rentahuman-mcp 2.0.0 → 2.2.0

package/README.md

@@ -277,6 +277,44 @@ Only workers whose profile country matches can apply or receive automatic
 outreach. The country gate still applies when remote work is allowed. Include a
 `city` for city-level targeting instead.
 
+#### Completion deadline (auto-reassign)
+
+The bounty-level `deadline` is the application cutoff. At or after that time,
+the listing leaves discovery and rejects new applications and direct uploads;
+it does not create a per-worker completion timer. Use `completionWindowHours`
+for accepted work:
+
+`create_bounty` and `update_bounty` accept `completionWindowHours` (number,
+1-720; `update_bounty` also accepts `null` to disable). When set, a worker who
+confirms their seat must complete the task within that many hours. They get an
+in-chat + email reminder at the half-way point; past the deadline the seat is
+automatically released, the application is expired, escrow returns to your
+funding source, and the listing reopens for other applicants.
+
+Workers may request more time. Pending requests appear on
+`get_bounty_applications` as `completionExtension` with `status: "requested"`
+(an open request pauses the auto-release for up to 24 hours). Answer with the
+`decide_extension_request` tool: `action: "approve"` grants the requested
+hours, `"deny"` resumes the original deadline, and `"grant"` with `hours`
+extends proactively — with or without an open request. For AI-managed bounties
+`completionWindowHours` overrides the default 6-hour managed work window;
+managed seats handle blockers through their own issue-report flow instead of
+extension requests.
+
+#### Automatic applicant review (autoAccept)
+
+`create_bounty` and `update_bounty` accept `autoAccept` (boolean, default
+true). When on, every new application is reviewed automatically: deterministic
+checks always run (account standing, country eligibility, payout viability,
+your blocklist), and an AI review runs only when the application contains
+free-text screening answers that need judgment. Qualified applicants are
+accepted (the standard worker-confirmation window still applies unless
+`skipAcceptanceConfirmation` is set), clear mismatches are rejected with a
+reason, and uncertain cases stay pending for your manual review via
+`get_bounty_applications` + `accept_application`. Pass `autoAccept: false` to
+review and accept every application yourself. Ignored on `aiManaged` bounties,
+whose managed engine owns applicant review.
+
 #### Microphone quality requirement
 
 `create_bounty` and `update_bounty` accept `micCheckRequired` (boolean, default

package/dist/serve.js

@@ -854,10 +854,58 @@ Use \`create_bounty\` with \`dryRun=true\` first:
 - Confirm the budget and evidence requirements
 - Post only after the user approves the preview
 
+### Writing a Great Bounty
+
+Well-specified bounties attract better applicants and avoid disputes. Always set:
+
+1. **Title + description** \u2014 a clear title (5\u2013200 chars) and a description more
+   detailed than the raw request. Expand a brief ask into a proper task spec.
+   Never put personal information (addresses, phone numbers, real names) in the
+   public description \u2014 share those privately in chat after acceptance.
+2. **Definition of done** (\`completionCriteria\`) \u2014 specific, measurable
+   criteria for what counts as complete.
+3. **Evidence** (\`evidenceTypes\` + \`evidenceCriteria\`) \u2014 always set both.
+   Rules of thumb:
+   - Anything physical/in-person: timestamped photos AND at least one short
+     video clip \u2014 still photos alone are easy to fake.
+   - Anything online: a live link PLUS a screenshot, because links can 404 or
+     get removed.
+   - Location-specific tasks: evidence must show the location (landmark,
+     storefront, street sign).
+4. **Requirements + skills** \u2014 infer concrete qualifications from the task
+   (e.g. "own professional camera equipment", "comfortable being in public").
+5. **Price** \u2014 fixed USD by default. Anchor to real-world freelancer rates for
+   the effort, location, urgency, and skill level. Underpriced bounties get
+   low-quality applicants.
+6. **Application cutoff** (\`deadline\`) \u2014 always set one; it must be in the
+   future. At the cutoff the listing leaves discovery and stops accepting new
+   applications or direct uploads. If accepted workers also need a time limit,
+   set \`completionWindowHours\`; that clock starts when each worker confirms
+   their seat.
