@pylonsync/create-pylon 0.4.21 → 0.4.22

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pylonsync/create-pylon",
-  "version": "0.4.21",
+  "version": "0.4.22",
   "description": "Scaffold a new Pylon app — realtime backend + web/mobile/expo frontends in one command. Run via `npm create @pylonsync/pylon@latest`.",
   "publishConfig": {
     "access": "public"

package/templates/_root/AGENTS.md

@@ -27,7 +27,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` or `<Suspense>`. The HTTP head commits when the shell is ready. Status, headers, and cookies set from a suspended subtree are lost, and `redirect` or `notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are available on mutations and actions, not queries.** An `action` has no direct `ctx.db`; use `ctx.runQuery` or `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **There is no `ctx.files` or `defineWorkflow`/`defineJob`.** Files go through `<FileUpload>` + `/api/files/*`; deferred execution is `ctx.scheduler.runAfter/runAt/cancel`.
 

package/templates/agency/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/ai-chat/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 
 Streaming agent turn — tokens to the caller, and to every device watching:
 

package/templates/ai-studio/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 
 Streaming agent turn — tokens to the caller, and to every device watching:
 

package/templates/barebones/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/chat/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 
 Streaming agent turn — tokens to the caller, and to every device watching:
 

package/templates/consumer/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/creator/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/crm/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/directory/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/helpdesk/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/inventory/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/invoices/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/local-service/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/marketplace/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/projects/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/restaurant/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/saas/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/shop/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/todo/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.
 

package/templates/waitlist/AGENTS.md

@@ -35,7 +35,7 @@ Pylon serves the API, auth, sync, WebSocket, SSE, and native React 19 SSR from o
 - **`response.*` / `response.redirect()` / `response.notFound()` must fire in the synchronous shell render**, before any `await` / `<Suspense>`. The HTTP head commits when the shell is ready; status/headers/cookies set from a suspended subtree are lost, and `redirect`/`notFound` thrown below a Suspense boundary are swallowed.
 - **`ctx.llm`, `ctx.rooms`, and `ctx.connections` are on mutation + action only, NOT query** (reactive purity). `action` has no direct `ctx.db`; use `ctx.runQuery` / `ctx.runMutation`.
 - **`ctx.llm.stream(request, onEvent)` streams tokens as they generate** and still resolves with the full response, so `stop_reason === "tool_use"` drives an agent tool loop. Events are `text_delta` / `tool_use_start` / `tool_input_delta` / `done`. Same auth + model-allowlist gating as `ctx.llm.complete`. Streaming does NOT extend the call deadline (`PYLON_FN_CALL_TIMEOUT`, 30s default) — set `timeout: <secs>` on the def for a long run.
-- **`ctx.stream.write(text)` reaches only the one client holding the HTTP response; `ctx.rooms.broadcast(room, topic, data)` reaches every subscriber of the room.** Broadcast is what makes agent output survive a closed tab or reach a second device. It resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
+- **`ctx.stream.write(text)` streams to the caller — and every fn stream is RESUMABLE**: the server buffers frames under a stream id (`streamFn`'s `onStreamId`), so a dropped connection or closed tab catches up via `resumeStream(id)`, including the final result after the handler finished. `ctx.rooms.broadcast(room, topic, data)` fans out to every CURRENTLY-CONNECTED subscriber (second device, second tab) but does not replay missed messages — use the stream id for anything that must survive a gap. Broadcast resolves `{ delivered: false }` when the room has no members — a no-op, not an error. Clients receive with `useRoomMessages(room, cb)` from `@pylonsync/react`; `useRoom` is the send side.
 - **It's `db.useQueryOne`, not `useOne`.** Validators and field types have aliases: `v.bool`/`v.boolean`, `v.float`/`v.number`.
 - **Use the supported file and scheduling APIs.** Files go through `<FileUpload>` and `/api/files/*`; there is no `ctx.files`. One-shot work uses `ctx.scheduler.runAfter`, `runAt`, or `cancel`; there is no `defineWorkflow` or `defineJob`. Recurring work uses `cron("0 * * * *", "fnName")` in `buildManifest({ crons: [...] })`, imported from `@pylonsync/sdk`. Make the target function `internal: true`. It runs with anonymous auth, but its own `ctx.db.*` calls are server-side and bypass policies. Use `ctx.auth.elevate({ admin: true, reason: "..." })`, with a mandatory reason, only when chaining another internal function through `ctx.scheduler`.