docs: every model-searchable page states the current surface

The copilot answers users from these pages (docs search), so a wrong sentence
becomes a wrong instruction. Audit fixes:

- chat: uploads live under uploads/, not the Files panel; on-demand workspace
  reach instead of a per-message snapshot; Chat runs Opus 4.8; connectors and
  deletes/restores as they actually behave; login pages via the shared browser
- cli: --select-output works on sync runs (only --async conflicts); runs get
  takes the same block selectors; secrets set needs --scope; workflows run runs
  the deployment or --manual; sim profiles honours --output; which groups have
  no singular alias; the embedded CLI has no profile, login, or config; @path
  reads the chat sandbox
- model defaults are claude-sonnet-5 (guardrails has none); API examples use
  https://www.sim.ai/api/v2 (apex 301s POSTs into GETs)
- quick reference / shortcuts: only affordances that exist (no Deploy tab, no
  workspace duplicate/export, Mod+B not Mod+E, variables under the ⋯ menu,
  <variable.name> syntax)
- editor read-only rules match round-trip-safety.ts; card links fixed
- sim-cli: runs-get selector error and the Settings label match the product;
  batch delete describes its ids as deleted, not updated; docs/api regenerated

Author: Sg312

apps/docs/content/docs/agents/index.mdx

@@ -17,7 +17,7 @@ The example throughout is an agent that scores inbound sales leads.
 
 ## The Agent block
 
-You set up the reasoning step by giving the Agent block a **model** and a **prompt**. The model is the LLM that powers it; you pick one from the available providers, and the default is `claude-sonnet-4-6`. The prompt is a system message that defines who the agent is and how it should behave, plus a user message that carries the input, usually a reference like `<start.input>`.
+You set up the reasoning step by giving the Agent block a **model** and a **prompt**. The model is the LLM that powers it; you pick one from the available providers, and the default is `claude-sonnet-5`. The prompt is a system message that defines who the agent is and how it should behave, plus a user message that carries the input, usually a reference like `<start.input>`.
 
 When it runs, the Agent block reasons, calls any tools it needs, and stores its result under its own name. By default that result is free text in `content`, read by a later block as `<agent.content>`, alongside run details like the model used, token counts, tool calls, and cost. Every setting and output field is in the [Agent block reference](/workflows/blocks/agent).
 

apps/docs/content/docs/chat/files.mdx

@@ -21,7 +21,7 @@ Use this to:
 - Drop in a PDF and ask Sim to turn it into a knowledge base document
 - Attach a design mockup and ask Sim to describe it or generate code from it
 
-Uploaded files appear in the Files panel in the sidebar and are accessible to all workflows in the workspace. Sim can also fetch a file directly from a URL and save it for you: "Download the JSON at [URL] and save it to the workspace."
+An attached file is stored under `uploads/` and readable by Sim for the rest of the conversation, but it does not appear in the Files panel and is not listed for workflows. Ask Sim to save a copy into workspace Files if you need it there. Sim can also fetch a file directly from a URL and save it for you: "Download the JSON at [URL] and save it to the workspace."
 
 ## Creating Documents
 
@@ -116,5 +116,5 @@ When a file opens in the resource panel, you can switch between three views:
   { question: "Can I use files created in Chat in workflows?", answer: "Yes. Workspace files can be referenced in workflows using the File block or by passing them as inputs." },
   { question: "What file types can I upload in Chat?", answer: "You can attach images, PDFs, text files, JSON, XML, and other document formats directly to a message." },
   { question: "What can Sim calculate or process?", answer: "Anything expressible as a short script — parsing JSON, number crunching, string transformations, deduplication, format conversions. Results come back in the chat." },
-  { question: "Is there a file size limit for generated files?", answer: "There is no hard limit on generated file size, but very large files may take longer to stream." },
+  { question: "Is there a file size limit for generated files?", answer: "Generated files are subject to the workspace file size limit; very large files also take longer to stream." },
 ]} />

apps/docs/content/docs/chat/index.mdx

@@ -24,7 +24,7 @@ Describe what you want and Sim handles it. Build a workflow, run research, gener
 
 ## How It Works
 
-Sim receives a snapshot of your entire workspace with every message — all workflows, tables, knowledge bases, files, credentials, jobs, and integrations. This is why you can refer to things by name without specifying IDs or paths:
+Sim can reach everything in your workspace on demand, so you can usually refer to things by name instead of by ID. Attaching a resource with `@` or **+** puts it directly in context:
 
 - "Run the invoice workflow"
 - "Add a row to the leads table"
@@ -66,7 +66,7 @@ Chat has two panes. On the left: the chat thread, where your messages and Sim's
 
