vybekiit 0.7.17 → 0.7.18

package/dist/global-skills/instrument-product-analytics/references/configuration.md

@@ -297,6 +297,10 @@ The [`PostHogConfig` object](https://github.com/PostHog/posthog-ios/blob/main/Po
 | setBeforeSendType: FunctionDefault: undefined | Hook that allows for amending, sampling, or dropping events before they are sent to PostHog. |
 | bootstrapType: PostHogBootstrapConfigDefault: nil | Seeds identity (distinctId, isIdentifiedId) and feature-flag state (featureFlags, featureFlagPayloads) before the first /flags response. Bootstrapped identity applies to the first session; only enabled flags are served, until the first /flags response replaces them. See [SDK bootstrapping](/docs/libraries/bootstrapping.md#behavior-on-mobile-sdks). |
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/django.md

@@ -291,6 +291,10 @@ Everything on this page works the same way on `6.9.3`. Event capture, the contex
 
 Later `7.x` releases add what the 6.x line does not receive, such as the Celery integration, tracing header sanitization, and `set_context_device_id`. They also changed the middleware's own captured properties: `7.x` sends the request IP as `$ip`, where `6.9.3` sends it as `$ip_address`, and `7.x` additionally captures `$request_path`, `$raw_user_agent`, and the authenticated user's `email`.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/dotnet.md

@@ -764,6 +764,10 @@ By default, the library buffers events before sending them to the `/batch` endpo
 
 To avoid this, call `await posthog.FlushAsync()` after processing every request by adding it as a middleware to your server. This allows `posthog.Capture()` to remain asynchronous for better performance.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/elixir.md

@@ -411,6 +411,10 @@ PostHog.capture(AnotherPostHog, "user_signed_up", %{distinct_id: "user123"})
 
 The library is maintained by the PostHog team since February 2025. Thanks to [nkezhaya](https://github.com/nkezhaya) for contributing v0.1.0. Thanks to [martosaur](https://github.com/martosaur) for contributing v2.0.0.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/flask.md

@@ -138,6 +138,10 @@ Everything on this page works the same way on `6.9.3`. Event capture, the contex
 
 Later `7.x` releases add what the 6.x line does not receive, such as the Celery integration, tracing header sanitization, and `set_context_device_id`. They also changed the middleware's own captured properties: `7.x` sends the request IP as `$ip`, where `6.9.3` sends it as `$ip_address`, and `7.x` additionally captures `$request_path`, `$raw_user_agent`, and the authenticated user's `email`.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/flutter.md