+
+**Application screening (\`applicationDetails\`)** \u2014 standard application
+bounties support pre-acceptance screening items: text questions, acknowledgment
+checkboxes, file uploads, and one required \`live_video\` field whose label is a
+script the applicant must record with the in-browser camera (pre-recorded files
+are rejected server-side).
+
+**Appearance-based bounties MUST include the live-video gate.** When the worker
+appears on camera or their appearance/presence is part of the deliverable \u2014
+sign holding, UGC, sponsored posts, on-camera video, brand-ambassador or
+GTM/promo appearances \u2014 always include one required \`live_video\` item with a
+label like: "Record a short video of yourself explaining, in 2 sentences, why
+you'd be a great fit for this task." This gives the poster a real look at each
+applicant before accepting. (Not applicable to direct-upload \`submissionMode\`
+bounties, which don't support \`applicationDetails\`.)
+
+Never use screening items to ask for passwords, OTP/2FA codes, API keys,
+government IDs, bank details, exact home addresses, or other sensitive personal
+information.
+
 For the fully managed beta, pass \`aiManaged: true\` and the platform will recruit
 and vet workers, review chat-delivered submissions, release approved payments,
 refund unused budget, and produce a final report. Managed bounties require a
-fixed USD price and 1\u201320 spots and cannot use \`mode: 'auto'\`. Poll the bounty's
+fixed USD price and 1\u201350 spots and cannot use \`mode: 'auto'\`. Poll the bounty's
 managed run or subscribe to \`run.report_ready\` for the finished work.
 
 ### Start a Conversation
@@ -1399,7 +1447,6 @@ function calculatePlatformFee(baseAmountCents) {
 }
 
 // ../contracts/src/schemas/requests/bounty.ts
-var BOUNTY_FIAT_CURRENCIES = ["USD", "EUR"];
 var BountyLocationRequest = Schema5.Struct({
   city: Schema5.optional(Schema5.String.pipe(Schema5.maxLength(100))),
   state: Schema5.optional(Schema5.String.pipe(Schema5.maxLength(100))),
@@ -1555,7 +1602,7 @@ var CreateBountyRequest = Schema5.Struct({
     description: BOUNTY_LOCATION_DESCRIPTION
   }),
   deadline: Schema5.optional(Schema5.String).annotations({
-    description: "Deadline for task completion (ISO 8601 format)"
+    description: "Application cutoff (ISO 8601 format). At or after this time, the listing is removed from discovery and no new applications or direct uploads are accepted. Use completionWindowHours for a post-acceptance completion deadline."
   }),
   estimatedHours: Schema5.Number.pipe(
     Schema5.finite(),
@@ -1572,10 +1619,8 @@ var CreateBountyRequest = Schema5.Struct({
   ).annotations({
     description: `Price in the specified currency (minimum $${BOUNTY_MIN_PRICE_USD})`
   }),
-  currency: Schema5.optional(
-    Schema5.Literal(...BOUNTY_FIAT_CURRENCIES)
-  ).annotations({
-    description: "USD or EUR (default USD)"
+  currency: Schema5.optional(Schema5.Literal("USD")).annotations({
+    description: "USD (default and only supported bounty currency)"
   }),
   bountyKind: Schema5.optional(Schema5.Literal("one_shot")).annotations({
     description: "Agent-facing bounty creation only supports one-shot bounties. Ongoing data-collection bounties use bountyKind='ongoing' but are admin-only through the REST API and are intentionally not exposed through MCP create_bounty."
@@ -1599,9 +1644,21 @@ var CreateBountyRequest = Schema5.Struct({
   autoExpireGhosts: Schema5.optional(Schema5.Boolean).annotations({
     description: "When true (and responseWindowHours is set), a ghosting worker\u2019s seat is automatically released at the deadline: their application is expired, the seat is freed, and the listing reopens for other applicants."
   }),
+  completionWindowHours: Schema5.optional(
+    Schema5.Number.pipe(
+      Schema5.int(),
+      Schema5.greaterThanOrEqualTo(1),
+      Schema5.lessThanOrEqualTo(720)
+    )
+  ).annotations({
+    description: "Auto-reassign completion deadline: hours a worker has to complete the task after confirming their seat (1-720). Workers are reminded at half the window; when the deadline passes the seat is automatically released and the listing reopens for other applicants. Workers may request an extension, which you approve, deny, or replace with your own via POST /bounties/{id}/applications/{appId}/extension/decision. For AI-managed bounties this overrides the default 6-hour work window. Omit for no completion deadline."