 <FAQ items={[
   { question: "How is Chat different from working inside a single workflow?", answer: "Inside a workflow, Sim is scoped to that workflow — it helps you build and edit that one thing. In Chat, Sim has access to your entire workspace and can build workflows, manage data, run research, schedule jobs, take actions across integrations, and more." },
-  { question: "What model does Sim use?", answer: "Sim always uses Claude Opus 4.6. There is no model selector." },
+  { question: "What model does Sim use?", answer: "Chat runs on Claude Opus 4.8. There is no model selector." },
   { question: "How do I reference an existing workflow or table?", answer: "Type @ followed by the name in the input, use the + menu, or drag the item from the sidebar into the chat." },
   { question: "How long can a Chat task run?", answer: "Up to one hour. For tasks that exceed that, set up a scheduled job or break the work into steps." },
   { question: "Can Sim work on multiple things at once?", answer: "Sim processes one message at a time. You can queue messages — they will be processed in order." },

apps/docs/content/docs/chat/knowledge.mdx

@@ -47,9 +47,9 @@ Ask Sim a question and it searches the specified knowledge base to answer:
 
 For knowledge bases that should stay current automatically, connectors sync content from external services on a schedule — no manual uploads needed. New content is added, changed content is re-processed, and deleted content is removed on every run.
 
-Connectors are configured through the knowledge base settings, not through Chat. Once connected, all synced content is immediately searchable by Sim and by any Agent block with the knowledge base attached.
+Connectors are usually configured in the knowledge base settings. Sim can also create, update, and sync them for you. Once connected, all synced content is immediately searchable by Sim and by any Agent block with the knowledge base attached.
 
-Sim ships with 49 built-in connectors, including Notion, Google Drive, Slack, GitHub, Confluence, HubSpot, Salesforce, Gmail, and more.
+Sim ships with 65 built-in connectors, including Notion, Google Drive, Slack, GitHub, Confluence, HubSpot, Salesforce, Gmail, and more.
 
 Examples of what you can sync:
 

apps/docs/content/docs/chat/research.mdx

@@ -39,6 +39,6 @@ When you need a structured, saved document rather than a chat answer, ask Sim to
 
 <FAQ items={[
   { question: "Does Sim have access to real-time information?", answer: "Yes. Sim queries live internet data. Results reflect current information, not a training cutoff." },
-  { question: "Can Sim read pages that require login?", answer: "No. Sim can only read publicly accessible pages." },
+  { question: "Can Sim read pages that require login?", answer: "Stateless fetching (web_fetch, web_search, crawling) reaches only publicly accessible pages. Sim can also drive a live browser session you share — anything you sign into there, Sim can read." },
   { question: "Where are research reports saved?", answer: "Reports are saved as files in your workspace and opened in the resource panel. You can find them in the Files section of the sidebar." },
 ]} />

apps/docs/content/docs/chat/tasks.mdx

@@ -125,7 +125,7 @@ Custom tools appear in the workflow editor and are callable from any Agent block
   { question: "What's the difference between a scheduled job and a deployed workflow?", answer: "A scheduled job runs a Chat prompt on a cron schedule — Sim decides what to do each time based on current workspace state. A deployed workflow runs a fixed, deterministic graph of blocks. Use jobs when you want Sim to reason and adapt; use workflows when you want predictable, auditable execution." },
   { question: "Can a scheduled job trigger a workflow?", answer: "Yes. Include it in the job prompt: 'Run the invoice sync workflow and then post the results to Slack.'" },
   { question: "How do I know what integrations are connected?", answer: "Ask Sim: 'What integrations are connected to this workspace?' or check the Integrations page." },
-  { question: "Can direct actions be undone?", answer: "No. Actions like sending emails, posting to Slack, or creating records are immediate and irreversible. Confirm the details before asking Sim to act." },
+  { question: "Can direct actions be undone?", answer: "External actions — emails, Slack posts, third-party records — cannot be undone. Workspace changes (workflows, tables, knowledge bases) are archived and restorable. Confirm the details before asking Sim to act." },
   { question: "Are environment variables visible to all workflows?", answer: "Yes. Environment variables are workspace-scoped and available to every workflow via {{ENV_VAR}} syntax." },
   { question: "What's the difference between MCP servers and custom tools?", answer: "MCP servers expose a set of tools from an external service over the MCP protocol — you connect an existing MCP-compatible server. Custom tools are single HTTP endpoints you define manually — useful for internal APIs that don't have an MCP server." },
 ]} />

apps/docs/content/docs/chat/workflows.mdx

@@ -28,7 +28,7 @@ Describe what the workflow should do — what triggers it, what it should do, wh
 Open an existing workflow with `@workflow-name` or the **+** menu, then describe the change. Sim reads the current structure before modifying it — you don't need to explain what already exists.
 