@@ -885,6 +885,10 @@ await Posthog().debug(true);
 await Posthog().debug(false);
 ```
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/go.md

@@ -564,6 +564,10 @@ The `name` is a special property which is used in the PostHog UI for the name of
 
 This library is largely based on the `analytics-go` package.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/identify-users.md

@@ -298,6 +298,10 @@ object DeepLinkIdentityManager {
 -   [How person processing works](/docs/how-posthog-works/ingestion-pipeline.md#2-person-processing)
 -   [An introductory guide to identifying users in PostHog](/tutorials/identifying-users-guide.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/ios.md

@@ -159,6 +159,10 @@ Now that you've installed the SDK, explore the configuration and usage options:
 -   [Learn about using all of the features of PostHog with iOS SDK](/docs/libraries/ios/usage.md)
 -   [Learn about configuration options for the iOS SDK](/docs/libraries/ios/configuration.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/laravel.md

@@ -167,6 +167,10 @@ PostHog::init(
 
 See the [PHP SDK docs](/docs/libraries/php.md) for usage examples and the full API reference.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/next-js.md

@@ -444,6 +444,10 @@ To improve the reliability of client-side tracking and make requests less likely
 -   [How to set up Next.js pages router analytics, feature flags, and more](/tutorials/nextjs-pages-analytics.md)
 -   [How to set up Next.js A/B tests](/tutorials/nextjs-ab-tests.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/nuxt-js-3-6.md

@@ -271,6 +271,10 @@ Alternatively, the following tutorials can help you get started:
 -   [How to set up A/B tests in Nuxt](/tutorials/nuxtjs-ab-tests.md)
 -   [How to set up surveys in Nuxt](/tutorials/nuxt-surveys.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/nuxt-js.md

@@ -284,6 +284,10 @@ Alternatively, the following tutorials can help you get started:
 -   [How to set up A/B tests in Nuxt](/tutorials/nuxtjs-ab-tests.md)
 -   [How to set up surveys in Nuxt](/tutorials/nuxt-surveys.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/php.md

@@ -643,6 +643,10 @@ PostHog::init(
 
 This library is largely based on the `analytics-php` package.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/posthog-python.md

@@ -2,7 +2,7 @@
 
 # PostHog Python SDK
 
-**SDK Version:** 7.38.4
+**SDK Version:** 7.39.2
 
 Integrate PostHog into any python application.
 
@@ -75,6 +75,7 @@ Initialize a new PostHog client instance.
 - **`capture_compression`** (`CaptureCompression`) - Request-body compression for capture-v1 uploads         (ignored in V0, which uses ``gzip``). ``CaptureCompression.GZIP``         or ``DEFLATE`` (or the strings ``"gzip"``/``"deflate"``). When         omitted, the ``POSTHOG_CAPTURE_COMPRESSION`` env var is consulted,         then the legacy ``gzip`` flag, then no compression.
 - **`secret_key`** (`any`) - A Personal API Key or Project Secret API Key, used to         authenticate local feature flag evaluation, remote config         payloads, and decrypted flag payloads. Example::              posthog.Client(project_api_key, secret_key="phx_...")
 - **`metrics?`** (`dict`)
+- **`enable_full_ai_capture`** (`bool`) - Route PostHog AI wrapper events through         the dedicated AI capture endpoint and capture full AI content:         skips string truncation and passes media (base64/data URIs)         through unredacted. ``privacy_mode`` always wins. Defaults to         False.
 - **`_use_ai_lane`** (`bool`)
 - **`_enable_multimodal_capture`** (`bool`)
 
@@ -104,7 +105,7 @@ Create an alias between two distinct IDs.
 
 - **`previous_id?`** (`Number`) - The previous distinct ID. Required - the call is dropped         with a warning if it is missing or empty.
 - **`distinct_id?`** (`str`) - The new distinct ID to alias to. Falls back to the         context distinct ID; the call is dropped with a warning if         neither is available.
-- **`timestamp`** (`datetime`) - The timestamp of the event.
+- **`timestamp`** (`datetime`) - The timestamp of the event. UTC is preferred; non-UTC         datetimes and parseable ISO timestamp strings are converted to UTC.
 - **`uuid?`** (`str`) - A unique identifier for the event. If provided, it must be a         valid UUID string or uuid.UUID instance; invalid values are         ignored and replaced with a newly generated UUID.
 - **`disable_geoip?`** (`bool`) - Whether to disable GeoIP for this event.
 
@@ -131,7 +132,7 @@ Identify a group and set its properties.
 - **`group_type?`** (`str`) - The type of group (e.g., 'company', 'team'). Required -         the call is dropped with a warning if it is missing or empty.
 - **`group_key?`** (`str`) - The unique identifier for the group. Required - the call         is dropped with a warning if it is missing or empty.
 - **`properties?`** (`dict[str, Any]`) - A dictionary of properties to set on the group.
