|
||||
throw new CiError({ code: "PR_CHANGED", stage: "publication", message: "PR closed or changed branches before the report artifact was ready",
|
||||
nextAction: "Run Explore for the current PR head and base before publishing a ready report." });
|
||||
|
||||
@@ -15,7 +15,7 @@ export type FailureCommentOptions = {
|
||||
runAttempt: string;
|
||||
/** The directory the failure job downloaded diagnostics artifacts into (`<stage>/<artifact>/…/error.json`). */
|
||||
diagnosticsPath?: string;
|
||||
/** The failed target's id; otherwise the one the first diagnostics artifact's name carries. */
|
||||
/** The failed target's id; otherwise every target the diagnostics artifacts name. */
|
||||
target?: string;
|
||||
/** What callers from before targets pass: a platform is the id of its default target. */
|
||||
platform?: ExplorePlatform;
|
||||
@@ -25,6 +25,8 @@ export type FailureCommentOptions = {
|
||||
};
|
||||
|
||||
type Diagnostic = { code: string; stage: string; message: string; nextAction: string };
|
||||
/** A failed target's diagnostic. `target` is absent when neither the artifact's name nor the file names one. */
|
||||
export type LocatedFailure = { diagnostic?: Diagnostic; target?: string; platform?: ExplorePlatform };
|
||||
const SHA = /^[0-9a-f]{40}$/;
|
||||
// `explore-<kind>-<run>-<attempt>-<target>`: the kind has no digits, so the first number is the run and the rest is the target id.
|
||||
const ARTIFACT_DIR = /^explore-[a-z-]+-\d+-\d+-([a-z][a-z0-9-]{0,31})$/;
|
||||
@@ -34,11 +36,14 @@ const MAX_DIAGNOSTIC_BYTES = 32_768;
|
||||
const CODE = /^[A-Z][A-Z0-9_]{1,63}$/;
|
||||
const STAGE = /^[a-z][a-z0-9-]{0,63}$/;
|
||||
|
||||
function parseDiagnostic(text: string, stage: string): Diagnostic | undefined {
|
||||
function parseJson(text: string): Record<string, unknown> | undefined {
|
||||
let parsed: unknown;
|
||||
try { parsed = JSON.parse(text); } catch { return undefined; }
|
||||
if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) return undefined;
|
||||
const value = parsed as Record<string, unknown>;
|
||||
return parsed && typeof parsed === "object" && !Array.isArray(parsed) ? parsed as Record<string, unknown> : undefined;
|
||||
}
|
||||
|
||||
function parseDiagnostic(value: Record<string, unknown> | undefined, stage: string): Diagnostic | undefined {
|
||||
if (!value) return undefined;
|
||||
const field = (name: string, max: number) => typeof value[name] === "string" && (value[name] as string).trim() && (value[name] as string).length <= max ? value[name] as string : undefined;
|
||||
const code = field("code", 64), message = field("message", 4000), nextAction = field("nextAction", 4000), stageName = field("stage", 64) ?? stage;
|
||||
if (!code || !CODE.test(code) || !message || !nextAction || !STAGE.test(stageName)) return undefined;
|
||||
@@ -46,32 +51,51 @@ function parseDiagnostic(text: string, stage: string): Diagnostic | undefined {
|
||||
return { code, stage: stageName, message, nextAction };
|
||||
}
|
||||
|
||||
/** Reads one error.json; `named` is the target its artifact directory names, else the one the file records. */
|
||||
async function readFailure(path: string, stage: string, named: string | undefined): Promise<LocatedFailure | undefined> {
|
||||
const info = await lstat(path).catch(() => undefined);
|
||||
if (!info) return undefined;
|
||||
const located = (target: string | undefined): LocatedFailure => ({ ...(target ? { target } : {}), ...(target === "ios" || target === "android" ? { platform: target as ExplorePlatform } : {}) });
|
||||
if (!info.isFile() || info.size > MAX_DIAGNOSTIC_BYTES) return located(named);
|
||||
const value = parseJson(await readFile(path, "utf8"));
|
||||
const target = named ?? (isTargetId(value?.target) ? value.target : undefined);
|
||||
const diagnostic = parseDiagnostic(value, stage);
|
||||
return diagnostic ? { diagnostic, ...located(target) } : located(target);
|
||||
}
|
||||
|
||||
/**
|
||||
* The error.json a failed job left behind and the target its artifact name carries (`ios` or `android` for a config
|
||||
* without targets, and for artifacts of versions before targets). A report failure's diagnostic takes precedence over
|
||||
* capture's; a present but unreadable file yields the generic failure rather than an earlier stage's error, and only
|
||||
* Every failed target's error.json and the target it belongs to (`ios` or `android` for a config without targets, and
|
||||
* for artifacts of versions before targets). actions/download-artifact puts each artifact a pattern matches in a
|
||||
* directory named after it, except when the pattern matches exactly one: that one lands in the stage's directory
|
||||
* itself, and the file names its target. A report failure's diagnostic takes precedence over its target's capture
|
||||
* diagnostic; a present but unreadable file yields the generic failure rather than an earlier stage's error, and only
|
||||
* regular files count (never symlinks out of the artifact). `platform` is set when the target id is a platform's.
|
||||
*/
|
||||
export async function locateFailureDiagnostic(root: string): Promise<{ diagnostic?: Diagnostic; target: string; platform?: ExplorePlatform } | undefined> {
|
||||
export async function locateFailureDiagnostics(root: string): Promise<LocatedFailure[]> {
|
||||
const failures: LocatedFailure[] = [];
|
||||
const seen = new Set<string>();
|
||||
for (const [stage, file] of [["report", "error.json"], ["capture", join("explore-diagnostics", "error.json")]] as const) {
|
||||
const entries = await readdir(join(root, stage), { withFileTypes: true }).catch(() => []);
|
||||
for (const entry of entries.filter(entry => entry.isDirectory() && artifactTarget(entry.name)).sort((a, b) => a.name.localeCompare(b.name))) {
|
||||
const path = join(root, stage, entry.name, file);
|
||||
const info = await lstat(path).catch(() => undefined);
|
||||
if (!info) continue;
|
||||
const target = artifactTarget(entry.name)!;
|
||||
const located: { target: string; platform?: ExplorePlatform } = { target, ...(target === "ios" || target === "android" ? { platform: target as ExplorePlatform } : {}) };
|
||||
if (!info.isFile() || info.size > MAX_DIAGNOSTIC_BYTES) return located;
|
||||
const diagnostic = parseDiagnostic(await readFile(path, "utf8"), stage);
|
||||
return diagnostic ? { diagnostic, ...located } : located;
|
||||
const candidates = [...entries.filter(entry => entry.isDirectory() && artifactTarget(entry.name)).sort((a, b) => a.name.localeCompare(b.name))
|
||||
.map(entry => ({ path: join(root, stage, entry.name, file), named: artifactTarget(entry.name) })), { path: join(root, stage, file), named: undefined }];
|
||||
for (const { path, named } of candidates) {
|
||||
const located = await readFailure(path, stage, named);
|
||||
if (!located || seen.has(located.target ?? "")) continue;
|
||||
seen.add(located.target ?? "");
|
||||
failures.push(located);
|
||||
}
|
||||
}
|
||||
return undefined;
|
||||
return failures;
|
||||
}
|
||||
|
||||
/** The first failure locateFailureDiagnostics finds: a report failure before a capture failure. */
|
||||
export async function locateFailureDiagnostic(root: string): Promise<LocatedFailure | undefined> {
|
||||
return (await locateFailureDiagnostics(root))[0];
|
||||
}
|
||||
|
||||
/**
|
||||
* The failure job's comment: a job died outside Explore's own progress comments (install, checkout, a crash
|
||||
* before the pipeline posted), so the sticky comment gets a failed record for that target from the same
|
||||
* before the pipeline posted), so the sticky comment gets a failed record for each failed target from the same
|
||||
* renderer every other writer uses. Nothing is posted when the PR is closed; a PR that moved on is marked
|
||||
* superseded so the failure lands under previous runs.
|
||||
*/
|
||||
@@ -94,27 +118,31 @@ export async function publishFailureComment(options: FailureCommentOptions): Pro
|
||||
return { posted: false, reason: "The PR is no longer an open same-repository PR." };
|
||||
}
|
||||
const superseded = pr.head?.sha !== options.headSha || pr.base?.sha !== options.baseSha;
|
||||
const located = options.diagnosticsPath ? await locateFailureDiagnostic(options.diagnosticsPath) : undefined;
|
||||
const target = requested ?? located?.target;
|
||||
// The failure job knows a target by its id alone; the comment's own record for that id supplies its label and platform.
|
||||
const platform: ExplorePlatform | undefined = target === "ios" || target === "android" ? target : undefined;
|
||||
const configPath = options.configPath ?? ".expo-explore/config.yaml";
|
||||
const now = Date.now();
|
||||
const diagnostic = located?.diagnostic;
|
||||
const state: PublicCommentState = {
|
||||
phase: "failed", mode: "changes", executionMode: "deterministic", configPath,
|
||||
pullRequest: { repositoryId: String(pr.base?.repo?.id ?? ""), repository: options.repository, number: options.pullNumber, title: String(pr.title ?? ""), url: String(pr.html_url ?? ""),
|
||||
base: { ref: String(pr.base?.ref ?? ""), sha: options.baseSha }, head: { ref: String(pr.head?.ref ?? ""), sha: options.headSha } },
|
||||
// No artifact URL, so no Viewer link: the target would only pick a report that this failure never uploaded.
|
||||
links: viewerLinks({ repository: options.repository, headSha: options.headSha, runId: options.runId, runAttempt: options.runAttempt, configPath }),
|
||||
startedAt: now, updatedAt: now, artifactOnly: true,
|
||||
...(platform ? { build: { platform, easProfile: "" } } : {}),
|
||||
failure: { step: diagnostic?.stage ?? "workflow", message: diagnostic
|
||||
? `${diagnostic.code}: ${diagnostic.message} Next action: ${diagnostic.nextAction}`
|
||||
: "Explore could not finish this review. See the run for the error code, cause, and next action. Fix the reported issue and rerun Explore." },
|
||||
...(superseded ? { superseded: true } : {}),
|
||||
};
|
||||
await upsertStickyComment({ repository: options.repository, issueNumber: options.pullNumber, body: renderPublicComment(state, undefined, target),
|
||||
...platformSectionMerge(state, target), token, fetchImpl: transport });
|
||||
const located = options.diagnosticsPath ? await locateFailureDiagnostics(options.diagnosticsPath) : [];
|
||||
// Each failed target gets its own failed record: since one target's failed capture no longer stops the others'
|
||||
// reports (brentvatne/euxy#172), several targets of one run can fail in different jobs.
|
||||
const failures: LocatedFailure[] = requested !== undefined ? [{ ...(located.find(failure => failure.target === requested) ?? located[0]), target: requested }]
|
||||
: located.length ? located : [{}];
|
||||
for (const { target, diagnostic } of failures) {
|
||||
// The failure job knows a target by its id alone; the comment's own record for that id supplies its label and platform.
|
||||
const platform: ExplorePlatform | undefined = target === "ios" || target === "android" ? target : undefined;
|
||||
const configPath = options.configPath ?? ".expo-explore/config.yaml";
|
||||
const now = Date.now();
|
||||
const state: PublicCommentState = {
|
||||
phase: "failed", mode: "changes", executionMode: "deterministic", configPath,
|
||||
pullRequest: { repositoryId: String(pr.base?.repo?.id ?? ""), repository: options.repository, number: options.pullNumber, title: String(pr.title ?? ""), url: String(pr.html_url ?? ""),
|
||||
base: { ref: String(pr.base?.ref ?? ""), sha: options.baseSha }, head: { ref: String(pr.head?.ref ?? ""), sha: options.headSha } },
|
||||
// No artifact URL, so no Viewer link: the target would only pick a report that this failure never uploaded.
|
||||
links: viewerLinks({ repository: options.repository, headSha: options.headSha, runId: options.runId, runAttempt: options.runAttempt, configPath }),
|
||||
startedAt: now, updatedAt: now, artifactOnly: true,
|
||||
...(platform ? { build: { platform, easProfile: "" } } : {}),
|
||||
failure: { step: diagnostic?.stage ?? "workflow", message: diagnostic
|
||||
? `${diagnostic.code}: ${diagnostic.message} Next action: ${diagnostic.nextAction}`
|
||||
: "Explore could not finish this review. See the run for the error code, cause, and next action. Fix the reported issue and rerun Explore." },
|
||||
...(superseded ? { superseded: true } : {}),
|
||||
};
|
||||
await upsertStickyComment({ repository: options.repository, issueNumber: options.pullNumber, body: renderPublicComment(state, undefined, target),
|
||||
...platformSectionMerge(state, target), token, fetchImpl: transport });
|
||||
}
|
||||
return { posted: true, ...(superseded ? { superseded: true } : {}) };
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
/**
|
||||
* Pauses between attempts of a GitHub lookup that may succeed later, 45 seconds in all. GitHub's Actions API is
|
||||
* eventually consistent just after an upload: in brentvatne/euxy's review run 39348956443, the duo-closed report job's
|
||||
* `actions/artifacts/<id>` answered 404 for the artifact that job had just uploaded, while the other four targets'
|
||||
* jobs found theirs.
|
||||
*/
|
||||
const GITHUB_LOOKUP_RETRY_DELAYS_MS = [3_000, 6_000, 12_000, 24_000] as const;
|
||||
|
||||
/**
|
||||
* Runs a read-only GitHub lookup again after each pause while `transient` says its failure may clear on its own. The
|
||||
* caller decides what is transient; any other failure, or the last one, is thrown as it is.
|
||||
*/
|
||||
export async function retryGitHubLookup<T>(lookup: () => Promise<T>, transient: (error: unknown) => boolean,
|
||||
sleep: (milliseconds: number) => Promise<void> = milliseconds => new Promise<void>(done => setTimeout(done, milliseconds))): Promise<T> {
|
||||
for (let retry = 0; ; retry += 1) {
|
||||
try { return await lookup(); }
|
||||
catch (error) {
|
||||
const delayMs = GITHUB_LOOKUP_RETRY_DELAYS_MS[retry];
|
||||
if (delayMs === undefined || !transient(error)) throw error;
|
||||
// A lookup that succeeds later would otherwise leave no trace of the failure in the job log.