+  }),
   keepApplicantsOnFill: Schema5.optional(Schema5.Boolean).annotations({
     description: "When true, pending applicants are kept (not auto-rejected) once all seats fill, so you can reuse the applicant pool after reopening or adding seats. Default false."
   }),
+  autoAccept: Schema5.optional(Schema5.Boolean).annotations({
+    description: "Automatically review applicants as they apply. Deterministic checks (account standing, country eligibility, payout viability, your blocklist) always run; an AI review runs only when the application contains free-text screening answers that need judgment. Qualified applicants are accepted (the standard worker-confirmation window still applies unless skipAcceptanceConfirmation is set), clear mismatches are rejected with a reason, and uncertain cases stay pending for your manual review. Default true; pass false to review and accept every application yourself. Ignored for aiManaged bounties, whose managed engine owns applicant review."
+  }),
   identityRequired: Schema5.optional(Schema5.Boolean).annotations({
     description: "Require applicants to pass an identity check (government ID) before applying. Verified once per account and reused across bounties. Default false."
   }),
@@ -1609,7 +1666,7 @@ var CreateBountyRequest = Schema5.Struct({
     description: "Require applicants to pass an on-device microphone quality check (live recording scored for noise, clipping, Bluetooth-headset bandwidth, and DNSMOS speech quality) before applying. Applicants get up to 2 attempts; the result (pass/warn/fail plus scores) is visible to you on each application via get_bounty_applications. Default false."
   }),
   aiManaged: Schema5.optional(Schema5.Literal(true)).annotations({
-    description: "BETA \u2014 fully AI-managed bounty. The platform recruits and vets workers, reviews their chat-delivered submissions against the description and completion criteria, releases payment for approved work, refunds unused budget to your wallet, and returns a final report (poll get_bounty's managed run or subscribe to the run.report_ready webhook). Requires fixed price in USD and 1-20 spots. Currently in beta \u2014 the API returns 403 managed_bounties_beta_disabled when unavailable."
+    description: "BETA \u2014 fully AI-managed bounty. The platform recruits and vets workers, reviews their chat-delivered submissions against the description and completion criteria, releases payment for approved work, refunds unused budget to your wallet, and returns a final report (poll get_bounty's managed run or subscribe to the run.report_ready webhook). Requires fixed price in USD and 1-50 spots. Currently in beta \u2014 the API returns 403 managed_bounties_beta_disabled when unavailable."
   }),
   submissionMode: Schema5.optional(
     Schema5.Literal(...BOUNTY_SUBMISSION_MODES)
@@ -1775,7 +1832,7 @@ var UpdateBountyRequest = Schema5.Struct({
     description: "New estimated duration in hours (min 5 minutes = 0.083)"
   }),
   deadline: Schema5.optional(Schema5.String).annotations({
-    description: "New deadline (ISO 8601 format, or null to remove)"
+    description: "New application cutoff (ISO 8601 format). At or after this time, no new applications or direct uploads are accepted. This does not retime accepted workers; use completionWindowHours for future confirmed seats."
   }),
   requirements: Schema5.optional(Schema5.Array(Schema5.String)).annotations({
     description: "New requirements list"
@@ -1813,6 +1870,17 @@ var UpdateBountyRequest = Schema5.Struct({
   autoExpireGhosts: Schema5.optional(Schema5.Boolean).annotations({
     description: "When true (with responseWindowHours set), ghosting workers\u2019 seats are auto-released at the deadline and the listing reopens."
   }),
+  completionWindowHours: Schema5.optional(
+    Schema5.NullOr(
+      Schema5.Number.pipe(
+        Schema5.int(),
+        Schema5.greaterThanOrEqualTo(1),
+        Schema5.lessThanOrEqualTo(720)
+      )
+    )
+  ).annotations({
+    description: "Auto-reassign completion deadline in hours (1-720), or null to disable. Only affects seats confirmed after the edit \u2014 live per-worker deadlines are not re-timed."
+  }),
   spotsAvailable: Schema5.optional(
     Schema5.Number.pipe(
       Schema5.int(),
@@ -1825,6 +1893,9 @@ var UpdateBountyRequest = Schema5.Struct({
   keepApplicantsOnFill: Schema5.optional(Schema5.Boolean).annotations({
     description: "When true, pending applicants are kept (not auto-rejected) once all seats fill, so you can draw from the same pool after reopening or adding seats. Default false."