-- **`timestamp`** (`datetime`) - The timestamp of the event.
+- **`timestamp`** (`datetime`) - The timestamp of the event. UTC is preferred; non-UTC         datetimes and parseable ISO timestamp strings are converted to UTC.
 - **`uuid`** (`str`) - A unique identifier for the event. If provided, it must be a         valid UUID string or uuid.UUID instance; invalid values are         ignored and replaced with a newly generated UUID.
 - **`disable_geoip?`** (`bool`) - Whether to disable GeoIP for this event.
 - **`distinct_id`** (`Number`) - The distinct ID of the user performing the action.
@@ -257,6 +258,23 @@ posthog.capture('$pageview', distinct_id="distinct_id_of_the_user", properties={
 
 ---
 
+#### capture_ai()
+
+**Release Tag:** public
+
+Capture an AI event on the dedicated AI capture endpoint.  Beta: the signature is stable; operational limits (per-event size cap, batching, endpoint) may change without notice.  Takes the same arguments and returns the same value as `capture()`: the event UUID, or None when the event was not admitted (disabled client, or dropped by `before_send`). The event is queued on an isolated AI lane with its own consumer pool and a higher per-event size cap, posting to the dedicated AI ingestion endpoint. The payload is sent as given — no redaction or truncation is applied here.
+
+### Parameters
+
+- **`event?`** (`str`)
+- **`kwargs?`** (`Unpack[OptionalCaptureArgs]`)
+
+### Returns
+
+- `Optional[str]`
+
+---
+
 ### Error Tracking methods
 
 #### capture_exception()
@@ -873,7 +891,7 @@ To marry up whatever a user does before they sign up or log in with what they do
 
 - **`previous_id?`** (`Number`) - The unique ID of the user before
 - **`distinct_id?`** (`str`) - The current unique id
-- **`timestamp?`** (`datetime`) - Optional timestamp for the event
+- **`timestamp`** (`datetime`) - Optional timestamp for the event. UTC is preferred; non-UTC         datetimes and parseable ISO timestamp strings are converted to UTC.
 - **`uuid?`** (`str`) - Optional UUID for the event
 - **`disable_geoip?`** (`bool`) - Whether to disable GeoIP lookup
 
@@ -902,7 +920,7 @@ Set properties on a group.
 - **`group_type?`** (`str`) - Type of your group. Required - the call is dropped with a         warning if it is missing or empty.
 - **`group_key?`** (`str`) - Unique identifier of the group. Required - the call is         dropped with a warning if it is missing or empty.
 - **`properties?`** (`dict[str, Any]`) - Properties to set on the group
-- **`timestamp?`** (`datetime`) - Optional timestamp for the event
+- **`timestamp`** (`datetime`) - Optional timestamp for the event. UTC is preferred; non-UTC         datetimes and parseable ISO timestamp strings are converted to UTC.
 - **`uuid?`** (`str`) - Optional UUID for the event
 - **`disable_geoip?`** (`bool`) - Whether to disable GeoIP lookup
 - **`distinct_id`** (`Number`) - Optional distinct ID of the user performing the action
@@ -1073,6 +1091,35 @@ capture(
 
 ---
 
+#### capture_ai()
+
+**Release Tag:** public
+
+Capture an AI event on the dedicated AI capture endpoint.  Beta: the signature is stable; operational limits (per-event size cap, batching, endpoint) may change without notice.  Takes the same arguments and returns the same value as `capture()`: the event UUID, or None when the event was not admitted (disabled client, or dropped by `before_send`). The event is delivered on an isolated queue with its own consumer pool and a higher per-event size cap, posting to the dedicated AI ingestion endpoint. The payload is sent as given — no redaction or truncation is applied here.
+
+### Parameters
+
+- **`event?`** (`str`) - The event name, normally one of the `$ai_*` event names.     **kwargs: Same optional arguments as `capture()`.
+- **`kwargs?`** (`Unpack[OptionalCaptureArgs]`)
+
+### Returns
+
+- `Optional[str]`
+
+### Examples
+
+```python
+from posthog import capture_ai
+
+uuid = capture_ai(
+    "$ai_generation",
+    distinct_id="user_123",
+    properties={"$ai_model": "gpt-5"},
+)
+```
+
+---
+
 #### capture_exception()
 
 **Release Tag:** public

package/dist/global-skills/instrument-product-analytics/references/python.md

@@ -903,6 +903,10 @@ Everything on this page works the same way on `6.9.3`. Event capture, the contex
 
 Later `7.x` releases add what the 6.x line does not receive, such as the Celery integration, tracing header sanitization, and `set_context_device_id`. They also changed the middleware's own captured properties: `7.x` sends the request IP as `$ip`, where `6.9.3` sends it as `$ip_address`, and `7.x` additionally captures `$request_path`, `$raw_user_agent`, and the authenticated user's `email`.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/react-native.md

@@ -1367,6 +1367,10 @@ posthog.setPersonPropertiesForFlags(...) // instead of `personProperties`
 posthog.setGroupPropertiesForFlags(...) // instead of `groupProperties`
 ```
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/react-router-v6.md

