You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -37,7 +38,7 @@ Review Code uses a disposable sandbox for the repository, but the Pi harness and
37
38
- Requires sandbox execution. The provider key stays in Sim, so hosted keys and BYOK are both supported.
38
39
- Needs a **GitHub token** that can clone the repo and submit reviews (see [Setup](#setup-cloud-code-review)).
39
40
- Needs the **Pull Request Number** to review.
40
-
- Does not load skills or memory, and never exposes shell, write, edit, or arbitrary network tools to the reviewer.
41
+
- Does not load skills or memory, and never exposes shell, write, or edit tools to the reviewer. Its only network access is [Internet Search](#internet-search), and only when you select a provider.
41
42
- Rechecks the PR immediately before submission and pins the review to the exact checked-out head commit.
42
43
- The deliverable is a **submitted review** — read `reviewUrl` and `commentsPosted`.
43
44
@@ -63,6 +64,22 @@ The model that drives the agent. Defaults to `claude-sonnet-4-6`. The dropdown c
63
64
64
65
Your key for the chosen provider. On hosted Sim it is optional for Local Dev and Review Code runs (a hosted key is used and metered to your workspace). **Create PR requires your own key** because its model client runs in the sandbox. When the provider supports workspace BYOK, you can store the key in **Settings → BYOK** instead of entering it on the block.
65
66
67
+
### Internet Search
68
+
69
+
Off by default. Pick a provider — **Exa**, **Serper**, **Parallel AI**, or **Firecrawl** — and the agent gains a single `web_search` tool that returns a handful of results, each with a title, URL, snippet, and (where the provider reports one) a publication date. It works the same way in all three modes, and it is the agent's only network access in Review Code. The tool accepts at most 20 calls **per block execution**, which bounds accidental tool loops. A Pi block inside a Loop or Parallel gets that allowance again on every iteration, so bound the iteration count too if you care about what a single workflow run can spend.
70
+
71
+
Search always uses **your own key** for the selected provider, entered in the block's **Search API Key** field. That field is the only source: there is no workspace BYOK fallback and Sim never supplies a hosted search key, so unlike the model key this field appears on every deployment. Leave it empty and the run fails with a setup error before any sandbox is created. Changing the provider in the editor clears the field, so re-enter the key that belongs to the provider you picked — a workflow you import, fork, or update through the API keeps whatever key was saved, so check it there.
72
+
73
+
<Callouttype="warn">
74
+
**Create PR exposes both keys to the agent.** Create PR runs the model client and the search client *inside* the sandbox, so the model key and the search key reach it as environment variables — and Pi copies its own environment into every shell command it runs. Your prompt, or instructions injected through the contents of the cloned repository, can therefore read either key and write it anywhere the agent can reach, including into the pull request itself. Sim strips verbatim key text out of run output, but that does not stop an agent that encodes the value first.
75
+
76
+
This is why the search key has no **Settings → BYOK** fallback. Workspace BYOK keys belong to the workspace rather than to you — Sim only ever displays them masked, and only workspace admins can add or remove them — so resolving one here would let anyone who can run a Pi block read a credential they cannot otherwise see. Requiring the key on the block keeps the exposure to a key its author already holds. Scope it to something you are willing to rotate.
77
+
</Callout>
78
+
79
+
Results are third-party data. The agent is instructed to treat them as quoted evidence and never to follow instructions found inside them — the same posture Pi takes toward repository contents.
80
+
81
+
Traffic goes both ways: the agent writes its own queries after reading the repository, so leave search on **None** in Review Code when the pull request comes from an untrusted fork of a private repo. Injected instructions in a diff could otherwise put repository text into a query sent to the provider.
82
+
66
83
### Repository (Create PR / Review Code)
67
84
68
85
-**Repository Owner / Repository Name** — the GitHub repo (for example `your-org` / `your-repo`).
@@ -176,6 +193,7 @@ Enable sandbox execution as for Create PR. BYOK is optional because the model cr
176
193
{ question: "Why does Local Dev need a public hostname?", answer: "Sim connects over raw SSH and blocks localhost, LAN, and private/reserved addresses for safety. Expose the machine with a TCP tunnel such as `ngrok tcp 22` and use the tunnel's host and port. Tailscale's private 100.x addresses won't work for the same reason." },
177
194
{ question: "What GitHub permissions does Create PR need?", answer: "A token that can clone, push, and open a PR. With a fine-grained token: select the repo and grant Contents: Read and write plus Pull requests: Read and write. With a classic token: the repo scope. For organization repos, the token must be SSO-authorized." },
178
195
{ question: "What GitHub permissions does Review Code need?", answer: "A token that can clone the repo and submit a review. With a fine-grained token: Contents: Read plus Pull requests: Read and write. Push permission is not required. With a classic token: the repo scope. For organization repos, the token must be SSO-authorized." },
196
+
{ question: "Can the agent search the web?", answer: "Only if you pick a provider under Internet Search — Exa, Serper, Parallel AI, or Firecrawl. That adds one web_search tool in every mode, backed by your own key for that provider, entered on the block; there is no BYOK fallback and Sim never supplies a search key. Leave it on None and the agent has no search tool at all." },
179
197
{ question: "Can I give it Gmail, Slack, or other integrations?", answer: "Yes, in Local Dev via the Tools field. Selected Sim tools run through Sim with your connected credentials, the same as the Agent block, so the agent can act beyond the repo while it codes. MCP and custom tools aren't supported yet." },
180
198
{ question: "Where do the changes or feedback go?", answer: "In Create PR, to a new branch and a pull request (read prUrl and branch). In Review Code, to a submitted GitHub review on the existing PR (read reviewUrl and commentsPosted). In Local Dev, the files are edited in place on the target machine — review them with git there. Create PR and Local Dev also return changedFiles and a diff." },
181
199
{ question: "What happens when memory or context gets large?", answer: "For Create PR and Local Dev, Sim trims memory before the run based on the memory type, and Pi compacts older turns as needed. Review Code does not load or save memory because a malicious PR could otherwise expose or poison prior context." },
Copy file name to clipboardExpand all lines: apps/sim/app/workspace/[workspaceId]/knowledge/[id]/components/add-connector-modal/add-connector-modal.tsx
+15-1Lines changed: 15 additions & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -92,14 +92,28 @@ export function AddConnectorModal({
0 commit comments