   }),
+  autoAccept: Schema5.optional(Schema5.Boolean).annotations({
+    description: "Turn automatic applicant review on or off. When on, deterministic checks always run and an AI review runs only for free-text screening answers; qualified applicants are accepted, clear mismatches rejected, uncertain cases left pending. Applications received while off stay pending; toggling on affects future applications only. Ignored on aiManaged bounties."
+  }),
   completionCriteria: Schema5.optional(
     Schema5.String.pipe(Schema5.minLength(10), Schema5.maxLength(2e3))
   ).annotations({
@@ -2031,6 +2102,24 @@ var ExpireApplicationRequest = Schema5.Struct({
     description: "Optional human-readable reason shown to the released worker (e.g. why the seat was reclaimed). Defaults to a generic no-activity explanation."
   })
 });
+var DecideExtensionRequest = Schema5.Struct({
+  bountyId: Schema5.String.annotations({ description: "The bounty ID" }),
+  applicationId: Schema5.String.annotations({
+    description: "The accepted application whose completion deadline to decide"
+  }),
+  action: Schema5.Literal("approve", "deny", "grant").annotations({
+    description: "'approve' grants the worker's open extension request, 'deny' declines it (the original deadline resumes), 'grant' extends by `hours` whether or not a request is open."
+  }),
+  hours: Schema5.optional(
+    Schema5.Number.pipe(
+      Schema5.int(),
+      Schema5.greaterThanOrEqualTo(1),
+      Schema5.lessThanOrEqualTo(720)
+    )
+  ).annotations({
+    description: "Extension length in hours. Required for 'grant'; for 'approve' it is only the fallback when the request did not name an hour count."
+  })
+});
 var GetBountyRequest = Schema5.Struct({
   bountyId: Schema5.String.annotations({
     description: "The unique ID of the bounty"
@@ -2055,7 +2144,6 @@ import { Schema as Schema7 } from "effect";
 
 // ../contracts/src/validation/qa-assignment-contract.ts
 import { Either, Schema as Schema6 } from "effect";
-var QA_ASSIGNMENT_CONTRACT_VERSION = 1;
 var QaAssignmentEligibilitySchema = Schema6.Struct({
   id: Schema6.String,
   label: Schema6.String,
@@ -2074,7 +2162,7 @@ var QaAssignmentCriterionSchema = Schema6.Struct({
   origin: Schema6.optional(Schema6.Literal("owner"))
 });
 var QaAssignmentContractSchema = Schema6.Struct({
-  version: Schema6.Literal(QA_ASSIGNMENT_CONTRACT_VERSION),
+  version: Schema6.Literal(1, 2),
   eligibility: Schema6.Array(QaAssignmentEligibilitySchema),
   task: Schema6.Struct({
     targetUrl: Schema6.String,
@@ -2083,7 +2171,9 @@ var QaAssignmentContractSchema = Schema6.Struct({
   }),
   submission: Schema6.Struct({
     evidenceMode: Schema6.Literal("photo", "video", "document"),
-    criteria: Schema6.Array(QaAssignmentCriterionSchema)
+    criteria: Schema6.Array(QaAssignmentCriterionSchema),
+    /** When 'required', every origin:'owner' criterion must be bound to video evidence at submission time. */
+    checklistEvidence: Schema6.optional(Schema6.Literal("required"))
   })
 });
 
@@ -2182,6 +2272,8 @@ var BountyPublicResponse = Schema7.Struct({
   fundingMethod: Schema7.optional(Schema7.String),
   identityRequired: Schema7.optional(Schema7.Boolean),
   micCheckRequired: Schema7.optional(Schema7.Boolean),
+  completionWindowHours: Schema7.optional(Schema7.Number),
+  autoAccept: Schema7.optional(Schema7.Boolean),
   requiredQualificationIds: Schema7.optional(Schema7.Array(Schema7.String)),
   supportedCountries: Schema7.optional(Schema7.Array(Schema7.String)),
   intakeClosedCountries: Schema7.optional(Schema7.Array(Schema7.String)),
@@ -2269,9 +2361,14 @@ var expireApplicationSpec = {
   description: "Release a previously accepted seat when the worker has ghosted (no message or submission after being accepted). Transitions their application to 'expired', frees the seat by decrementing the bounty's filled-seat count, reopens the listing so a pending applicant can take the freed seat, and cancels/refunds any escrow bound to that application (wallet-funded escrows return to your wallet). The released worker is notified. Owner only; only works on 'accepted' applications.",
   input: ExpireApplicationRequest
 };
+var decideExtensionSpec = {
+  name: "decide_extension_request",