@@ -385,6 +385,10 @@ This guide walks you through setting up PostHog for React Router V6. If you're u
      -   [PostHog AI](/docs/posthog-ai.md): After capturing events, use PostHog AI to help you understand your data and build insights.
      -   [Feature flags and experiments](/docs/libraries/react.md#feature-flags): Feature flag and experiment setup is the same as React. You can find more details in the React integration guide.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/react-router-v7-data-mode.md

@@ -373,6 +373,10 @@ This guide walks you through setting up PostHog for React Router V7 in data mode
      -   [PostHog AI](/docs/posthog-ai.md): After capturing events, use PostHog AI to help you understand your data and build insights.
      -   [Feature flags and experiments](/docs/libraries/react.md#feature-flags): Feature flag and experiment setup is the same as React. You can find more details in the React integration guide.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/react-router-v7-declarative-mode.md

@@ -385,6 +385,10 @@ This guide walks you through setting up PostHog for React Router V7 in declarati
      -   [PostHog AI](/docs/posthog-ai.md): After capturing events, use PostHog AI to help you understand your data and build insights.
      -   [Feature flags and experiments](/docs/libraries/react.md#feature-flags): Feature flag and experiment setup is the same as React. You can find more details in the React integration guide.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/react-router-v7-framework-mode.md

@@ -488,6 +488,10 @@ This guide walks you through setting up PostHog for React Router V7 in framework
      -   [PostHog AI](/docs/posthog-ai.md): After capturing events, use PostHog AI to help you understand your data and build insights.
      -   [Feature flags and experiments](/docs/libraries/react.md#feature-flags): Feature flag and experiment setup is the same as React. You can find more details in the React integration guide.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/ruby-on-rails.md

@@ -601,6 +601,10 @@ Ensure you've set `personal_api_key` in your configuration.
 
 For any technical questions for how to integrate specific PostHog features into Rails (such as analytics, feature flags, A/B testing, etc.), have a look at our [Ruby SDK docs](/docs/libraries/ruby.md).
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/ruby.md

@@ -756,6 +756,10 @@ posthog.clear
 
 This library is largely based on the `analytics-ruby` package.
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/svelte.md

@@ -265,6 +265,10 @@ Alternatively, the following tutorials can help you get started:
 -   [How to set up A/B tests in Svelte](/tutorials/svelte-ab-tests.md)
 -   [How to set up surveys in Svelte](/tutorials/svelte-surveys.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/tanstack-start.md

@@ -212,6 +212,10 @@ The server-side `capture` call requires a `distinctId` (the user identifier), an
 
 Installing the JS Web SDK and Node SDK means all of their functionality is available in your TanStack Start project. To learn more about this, have a look at our [JS Web SDK docs](/docs/libraries/js/usage.md) and [Node SDK docs](/docs/libraries/node.md).
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/usage.md

@@ -632,6 +632,10 @@ PostHogSDK.shared.debug(true)
 PostHogSDK.shared.debug(false)
 ```
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/instrument-product-analytics/references/vue-js.md

@@ -337,6 +337,10 @@ Alternatively, the following tutorials can help you get started:
 -   [How to set up A/B tests in Vue](/tutorials/vue-ab-tests.md)
 -   [How to set up surveys in Vue](/tutorials/vue-surveys.md)
 
+### Still have questions?
+
+Ask PostHog AI
+
 ### Was this page useful?
 
 HelpfulCould be better

package/dist/global-skills/manifest.json

@@ -53,6 +53,7 @@
     "expo-module",
     "expo-native-ui",
     "expo-observe",
+    "expo-overview",
     "expo-project-structure",
     "expo-router",
     "expo-skill-eval",
@@ -127,5 +128,5 @@
     "wrangler",
     "xcode-project-setup"
   ],
-  "count": 126
+  "count": 127
 }

package/dist/global-skills/neon/SKILL.md

@@ -362,7 +362,7 @@ For reading env you _already_ have on disk (typed and validated against your `ne
 
 ## Observability
 
-Neon exposes branch-scoped logs. **Today they cover Neon Functions and Object Storage only.** Postgres computes and the AI Gateway are coming; until then, neither emits records. Logs are region-gated like the other beta services above — only `us-east-2` is enabled today, and a branch in any other region answers `404` with reason `telemetry_not_enabled` rather than an empty result.
+Neon exposes branch-scoped logs. **Today they cover Neon Functions and Object Storage only.** Postgres computes and the AI Gateway are coming; until then, neither emits records. Logs are region-gated like the other beta services above. Only `us-east-2` is enabled today. A branch that can't serve logs at all answers `404` with `reason: telemetry_not_enabled` (the message says whether it's the wrong region or a branch not collecting telemetry yet), versus a `200` empty result when the branch is enabled but has no records in the window; an unknown branch answers `reason: branch_not_found`.
 
 Use Neon CLI 3.1 or newer first. **Decide which branch you are querying.** Without `--branch`, the CLI uses the branch pinned in `.neon`, or the project's default branch when the workspace isn't linked. A deployed function or bucket usually lives on a different branch than the one checked out for development, so an empty result is more often the wrong branch than a missing log.
 
@@ -374,7 +374,7 @@ neon logs fields
 neon logs field-values service_name --since 1h
 ```
 