 - "Add a condition that routes to a different branch if the confidence score is below 0.7"
-- "Replace the GPT-4o model with Claude Opus 4.6 on the summarizer block"
+- "Replace the GPT-4o model with Claude Opus 5 on the summarizer block"
 - "Add a Slack notification at the end that includes the output"
 
 ## Running Workflows
@@ -70,7 +70,7 @@ Sim can deploy a workflow as any of the three deployment types:
 
 | Deployment type | What it creates |
 |----------------|----------------|
-| **API** | A REST endpoint at `https://sim.ai/api/workflows/{id}/execute` |
+| **API** | A REST endpoint at `https://www.sim.ai/api/v2/workflows/{id}/execute` |
 | **Chat** | A hosted conversational interface with a shareable URL |
 | **MCP tool** | An MCP server that exposes the workflow as a tool |
 
@@ -114,5 +114,5 @@ Variables set this way are available via `<variable.VARIABLE_NAME>` syntax insid
   { question: "Can Sim edit a workflow while it's deployed?", answer: "Yes. Editing a workflow does not affect the live deployment. The deployed version is a snapshot — you need to ask Sim to redeploy to push changes to production." },
   { question: "Can I run a workflow with specific inputs from Chat?", answer: "Yes. Describe the inputs in your message and Sim passes them to the workflow's start block." },
   { question: "How does Sim know what my workflow does?", answer: "When you reference a workflow, Sim loads its full structure — every block, connection, and configuration — before acting on it." },
-  { question: "What happens to a workflow's deployment when I delete it?", answer: "The workflow and all its deployments are permanently removed. Any API endpoints, chat URLs, or MCP tools that pointed to that workflow will stop working." },
+  { question: "What happens to a workflow's deployment when I delete it?", answer: "The workflow is archived and its API endpoints, chat URLs, and MCP tools stop working immediately. It can be restored (sim workflows restore, or ask Sim) until it is purged." },
 ]} />

apps/docs/content/docs/cli/authentication.mdx

@@ -5,6 +5,12 @@ description: Sign in from the terminal, authenticate CI with an API key, and kee
 
 import { Callout } from 'fumadocs-ui/components/callout'
 
+<Callout>
+These settings apply to the CLI you install locally. When Sim runs a `sim`
+command for you inside Chat, it uses your session identity — there is no profile,
+no `sim login`, and no config file.
+</Callout>
+
 The CLI authenticates with a Sim API key. `sim login` mints and stores one; in CI
 you supply one through the environment instead.
 
@@ -98,7 +104,7 @@ removed, so it cannot leave dangling references.
 
 <Callout type="warn">
 `sim logout` removes the key from disk but does **not** revoke it. Revoke keys in
-Sim under **Settings → API keys**.
+Sim under **Settings → Sim API keys**.
 </Callout>
 
 ## Authenticating CI
@@ -113,7 +119,7 @@ export SIM_WORKSPACE="2f6d0b1c-8a34-4d92-b7e5-31c8a0f45d67"
 sim workflows run 3a9e21d8-5f47-4c0b-b2ea-91d7c6034ef8 --input '{"source":"nightly"}' --output json
 ```
 
-Create the key in Sim under **Settings → API keys**. Store it as a secret in your
+Create the key in Sim under **Settings → Sim API keys**. Store it as a secret in your
 CI provider — never commit it.
 
 `SIM_CONFIG_DIR` relocates both files if you need them somewhere other than

apps/docs/content/docs/cli/commands.mdx

@@ -11,9 +11,10 @@ Every `sim` command follows the same shape:
 sim <resource> [sub-resource] <verb> [arguments] [options]
 ```
 
-Resource groups are plural, and each one also accepts its singular spelling —
-`sim workflow get` and `sim workflows get` are the same command. `knowledge`
-additionally answers to `kb`.
+Most resource groups also accept a singular spelling (`sim workflow get` =
+`sim workflows get`); `knowledge` answers to `kb`. `blocks`, `tools`,
+`chat-deployments`, `connector-types`, `meta`, `billing`, and
+`workflow-mcp-servers` have no alias.
 
 ## Global options
 

apps/docs/content/docs/cli/configuration.mdx

@@ -3,6 +3,10 @@ title: Configuration
 description: Profiles, config files, environment variables, and how each setting is resolved
 ---
 
+These settings apply to the CLI you install locally. When Sim runs a `sim`
+command for you inside Chat, it uses your session identity — there is no profile,
+no `sim login`, and no config file.
+
 The CLI has four settings: **endpoint**, **API key**, **workspace**, and **output
 format**. Each resolves independently, so a saved default can still be overridden
 for a single command.