+  description: "Answer a worker's completion-deadline extension request on one of your bounties, or proactively extend a worker's deadline. Only meaningful when the bounty sets completionWindowHours. 'approve' grants the worker's requested hours, 'deny' declines (the original deadline resumes and the overdue seat will auto-release), 'grant' extends by `hours` with or without an open request. Pending requests appear on applications from get_bounty_applications as completionExtension with status 'requested'; an open request pauses the auto-release for up to 24 hours. Owner only.",
+  input: DecideExtensionRequest
+};
 var updateBountySpec = {
   name: "update_bounty",
-  description: "Update ordinary one-shot bounty details. You can modify the title, description, price, deadline, location, requiredLinks, applicationDetails, lifecycleMessages, liveCaptureRequirement, reactivate hidden inactive bounties, and more. To target an entire country, pass location with an ISO country code and isRemoteAllowed=false while omitting city and state. Live capture and required-link requirements can only be changed before applications are received. applicationDetails may be changed after applications are received; existing applications keep their original answers, while future applications use the latest fields. applicationDetails are application detail items for standard application bounties only; blank rows are ignored, uploads are capped at 3 fields, acknowledgments at 5 fields, and camera-only live_video at 1 required field. lifecycleMessages can define auto-message templates for acceptance, rejection, and submission review transitions. Admin-only ongoing bounty settings are intentionally not exposed through MCP. You can also pause/unpause a bounty (status 'paused'/'open'), close an unassigned bounty and return its unused funding (status 'closed'), increase seats via spotsAvailable, and keep pending applicants on fill via keepApplicantsOnFill. Use cancel_bounty for cancellation and refund handling. Work completion and payment are system-managed from escrow and payout evidence; status 'completed' and 'paid' cannot be set directly.",
+  description: "Update ordinary one-shot bounty details. You can modify the title, description, price, application-cutoff deadline, location, requiredLinks, applicationDetails, lifecycleMessages, liveCaptureRequirement, reactivate hidden inactive bounties, and more. The deadline stops new applications and direct uploads; completionWindowHours controls post-acceptance completion timing. To target an entire country, pass location with an ISO country code and isRemoteAllowed=false while omitting city and state. Live capture and required-link requirements can only be changed before applications are received. applicationDetails may be changed after applications are received; existing applications keep their original answers, while future applications use the latest fields. applicationDetails are application detail items for standard application bounties only; blank rows are ignored, uploads are capped at 3 fields, acknowledgments at 5 fields, and camera-only live_video at 1 required field. lifecycleMessages can define auto-message templates for acceptance, rejection, and submission review transitions. Admin-only ongoing bounty settings are intentionally not exposed through MCP. You can also pause/unpause a bounty (status 'paused'/'open'), close an unassigned bounty and return its unused funding (status 'closed'), increase seats via spotsAvailable, keep pending applicants on fill via keepApplicantsOnFill, and change the auto-reassign completion deadline via completionWindowHours (null disables; only affects seats confirmed after the edit), and toggle automatic applicant review via autoAccept (applications received while off stay pending; toggling on affects future applications only; ignored on aiManaged bounties). Use cancel_bounty for cancellation and refund handling. Work completion and payment are system-managed from escrow and payout evidence; status 'completed' and 'paid' cannot be set directly.",
   input: UpdateBountyRequest
 };
 var cancelBountySpec = {
@@ -3143,10 +3240,14 @@ var handleCreateBounty = (args) => Effect9.gen(function* () {
       currency,
       spotsAvailable,
       ...params.aiManaged !== void 0 ? { aiManaged: params.aiManaged } : {},
+      // Default-on unless explicitly disabled; aiManaged bounties never
+      // store the flag (the managed engine owns applicant review).