-`--source` accepts `function`, `storage`, and `pg_endpoint`, but only `function` and `storage` return records today — `pg_endpoint` is accepted and comes back empty until Postgres logs ship. The window defaults to 1h on `query` and 6h on `field-values`, and cannot exceed 7d on either. If Neon reports `--minimum-severity` as unsupported on a branch, use `--severity-text` instead. Run `neon logs --help` for the full filter and pagination interface.
+`--source` accepts `function`, `storage`, and `pg_endpoint`, but only `function` and `storage` return records today — `pg_endpoint` is accepted and comes back empty until Postgres logs ship. The window defaults to 1h on `query` and 6h on `field-values`, and cannot exceed 7d on either. If Neon reports `--minimum-severity` as unsupported on a branch, use `--severity-text` instead (an exact, case-sensitive match, e.g. `ERROR`); severities vary by source, so confirm what a branch carries with `neon logs field-values severity_text`. Run `neon logs --help` for the full filter and pagination interface.
 
 `--logql` replaces the structured filters with a raw stream selector or line filter. Its stream label is `entity_type`, not `source`:
 

package/dist/global-skills/neon-ai-gateway/SKILL.md

@@ -4,7 +4,7 @@ description: >-
   One API and one credential for frontier and open-source LLMs, built into your
   Neon branch and powered by Databricks. Use when a user wants to call an LLM,
   add AI/chat/an agent to their app, route between model providers (OpenAI,
-  Anthropic, Google/Gemini, Meta, Alibaba, DeepSeek), or avoid juggling
+  Anthropic, Google/Gemini, Meta, Alibaba, and more), or avoid juggling
   separate provider API keys and accounts — especially when they already use
   Neon and want AI requests to branch with their project. Works with the OpenAI
   SDK, Anthropic SDK, google-genai, the Vercel AI SDK, and Mastra by changing
@@ -29,7 +29,7 @@ npx skills add neondatabase/agent-skills --skill neon
 
 This is a public beta feature and only available in `us-east-2`.
 
-The Neon AI Gateway is the LLM inference layer built into your Neon branch: one API and one Neon credential give you access to frontier and open-source models from Anthropic, OpenAI, Google, Meta, Alibaba, DeepSeek, and Databricks — powered by Databricks. Your existing OpenAI/Anthropic/Gemini SDK works by changing only the base URL.
+The Neon AI Gateway is the LLM inference layer built into your Neon branch: one API and one Neon credential give you access to frontier and open-source models from many providers (Anthropic, OpenAI, Google, Meta, and more), all hosted and powered by Databricks. The catalog shifts over time, so treat `/v1/models` and the [models.dev Neon page](https://models.dev/providers/neon) as the source of truth rather than a fixed provider list. Your existing OpenAI/Anthropic/Gemini SDK works by changing only the base URL.
 
 Use this skill to help the user send model calls through the gateway, wire it into the AI SDK or Mastra, and switch providers without rewiring code. Deliver a working inference request, a configured agent, or a precise answer from the official Neon docs.
 
@@ -37,7 +37,7 @@ Use this skill to help the user send model calls through the gateway, wire it in
 
 Reach for the AI Gateway whenever an app or agent needs to call an LLM and the user would rather not manage model providers themselves:
 