|
||||
process.stderr.write(`GitHub lookup failed (${(error instanceof Error ? error.message : String(error)).split("\n", 1)[0]}); trying again in ${delayMs / 1000} s\n`);
|
||||
await sleep(delayMs);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -7,6 +7,7 @@ import { Uint8ArrayReader, Uint8ArrayWriter, ZipWriter, configure } from "@zip.j
|
||||
import { loadReport, MAX_METADATA_BYTES } from "./agent-api.js";
|
||||
import { MAX_ASSET_BYTES, manifestBody, PREVIEW_ASSET } from "./preview-manifest.js";
|
||||
import { publishCiReportComment, readCiReportInput, type CiReportInput } from "./artifact.js";
|
||||
import { retryGitHubLookup } from "./github-lookup.js";
|
||||
import { readZipDirectory, readZipEntry } from "./zip-reader.js";
|
||||
import { reviewChangeCount, reviewDevice } from "./pr-comment-body.js";
|
||||
import { isTargetId, warnIgnoredExpiry, type ExplorePlatform } from "../config/explore-config.js";
|
||||
@@ -54,7 +55,7 @@ export type PreviewDeployOptions = (PreviewReportInput | {
|
||||
environment?: NodeJS.ProcessEnv;
|
||||
transport?: typeof fetch;
|
||||
run?: CommandRunner;
|
||||
/** Pause between `eas deploy` attempts; tests replace it so retries take no real time. */
|
||||
/** Pause between `eas deploy` attempts and between GitHub lookups that may succeed later; tests replace it so retries take no real time. */
|
||||
sleep?: (milliseconds: number) => Promise<void>;
|
||||
/** The preview export (client/ and server/); defaults to the one shipped in this package. */
|
||||
exportPath?: string;
|
||||
@@ -386,7 +387,7 @@ export async function deployPreview(options: PreviewDeployOptions): Promise<Prev
|
||||
if (pr.origin !== "compare") for (const report of reports) {
|
||||
try {
|
||||
await publishCiReportComment({ inputPath: report.entry.inputPath, artifactUrl: report.entry.artifactUrl, environment, transport,
|
||||
...commentTarget(report), previewFailed: true });
|
||||
...commentTarget(report), previewFailed: true, ...(options.sleep ? { sleep: options.sleep } : {}) });
|
||||
} catch { /* the deployment failure is the one to report */ }
|
||||
}
|
||||
throw error;
|
||||
@@ -398,7 +399,7 @@ export async function deployPreview(options: PreviewDeployOptions): Promise<Prev
|
||||
let headSha = pr.head.sha;
|
||||
if (pr.origin !== "compare") for (const report of reports) {
|
||||
const published = await publishCiReportComment({ inputPath: report.entry.inputPath, artifactUrl: report.entry.artifactUrl, environment, transport,
|
||||
...commentTarget(report), preview: { url: previewUrl, expiresAt: null } });
|
||||
...commentTarget(report), preview: { url: previewUrl, expiresAt: null }, ...(options.sleep ? { sleep: options.sleep } : {}) });
|
||||
headSha = published.headSha;
|
||||
}
|
||||
return { previewUrl, expiresAt: null, deploymentId: hosted.deploymentId, deploymentUrl: hosted.deploymentUrl,
|
||||
@@ -435,7 +436,9 @@ async function writeCompareSummary(environment: NodeJS.ProcessEnv, comparison: C
|
||||
}
|
||||
|
||||
type HostedReportInput = { zip: Uint8Array; sha256: string; file: string; query: string };
|
||||
export type HostedDeployment = { previewUrl: string; expiresAt: string | null; deploymentId: string; deploymentUrl: string; aliasUrl?: string; project: string; owner: string };
|
||||
export type HostedDeployment = { previewUrl: string; expiresAt: string | null; deploymentId: string; deploymentUrl: string; aliasUrl?: string;
|
||||
/** The link is the alias, which still served an earlier deployment when the wait for it ran out. */
|
||||
aliasBehind?: true; project: string; owner: string };
|
||||
|
||||
/** EAS Hosting alias names: lowercase slugs, as `eas deploy --alias` normalises them. */
|
||||
export const HOSTING_ALIAS = /^[a-z0-9][a-z0-9-]{0,38}[a-z0-9]$/;
|
||||
@@ -495,6 +498,13 @@ async function deployReports(options: {
|
||||
alias?: string;
|
||||
/** A caller-chosen `/p/<token>`; with `alias`, the hosted link is identical from one run to the next. */
|
||||
token?: string;
|
||||
/** How long the alias has to serve this deployment once the deployment does; `verifyTimeoutMs` by default. */
|
||||
aliasWaitMs?: number;
|
||||
/**
|
||||
* Link the alias even when it still serves an earlier deployment after `aliasWaitMs`, for a link whose readers are
|
||||
* told it can lag, rather than the deployment's own host.
|
||||
*/
|
||||
linkBehindAlias?: boolean;
|
||||
sleep?: (milliseconds: number) => Promise<void>;
|
||||
}): Promise<HostedDeployment> {
|
||||
const { reports, project, environment, run, transport, now, random } = options;
|
||||
@@ -571,7 +581,8 @@ async function deployReports(options: {
|
||||
throw deployError("PREVIEW_DEPLOY_FAILED", `EAS Hosting deployed ${deploymentUrl.origin} but did not report the alias ${options.alias}.`,
|
||||
"Check the deployment's aliases in the EAS Hosting dashboard and rerun.", { retryable: true, details: { project, owner, alias: options.alias } });
|
||||
}
|
||||
const verify = (origin: string, alias = false) => verifyDeployment({ origin, token, transport, now, timeoutMs: options.verifyTimeoutMs, alias,
|
||||
const verify = (origin: string, alias = false) => verifyDeployment({ origin, token, transport, now, alias,
|
||||
timeoutMs: alias ? options.aliasWaitMs ?? options.verifyTimeoutMs : options.verifyTimeoutMs,
|
||||
reports: reports.map((report, index) => ({ query: report.query, ...written[index]! })),
|
||||
...(listing ? { listing: JSON.stringify(listing.map(({ path: _path, ...rest }) => rest)) } : {}) });
|
||||
const seconds = (milliseconds: number) => `${Math.round(milliseconds / 1000)} s after eas deploy returned`;
|
||||
@@ -581,7 +592,9 @@ async function deployReports(options: {
|
||||
// taken longer than the whole budget (every verification failure of 2026-10-14 was the alias, with the deployment
|
||||
// serving in 1 s). The deployment is verified and immutable, so when the alias is still behind the pull request
|
||||
// links the deployment instead of failing the job; the alias catches up on its own and the next push relinks it.
|
||||
// With `linkBehindAlias` it links the alias anyway, and its readers are told the link can lag.
|
||||
let linkOrigin = deploymentUrl.origin;
|
||||
let aliasBehind = false;
|
||||
if (aliasUrl) {
|
||||
try {
|
||||
const alias = await verify(aliasUrl.origin, true);
|
||||
@@ -589,12 +602,16 @@ async function deployReports(options: {
|
||||
linkOrigin = aliasUrl.origin;
|
||||
} catch (error) {
|
||||
if ((error as { code?: string }).code !== "PREVIEW_ALIAS_BEHIND") throw error;
|
||||
process.stderr.write(`::warning::${(error as Error).message} The pull request links the deployment ${deploymentUrl.origin} instead.\n`);
|
||||
aliasBehind = Boolean(options.linkBehindAlias);
|
||||
if (aliasBehind) linkOrigin = aliasUrl.origin;
|
||||
process.stderr.write(`::warning::${(error as Error).message} ${aliasBehind
|
||||
? `The pull request links it anyway, until it catches up, beside the deployment ${deploymentUrl.origin}.`
|
||||
: `The pull request links the deployment ${deploymentUrl.origin} instead.`}\n`);
|
||||
}
|
||||
}
|
||||
const previewUrl = `${linkOrigin}/p/${token}`;
|
||||
return { previewUrl, expiresAt: null, deploymentId: deployment.identifier!, deploymentUrl: deploymentUrl.origin,
|
||||
...(aliasUrl ? { aliasUrl: aliasUrl.origin } : {}), project, owner };
|
||||
...(aliasUrl ? { aliasUrl: aliasUrl.origin } : {}), ...(aliasBehind ? { aliasBehind: true as const } : {}), project, owner };
|
||||
} finally {
|
||||
await rm(work, { recursive: true, force: true });
|
||||
}
|
||||
@@ -668,8 +685,20 @@ export type FixturePreviewOptions = {
|
||||
random?: (bytes: number) => Uint8Array;
|
||||
onSecret?: (secret: string) => void;
|
||||
verifyTimeoutMs?: number;
|
||||
/** How long the alias has to serve the new deployment before the link is the alias anyway; FIXTURE_ALIAS_WAIT_MS by default. */
|
||||
aliasWaitMs?: number;
|
||||
};
|
||||
|
||||
/**
|
||||
* How long a fixture preview waits for its alias. An edge of EAS Hosting that served an alias keeps serving the
|
||||
* deployment it named for about five minutes (307–314 s, measured 2026-10-19 redeploying back to back from one machine),
|
||||
* so a deploy whose check reaches an edge that served the alias in the last five minutes, to the previous deploy's check
|
||||
* or to a reviewer, finds it behind; otherwise it has moved within seconds. Waiting the whole verification budget for
|
||||
* that held a third of the pull requests' deploy jobs for three minutes, only to link the deployment instead. The pull
|
||||
* request's comment says when the alias is behind.
|
||||
*/
|
||||
export const FIXTURE_ALIAS_WAIT_MS = 20_000;
|
||||
|
||||
/**
|
||||
* Host fixed reports behind a fixed alias with this checkout's Viewer: the Explore repository's own pull requests
|
||||
* preview their Viewer changes on real data. No GitHub token, no expiry; each run replaces what the alias serves.
|
||||
@@ -697,6 +726,7 @@ export async function deployFixturePreview(options: FixturePreviewOptions): Prom
|
||||
projectHint: "Give EXPO_TOKEN's account permission to create projects, or pass --project with an existing slug.",
|
||||
exportPath, environment, run: options.run ?? defaultRun, ...(options.sleep ? { sleep: options.sleep } : {}), transport: options.transport ?? fetch, now: options.now ?? Date.now, random,
|
||||
...(options.onSecret ? { onSecret: options.onSecret } : {}), verifyTimeoutMs: options.verifyTimeoutMs ?? 180_000, alias: options.alias,
|
||||
aliasWaitMs: options.aliasWaitMs ?? FIXTURE_ALIAS_WAIT_MS, linkBehindAlias: true,
|
||||
...(options.token ? { token: options.token } : {}) });
|
||||
}
|
||||
|
||||
@@ -760,23 +790,43 @@ export async function deployLocalReports(options: {
|
||||
/** explore-(capture|review)-<run>-<attempt>-<target id>; the id starts with a letter, so the run and attempt end unambiguously. */
|
||||
const ARTIFACT_DIRECTORY = /^explore-(capture|review)-\d+-\d+-([a-z][a-z0-9-]{0,31})$/;
|
||||
|
||||
/**
|
||||
* The target a lone artifact holds. actions/download-artifact puts each artifact a pattern matches in a directory named
|
||||
* after it, except when the pattern matches exactly one, which it extracts into the download path itself: then only the
|
||||
* report names its target (its platform for configs without targets).
|
||||
*/
|
||||
async function unnamedArtifactTarget(root: string, kind: "capture" | "review"): Promise<string | undefined> {
|
||||
const file = join(root, kind === "capture" ? "report-input.json" : "review.json");
|
||||
if (!(await lstat(file).catch(() => undefined))?.isFile()) return undefined;
|
||||
const runtime = kind === "capture" ? (await readCiReportInput(file)).publicReview.runtime
|
||||
: (JSON.parse(await readFile(file, "utf8")) as Partial<ArtifactReport>).review?.runtime;
|
||||
const id = readTarget(runtime?.target)?.id ?? runtime?.platform;
|
||||
return isTargetId(id) ? id : undefined;
|
||||
}
|
||||
|
||||
/**
|
||||
* The fan-in deploy job's inputs: actions/download-artifact puts each explore-capture-<run>-<attempt>-<target>
|
||||
* directory under --inputs and each explore-review-… directory under --reports (the target is the platform for
|
||||
* configs without targets). Pairs them by target, in the order the run's review lists its targets, and looks up each
|
||||
* report artifact's URL on the run, since matrix jobs cannot hand their artifact URLs forward.
|
||||
* report artifact's URL on the run, since matrix jobs cannot hand their artifact URLs forward. A target whose capture
|
||||
* failed uploaded no capture artifact, and one whose report job failed no report artifact: the preview serves the
|
||||
* targets that have both, and the review workflow's failure job names the others on the comment.
|
||||
*/
|
||||
export async function collectPlatformReports(options: { inputsPath: string; reportsPath: string; environment?: NodeJS.ProcessEnv; transport?: typeof fetch }): Promise<PreviewReportInput[]> {
|
||||
export async function collectPlatformReports(options: { inputsPath: string; reportsPath: string; environment?: NodeJS.ProcessEnv; transport?: typeof fetch;
|
||||
/** Pause between artifact lookups that may succeed later; tests replace it so retries take no real time. */
|
||||
sleep?: (milliseconds: number) => Promise<void> }): Promise<PreviewReportInput[]> {
|
||||
const environment = options.environment ?? process.env; const transport = options.transport ?? fetch;
|
||||
const directories = async (root: string, kind: "capture" | "review") => {
|
||||
const found = new Map<string, string>();
|
||||
for (const name of (await readdir(root)).sort()) {
|
||||
// A pattern that matched nothing leaves no directory behind.