+      ...params.aiManaged ? {} : { autoAccept: params.autoAccept !== false },
       requirements: params.requirements || [],
       skillsNeeded: params.skillsNeeded || [],
       identityRequired: params.identityRequired || false,
       keepApplicantsOnFill: params.keepApplicantsOnFill || false,
+      completionWindowHours: params.completionWindowHours ?? null,
       requiredLinks: params.requiredLinks || [],
       applicationDetails: screeningFields,
       submissionMode: params.submissionMode || "application",
@@ -3193,6 +3294,7 @@ var handleCreateBounty = (args) => Effect9.gen(function* () {
       price: params.price,
       currency: params.currency || "USD",
       ...params.aiManaged !== void 0 ? { aiManaged: params.aiManaged } : {},
+      ...params.aiManaged ? {} : { autoAccept: params.autoAccept !== false },
       status: "open",
       applicationCount: 0,
       viewCount: 0,
@@ -3200,6 +3302,7 @@ var handleCreateBounty = (args) => Effect9.gen(function* () {
       micCheckRequired: params.micCheckRequired || false,
       liveCaptureRequirement: params.liveCaptureRequirement,
       keepApplicantsOnFill: params.keepApplicantsOnFill || false,
+      ...params.completionWindowHours !== void 0 ? { completionWindowHours: params.completionWindowHours } : {},
       requiredLinks: params.requiredLinks || [],
       applicationDetails: screeningFields,
       submissionMode: params.submissionMode || "application",
@@ -3615,6 +3718,36 @@ var expireApplicationTool = toMcpTool(
     return ok(result);
   })
 );
+var decideExtensionTool = toMcpTool(
+  decideExtensionSpec,
+  (params) => Effect9.gen(function* () {
+    const identity2 = yield* Identity;
+    const api = yield* ApiClient;
+    const rateLimit = yield* RateLimit;
+    const config = yield* McpConfig;
+    yield* rateLimit.check("decide_extension_request");
+    if (config.mockMode) {
+      return ok({
+        success: true,
+        action: params.action,
+        message: params.action === "deny" ? "Extension declined (mock)." : "Deadline extended (mock).",
+        mode: "mock"
+      });
+    }
+    const verification = yield* identity2.createVerification(
+      `extension_decision:${params.bountyId}:${params.applicationId}`
+    );
+    const result = yield* api.post(
+      `/bounties/${params.bountyId}/applications/${params.applicationId}/extension/decision`,
+      {
+        action: params.action,
+        ...params.hours !== void 0 ? { hours: params.hours } : {},
+        ...verification
+      }
+    );
+    return ok(result);
+  })
+);
 var getBountyOutreachStatusTool = toMcpTool(
   getBountyOutreachStatusSpec,
   (params) => Effect9.gen(function* () {
@@ -3668,7 +3801,7 @@ var payEnterpriseBountyTool = toMcpTool(
 var bountyTools = [
   {
     name: "create_bounty",
-    description: "Create a one-shot task bounty for humans to apply to. To target an entire country, pass location with an ISO country code and isRemoteAllowed=false while omitting city and state. **IMPORTANT: Always call with dryRun=true first** to preview the bounty. Dry-run `preview.fundingTotal` is the total funding requirement before any existing wallet balance is applied. Show that estimate to the operator before posting. Show the preview to the user and ask 'Here's your bounty \u2014 would you like to edit anything before posting?' Only call again with dryRun=false (or omitted) after the user confirms. **You MUST help the user define completionCriteria and evidenceTypes** \u2014 ask what 'done' looks like and what proof they need (text/data, photos, video, or links). For specialized standard-application tasks, configure applicationDetails so applicants provide application details before review. Blank rows are ignored; application upload fields are one file each and capped at 3 total; acknowledgment checkboxes are capped at 5 total and can be optional or required; and one required live_video field may contain a script applicants must record with the in-browser camera. Do not ask for passwords, OTP/2FA codes, API keys, private keys, seed phrases, government IDs, bank/card details, exact home addresses, dates of birth, or other sensitive personal information. For direct-review collection bounties, use submissionMode='photo_upload', 'video_upload', or 'document_upload' with matching submission settings instead of applicationDetails. lifecycleMessages can define auto-message templates for acceptance, rejection, and submission review transitions. You can require applicants to provide specific links (LinkedIn, GitHub, resume, etc.) using the requiredLinks parameter. Requires RENTAHUMAN_API_KEY from the account owner. Standard accounts use available wallet balance first; if the wallet cannot cover the bounty, the response includes deposit_url and checkout_total (the hosted charge after wallet balance is applied) and the account owner must complete checkout before the bounty is visible. Supports multi-person bounties by setting spotsAvailable > 1. Ongoing data-collection programs are managed separately and cannot be created through this tool. Pass optional `idempotencyKey` to make this safe to retry (a replayed key returns the original result instead of duplicating). BETA: pass aiManaged: true to have the platform fully manage the bounty \u2014 automated recruiting, vetting, submission review, payment release, and a final report. Fixed price USD only, 1-20 spots. Poll the bounty's managed run or subscribe to run.report_ready for the finished work.",