-- **One credential instead of many provider accounts.** A single Neon credential reaches the entire model catalog across seven providers. No separate OpenAI / Anthropic / Google billing, keys, or signups to provision and rotate.
+- **One credential instead of many provider accounts.** A single Neon credential reaches the entire model catalog across every provider Databricks hosts. No separate OpenAI / Anthropic / Google billing, keys, or signups to provision and rotate.
 - **Switch models without rewiring.** The unified endpoint is OpenAI-compatible and works with every model in the catalog — change one `model` field to move between Claude, GPT, and Gemini. Standard SDKs (OpenAI, Anthropic, google-genai) work with just a base-URL change.
 - **AI follows your branches.** Each branch has its own gateway endpoint, scoped with the same lineage as your database. AI requests from a preview/feature branch are isolated to that branch — the same isolation your data already gets — which makes preview, CI, and agent environments self-contained.
 - **No extra infrastructure, and it's already next to your data.** The gateway lives inside your Neon project (and is injected into Neon Functions automatically), runs on the same Databricks infrastructure that serves trillions of tokens a month, and supports streaming (SSE) out of the box.
@@ -46,7 +46,7 @@ If the user already has a deep, single-provider integration and no interest in N
 
 ## What It Does
 
-- **One API for all models** — Frontier and open-source models behind a single endpoint, addressed by their catalog ID (e.g. `claude-sonnet-4-6`, `gpt-5-mini`, `gemini-2-5-flash`).
+- **One API for all models** — Frontier and open-source models behind a single endpoint, addressed by their catalog ID (e.g. `claude-sonnet-4-6`, `gpt-5-mini`, `gemini-3-flash`).
 - **Standard SDKs, one URL change** — OpenAI SDK and AI SDK (OpenAI-compatible MLflow/Responses routes), Anthropic SDK (native Messages), google-genai (native Gemini).
 - **Branch-scoped** — Each branch gets its own gateway host; the Neon credential authorizes requests for that branch and its descendants.
 - **Streaming** — Server-sent events work on all endpoints with no extra configuration.
@@ -55,7 +55,7 @@ If the user already has a deep, single-provider integration and no interest in N
 
 Check these preconditions before setting anything up:
 
-The AI Gateway is a public beta feature available only on new projects in the `us-east-2` region; it can't be enabled on existing projects. Foundation model access requires a paid Neon plan. Confirm the user's project is a new project in `us-east-2`.
+The AI Gateway is a public beta feature available in the `us-east-2` region. Foundation model access requires a paid Neon plan. Confirm the user's project is in `us-east-2`.
 
 ### Enabling the gateway: plan and model-catalog gating
 
@@ -112,10 +112,10 @@ When `preview.aiGateway` is enabled, Neon injects the gateway credentials as **N
 
 - `/v1` — unified, OpenAI **Chat Completions**-compatible; recommended default, works with every provider (`/v1/chat/completions`).
 - `/openai/v1` — OpenAI **Responses** API (required for `gpt-5-…-codex` variants and `gpt-5-5-pro`); the `@ai-sdk/openai` provider uses the Responses API by default (`/openai/v1/responses`).
-- `/anthropic/v1` — native Anthropic Messages (extended thinking, prompt caching); mirrors the real Anthropic API path (`/anthropic/v1/messages`).
-- `/gemini/v1beta/...` — native Gemini `generateContent` (`/gemini/v1beta/models/<model>:generateContent`).
+- `/anthropic` — native Anthropic Messages (extended thinking, prompt caching). Give the Anthropic SDK this as its base URL and it appends `/v1/messages` itself, so the full request path is `/anthropic/v1/messages`.
+- `/gemini` — native Gemini `generateContent`. Give google-genai this as its base URL and it appends `/v1beta/models/<model>:generateContent` itself, so the full request path is `/gemini/v1beta/models/<model>:generateContent`.
 
-So `${NEON_AI_GATEWAY_BASE_URL}/v1` is the chat-completions endpoint, `${NEON_AI_GATEWAY_BASE_URL}/openai/v1` the OpenAI Responses endpoint, and so on.
+So `${NEON_AI_GATEWAY_BASE_URL}/v1` is the chat-completions endpoint and `${NEON_AI_GATEWAY_BASE_URL}/openai/v1` the OpenAI Responses endpoint (both appended by you); for the native Anthropic and Gemini dialects you hand the SDK the shorter `/anthropic` or `/gemini` base and it appends the rest. See [Use with Plain SDKs](#use-with-plain-sdks-lower-level) below.
 
 For typed, validated access to the injected credentials, pass the same `neon.ts` config object to `parseEnv` from `@neon/env` — it returns an `env.aiGateway` namespace (`apiKey`, `baseUrl`) derived from your config.
 