|
||||
for (const name of (await readdir(root).catch(() => [] as string[])).sort()) {
|
||||
const match = ARTIFACT_DIRECTORY.exec(name);
|
||||
if (!match || match[1] !== kind || !isTargetId(match[2])) continue;
|
||||
if (found.has(match[2]!)) throw previewError("PREVIEW_REPORTS_INVALID", `Several ${kind} artifacts for ${match[2]} were downloaded`,
|
||||
"Download only this run attempt's artifacts into the --inputs and --reports directories.");
|
||||
found.set(match[2]!, join(root, name));
|
||||
}
|
||||
if (!found.size) { const id = await unnamedArtifactTarget(root, kind); if (id) found.set(id, root); }
|
||||
return found;
|
||||
};
|
||||
const inputs = await directories(options.inputsPath, "capture"); const reports = await directories(options.reportsPath, "review");
|
||||
@@ -787,8 +837,9 @@ export async function collectPlatformReports(options: { inputsPath: string; repo
|
||||
const entries: PreviewReportInput[] = [];
|
||||
for (const [id, inputDirectory] of inputs) {
|
||||
const reportPath = reports.get(id);
|
||||
if (!reportPath) throw previewError("PREVIEW_REPORTS_INCOMPLETE", `The ${id} capture has no report artifact to deploy`,
|
||||
"Rerun the workflow; the report job for that target did not upload its explore-review artifact.");
|
||||
// In brentvatne/euxy#172 (review run 39348956443) one target's failed job kept every other target's report off the
|
||||
// PR; a target without a report is left out of the preview instead.
|
||||
if (!reportPath) { process.stderr.write(`The ${id} capture has no report artifact (its report job failed), so the preview leaves it out.\n`); continue; }
|
||||
const inputPath = join(inputDirectory, "report-input.json");
|
||||
const runtime = (await readCiReportInput(inputPath)).publicReview.runtime;
|
||||
// A report from before targets names only its platform, and its artifact is named after it.
|
||||
@@ -798,6 +849,8 @@ export async function collectPlatformReports(options: { inputsPath: string; repo
|
||||
const target = named ?? (id === "ios" || id === "android" ? platformTarget(id) : { id, platform: runtime.platform ?? "ios", label: id });
|
||||
entries.push({ ...(id === target.platform ? { platform: target.platform } : {}), target, inputPath, reportPath, artifactUrl: "" });
|
||||
}
|
||||
if (!entries.length) throw previewError("PREVIEW_REPORTS_INCOMPLETE", "No target's capture has a report artifact to deploy",
|
||||
"Rerun the workflow; the report jobs did not upload their explore-review artifacts.");
|
||||
// Config order, as the review lists its targets (or, before targets, its platforms); directory order otherwise.
|
||||
const listed = (await readCiReportInput(entries[0]!.inputPath)).publicReview.runtime;
|
||||
const order: string[] = listed.targets?.map(target => target.id) ?? listed.platforms ?? [];
|
||||
@@ -812,14 +865,22 @@ export async function collectPlatformReports(options: { inputsPath: string; repo
|
||||
for (const entry of entries) {
|
||||
const name = `explore-review-${review.runId}-${review.runAttempt}-${entry.target!.id}`;
|
||||
const url = `https://api.github.com/repos/${repository}/actions/runs/${review.runId}/artifacts?per_page=100&name=${encodeURIComponent(name)}`;
|
||||
const response = await transport(url, { headers: { accept: "application/vnd.github+json", authorization: `Bearer ${environment.GITHUB_TOKEN ?? ""}`,
|
||||
"x-github-api-version": "2022-11-28" }, signal: AbortSignal.timeout(60_000) });
|
||||
const body = response.ok ? await response.json() as { artifacts?: Array<{ id?: unknown; name?: unknown; expired?: unknown }> } : undefined;
|
||||
const artifact = body?.artifacts?.find(candidate => candidate.name === name && candidate.expired !== true);
|
||||
if (!artifact || typeof artifact.id !== "number" || !Number.isSafeInteger(artifact.id) || artifact.id <= 0) {
|
||||
throw deployError("REPORT_ARTIFACT_MISSING", `The run has no artifact named ${name} (HTTP ${response.status}).`,
|
||||
"Rerun the workflow so every target's report job uploads its artifact before the deploy job runs.", { retryable: true });
|
||||
}
|
||||
// The run's artifact list can lag an upload, as the artifact lookup of a report job's publication does, so an
|
||||
// empty list, a 404, a 5xx or no answer is looked up again; a bad token or a missing permission fails at once.
|
||||
const artifact = await retryGitHubLookup(async () => {
|
||||
const response = await transport(url, { headers: { accept: "application/vnd.github+json", authorization: `Bearer ${environment.GITHUB_TOKEN ?? ""}`,
|
||||
"x-github-api-version": "2022-11-28" }, signal: AbortSignal.timeout(60_000) });
|
||||
const body = response.ok ? await response.json() as { artifacts?: Array<{ id?: unknown; name?: unknown; expired?: unknown }> } : undefined;
|
||||
const found = body?.artifacts?.find(candidate => candidate.name === name && candidate.expired !== true);
|
||||
if (!found || typeof found.id !== "number" || !Number.isSafeInteger(found.id) || found.id <= 0) {
|
||||
throw deployError("REPORT_ARTIFACT_MISSING", `The run has no artifact named ${name} (HTTP ${response.status}).`,
|
||||
"Rerun the workflow so every target's report job uploads its artifact before the deploy job runs.", { retryable: true, details: { status: response.status } });
|
||||
}
|
||||
return found;
|
||||
}, error => {
|
||||
const status = error instanceof CiError ? error.details?.status : undefined;
|
||||
return !(error instanceof CiError) || typeof status === "number" && (status === 200 || status === 404 || status >= 500);
|
||||
}, options.sleep);
|
||||
entry.artifactUrl = `https://github.com/${repository}/actions/runs/${review.runId}/artifacts/${artifact.id}`;
|
||||
}
|
||||
return entries;
|
||||
|
||||
@@ -148,6 +148,12 @@ export async function reportCiError(error: unknown, options: {
|
||||
env?: NodeJS.ProcessEnv;
|
||||
secrets?: readonly string[];
|
||||
diagnosticsPath?: string;
|
||||
/**
|
||||
* The matrix target the failed command ran for, written into the diagnostics file. actions/download-artifact puts an
|
||||
* artifact in a directory named after it only when a pattern matches several, so the failure job cannot always read
|
||||
* the target from where the file lands.
|
||||
*/
|
||||
target?: string;
|
||||
write?: (value: string) => void;
|
||||
} = {}): Promise<CiErrorData> {
|
||||
const env = options.env ?? process.env;
|
||||
@@ -166,7 +172,7 @@ export async function reportCiError(error: unknown, options: {
|
||||
if (env.GITHUB_STEP_SUMMARY) outputs.push({ label: "job summary", operation: appendFile(env.GITHUB_STEP_SUMMARY, `${renderCiErrorSummary(error, renderOptions)}\n`) });
|
||||
if (options.diagnosticsPath) outputs.push({ label: "diagnostics file", operation: (async () => {
|
||||
await mkdir(dirname(options.diagnosticsPath!), { recursive: true });
|
||||
await writeFile(options.diagnosticsPath!, `${JSON.stringify(diagnostic, null, 2)}\n`);
|
||||
await writeFile(options.diagnosticsPath!, `${JSON.stringify(options.target ? { ...diagnostic, target: options.target } : diagnostic, null, 2)}\n`);
|
||||
})() });
|
||||
const results = await Promise.allSettled(outputs.map(output => output.operation));
|
||||
for (const [index, result] of results.entries()) {
|
||||
|
||||
@@ -219,8 +219,12 @@ jobs:
|
||||
${{ runner.temp }}/explore-review/agent-usage.jsonl
|
||||
retention-days: 7
|
||||
if-no-files-found: ignore
|
||||
# Each target's report runs once its own capture uploaded one, whatever the other targets' captures did, as in the
|
||||
# review workflow (brentvatne/euxy#172): needs.capture.result is the whole matrix's, so each leg looks for its own
|
||||
# artifact, and a target whose capture failed packages and links nothing. !cancelled() keeps a cancelled run stopped.
|
||||
report:
|
||||
needs: [targets, capture]
|
||||
if: needs.targets.result == 'success' && !cancelled()
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -229,19 +233,34 @@ jobs:
|
||||
timeout-minutes: 20
|
||||
permissions:
|
||||
contents: read
|
||||
outputs:
|
||||
# "true" from every leg that linked its report, so "true" once any did: the deploy job runs only then.
|
||||
published: ${{ steps.publish.outputs.published }}
|
||||
env:
|
||||
TARGET: ${{ matrix.target }}
|
||||
steps:
|
||||
# Downloading by name fails when the artifact is missing. A pattern that matches nothing downloads nothing and
|
||||
# succeeds, so only a download that went wrong fails this step; its one match is extracted into the path itself.
|
||||
- name: Download this target's captured review
|
||||
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
|
||||
with:
|
||||
pattern: explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.target }}
|
||||
path: ${{ runner.temp }}/explore-review
|
||||
- name: Check that this target's capture succeeded
|
||||
id: captured
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
if [[ -f "$RUNNER_TEMP/explore-review/report-input.json" ]]; then echo "found=true" >> "$GITHUB_OUTPUT"
|
||||
else echo "The $TARGET capture uploaded no review: its capture job failed."; fi
|
||||
- *setup-node
|
||||
- *install-explore
|
||||
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
|
||||
with:
|
||||
name: explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.target }}
|
||||
path: ${{ runner.temp }}/explore-review
|
||||
- name: Package the report
|
||||
if: steps.captured.outputs.found == 'true'
|
||||
shell: bash
|
||||
run: node "$TOOLS/dist/cli.js" ci:report --input "$RUNNER_TEMP/explore-review/report-input.json" --output "$RUNNER_TEMP/explore-report" --target "$TARGET"
|
||||
- name: Upload the report
|
||||
if: steps.captured.outputs.found == 'true'
|
||||
id: report
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
@@ -250,10 +269,15 @@ jobs:
|
||||
retention-days: 30
|
||||
if-no-files-found: error
|
||||
- name: Link the report from the run summary
|
||||
if: steps.captured.outputs.found == 'true'
|
||||
id: publish
|
||||
env:
|
||||
ARTIFACT_URL: ${{ steps.report.outputs.artifact-url }}
|
||||
shell: bash
|
||||
run: node "$TOOLS/dist/cli.js" ci:publish --input "$RUNNER_TEMP/explore-review/report-input.json" --artifact-url "$ARTIFACT_URL" --target "$TARGET"
|
||||
run: |
|
||||
set -euo pipefail
|
||||
node "$TOOLS/dist/cli.js" ci:publish --input "$RUNNER_TEMP/explore-review/report-input.json" --artifact-url "$ARTIFACT_URL" --target "$TARGET"
|
||||
echo "published=true" >> "$GITHUB_OUTPUT"
|
||||
- name: Upload report failure diagnostics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
@@ -264,9 +288,10 @@ jobs:
|
||||
if-no-files-found: ignore
|
||||
# Hosted report (opt-in, report.preview in config.yaml): one token-gated EAS Hosting deployment serving every target's report.
|
||||
# This is the only job after capture that holds EXPO_TOKEN; it writes the link to the run summary.
|
||||
# It runs once any target linked its report, and serves the targets that did; a failed target has no report to wait for.
|
||||
deploy:
|
||||
needs: [targets, capture, report]
|
||||
if: needs.capture.outputs.preview == 'eas'
|
||||
if: needs.report.outputs.published == 'true' && needs.capture.outputs.preview == 'eas' && !cancelled()
|
||||
runs-on: ubuntu-22.04
|
||||
timeout-minutes: 20
|
||||
permissions:
|
||||
@@ -275,7 +300,8 @@ jobs:
|
||||
steps:
|
||||
- *setup-node
|
||||
- *install-explore
|
||||
# One directory per target artifact (explore-capture-<run>-<attempt>-<target>, explore-review-<run>-<attempt>-<target>).
|
||||
# One directory per target artifact (explore-capture-<run>-<attempt>-<target>, explore-review-<run>-<attempt>-<target>),
|
||||
# or a lone artifact's files in the path itself; ci:deploy reads both.
|
||||
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
|
||||
with:
|
||||
pattern: explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-*
|
||||
|
||||
@@ -207,8 +207,14 @@ jobs:
|
||||
${{ runner.temp }}/explore-review/agent-usage.jsonl
|
||||
retention-days: 7
|
||||
if-no-files-found: ignore
|
||||
# Each target's report runs once its own capture uploaded one, whatever the other targets' captures did: in
|
||||
# brentvatne/euxy#172 (run 39348956443) one flaky simulator session failed one of five captures, and with the report
|
||||
# waiting on every capture the PR got no report at all. needs.capture.result is the whole matrix's, so each leg looks
|
||||
# for its own artifact instead; a target whose capture failed uploaded none, packages and publishes nothing here, and
|
||||
# is named by the failure job. !cancelled() lets the legs run after a failed capture leg, but not in a cancelled run.
|
||||
report:
|
||||
needs: [targets, capture]
|
||||
if: needs.targets.result == 'success' && !cancelled()
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -219,19 +225,34 @@ jobs:
|
||||
contents: read
|
||||
actions: read
|
||||
pull-requests: write
|
||||
outputs:
|
||||
# "true" from every leg that published, so "true" once any did: the deploy job runs only then.
|
||||
published: ${{ steps.publish.outputs.published }}
|
||||
env:
|
||||
TARGET: ${{ matrix.target }}
|
||||
steps:
|
||||
# Downloading by name fails when the artifact is missing. A pattern that matches nothing downloads nothing and
|
||||
# succeeds, so only a download that went wrong fails this step; its one match is extracted into the path itself.
|
||||
- name: Download this target's captured review
|
||||
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
|
||||
with:
|
||||
pattern: explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.target }}
|
||||
path: ${{ runner.temp }}/explore-review
|
||||
- name: Check that this target's capture succeeded
|
||||
id: captured
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
if [[ -f "$RUNNER_TEMP/explore-review/report-input.json" ]]; then echo "found=true" >> "$GITHUB_OUTPUT"
|
||||
else echo "The $TARGET capture uploaded no review: its capture job failed, and the failure job reports it."; fi
|
||||
- *setup-node
|
||||
- *install-explore
|
||||
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
|
||||
with:
|
||||
name: explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.target }}
|
||||
path: ${{ runner.temp }}/explore-review
|
||||
- name: Package hosted review bundle
|
||||
if: steps.captured.outputs.found == 'true'
|
||||
shell: bash
|
||||
run: node "$TOOLS/dist/cli.js" ci:report --input "$RUNNER_TEMP/explore-review/report-input.json" --output "$RUNNER_TEMP/explore-report" --target "$TARGET"
|
||||
- name: Upload hosted review bundle
|
||||
if: steps.captured.outputs.found == 'true'
|
||||
id: viewer
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
@@ -240,11 +261,16 @@ jobs:
|
||||
retention-days: 30
|
||||
if-no-files-found: error
|
||||
- name: Publish current PR hosted links
|
||||
if: steps.captured.outputs.found == 'true'
|
||||
id: publish
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ github.token }}
|
||||
ARTIFACT_URL: ${{ steps.viewer.outputs.artifact-url }}
|
||||
shell: bash
|
||||
run: node "$TOOLS/dist/cli.js" ci:publish --input "$RUNNER_TEMP/explore-review/report-input.json" --artifact-url "$ARTIFACT_URL" --target "$TARGET"
|
||||
run: |
|
||||
set -euo pipefail
|
||||
node "$TOOLS/dist/cli.js" ci:publish --input "$RUNNER_TEMP/explore-review/report-input.json" --artifact-url "$ARTIFACT_URL" --target "$TARGET"
|
||||
echo "published=true" >> "$GITHUB_OUTPUT"
|
||||
- name: Upload report failure diagnostics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
@@ -256,9 +282,10 @@ jobs:
|
||||
# Hosted preview (opt-in, report.preview in config.yaml): one token-gated EAS Hosting deployment per review, serving every target's report.
|
||||
# This is the only job after capture that holds EXPO_TOKEN; the report job stays credential-free and has already
|
||||
# published the Download report link, so a failed deployment leaves the comment on the download-and-drop flow.
|
||||
# It runs once any target published its report, and serves the targets that did; a failed target has no report to wait for.
|
||||
deploy:
|
||||
needs: [targets, capture, report]
|
||||
if: needs.capture.outputs.preview == 'eas'
|
||||
if: needs.report.outputs.published == 'true' && needs.capture.outputs.preview == 'eas' && !cancelled()
|
||||
runs-on: ubuntu-22.04
|
||||
timeout-minutes: 20
|
||||
permissions:
|
||||
@@ -268,7 +295,8 @@ jobs:
|
||||
steps:
|
||||
- *setup-node
|
||||
- *install-explore
|
||||
# One directory per target artifact (explore-capture-<run>-<attempt>-<target>, explore-review-<run>-<attempt>-<target>).
|
||||
# One directory per target artifact (explore-capture-<run>-<attempt>-<target>, explore-review-<run>-<attempt>-<target>),
|
||||
# or a lone artifact's files in the path itself; ci:deploy reads both.
|
||||
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
|
||||
with:
|
||||
pattern: explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-*
|
||||
@@ -317,6 +345,6 @@ jobs:
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# The diagnostics artifacts are data files from this run and attempt, never executable report code;
|
||||
# the first error.json names the failed target, and the comment keeps every other target's result.
|
||||
# The diagnostics artifacts are data files from this run and attempt, never executable report code; each
|
||||
# error.json names its failed target, which gets a failed record, and the comment keeps every other target's result.
|
||||
node "$TOOLS/dist/cli.js" ci:failure --pr "${PR_NUMBER:-0}" --head "${HEAD_SHA:-}" --base "${BASE_SHA:-}" --diagnostics "$RUNNER_TEMP/explore-failure"
|
||||
@@ -293,7 +293,7 @@ test("action rejects unsupported Node versions before installing tools", async t
|
||||
test("the deploy job is the only post-capture job that holds EXPO_TOKEN, and it runs only for a requested hosted preview", () => {
|
||||
const deploy = review.jobs.deploy;
|
||||
assert.deepEqual(deploy.needs, ["targets", "capture", "report"]);
|
||||
assert.equal(deploy.if, "needs.capture.outputs.preview == 'eas'");
|
||||
assert.equal(deploy.if, "needs.report.outputs.published == 'true' && needs.capture.outputs.preview == 'eas' && !cancelled()");
|
||||
assert.deepEqual(deploy.permissions, { contents: "read", actions: "read", "pull-requests": "write" });
|
||||
const step = deploy.steps.find(step => step.name === "Deploy the hosted preview and publish its Explore report links");
|
||||
assert.equal(step.env.EXPO_TOKEN, "${{ secrets.EXPO_TOKEN }}");
|
||||
@@ -305,7 +305,8 @@ test("the deploy job is the only post-capture job that holds EXPO_TOKEN, and it
|
||||
assert.deepEqual(downloads.map(step => step.with.pattern), ["explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-*", "explore-review-${{ github.run_id }}-${{ github.run_attempt }}-*"]);
|
||||
assert.ok(downloads.every(step => step.with.name === undefined && step.with["merge-multiple"] === undefined));
|
||||
assert.doesNotMatch(JSON.stringify(deploy), /OPENAI_API_KEY|ANTHROPIC_API_KEY/);
|
||||
assert.equal(review.jobs.report.outputs, undefined);
|
||||
// A report job hands forward only whether it published; its artifact URL is looked up again (matrix outputs keep one leg's value).
|
||||
assert.deepEqual(review.jobs.report.outputs, { published: "${{ steps.publish.outputs.published }}" });
|
||||
// capture:review writes preview=<hosting> to the step outputs from the reviewed config.
|
||||
assert.equal(review.jobs.capture.outputs.preview, "${{ steps.capture.outputs.preview }}");
|
||||
assert.match(review.jobs.capture.steps.find(step => step.id === "capture").run, /capture:review/);
|
||||
@@ -314,6 +315,48 @@ test("the deploy job is the only post-capture job that holds EXPO_TOKEN, and it
|
||||
assert.match(review.jobs.failure.if, /needs\.deploy\.result == 'failure'/);
|
||||
});
|
||||
|
||||
test("one target's failed capture keeps neither the other targets' reports nor the preview off the PR (brentvatne/euxy#172)", async t => {
|
||||
for (const workflow of [review, compare]) {
|
||||
const report = workflow.jobs.report;
|
||||
// A plain needs: [capture] skips every report once one capture leg fails; !cancelled() runs them, except in a cancelled run.
|
||||
assert.equal(report.if, "needs.targets.result == 'success' && !cancelled()");
|
||||
assert.deepEqual(report.needs, ["targets", "capture"]);
|
||||
const [download, check] = report.steps;
|
||||
assert.ok(download.uses.startsWith("actions/download-artifact@"));
|
||||
// A pattern without a wildcard names this leg's artifact alone, and matching nothing is not a failure, as a name is.
|
||||
assert.deepEqual(download.with, { pattern: "explore-capture-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.target }}", path: "${{ runner.temp }}/explore-review" });
|
||||
assert.equal(download["continue-on-error"], undefined, "a download that went wrong still fails the leg");
|
||||
assert.equal(check.id, "captured");
|
||||
const explore = report.steps.filter(step => /cli\.js" ci:(report|publish)/.test(step.run ?? "") || step.uses?.startsWith("actions/upload-artifact@") && step.if !== "always()");
|
||||
assert.equal(explore.length, 3);
|
||||
for (const step of explore) assert.equal(step.if, "steps.captured.outputs.found == 'true'", step.name);
|
||||
const publish = report.steps.find(step => step.id === "publish");
|
||||
assert.match(publish.run, /ci:publish[^\n]*\n\s*echo "published=true" >> "\$GITHUB_OUTPUT"/, "published only once ci:publish succeeded");
|
||||
assert.deepEqual(report.outputs, { published: "${{ steps.publish.outputs.published }}" });
|
||||
assert.equal(workflow.jobs.deploy.if, "needs.report.outputs.published == 'true' && needs.capture.outputs.preview == 'eas' && !cancelled()");
|
||||
assert.deepEqual(workflow.jobs.deploy.needs, ["targets", "capture", "report"]);
|
||||
// The check reads what the download left: this target's report input, or nothing.
|
||||
const root = await mkdtemp(join(tmpdir(), "explore-report-check-"));
|
||||
t.after(() => rm(root, { recursive: true, force: true }));
|
||||
const runCheck = async () => {
|
||||
const output = join(root, "output"); await writeFile(output, "");
|
||||
const result = spawnSync("bash", ["-c", check.run], { encoding: "utf8", env: { ...process.env, RUNNER_TEMP: root, GITHUB_OUTPUT: output, TARGET: "duo-open" } });
|
||||
assert.equal(result.status, 0, result.stderr);
|
||||
return { output: await readFile(output, "utf8"), stdout: result.stdout };
|
||||
};
|
||||
const failed = await runCheck();
|
||||
assert.equal(failed.output, "");
|
||||
assert.match(failed.stdout, /The duo-open capture uploaded no review: its capture job failed/);
|
||||
await mkdir(join(root, "explore-review"), { recursive: true });
|
||||
await writeFile(join(root, "explore-review", "report-input.json"), "{}");
|
||||
assert.equal((await runCheck()).output, "found=true\n");
|
||||
}
|
||||
// The failure job still runs when a capture leg failed, and names that target from its diagnostics.
|
||||
const failure = review.jobs.failure;
|
||||
assert.match(failure.if, /^always\(\) && \(.*needs\.capture\.result == 'failure'.*needs\.report\.result == 'failure'/);
|
||||
for (const step of failure.steps.filter(step => step.uses?.startsWith("actions/download-artifact@"))) assert.equal(step["continue-on-error"], true, step.name);
|
||||
});
|
||||
|
||||
test("closing a pull request runs nothing: hosted previews stay until a developer deletes them", () => {
|
||||
assert.ok(!review.on.pull_request_target.types.includes("closed"));
|
||||
assert.doesNotMatch(review.jobs.targets.if, /closed/);
|
||||
|
||||
@@ -439,6 +439,42 @@ test("a reader stuck on the dark panel after a fold is reset once more before th
|
||||
assert.equal(stuck.calls.filter(call => call.tool === "stop-all-simulator-servers").length, 2, "before the fold and once after, not in a loop");
|
||||
});
|
||||
|
||||
// brentvatne/euxy#172, review run 39348956443: the fold after capture restarted SpringBoard failed with this, before it ran.
|
||||
const DEPENDENCY_FAILED = "argent run fold failed: [Tool:fold] Service dependency failed: [SimulatorServer:74195B53-4DBC-4EAA-9991-F98E5BB86BA8] Timed out waiting for simulator-server to become ready";
|
||||
|
||||
test("a fold whose simulator-server did not start is sent again after a pause, and then folds", async () => {
|
||||
const lit = { activeScreen: 3, screen: { id: 3, panel: "inner panel", width: 2007, height: 2853 }, posture: "open", hingeAngle: 180 };
|
||||
const { run, calls, context } = harness("ios", { "list-devices": DUO_DEVICES, "ui-tree": DUO_OPEN_EDIT_LANE, "stop-all-simulator-servers": { stopped: [] },
|
||||
fold: [new ArgentCallError(DEPENDENCY_FAILED, true), lit] });
|
||||
const pauses = [];
|
||||
context.sleep = async milliseconds => { pauses.push(milliseconds); };
|
||||
assert.deepEqual((await run(["fold", "open", ...flags("ios")])).json.data, { action: "fold", pose: "open" });
|
||||
assert.equal(calls.filter(call => call.tool === "fold").length, 2);
|
||||
assert.deepEqual(pauses, [3_000], "one pause before the fold is sent again");
|
||||
});
|
||||
|
||||
test("a fold whose simulator-server never starts fails as it did before, after two more tries", async () => {
|
||||
const { run, calls, context } = harness("ios", { "list-devices": DUO_DEVICES, "ui-tree": DUO_OPEN_EDIT_LANE, "stop-all-simulator-servers": { stopped: [] },
|
||||
fold: new ArgentCallError(DEPENDENCY_FAILED, true) });
|
||||
const pauses = [];
|
||||
context.sleep = async milliseconds => { pauses.push(milliseconds); };
|
||||
const failed = await run(["fold", "open", ...flags("ios")]);
|
||||
assert.deepEqual(failed.json.error, { code: "ARGENT_TOOL_FAILED", message: DEPENDENCY_FAILED });
|
||||
assert.equal(calls.filter(call => call.tool === "fold").length, 3);
|
||||
assert.deepEqual(pauses, [3_000, 6_000]);
|
||||
});
|
||||
|
||||
test("a UI action that failed for another reason is still sent once, even when its message mentions a dependency", async () => {
|
||||
// Only the tool's own wrap counts: a nested tool's dependency failure is not this tool failing to start.
|
||||
for (const message of ["argent run gesture-tap failed: [Tool:gesture-tap] simulator-server answered 500",
|
||||
"argent run gesture-tap failed: [Tool:gesture-tap] [Tool:keyboard] Service dependency failed: [SimulatorServer:x] Timed out"]) {
|
||||
const { run, calls } = harness("ios", { "list-devices": IOS_DEVICES, "ui-tree": IOS_HOME, "gesture-tap": new ArgentCallError(message, true) });
|
||||
const pressed = await run(["press", "10", "10", ...flags("ios")]);
|
||||
assert.deepEqual(pressed.json.error, { code: "ARGENT_TOOL_FAILED", message });
|
||||
assert.equal(calls.filter(call => call.tool === "gesture-tap").length, 1, message);
|
||||
}
|
||||
});
|
||||
|
||||
test("an alert that is not the link prompt is left for capture to answer", async () => {
|
||||
const other = { ...IOS_HOME, alertVisible: true, foregroundApp: "com.apple.springboard",
|
||||
roots: [{ type: "Alert", label: "Delete all data?", frame: { x: 0.1, y: 0.4, width: 0.8, height: 0.2 }, children: [
|
||||
|
||||
@@ -881,3 +881,201 @@ test("when nothing passes preflight, the first failure is reported", async () =>
|
||||
const createSession = (config, { auth }) => ({ async preflight() { throw new Error(`${config.provider} ${auth} refused`); } });
|
||||
await assert.rejects(preflightModelSession({ createSession }, {}, () => {}), /anthropic local-login refused/);
|
||||
});
|
||||
|
||||
const { assertReplayFits, createReplaySession, parseReplayPlan, replaySetup } = await tsImport("../../src/binary/replay.ts", import.meta.url);
|
||||
|
||||
function replayDevice(screens = SCREENS) {
|
||||
let screen = "home", frames = 0;
|
||||
const acted = [];
|
||||
return { acted, options: {
|
||||
observe: async includeImage => ({ nodes: screens[screen], capturedAt: new Date().toISOString(),
|
||||
...(includeImage ? { frameId: `replay-${++frames}`, png: PNG, imageSha256: `${frames}`.padStart(64, "b") } : {}) }),
|
||||
act: async action => {
|
||||
acted.push(action);
|
||||
if (action.label === "Missing" || action.label === "Nowhere") throw new Error(`No element labelled ${action.label}`);
|
||||
if (action.action === "tap" && action.label === "Settings") screen = "settings";
|
||||
if (action.action === "tap" && action.label === "Dark mode" && screens.settingsDark) screen = "settingsDark";
|
||||
if (action.action === "back") screen = "home";
|
||||
},
|
||||
} };
|
||||
}
|
||||
|
||||
test("a replay plan takes the same steps on each run: platform-only steps are skipped, optional failures are passed over and listed", async () => {
|
||||
const plan = parseReplayPlan({ steps: [
|
||||
{ capture: "Home" },
|
||||
{ action: "tap", label: "Missing", optional: true },
|
||||
{ action: "tap", label: "Android only", platforms: ["android"] },
|
||||
{ action: "tap", label: "Settings" }, { capture: "Settings" },
|
||||
{ action: "tap", label: "Dark mode" }, { capture: "Settings", state: "dark" },
|
||||
{ action: "back" },
|
||||
] });
|
||||
const device = replayDevice();
|
||||
const { result, map } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options });
|
||||
assert.equal(result.stopReason, "finished");
|
||||
assert.match(result.summary, /Every planned screen was captured\. Optional steps skipped because they failed: step 2 \(tap "Missing"\)\.$/);
|
||||
assert.deepEqual(map.screens.map(screen => screen.title), ["Home", "Settings"]);
|
||||
assert.ok(!device.acted.some(action => action.label === "Android only"));
|
||||
assert.ok(map.variants.some(variant => variant.name === "dark"), "the dark state is recorded as a variant");
|
||||
});
|
||||
|
||||
test("a failed replay step stops the run, keeps what was captured, and names the screens it did not reach", async () => {
|
||||
const plan = parseReplayPlan({ steps: [
|
||||
{ capture: "Home" }, { action: "tap", label: "Settings" }, { capture: "Settings" }, { action: "back" },
|
||||
{ action: "tap", label: "Nowhere" }, { capture: "Never" }, { capture: "Android screen", platforms: ["android"] },
|
||||
] });
|
||||
const device = replayDevice();
|
||||
const { result, map } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options });
|
||||
assert.equal(result.stopReason, "blocked");
|
||||
assert.deepEqual(map.screens.map(screen => screen.title), ["Home", "Settings"]);
|
||||
assert.match(result.summary, /Replay step 5 \(tap "Nowhere"\) failed: .*No element labelled Nowhere.*Not captured: Never$/);
|
||||
});
|
||||
|
||||
test("a blocked step names the screens still ahead before earlier misses, within stop_blocked's limit", async () => {
|
||||
const plan = parseReplayPlan({ steps: [
|
||||
{ capture: "Home" },
|
||||
...Array.from({ length: 20 }, (_, index) => ({ capture: `Earlier miss ${index} ${"x".repeat(60)}` })),
|
||||
{ action: "tap", label: "Nowhere" },
|
||||
{ capture: "Ahead" },
|
||||
] });
|
||||
const device = replayDevice();
|
||||
const { result } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options, maxTurns: 100 });
|
||||
assert.equal(result.stopReason, "blocked");
|
||||
assert.ok(result.summary.length <= 1000, `${result.summary.length} characters`);
|
||||
assert.match(result.summary, /Not captured: Ahead, Earlier miss 0 .* and \d+ more$/);
|
||||
});
|
||||
|
||||
test("a destructive or app-leaving tap in a replay plan is refused, as a model's would be", async () => {
|
||||
const plan = parseReplayPlan({ steps: [
|
||||
{ capture: "Home" }, { action: "tap", label: "Share", optional: true }, { action: "tap", label: "Delete account" }, { capture: "Gone" },
|
||||
] });
|
||||
const device = replayDevice();
|
||||
const { result, map } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options });
|
||||
assert.equal(result.stopReason, "blocked");
|
||||
assert.match(result.summary, /^Replay step 3 \(tap "Delete account"\) failed: "Delete account" looks destructive.*Not captured: Gone$/);
|
||||
assert.deepEqual(device.acted, [], "neither tap reaches the device");
|
||||
assert.deepEqual(map.actionAttempts.map(attempt => [attempt.action.label, attempt.outcome]), [["Share", "blocked"], ["Delete account", "blocked"]]);
|
||||
});
|
||||
|
||||
test("a replay plan is checked before any device starts: unknown, hostile and malformed fields are refused", () => {
|
||||
const refused = (step, pattern) => assert.throws(() => parseReplayPlan({ steps: [step] }), error => error.code === "REPLAY_PLAN_INVALID" && pattern.test(error.message), JSON.stringify(step));
|
||||
assert.throws(() => parseReplayPlan({ steps: [] }), /no steps/);
|
||||
assert.throws(() => parseReplayPlan({ steps: [{ capture: "Home" }], step: [] }), /field "step" it does not take/);
|
||||
refused({ action: "tap" }, /exactly one of label or identifier/);
|
||||
refused({ action: "swipe" }, /needs a capture title or an action/);
|
||||
refused({ action: "constructor" }, /needs a capture title or an action/);
|
||||
refused({ capture: "Home", platforms: ["web"] }, /platforms must list ios and\/or android/);
|
||||
// A coordinate tap's fields would turn a label tap into a tap whose risk comes from `target`.
|
||||
refused({ action: "tap", label: "Delete account", frameId: "frame-1", x: 0.2, y: 0.15, target: "Next" }, /^Step 1 \(tap\) has a field "frameId" it does not take; a tap step takes action, label, identifier, platforms, optional\.$/);
|
||||
refused({ action: "tap", label: "Next", platform: ["ios"] }, /field "platform"/);
|
||||
refused({ action: "tap", label: "Next", optinal: true }, /field "optinal"/);
|
||||
refused({ capture: "Home", optional: true }, /\(capture\) has a field "optional"/);
|
||||
refused({ capture: "Home", action: "tap", label: "Next" }, /\(capture\) has a field "action"/);
|
||||
refused({ action: "back", label: "Back" }, /\(back\) has a field "label"/);
|
||||
refused({ action: "scroll", direction: ["up"] }, /scroll needs a direction/);
|
||||
refused({ action: "scroll", direction: "sideways" }, /scroll needs a direction/);
|
||||
refused({ action: "tap", label: "x".repeat(257) }, /label must be 1–256 characters without control characters/);
|
||||
refused({ action: "tap", identifier: "row\nnext" }, /identifier must be 1–256 characters/);
|
||||
refused({ action: "fill", label: "Name", text: "two\nlines" }, /fill needs text: one line/);
|
||||
refused({ action: "type", text: "x".repeat(2001) }, /type needs text/);
|
||||
refused({ action: "type", text: "{{secret:lowercase}}" }, /invalid secret reference/);
|
||||
refused({ action: "type", text: "{{secret:OPENAI_API_KEY}}" }, /cannot reference provider/);
|
||||
refused({ action: "wait", milliseconds: 15_001 }, /between 1 and 15000/);
|
||||
assert.deepEqual(parseReplayPlan({ steps: [{ capture: "Home" }] }).steps, [{ capture: "Home" }]);
|
||||
assert.deepEqual(parseReplayPlan({ steps: [{ action: "scroll", direction: "down", optional: true, platforms: ["ios"] }] }).steps,
|
||||
[{ action: "scroll", direction: "down", platforms: ["ios"], optional: true }]);
|
||||
});
|
||||
|
||||
test("a replay plan with no steps for the platform, or more than the budgets hold, is refused before any device starts", () => {
|
||||
const limits = { maxScreens: 40, maxActions: 150, maxTurns: 400 };
|
||||
assert.throws(() => assertReplayFits(parseReplayPlan({ steps: [{ capture: "Home", platforms: ["android"] }, { action: "back", platforms: ["android"] }] }), "ios", limits),
|
||||
error => error.code === "REPLAY_PLAN_EMPTY" && /No step of the replay plan runs on ios/.test(error.message));
|
||||
const plan = parseReplayPlan({ steps: [{ capture: "Home" }, { action: "tap", label: "Settings" }, { capture: "Settings" }, { action: "back" }, { action: "wait", milliseconds: 100 }] });
|
||||
assert.doesNotThrow(() => assertReplayFits(plan, "ios", limits));
|
||||
assert.throws(() => assertReplayFits(plan, "ios", { ...limits, maxScreens: 2, maxActions: 1 }),
|
||||
error => error.code === "REPLAY_PLAN_OVER_BUDGET" && /2 captures, which need a screen budget of at least 3 \(it is 2\) and 2 actions, more than the action budget of 1/.test(error.message)
|
||||
&& /--max-screens 3 --max-actions 2/.test(error.nextAction));
|
||||
assert.throws(() => assertReplayFits(plan, "ios", { ...limits, maxTurns: 8 }), /takes 9 tool calls, more than the 8/);
|
||||
});
|
||||
|
||||
test("a replay that runs out of budget names the planned screens it did not reach in the gap", async () => {
|
||||
const plan = parseReplayPlan({ steps: [{ capture: "Home" }, { action: "tap", label: "Settings" }, { capture: "Settings" }, { action: "back" }, { capture: "Later" }] });
|
||||
const device = replayDevice();
|
||||
const session = createReplaySession(plan, "ios");
|
||||
const { result, map } = await harness([], { session, budgetNote: session.budgetNote, ...device.options, maxScreens: 2 });
|
||||
assert.equal(result.stopReason, "budget-screens");
|
||||
assert.match(map.gaps.at(-1).message, /^The exploration stopped at its screens budget with \d+ controls unexplored\. Not captured: Settings, Later\.$/);
|
||||
});
|
||||
|
||||
test("a capture of a screen the plan already captured under another title is reported and does not rename it", async () => {
|
||||
const plan = parseReplayPlan({ steps: [
|
||||
{ capture: "Home" }, { capture: "Start" }, { capture: "home" }, { action: "tap", label: "Settings" }, { action: "back" },
|
||||
] });
|
||||
const device = replayDevice();
|
||||
const { result, map } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options });
|
||||
assert.equal(result.stopReason, "finished");
|
||||
assert.deepEqual(map.screens.map(screen => screen.title), ["Home", "Home → Settings"]);
|
||||
assert.match(result.summary, /Not captured: Start \(looked the same as Home\)\. Also reached, not in the plan: 1 unnamed screen\.$/);
|
||||
});
|
||||
|
||||
test("a planned state that the explorer merges into an earlier screen is neither reported as unplanned nor left in the map", async () => {
|
||||
// The README's own example: Dark mode changes the tree, and the capture titled Settings folds that new screen into Settings.
|
||||
const screens = { ...SCREENS, settingsDark: [...SCREENS.settings, { type: "Button", label: "Theme options" }] };
|
||||
const plan = parseReplayPlan({ steps: [
|
||||
{ capture: "Home" }, { action: "tap", label: "Settings" }, { capture: "Settings" },
|
||||
{ action: "tap", label: "Dark mode" }, { capture: "Settings", state: "dark" },
|
||||
] });
|
||||
const device = replayDevice(screens);
|
||||
const { result, map } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options });
|
||||
assert.equal(result.stopReason, "finished");
|
||||
assert.deepEqual(map.screens.map(screen => screen.title), ["Home", "Settings"]);
|
||||
const settings = map.screens.find(screen => screen.title === "Settings");
|
||||
assert.ok(map.variants.some(variant => variant.screenId === settings.id && variant.name === "dark"));
|
||||
assert.equal(result.summary, "Replayed 5 planned steps on ios. Every planned screen was captured.");
|
||||
});
|
||||
|
||||
test("a long replay summary is kept within finish's limit, the most useful names first", async () => {
|
||||
const titles = Array.from({ length: 60 }, (_, index) => `Planned screen ${String(index).padStart(2, "0")} ${"y".repeat(60)}`);
|
||||
const plan = parseReplayPlan({ steps: [{ capture: "Home" }, ...titles.map(title => ({ capture: title }))] });
|
||||
const device = replayDevice();
|
||||
const { result } = await harness([], { session: createReplaySession(plan, "ios"), ...device.options, maxTurns: 200 });
|
||||
assert.equal(result.stopReason, "finished");
|
||||
assert.ok(result.summary.length <= 4000, `${result.summary.length} characters`);
|
||||
assert.match(result.summary, /^Replayed 61 planned steps on ios\. Not captured: Planned screen 00 y+ \(looked the same as Home\), .* and \d+ more\.$/);
|
||||
});
|
||||
|
||||
test("a refused finish ends the replay with stop_blocked instead of a turn budget, and a refused stop is an error", async () => {
|
||||
const plan = parseReplayPlan({ steps: [{ action: "back" }] });
|
||||
const calls = [];
|
||||
const request = refuse => ({ signal: new AbortController().signal, callTool: async (name, input) => {
|
||||
calls.push({ name, input });
|
||||
const value = name === "get_progress" ? { captured: [] } : refuse.includes(name) ? { ok: false, code: "AGENT_ACTION_INVALID", message: `${name} refused` } : { ok: true };
|
||||
return { content: [{ type: "text", text: JSON.stringify(value) }], ...(refuse.includes(name) ? { isError: true } : {}) };
|
||||
} });
|
||||
await createReplaySession(plan, "ios").run(request(["finish"]));
|
||||
assert.deepEqual(calls.map(call => call.name), ["act", "get_progress", "finish", "stop_blocked"]);
|
||||
assert.match(calls.at(-1).input.reason, /^The replay could not finish \(finish refused\)\. Replayed 1 planned steps on ios\./);
|
||||
await assert.rejects(createReplaySession(plan, "ios").run(request(["finish", "stop_blocked"])), { code: "REPLAY_STOP_REFUSED" });
|
||||
});
|
||||
|
||||
test("a replay plan's {{secret:NAME}} inputs are read before any device starts and typed for the plan", async () => {
|
||||
const { runBinaryExploration, runSessionExploration } = await tsImport("../../src/binary/run.ts", import.meta.url);
|
||||
const { createExplorationInputs } = await tsImport("../../src/config/exploration-inputs.ts", import.meta.url);
|
||||
const plan = parseReplayPlan({ steps: [{ capture: "Home" }, { action: "fill", label: "Password", text: "{{secret:APP_TEST_PASSWORD}}" }] });
|
||||
const output = await mkdtemp(join(tmpdir(), "explore-replay-"));
|
||||
for (const run of [runBinaryExploration, runSessionExploration]) {
|
||||
await assert.rejects(run({ archive: join(output, "missing.apk"), output, replay: plan, environment: {} }),
|
||||
error => error.code === "EXPLORATION_SECRET_MISSING" && /APP_TEST_PASSWORD/.test(error.message));
|
||||
await assert.rejects(run({ archive: join(output, "missing.apk"), output, replay: plan, environment: {}, provider: "openai", hints: "Look around" }),
|
||||
error => error.code === "REPLAY_OPTIONS_IGNORED" && /--provider and --hints would do nothing/.test(error.message));
|
||||
await assert.rejects(run({ archive: join(output, "missing.apk"), output, replay: { steps: [{ action: "tap", label: "Next", optinal: true }] }, environment: {} }), { code: "REPLAY_PLAN_INVALID" });
|
||||
await assert.rejects(run({ archive: join(output, "missing.apk"), output, replay: parseReplayPlan({ steps: [{ action: "open", url: "https://example.com" }] }), environment: {} }),
|
||||
error => error.code === "REPLAY_PLAN_INVALID" && /^Step 1: https: URLs leave the app/.test(error.message));
|
||||
}
|
||||
const device = replayDevice();
|
||||
const inputs = createExplorationInputs({ setup: replaySetup(plan), environment: { APP_TEST_PASSWORD: "hunter2-test" } });
|
||||
const { result, map } = await harness([], { session: createReplaySession(plan, "ios"), inputs, ...device.options });
|
||||
assert.equal(result.stopReason, "finished");
|
||||
assert.deepEqual(device.acted, [{ action: "fill", label: "Password", text: "hunter2-test" }]);
|
||||
assert.equal(map.actionAttempts[0].action.input.value, "{{secret:APP_TEST_PASSWORD}}");
|
||||
assert.ok(!JSON.stringify(map).includes("hunter2-test"));
|
||||
});
|
||||
@@ -173,6 +173,22 @@ test("CI argument failures preserve JSON output, annotation, summary, and diagno
|
||||
assert.match(await readFile(summary, "utf8"), /Next action/);
|
||||
});
|
||||
|
||||
test("a failed command's diagnostics file names the matrix target it ran for, so the failure comment can", async (t) => {
|
||||
const root = await mkdtemp(join(tmpdir(), "explore-cli-target-"));
|
||||
t.after(() => rm(root, { recursive: true, force: true }));
|
||||
const cli = new URL("../../src/cli.ts", import.meta.url);
|
||||
const run = target => {
|
||||
const result = spawnSync(process.execPath, ["--import", "tsx", cli.pathname, "ci:report", "--input", join(root, "missing.json"), "--output", join(root, "out"), "--target", target],
|
||||
{ encoding: "utf8", env: { ...process.env, GITHUB_ACTIONS: "true", RUNNER_TEMP: root } });
|
||||
assert.equal(result.status, 1, result.stderr);
|
||||
return readFile(join(root, "explore-diagnostics/error.json"), "utf8").then(JSON.parse);
|
||||
};
|
||||
const written = await run("duo-closed");
|
||||
assert.equal(written.target, "duo-closed");
|
||||
assert.equal(written.code, "REPORT_INPUT_INVALID");
|
||||
assert.equal((await run("../ios")).target, undefined, "only a valid target id is written");
|
||||
});
|
||||
|
||||
test("source worker failures emit a structured diagnostic without a raw stack", () => {
|
||||
const worker = new URL("../../src/source/plan-worker.ts", import.meta.url);
|
||||
const result = spawnSync(process.execPath, ["--import", "tsx", worker.pathname], { input: "{", encoding: "utf8" });
|
||||
|
||||
@@ -7,7 +7,7 @@ import test from "node:test";
|
||||
import { prepareCaptureReview } from "../../dist/review/capture-review.js";
|
||||
import { createSourceCapturePlan } from "../../dist/source/capture-plan.js";
|
||||
import { writeCiReportInput, exportCiReport } from "../../dist/report/artifact.js";
|
||||
import { collectPlatformReports, deployExplorationReport, deployFixturePreview, deployLocalReports, fixtureReports, deployPreview, previewProjectSlug, readReportZip, whoamiAccounts, zipReportDirectory } from "../../dist/report/preview-deploy.js";
|
||||
import { collectPlatformReports, deployExplorationReport, deployFixturePreview, deployLocalReports, FIXTURE_ALIAS_WAIT_MS, fixtureReports, deployPreview, previewProjectSlug, readReportZip, whoamiAccounts, zipReportDirectory } from "../../dist/report/preview-deploy.js";
|
||||
import { spawnSync } from "node:child_process";
|
||||
import { ZipReader, Uint8ArrayReader, TextWriter, configure } from "@zip.js/zip.js";
|
||||
import { viewerLinks } from "../../dist/report/viewer-links.js";
|
||||
@@ -387,11 +387,76 @@ test("collectPlatformReports pairs downloaded artifact directories by platform a
|
||||
const lookups = eas.requests.filter(request => request.url.pathname.endsWith("/actions/runs/10/artifacts"));
|
||||
assert.deepEqual(lookups.map(request => request.url.searchParams.get("name")), ["explore-review-10-1-android", "explore-review-10-1-ios"]);
|
||||
assert.ok(lookups.every(request => request.options.headers.authorization === "Bearer test-token"));
|
||||
// A target whose report job failed (brentvatne/euxy#172) is left out; the others still deploy, without waiting for it.
|
||||
await rm(join(root, "reports", "explore-review-10-1-android"), { recursive: true });
|
||||
const before = eas.requests.length;
|
||||
const remaining = await collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport: eas.transport });
|
||||
assert.deepEqual(remaining.map(entry => entry.target.id), ["ios"]);
|
||||
assert.deepEqual(eas.requests.slice(before).map(request => request.url.searchParams.get("name")), ["explore-review-10-1-ios"], "no lookup for the target without a report");
|
||||
await rm(join(root, "reports", "explore-review-10-1-ios"), { recursive: true });
|
||||
await assert.rejects(collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport: eas.transport }),
|
||||
error => error.code === "PREVIEW_REPORTS_INCOMPLETE");
|
||||
});
|
||||
|
||||
test("collectPlatformReports reads a lone target's artifacts, which download-artifact extracts into the path itself", async t => {
|
||||
const fixture = await asTarget(await exportFixture(t), TARGETS[2]);
|
||||
const root = await mkdtemp(join(tmpdir(), "explore-fanin-lone-")); t.after(() => rm(root, { recursive: true, force: true }));
|
||||
// Four of five captures failed, so each pattern matched one artifact: its files sit in --inputs and --reports themselves.
|
||||
await mkdir(join(root, "inputs"), { recursive: true }); await cp(fixture.inputPath, join(root, "inputs", "report-input.json"));
|
||||
await cp(fixture.reportPath, join(root, "reports"), { recursive: true });
|
||||
const eas = easFixture();
|
||||
const transport = async (input, options) => {
|
||||
const url = new URL(input);
|
||||
if (url.pathname.endsWith("/actions/runs/10/artifacts") && url.searchParams.get("name") === "explore-review-10-1-duo-open") {
|
||||
return new Response(JSON.stringify({ artifacts: [{ id: 33, name: "explore-review-10-1-duo-open" }] }), { status: 200 });
|
||||
}
|
||||
return eas.transport(input, options);
|
||||
};
|
||||
const [entry, ...rest] = await collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport });
|
||||
assert.deepEqual(rest, []);
|
||||
assert.deepEqual([entry.target.id, entry.inputPath, entry.reportPath, entry.artifactUrl.split("/").at(-1)],
|
||||
["duo-open", join(root, "inputs", "report-input.json"), join(root, "reports"), "33"]);
|
||||
// A pattern that matched nothing left no directory: there is nothing to deploy, and that is said plainly.
|
||||
await assert.rejects(collectPlatformReports({ inputsPath: join(root, "missing"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport }),
|
||||
error => error.code === "PREVIEW_REPORTS_MISSING");
|
||||
});
|
||||
|
||||
test("collectPlatformReports looks up a report artifact the run does not list yet again, but not one its token cannot read", async t => {
|
||||
const ios = await exportFixture(t);
|
||||
const root = await mkdtemp(join(tmpdir(), "explore-fanin-late-")); t.after(() => rm(root, { recursive: true, force: true }));
|
||||
const { cp } = await import("node:fs/promises");
|
||||
await mkdir(join(root, "inputs", "explore-capture-10-1-ios"), { recursive: true }); await cp(ios.inputPath, join(root, "inputs", "explore-capture-10-1-ios", "report-input.json"));
|
||||
await cp(ios.reportPath, join(root, "reports", "explore-review-10-1-ios"), { recursive: true });
|
||||
const eas = easFixture();
|
||||
const listing = answers => {
|
||||
const lookups = [];
|
||||
const transport = async (input, options) => {
|
||||
const url = new URL(input);
|
||||
if (!url.pathname.endsWith("/actions/runs/10/artifacts")) return eas.transport(input, options);
|
||||
lookups.push(url);
|
||||
const answer = answers[Math.min(lookups.length, answers.length) - 1];
|
||||
return answer ? new Response(JSON.stringify(answer.body ?? {}), { status: answer.status }) : eas.transport(input, options);
|
||||
};
|
||||
return { lookups, transport };
|
||||
};
|
||||
const pauses = [];
|
||||
const sleep = async milliseconds => { pauses.push(milliseconds); };
|
||||
// The list lags the report job's upload: empty, then a 404, then the artifact.
|
||||
const late = listing([{ status: 200, body: { artifacts: [] } }, { status: 404 }, undefined]);
|
||||
const [entry] = await collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport: late.transport, sleep });
|
||||
assert.equal(entry.artifactUrl, artifactUrl.replace(/20$/, "21"));
|
||||
assert.equal(late.lookups.length, 3);
|
||||
assert.equal(pauses.length, 2);
|
||||
const denied = listing([{ status: 403 }]);
|
||||
await assert.rejects(collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport: denied.transport, sleep }),
|
||||
error => error.code === "REPORT_ARTIFACT_MISSING" && /HTTP 403/.test(error.message));
|
||||
assert.equal(denied.lookups.length, 1);
|
||||
const never = listing([{ status: 200, body: { artifacts: [] } }]);
|
||||
await assert.rejects(collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport: never.transport, sleep }),
|
||||
error => error.code === "REPORT_ARTIFACT_MISSING");
|
||||
assert.equal(never.lookups.length, 5);
|
||||
});
|
||||
|
||||
const now = Date.UTC(2026, 8, 11, 3, 7);
|
||||
const STALE_COMMENT = `<!-- expo-explore-ci -->
|
||||
Explore review for abc · Managed via config
|
||||
@@ -456,6 +521,20 @@ test("a standalone report deploys to a fixed alias with a fixed token, verifies
|
||||
assert.match(plain.previewUrl, /^https:\/\/acme-explore--1lcbdcpwn3\.expo\.app\/p\/[a-z2-7]{32}$/);
|
||||
assert.notEqual(plain.previewUrl, result.previewUrl, "without a fixed token the link is random");
|
||||
|
||||
// A standalone report's alias that is still behind after the whole budget: its link is the deployment, which
|
||||
// serves this run, and nothing says the alias is behind (only a fixture preview's comment explains a lagging link).
|
||||
const behind = easFixture({ aliasServes: false });
|
||||
let clock = now;
|
||||
const quiet = process.stderr.write.bind(process.stderr);
|
||||
process.stderr.write = () => true;
|
||||
let fallback;
|
||||
try {
|
||||
fallback = await deployExplorationReport({ reportPath, project: "acme-explore", owner: "brent-org", exportPath, alias: "bluesky", token,
|
||||
environment: deployEnvironment, transport: behind.transport, run: behind.run, now: () => (clock += 31_000), verifyTimeoutMs: 60_000 });
|
||||
} finally { process.stderr.write = quiet; }
|
||||
assert.equal(fallback.previewUrl, `https://acme-explore--1lcbdcpwn3.expo.app/p/${token}`);
|
||||
assert.equal(fallback.aliasBehind, undefined);
|
||||
|
||||
await assert.rejects(deployExplorationReport({ reportPath, project: "acme-explore", owner: "brent-org", exportPath, alias: "Blue Sky",
|
||||
environment: deployEnvironment, transport: eas.transport, run: eas.run, verifyTimeoutMs: 1 }), error => error.code === "PREVIEW_ALIAS_INVALID");
|
||||
await assert.rejects(deployExplorationReport({ reportPath, project: "acme-explore", owner: "brent-org", exportPath, token: "short",
|
||||
@@ -487,21 +566,28 @@ test("a fixture preview seals each platform's ZIP as is behind one alias and lis
|
||||
const served = eas.requests.filter(request => request.url.pathname === `/p/${token}/manifest.json`).map(request => request.url.searchParams.get("platform"));
|
||||
assert.deepEqual([...new Set(served)].sort(), ["android", "ios"], "both platforms' manifests are verified");
|
||||
|
||||
// The alias lagging the deployment past the budget is not a failed deployment: the deployment is verified, so the
|
||||
// link is the deployment's own origin and the job log carries a warning (every 2026-10-14 "HTTP 404" failure was this).
|
||||
// The alias lagging the deployment is not a failed deployment (every 2026-10-14 "HTTP 404" failure was this): the
|
||||
// deployment is verified, so after FIXTURE_ALIAS_WAIT_MS, not the whole verification budget, the pull request links
|
||||
// the alias anyway, says it is behind, and the job log carries a warning.
|
||||
const behind = easFixture({ aliasOrigin: "https://explore-viewer-pr--pr-12.expo.app", aliasServes: false });
|
||||
let clock = now; const ticking = () => (clock += 31_000);
|
||||
// Each poll really waits 3 s, so the clock moves 7 s a reading: the 20 s wait is three polls, not twenty.
|
||||
let clock = now; const ticking = () => (clock += 7_000);
|
||||
const quiet = process.stderr.write.bind(process.stderr); const logged = [];
|
||||
process.stderr.write = chunk => { logged.push(String(chunk)); return true; };
|
||||
let linked;
|
||||
try {
|
||||
linked = await deployFixturePreview({ reports: [{ platform: "ios", zipPath: join(root, "ios.zip") }], project: "explore-viewer-pr", owner: "brent-org", alias: "pr-12", token,
|
||||
exportPath, environment: deployEnvironment, transport: behind.transport, run: behind.run, now: ticking, verifyTimeoutMs: 60_000 });
|
||||
exportPath, environment: deployEnvironment, transport: behind.transport, run: behind.run, now: ticking, verifyTimeoutMs: 180_000 });
|
||||
} finally { process.stderr.write = quiet; }
|
||||
assert.equal(linked.previewUrl, `https://acme-explore--1lcbdcpwn3.expo.app/p/${token}`);
|
||||
assert.equal(linked.previewUrl, `https://explore-viewer-pr--pr-12.expo.app/p/${token}`);
|
||||
assert.equal(linked.aliasUrl, "https://explore-viewer-pr--pr-12.expo.app");
|
||||
assert.equal(linked.aliasBehind, true);
|
||||
assert.equal(linked.deploymentUrl, "https://acme-explore--1lcbdcpwn3.expo.app", "the comment links the verified deployment beside the alias");
|
||||
assert.equal(logged.filter(line => /^Deployment https:\/\/acme-explore--1lcbdcpwn3\.expo\.app serves this run's report \(\d+ s after eas deploy returned\)\./.test(line)).length, 1);
|
||||
assert.equal(logged.filter(line => /^::warning::The alias https:\/\/explore-viewer-pr--pr-12\.expo\.app still answers HTTP 404 \d+ s after eas deploy returned\. The pull request links the deployment https:\/\/acme-explore--1lcbdcpwn3\.expo\.app instead\./.test(line)).length, 1);
|
||||
const warning = logged.find(line => /^::warning::The alias https:\/\/explore-viewer-pr--pr-12\.expo\.app still answers HTTP 404 \d+ s after eas deploy returned\. The pull request links it anyway, until it catches up, beside the deployment https:\/\/acme-explore--1lcbdcpwn3\.expo\.app\./.test(line));
|
||||
assert.ok(warning, logged.join(""));
|
||||
const waited = Number(/HTTP 404 (\d+) s/.exec(warning)[1]);
|
||||
assert.ok(waited >= FIXTURE_ALIAS_WAIT_MS / 1000 && waited < FIXTURE_ALIAS_WAIT_MS / 1000 + 15, `gave up on the alias after ${waited} s, not the 180 s budget`);
|
||||
assert.ok(behind.requests.some(request => request.url.origin === "https://explore-viewer-pr--pr-12.expo.app"), "the alias was polled");
|
||||
|
||||
// The example report keeps one token and the same fixtures, so an alias still on the previous deployment serves the
|
||||
@@ -513,7 +599,8 @@ test("a fixture preview seals each platform's ZIP as is behind one alias and lis
|
||||
linked = await deployFixturePreview({ reports: [{ platform: "ios", zipPath: join(root, "ios.zip") }], project: "explore-viewer-pr", owner: "brent-org", alias: "pr-12", token,
|
||||
exportPath, environment: deployEnvironment, transport: stale.transport, run: stale.run, now: ticking, verifyTimeoutMs: 60_000 });
|
||||
} finally { process.stderr.write = quiet; }
|
||||
assert.equal(linked.previewUrl, `https://acme-explore--1lcbdcpwn3.expo.app/p/${token}`);
|
||||
assert.equal(linked.previewUrl, `https://explore-viewer-pr--pr-12.expo.app/p/${token}`);
|
||||
assert.equal(linked.aliasBehind, true);
|
||||
assert.equal(logged.filter(line => /^::warning::The alias https:\/\/explore-viewer-pr--pr-12\.expo\.app still serves an earlier deployment \d+ s after eas deploy returned\./.test(line)).length, 1);
|
||||
|
||||
await assert.rejects(deployFixturePreview({ reports: [{ platform: "ios", zipPath: join(root, "ios.zip") }, { platform: "ios", zipPath: join(root, "ios.zip") }],
|
||||
@@ -789,7 +876,9 @@ test("ci:deploy pairs target-named artifacts, deploys them in config order, and
|
||||
const entries = await collectPlatformReports({ inputsPath: join(root, "inputs"), reportsPath: join(root, "reports"), environment: deployEnvironment, transport });
|
||||
assert.deepEqual(entries.map(entry => [entry.target.id, entry.platform, entry.artifactUrl.split("/").at(-1)]),
|
||||
[["iphone", undefined, "31"], ["duo-closed", undefined, "32"], ["duo-open", undefined, "33"], ["android", "android", "34"]], "config order, not directory order");
|
||||
const sealed = await deployPreview({ reports: entries.map(({ platform: _platform, ...entry }) => entry), exportPath: fixtures[0].exportPath, environment: deployEnvironment, transport, run: eas.run, now: () => now, verifyTimeoutMs: 1 })
|
||||
// The fixture serves none of these artifacts by id, so each comment's artifact lookup answers 404 through all its retries.
|
||||
const sealed = await deployPreview({ reports: entries.map(({ platform: _platform, ...entry }) => entry), exportPath: fixtures[0].exportPath, environment: deployEnvironment, transport, run: eas.run, now: () => now, verifyTimeoutMs: 1,
|
||||
sleep: async () => {} })
|
||||
.catch(error => error);
|
||||
// Publishing each target's comment section after the deployment is the comment code's (publishCiReportComment, which needs
|
||||
// the target to name the artifact); the deployment itself must have been written per target either way.
|
||||
|
||||
@@ -710,6 +710,53 @@ test('several targets share a comment: named in config order in the subtitle, ea
|
||||
assert.match(next, /\n- \[bbbbbbbb\]\(<[^>]+>\) · iPhone 17 🟩 3 changes \(.*?\) · iPhone Duo \\\(closed\\\) ⏳ did not finish \(.*?\) · iPhone Duo \\\(open\\\) 🟩 3 changes \(.*?\) · Pixel 7 🟩 3 changes /);
|
||||
});
|
||||
|
||||
test('one of five targets failed: the comment shows the four reports and that failure, and no new-run banner (brentvatne/euxy#172)', async t => {
|
||||
const { platformSectionMerge, readCommentRecords } = await import('../../dist/report/pr-comment-body.js');
|
||||
const { publishFailureComment } = await import('../../dist/report/failure-comment.js');
|
||||
const { mkdir, mkdtemp, rm, writeFile } = await import('node:fs/promises');
|
||||
const { tmpdir } = await import('node:os');
|
||||
const { join } = await import('node:path');
|
||||
const targets = [...duoTargets, { id: 'pixel-dark', platform: 'android', label: 'Pixel 7 (dark)' }];
|
||||
const configPath = '.expo-explore/config.yaml';
|
||||
const firstAttempt = viewerLinks({ artifactUrl: 'https://github.com/expo/explore-playground/actions/runs/42/artifacts/7650', repository: pullRequest.repository, headSha, runId: '42', runAttempt: '1', configPath });
|
||||
const working = viewerLinks({ repository: pullRequest.repository, headSha, runId: '42', runAttempt: '2', configPath });
|
||||
// Attempt 1 published every target; attempt 2 captured them all at once, and the iPhone Duo (open) session failed.
|
||||
let body;
|
||||
for (const target of targets) body = platformSectionMerge(targetState(target, { targets, links: firstAttempt }), target.id).merge(body);
|
||||
for (const target of targets) body = platformSectionMerge(targetState(target, { targets, links: working, phase: 'capturing', review: undefined, evidence: undefined,
|
||||
capture: { planned: { base: 3, head: 3 }, done: { base: 3, head: 1 }, baseFromCache: false, current: 'head' } }), target.id).merge(body);
|
||||
assert.match(visible(body), /New run in progress/);
|
||||
for (const target of targets.filter(target => target.id !== 'duo-open')) body = platformSectionMerge(targetState(target, { targets }), target.id).merge(body);
|
||||
|
||||
const root = await mkdtemp(join(tmpdir(), 'explore-one-failed-')); t.after(() => rm(root, { recursive: true, force: true }));
|
||||
for (const target of targets) await mkdir(join(root, 'capture', `explore-diagnostics-42-2-${target.id}`, 'explore-diagnostics'), { recursive: true });
|
||||
await writeFile(join(root, 'capture', 'explore-diagnostics-42-2-duo-open', 'explore-diagnostics', 'error.json'), JSON.stringify({ code: 'ARGENT_TOOL_FAILED', stage: 'session',
|
||||
message: 'fold: argent run fold failed: [Tool:fold] Service dependency failed', nextAction: 'Rerun the capture.', retryable: false, target: 'duo-open' }));
|
||||
let comments = [{ id: 5, user: { login: 'github-actions[bot]' }, body }];
|
||||
const transport = async (input, init = {}) => {
|
||||
const url = new URL(input);
|
||||
if (url.pathname === '/repos/expo/explore-playground/pulls/1') return Response.json({ state: 'open', draft: false, title: pullRequest.title, html_url: pullRequest.url,
|
||||
base: { ref: 'main', sha: baseSha, repo: { id: 1, full_name: pullRequest.repository } }, head: { ref: pullRequest.head.ref, sha: headSha, repo: { full_name: pullRequest.repository } } });
|
||||
if (url.pathname === '/repos/expo/explore-playground/issues/1/comments') return Response.json(comments);
|
||||
if (url.pathname === '/repos/expo/explore-playground/issues/comments/5' && init.method === 'PATCH') {
|
||||
comments = [{ ...comments[0], body: JSON.parse(init.body).body }]; return Response.json({ id: 5 });
|
||||
}
|
||||
throw new Error(`unexpected request ${init.method ?? 'GET'} ${url}`);
|
||||
};
|
||||
assert.deepEqual(await publishFailureComment({ repository: pullRequest.repository, pullNumber: 1, headSha, baseSha, runId: '42', runAttempt: '2', diagnosticsPath: root,
|
||||
environment: { GITHUB_TOKEN: 'test-token' }, transport }), { posted: true });
|
||||
const final = comments[0].body;
|
||||
assert.doesNotMatch(visible(final), /New run in progress|New run failed/);
|
||||
assert.equal(readCommentRecords(final).previous, undefined, "attempt 1's records go once every target of attempt 2 finished");
|
||||
const records = readCommentRecords(final).current;
|
||||
assert.deepEqual(targets.map(target => [records[target.id].runAttempt, records[target.id].phase]),
|
||||
[['2', 'ready'], ['2', 'ready'], ['2', 'failed'], ['2', 'ready'], ['2', 'ready']]);
|
||||
assert.match(statusOf(final, 'iPhone Duo \\(open\\)'), /^\*\*iPhone Duo \\\(open\\\) failed\*\* · session · ARGENT\\_TOOL\\_FAILED\\: fold\\: argent run fold failed/);
|
||||
// Each published target links its report; the failure's record is the newest, so it sets the updated time.
|
||||
assert.ok(subtitleOf(final).startsWith(`<sub>[iPhone 17](<${reportUrl}>) · [iPhone Duo \\(closed\\)](<${reportUrl}>) · iPhone Duo \\(open\\) · [Pixel 7](<${reportUrl}>) · [Pixel 7 \\(dark\\)](<${reportUrl}>) · ${commits} · updated `), subtitleOf(final));
|
||||
assert.equal(titleOf(final), `### 3 screens changed · [Review in Explore](<${reportUrl}>)`);
|
||||
});
|
||||
|
||||
test('a comment written by a per-platform version keeps parsing, and malformed target records are dropped', async () => {
|
||||
const { platformSectionMerge, readCommentRecords } = await import('../../dist/report/pr-comment-body.js');
|
||||
const { encodeRecordPayload } = await import('../../dist/report/pr-comment-record.js');
|
||||
|
||||
@@ -38,3 +38,40 @@ test("link schemes are approved once each, lowercased, never http or https, and
|
||||
assert.deepEqual(approveSessionUrlSchemes(none.eas, "session-1", new Set(), "dev.example.app", ["example"]), []);
|
||||
assert.equal(none.calls.length, 0);
|
||||
});
|
||||
|
||||
// The host can fail an action once, as `app.approveUrlScheme` did in its `simctl spawn … defaults write` (euxy run 39348933440).
|
||||
function flakyEas(failures) {
|
||||
const calls = [];
|
||||
const eas = args => {
|
||||
calls.push(args);
|
||||
if (calls.length <= failures) throw new Error("eas simulator:control exited with status 1: The simulator could not run app.approveUrlScheme");
|
||||
return { stdout: "{}" };
|
||||
};
|
||||
return { calls, eas };
|
||||
}
|
||||
|
||||
test("an action that fails once is sent again after a pause", () => {
|
||||
const { calls, eas } = flakyEas(1);
|
||||
const pauses = [];
|
||||
simulatorControl(eas, "session-1", "app.approveUrlScheme", ["dev.example.app", "example"], { sleep: milliseconds => pauses.push(milliseconds) });
|
||||
assert.equal(calls.length, 2);
|
||||
assert.deepEqual(calls[1], calls[0]);
|
||||
assert.equal(pauses.length, 1);
|
||||
});
|
||||
|
||||
test("an action that keeps failing throws EAS's reason after its last attempt, with no pause after it", () => {
|
||||
const { calls, eas } = flakyEas(Infinity);
|
||||
const pauses = [];
|
||||
assert.throws(() => simulatorControl(eas, "session-1", "app.approveUrlScheme", ["dev.example.app", "example"], { sleep: milliseconds => pauses.push(milliseconds) }),
|
||||
/could not run app\.approveUrlScheme/);
|
||||
assert.equal(calls.length, 3);
|
||||
assert.equal(pauses.length, calls.length - 1);
|
||||
assert.ok(pauses.every(milliseconds => milliseconds > 0 && milliseconds <= 10_000));
|
||||
});
|
||||
|
||||
test("a link scheme the host fails to approve once is approved on the next attempt", () => {
|
||||
const { calls, eas } = flakyEas(1);
|
||||
const approved = approveSessionUrlSchemes(eas, "session-1", new Set(["app.approveUrlScheme"]), "dev.example.app", ["example"], { sleep: () => {} });
|
||||
assert.deepEqual(approved, ["example"]);
|
||||
assert.equal(calls.length, 2);
|
||||
});
|
||||
@@ -133,11 +133,14 @@ test("report export rejects path traversal and symlink images from downloaded ev
|
||||
});
|
||||
|
||||
function transportFixture({ stale = false, expired = false, artifactName = "explore-review-10-1", artifactRun = 10, attempt = 1,
|
||||
status, headers } = {}) {
|
||||
status, headers, artifactNotFound = 0 } = {}) {
|
||||
const calls = [];
|
||||
let artifactLookups = 0;
|
||||
const transport = async (input, options = {}) => {
|
||||
const url = new URL(input); calls.push({ url, options });
|
||||
if (status) return new Response("private-upstream-error", { status, headers });
|
||||
// GitHub can answer 404 for an artifact its run uploaded moments ago (euxy run 39348956443).
|
||||
if (url.pathname.endsWith("/actions/artifacts/20") && (artifactLookups += 1) <= artifactNotFound) return new Response("Not Found", { status: 404 });
|
||||
if (url.pathname.endsWith("/actions/artifacts/20")) return Response.json({ id: 20, name: artifactName, expired, workflow_run: { id: artifactRun } });
|
||||
if (url.pathname.endsWith("/actions/runs/10/attempts/1")) return Response.json({ id: 10, run_attempt: attempt, status: "in_progress", conclusion: null });
|
||||
if (url.pathname.endsWith("/pulls/1")) return Response.json({ state: "open", base: pr.base,
|
||||
@@ -191,7 +194,8 @@ test("report publication separates credential, permission, rate limit, and servi
|
||||
[503, {}, "GITHUB_REQUEST_FAILED", true, /service status/],
|
||||
]) {
|
||||
const { transport, calls } = transportFixture({ status, headers });
|
||||
await assert.rejects(publishCiReportComment({ inputPath, artifactUrl, environment, transport }), error => {
|
||||
const pauses = [];
|
||||
await assert.rejects(publishCiReportComment({ inputPath, artifactUrl, environment, transport, sleep: async milliseconds => { pauses.push(milliseconds); } }), error => {
|
||||
assert.equal(error.code, code);
|
||||
assert.equal(error.stage, "publication");
|
||||
assert.equal(error.retryable, retryable);
|
||||
@@ -200,9 +204,36 @@ test("report publication separates credential, permission, rate limit, and servi
|
||||
return true;
|
||||
});
|
||||
assert.equal(calls.some(call => call.options.method === "POST"), false);
|
||||
// Only a 5xx is looked up again; a bad token, a missing permission and a rate limit fail on the first answer.
|
||||
assert.equal(calls.length, status >= 500 ? 5 : 1, `${status} ${JSON.stringify(headers)}`);
|
||||
assert.equal(pauses.length, calls.length - 1);
|
||||
}
|
||||
});
|
||||
|
||||
test("an artifact GitHub does not list yet is looked up again, and one it never lists keeps the not-found failure", async t => {
|
||||
const { inputPath } = await fixture(t);
|
||||
const late = transportFixture({ artifactNotFound: 1 });
|
||||
const pauses = [];
|
||||
await publishCiReportComment({ inputPath, artifactUrl, environment, transport: late.transport, sleep: async milliseconds => { pauses.push(milliseconds); } });
|
||||
assert.equal(late.calls.filter(call => call.url.pathname.endsWith("/actions/artifacts/20")).length, 2);
|
||||
assert.equal(pauses.length, 1);
|
||||
assert.ok(late.calls.some(call => call.options.method === "POST"), "the comment is published once the artifact is found");
|
||||
|
||||
const missing = transportFixture({ artifactNotFound: Infinity });
|
||||
const waited = [];
|
||||
await assert.rejects(publishCiReportComment({ inputPath, artifactUrl, environment, transport: missing.transport, sleep: async milliseconds => { waited.push(milliseconds); } }), error => {
|
||||
assert.equal(error.code, "GITHUB_RESOURCE_NOT_FOUND");
|
||||
assert.equal(error.message, "Report publication GitHub check failed (404)");
|
||||
assert.match(error.nextAction, /artifact ID/);
|
||||
return true;
|
||||
});
|
||||
assert.equal(missing.calls.length, 5);
|
||||
assert.equal(waited.length, 4, "no pause after the last lookup");
|
||||
const total = waited.reduce((sum, milliseconds) => sum + milliseconds, 0);
|
||||
assert.ok(total >= 30_000 && total <= 60_000, `${total} ms of pauses`);
|
||||
assert.equal(missing.calls.some(call => call.options.method === "POST"), false);
|
||||
});
|
||||
|
||||
test("stale PRs, expired artifacts, foreign artifacts, and replayed attempts cannot announce Ready", async t => {
|
||||
const { inputPath } = await fixture(t);
|
||||
const moved = transportFixture({ stale: true });
|
||||
|
||||
@@ -67,7 +67,7 @@ test("baseline restore rejects foreign workflows, revisions, branches, and unfin
|
||||
event: "push", head_repository: { full_name: "acme/app" } };
|
||||
const mutations = [
|
||||
{ workflow_id: 99 }, { head_sha: "b".repeat(40) }, { head_branch: "feature" },
|
||||
{ conclusion: null }, { head_repository: { full_name: "fork/app" } }, { event: "pull_request_target" },
|
||||
{ conclusion: null }, { conclusion: "cancelled" }, { head_repository: { full_name: "fork/app" } }, { event: "pull_request_target" },
|
||||
];
|
||||
const runs = Object.fromEntries(mutations.map((mutation, i) => [i + 30, { ...valid, ...mutation, id: i + 30 }]));
|
||||
runs[20] = valid;
|
||||
@@ -90,6 +90,20 @@ test("baseline restore rejects foreign workflows, revisions, branches, and unfin
|
||||
assert.deepEqual(names, [`explore-baseline-${"a".repeat(40)}-ios`, `explore-baseline-${"a".repeat(40)}`], "iOS also accepts the unsuffixed name older baselines used");
|
||||
});
|
||||
|
||||
test("a target's baseline from a run another target's baseline failed in is still reused (brentvatne/euxy#172)", async () => {
|
||||
// The baseline job uploads its artifact only after its own steps passed, so the run's failure is another target's.
|
||||
const run = { id: 20, workflow_id: 77, conclusion: "failure", head_sha: "a".repeat(40), head_branch: "main", event: "push", head_repository: { full_name: "acme/app" } };
|
||||
const transport = async input => {
|
||||
const url = new URL(input);
|
||||
if (url.pathname === "/repos/acme/app") return Response.json({ default_branch: "main" });
|
||||
if (url.pathname === "/repos/acme/app/actions/workflows/explore-baseline.yml") return Response.json({ id: 77 });
|
||||
if (url.pathname === "/repos/acme/app/actions/artifacts") return Response.json({ artifacts: [{ id: 20, workflow_run: { id: 20 }, expired: false }] });
|
||||
if (url.pathname === "/repos/acme/app/actions/runs/20") return Response.json(run);
|
||||
throw new Error(`unexpected request ${url}`);
|
||||
};
|
||||
assert.deepEqual(await findBaselineArtifact({ sha: "a".repeat(40), target: "iphone", environment, transport }), { id: 20, run: 20 });
|
||||
});
|
||||
|
||||
test("a target's baseline is named after its id; only target ios also reuses the unsuffixed name", async () => {
|
||||
const lookups = async target => {
|
||||
const names = [];
|
||||
@@ -145,10 +159,19 @@ async function reportFailure(t, { capture, report, comments = [], pr = samplePr(
|
||||
const url = new URL(input);
|
||||
assert.equal(init.headers?.authorization, "Bearer test-token");
|
||||
if (url.pathname === "/repos/acme/app/pulls/91") return Response.json(pr);
|
||||
// The comments as GitHub holds them, so a second write merges into the first.
|
||||
if (url.pathname === "/repos/acme/app/issues/91/comments" && (init.method ?? "GET") === "GET") return Response.json(comments);
|
||||
if (url.pathname === "/repos/acme/app/issues/91/comments" && init.method === "POST") { writes.push({ action: "create", body: JSON.parse(init.body).body }); return Response.json({ id: 100 }); }
|
||||
if (url.pathname === "/repos/acme/app/issues/91/comments" && init.method === "POST") {
|
||||
const body = JSON.parse(init.body).body;
|
||||
writes.push({ action: "create", body }); comments = [...comments, { id: 100, user: { login: "github-actions[bot]" }, body }];
|
||||
return Response.json({ id: 100 });
|
||||
}
|
||||
const update = /^\/repos\/acme\/app\/issues\/comments\/(\d+)$/.exec(url.pathname);
|
||||
if (update && init.method === "PATCH") { writes.push({ action: "update", comment_id: Number(update[1]), body: JSON.parse(init.body).body }); return Response.json({ id: Number(update[1]) }); }
|
||||
if (update && init.method === "PATCH") {
|
||||
const body = JSON.parse(init.body).body;
|
||||
writes.push({ action: "update", comment_id: Number(update[1]), body }); comments = comments.map(comment => comment.id === Number(update[1]) ? { ...comment, body } : comment);
|
||||
return Response.json({ id: Number(update[1]) });
|
||||
}
|
||||
throw new Error(`unexpected request ${init.method ?? "GET"} ${url}`);
|
||||
};
|
||||
const result = await publishFailureComment({ repository: "acme/app", pullNumber: 91, headSha: head, baseSha: base, runId: "1234", runAttempt: "1",
|
||||
@@ -296,6 +319,51 @@ test("a failed target is named by its artifact and keeps the label and config or
|
||||
assert.equal(located.diagnostic.code, "APP_INPUT_MISSING");
|
||||
});
|
||||
|
||||
test("a lone failed job's diagnostics, which download-artifact extracts without its artifact's directory, still name the target (euxy#172 attempt 1)", async t => {
|
||||
// Run 39348956443 attempt 1: only duo-closed's report job failed (ci:publish's artifact lookup answered 404), so the
|
||||
// failure job's pattern matched one artifact, extracted into report/ itself, and the comment said "iOS failed".
|
||||
const report = { ...sampleDiagnostic(), code: "GITHUB_RESOURCE_NOT_FOUND", stage: "publication", message: "Report publication GitHub check failed (404)", target: "duo-closed" };
|
||||
const [write] = await reportFailure(t, { mutateFiles: async directory => {
|
||||
await mkdir(join(directory, "explore-failure", "report"), { recursive: true });
|
||||
await writeFile(join(directory, "explore-failure", "report", "error.json"), JSON.stringify(report));
|
||||
} });
|
||||
assert.match(write.body, /^<!-- expo-explore-record:duo-closed:/m);
|
||||
assert.match(write.body, /^\*\*duo\\-closed failed\*\* · publication · GITHUB\\_RESOURCE\\_NOT\\_FOUND/m);
|
||||
assert.doesNotMatch(write.body, /iOS failed/);
|
||||
// A capture diagnostics artifact on its own keeps its explore-diagnostics directory; a target id the file names is checked.
|
||||
const [capture] = await reportFailure(t, { mutateFiles: async directory => {
|
||||
await mkdir(join(directory, "explore-failure", "capture", "explore-diagnostics"), { recursive: true });
|
||||
await writeFile(join(directory, "explore-failure", "capture", "explore-diagnostics", "error.json"), JSON.stringify({ ...sampleDiagnostic(), target: "duo-open" }));
|
||||
} });
|
||||
assert.match(capture.body, /^\*\*duo\\-open failed\*\* · capture\\-head · APP\\_INPUT\\_MISSING/m);
|
||||
const [invalid] = await reportFailure(t, { mutateFiles: async directory => {
|
||||
await mkdir(join(directory, "explore-failure", "report"), { recursive: true });
|
||||
await writeFile(join(directory, "explore-failure", "report", "error.json"), JSON.stringify({ ...report, target: "../ios" }));
|
||||
} });
|
||||
assert.match(invalid.body, /^<!-- expo-explore-record:ios:/m, "an invalid target id is no target: the record falls back to ios, as before targets");
|
||||
});
|
||||
|
||||
test("every failed target of a run gets its own failed record, and a target's report failure outranks its capture's", async t => {
|
||||
const { locateFailureDiagnostics } = await import("../../dist/report/failure-comment.js");
|
||||
const writes = await reportFailure(t, { mutateFiles: async directory => {
|
||||
const root = join(directory, "explore-failure");
|
||||
// Every capture leg uploads diagnostics; only the failed ones hold an error.json.
|
||||
for (const target of ["iphone", "duo-closed", "duo-open", "android"]) await mkdir(join(root, "capture", `explore-diagnostics-1234-1-${target}`, "explore-diagnostics"), { recursive: true });
|
||||
await writeFile(join(root, "capture", "explore-diagnostics-1234-1-duo-open", "explore-diagnostics", "error.json"), JSON.stringify({ ...sampleDiagnostic(), code: "CONTROLLER_READER_STUCK", stage: "session" }));
|
||||
await writeFile(join(root, "capture", "explore-diagnostics-1234-1-android", "explore-diagnostics", "error.json"), JSON.stringify(sampleDiagnostic()));
|
||||
await mkdir(join(root, "report", "explore-report-diagnostics-1234-1-android"), { recursive: true });
|
||||
await writeFile(join(root, "report", "explore-report-diagnostics-1234-1-android", "error.json"), JSON.stringify({ ...sampleDiagnostic(), code: "REPORT_EXPORT_FAILED", stage: "export" }));
|
||||
const located = await locateFailureDiagnostics(root);
|
||||
assert.deepEqual(located.map(failure => [failure.target, failure.diagnostic.code]), [["android", "REPORT_EXPORT_FAILED"], ["duo-open", "CONTROLLER_READER_STUCK"]]);
|
||||
} });
|
||||
assert.equal(writes.length, 2);
|
||||
assert.equal(writes[1].action, "update", "the second failure merges into the comment the first created");
|
||||
assert.match(writes[1].body, /^\*\*Android failed\*\* · export · REPORT\\_EXPORT\\_FAILED/m);
|
||||
assert.match(writes[1].body, /^\*\*duo\\-open failed\*\* · session · CONTROLLER\\_READER\\_STUCK/m);
|
||||
assert.doesNotMatch(writes[1].body, /APP\\_INPUT\\_MISSING/);
|
||||
assert.deepEqual(writes.result, { posted: true });
|
||||
});
|
||||
|
||||
test("ci.trustedAuthors on the default branch admits listed authors without write access, nobody else", async t => {
|
||||
const block = "app:\n bundleId: com.acme.app\nci:\n trustedAuthors:\n - devin-ai-integration[bot] # reviews\n - 'Renovate[bot]'\nreport:\n preview:\n hosting: eas\n";
|
||||
const flow = "ci: # bots\n trustedAuthors: [\"devin-ai-integration[bot]\", 'renovate[bot]'] # quoted: plain scalars cannot hold [ ] in flow style\n";
|
||||
|
||||
Reference in new issue
Block a user