+    description: "Create a one-shot task bounty for humans to apply to. To target an entire country, pass location with an ISO country code and isRemoteAllowed=false while omitting city and state. **IMPORTANT: Always call with dryRun=true first** to preview the bounty. Dry-run `preview.fundingTotal` is the total funding requirement before any existing wallet balance is applied. Show that estimate to the operator before posting. Show the preview to the user and ask 'Here's your bounty \u2014 would you like to edit anything before posting?' Only call again with dryRun=false (or omitted) after the user confirms. **You MUST help the user define completionCriteria and evidenceTypes** \u2014 ask what 'done' looks like and what proof they need (text/data, photos, video, or links). For specialized standard-application tasks, configure applicationDetails so applicants provide application details before review. Blank rows are ignored; application upload fields are one file each and capped at 3 total; acknowledgment checkboxes are capped at 5 total and can be optional or required; and one required live_video field may contain a script applicants must record with the in-browser camera. For appearance-based bounties where the worker appears on camera or their presence is part of the deliverable (sign holding, UGC, sponsored posts, on-camera video, promo/GTM appearances), always include one required live_video field with a label asking the applicant to explain in two sentences why they are a good fit \u2014 this gates applications on a live self-recorded video so the poster sees each applicant before accepting. Do not ask for passwords, OTP/2FA codes, API keys, private keys, seed phrases, government IDs, bank/card details, exact home addresses, dates of birth, or other sensitive personal information. For direct-review collection bounties, use submissionMode='photo_upload', 'video_upload', or 'document_upload' with matching submission settings instead of applicationDetails. lifecycleMessages can define auto-message templates for acceptance, rejection, and submission review transitions. You can require applicants to provide specific links (LinkedIn, GitHub, resume, etc.) using the requiredLinks parameter. Requires RENTAHUMAN_API_KEY from the account owner. Standard accounts use available wallet balance first; if the wallet cannot cover the bounty, the response includes deposit_url and checkout_total (the hosted charge after wallet balance is applied) and the account owner must complete checkout before the bounty is visible. Supports multi-person bounties by setting spotsAvailable > 1. Set completionWindowHours (1-720) to give confirmed workers a completion deadline: overdue seats auto-release and reopen for other applicants; workers may request extensions you answer with decide_extension_request. Ongoing data-collection programs are managed separately and cannot be created through this tool. Pass optional `idempotencyKey` to make this safe to retry (a replayed key returns the original result instead of duplicating). Applicants are auto-reviewed by default (autoAccept, default true): deterministic checks always run and an AI review runs only for free-text screening answers \u2014 qualified applicants are accepted, clear mismatches rejected with a reason, uncertain cases left pending for manual review; pass autoAccept: false to review and accept every application yourself. BETA: pass aiManaged: true to have the platform fully manage the bounty \u2014 automated recruiting, vetting, submission review, payment release, and a final report. Fixed price USD only, 1-50 spots. Poll the bounty's managed run or subscribe to run.report_ready for the finished work.",
     inputSchema: toInputSchema(CreateBountyRequest),
     handler: handleCreateBounty
   },
@@ -3686,6 +3819,7 @@ var bountyTools = [
   acceptApplicationTool,
   rejectApplicationTool,
   expireApplicationTool,
+  decideExtensionTool,
   getBountyOutreachStatusTool,
   boostBountyOutreachTool,
   payEnterpriseBountyTool
@@ -4650,7 +4784,7 @@ var CreateHumanizationRequest = Schema13.Struct({
     Schema13.greaterThanOrEqualTo(BOUNTY_MIN_PRICE_USD * 100),
     Schema13.lessThanOrEqualTo(MAX_PRICE_CENTS)
   ),
-  currency: Schema13.optionalWith(Schema13.Literal("USD", "EUR"), {
+  currency: Schema13.optionalWith(Schema13.Literal("USD"), {
     default: () => "USD"
   }),
   applicantScreening: Schema13.optional(
@@ -7680,7 +7814,10 @@ var req = createRequire(import.meta.url);
 var { version } = req("../package.json");
 var server = new Server(
   { name: "rentahuman-mcp", version },
-  { capabilities: { tools: {}, resources: {} } }
+  {
+    capabilities: { tools: {}, resources: {} },
+    instructions: 'RentAHuman lets AI agents hire humans for real-world tasks. Before creating your first bounty, read the rentahuman://guide resource \u2014 especially the "Writing a Great Bounty" section covering definition of done, evidence requirements, pricing, application screening, and the required live-video application gate for appearance-based work (sign holding, UGC, sponsored posts, promo appearances).'
+  }
 );
 server.setRequestHandler(ListToolsRequestSchema, async () => {
   const tools = await runtime.runPromise(

package/dist/types/index.d.ts

@@ -65,12 +65,14 @@ declare const CreateBountyRequest: Schema.Struct<{
     estimatedHours: Schema.refine<number, Schema.filter<typeof Schema.Number>>;
     priceType: Schema.Literal<["fixed", "hourly"]>;
     price: Schema.refine<number, Schema.filter<typeof Schema.Number>>;
-    currency: Schema.optional<Schema.Literal<["USD", "EUR"]>>;
+    currency: Schema.optional<Schema.Literal<["USD"]>>;
     bountyKind: Schema.optional<Schema.Literal<["one_shot"]>>;
     spotsAvailable: Schema.optional<Schema.filter<Schema.filter<typeof Schema.Number>>>;
     responseWindowHours: Schema.optional<Schema.filter<Schema.filter<typeof Schema.Number>>>;
     autoExpireGhosts: Schema.optional<typeof Schema.Boolean>;
+    completionWindowHours: Schema.optional<Schema.filter<Schema.filter<Schema.filter<typeof Schema.Number>>>>;
     keepApplicantsOnFill: Schema.optional<typeof Schema.Boolean>;
+    autoAccept: Schema.optional<typeof Schema.Boolean>;
     identityRequired: Schema.optional<typeof Schema.Boolean>;
     micCheckRequired: Schema.optional<typeof Schema.Boolean>;
     aiManaged: Schema.optional<Schema.Literal<[true]>>;
@@ -145,8 +147,10 @@ declare const UpdateBountyRequest: Schema.Struct<{
     micCheckRequired: Schema.optional<typeof Schema.Boolean>;
     responseWindowHours: Schema.optional<Schema.filter<Schema.filter<typeof Schema.Number>>>;
     autoExpireGhosts: Schema.optional<typeof Schema.Boolean>;
+    completionWindowHours: Schema.optional<Schema.NullOr<Schema.filter<Schema.filter<Schema.filter<typeof Schema.Number>>>>>;
     spotsAvailable: Schema.optional<Schema.filter<Schema.filter<Schema.filter<typeof Schema.Number>>>>;
     keepApplicantsOnFill: Schema.optional<typeof Schema.Boolean>;
+    autoAccept: Schema.optional<typeof Schema.Boolean>;
     completionCriteria: Schema.optional<Schema.filter<Schema.filter<typeof Schema.String>>>;
     evidenceTypes: Schema.optional<Schema.filter<Schema.Array$<Schema.Literal<["text", "photo", "video", "link"]>>>>;
     evidenceCriteria: Schema.optional<Schema.filter<typeof Schema.String>>;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rentahuman-mcp",
-  "version": "2.0.0",
+  "version": "2.2.0",
   "description": "MCP server for AI agents to browse and book humans on rentahuman.ai",
   "keywords": [
     "ai",
@@ -63,7 +63,7 @@
   "devDependencies": {
     "@types/node": "^25.9.5",
     "tsup": "^8.5.1",
-    "tsx": "^4.23.1",
+    "tsx": "^4.23.12",
     "typescript": "^5.9.3"
   },
   "engines": {