@@ -130,7 +130,7 @@ import { neon } from "@neon/ai-sdk-provider";
 import { streamText } from "ai";
 
 const result = streamText({
-  model: neon("gpt-5-mini"), // or claude-sonnet-4-6, gemini-2-5-flash, ...
+  model: neon("gpt-5-mini"), // or claude-sonnet-4-6, gemini-3-flash, ...
   messages,
   tools: {
     image_generation: neon.tools.imageGeneration({
@@ -149,7 +149,7 @@ import { neon } from "@neon/ai-sdk-provider";
 import { generateText } from "ai";
 
 const { text } = await generateText({
-  model: neon("claude-haiku-4-5"), // or gpt-5-3-codex, gemini-2-5-flash, ...
+  model: neon("claude-haiku-4-5"), // or gpt-5-3-codex, gemini-3-flash, ...
   prompt: "Summarize Postgres for me.",
 });
 ```
@@ -213,7 +213,7 @@ const client = new OpenAI({
 });
 
 const res = await client.responses.create({
-  model: "gpt-5-mini", // swap to claude-sonnet-4-6, gemini-2-5-flash, ...
+  model: "gpt-5-mini", // swap to claude-sonnet-4-6, gemini-3-flash, ...
   input: "What is Neon?",
 });
 ```
@@ -236,7 +236,7 @@ The Anthropic SDK and google-genai work the same way for native provider feature
 
 ## Model Identifiers
 
-Use a model's catalog ID directly in the `model` field — e.g. `claude-sonnet-4-6`, `gpt-5-mini`, `gemini-2-5-flash`. No provider prefix is needed. To look up the exact identifiers the gateway serves, which underlying model each maps to, and their context windows, pricing, and capabilities, use any of:
+Use a model's catalog ID directly in the `model` field — e.g. `claude-sonnet-4-6`, `gpt-5-mini`, `gemini-3-flash`. No provider prefix is needed. To look up the exact identifiers the gateway serves, which underlying model each maps to, and their context windows, pricing, and capabilities, use any of:
 
 - **models.dev Neon provider page: https://models.dev/providers/neon** — the canonical, always-current list of the Neon provider's model IDs and their underlying models. The machine-readable catalog is at https://models.dev/api.json (the `neon` key).
 - **Models doc:** see Further Reading.
@@ -272,7 +272,7 @@ Any Neon credential (`nt_live_...`) valid for the branch works as the bearer tok
       "canonical_slug": "claude-sonnet-4-6",
       "name": "Claude Sonnet 4.6",            // human-readable display name
       "object": "model",
-      "owned_by": "anthropic",                // anthropic | openai | google | meta | alibaba | databricks
+      "owned_by": "anthropic",                // provider slug, e.g. anthropic | openai | google | meta | alibaba | databricks | ... (non-exhaustive; read live)
       "created": 0,
       "enabled": true,
       "context_length": null,

package/dist/global-skills/neon-functions/SKILL.md

@@ -55,7 +55,7 @@ If the workload is a pure static site, a cron/background job that needs its own
 
 ## Availability
 
-Check this precondition before setting anything up: Neon Functions is a public beta feature available only on new projects in the `us-east-2` region. Confirm the user's Neon project is a new project in `us-east-2`; it can't be enabled on existing projects. Functions usage isn't billed during the public beta.
+Check this precondition before setting anything up: Neon Functions is a public beta feature available in the `us-east-2` region. Confirm the user's Neon project is in `us-east-2`. Functions usage isn't billed during the public beta.
 
 ## Architecture: Where Functions Fit
 
@@ -135,7 +135,7 @@ neon dev      # serves every function in neon.ts with hot reload; injects DATABA
 neon deploy   # bundles with esbuild, uploads, and applies neon.ts to the linked branch
 ```
 
-To deploy a single function without `neon.ts`: `neon functions deploy <slug> --src src/index.ts` (`--src` takes either the entry file or a directory containing `index.ts`, `index.mjs`, or `index.js`). Retrieve the public URL with `neon functions get <slug>` (the `invocation_url` field, of the form `https://<branch_id>-<slug>.compute.c-1.us-east-2.aws.neon.tech`). Manage with `neon functions list|get|delete`.
+To deploy a single function without `neon.ts`: `neon functions deploy <slug> --src src/index.ts` (`--src` takes either the entry file or a directory containing `index.ts`, `index.mjs`, or `index.js`). Retrieve the public URL with `neon functions get <slug>` (the `invocation_url` field, of the form `https://<branch_id>-<slug>.compute.<cell>.us-east-2.aws.neon.tech`). Manage with `neon functions list|get|delete`.
 
 When `neon checkout` _creates_ a new branch and a `neon.ts` is present, it applies the policy automatically — deploying the function to the fresh branch. Checking out an existing branch does not re-deploy; run `neon deploy` explicitly.
 
@@ -229,7 +229,7 @@ Functions are long-running but **still serverless** — they are a request/respo
 
 - **Time to first byte: 15 minutes.** Your handler must _begin_ returning a response within 15 minutes of receiving a request. Most handlers finish in seconds; the 15-minute ceiling exists so agent workloads like image/video generation have room.
 - **Heartbeat: 15 minutes.** Open WebSocket/SSE connections stay alive as long as data flows. The timeout only fires when a connection goes silent — send at least one byte every 15 minutes to keep a quiet stream alive.
-- **`waitUntil`: 15 minutes.** Work registered with `waitUntil` keeps the invocation alive after the response is sent, up to 15 minutes — for cleanup like analytics writes and audit logs, **not** a background job runner. (`waitUntil` from `@neon/functions` is currently a stub during the preview.)
+- **`waitUntil`: 15 minutes.** Work registered with `waitUntil` (from `@neon/functions`) keeps the invocation alive after the response is sent, up to 15 minutes — for cleanup like analytics writes and audit logs, **not** a background job runner. Off the Neon runtime (local `neon dev`, tests) it's a no-op: the promise still runs but isn't tracked.
 - **Idle eviction.** With no active connections Neon shuts the function down; it may also evict/restart for operational reasons — e.g. maintenance, or moving the function to a different compute node (active functions can run for hours first). Treat eviction like a process restart — WebSocket/SSE clients must reconnect. Neon sends `SIGINT` before evicting, so a `process.on("SIGINT", ...)` handler lets you detect that the function is about to be evicted and run any last-minute cleanup. You don't need one just to close Postgres connections — Neon's pooler reclaims those on its own.
 - **Runtime:** Node.js 24, memory fixed at 2048 MiB during the preview. Slugs must match `^[a-z0-9]{1,20}$`. **An isolate is reused across many requests** — multiple requests can be in flight on the same isolate at once (interleaved on Node's single-threaded event loop), and under load the runtime runs several isolates in parallel, each with its own copy of module state. State held in module scope is therefore per-isolate (shared by every request that isolate handles) and in-memory only — persist anything that must survive eviction in Postgres. This reuse is exactly why you create a connection pool once at module scope rather than per request (see [Connecting to Postgres](#connecting-to-postgres)).
 

package/dist/global-skills/neon-functions/references/ai-sdk.md

@@ -51,7 +51,7 @@ export default {
     const { messages } = (await request.json()) as { messages: ModelMessage[] };
 
     const result = streamText({
-      model: neon("claude-sonnet-4-6"), // swap to gpt-5-mini, gemini-2-5-flash, …
+      model: neon("claude-sonnet-4-6"), // swap to gpt-5-mini, gemini-3-flash, …
       system: "You are a concise assistant with access to the user's todos.",
       messages,
       tools: {

package/dist/global-skills/neon-object-storage/SKILL.md

@@ -53,7 +53,7 @@ If the user has no Neon project, isn't on Postgres, and just needs a standalone
 
 ## Availability
 
-Check this precondition before setting anything up: Neon Object Storage is a public beta feature available only on new projects in the `us-east-2` region. Confirm the user's Neon project is a new project in `us-east-2` before proceeding; it can't be enabled on existing projects.
+Check this precondition before setting anything up: Neon Object Storage is a public beta feature available in the `us-east-2` region. Confirm the user's Neon project is in `us-east-2` before proceeding.
 
 ## Setup
 

package/dist/global-skills/resend/SKILL.md

@@ -4,7 +4,7 @@ description: Use when working with the Resend email API — sending transactiona
 license: MIT
 metadata:
     author: resend
-    version: "3.5.2"
+    version: "3.6.0"
     homepage: https://resend.com/agent-skills
     source: https://github.com/resend/resend-skills
     openclaw: