Skip to content

Commit 756127b

Browse files
committed
docs: site layout and README improvements
- Add Gemini base URL setup instructions to README (both SDK versions) - Add missing ANTHROPIC_API_KEY=mock-key to README env block - Center orphan WebSocket APIs card in features grid - Move Real-World Usage section to bottom of docs site - Tighten section padding (6rem → 3rem) - Remove inconsistent border-top on comparison section - Match Real-World Usage heading and description style to other sections
1 parent e75918a commit 756127b

2 files changed

Lines changed: 46 additions & 29 deletions

File tree

README.md

Lines changed: 22 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -117,9 +117,29 @@ OPENAI_API_KEY=mock-key
117117
118118
# Or for Anthropic Claude:
119119
ANTHROPIC_BASE_URL=http://localhost:5555/v1
120+
ANTHROPIC_API_KEY=mock-key
120121
121-
# Or for Google Gemini — point at the base URL:
122-
# http://localhost:5555/v1beta
122+
# Or for Google Gemini (set baseUrl in code — see below):
123+
GOOGLE_API_KEY=mock-key
124+
```
125+
126+
For Google Gemini, the SDK doesn't support a base URL env var — pass it in code:
127+
128+
```typescript
129+
// @google/genai (v1.x)
130+
import { GoogleGenAI } from "@google/genai";
131+
const ai = new GoogleGenAI({
132+
apiKey: process.env.GOOGLE_API_KEY,
133+
httpOptions: { baseUrl: "http://localhost:5555" },
134+
});
135+
136+
// @google/generative-ai (v0.x)
137+
import { GoogleGenerativeAI } from "@google/generative-ai";
138+
const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY!);
139+
const model = genAI.getGenerativeModel(
140+
{ model: "gemini-2.0-flash" },
141+
{ baseUrl: "http://localhost:5555" },
142+
);
123143
```
124144

125145
### JSON Fixture Files

docs/index.html

Lines changed: 24 additions & 27 deletions
Original file line numberDiff line numberDiff line change
@@ -433,7 +433,7 @@
433433

434434
/* ─── Sections ───────────────────────────────────────────────── */
435435
section {
436-
padding: 6rem 0;
436+
padding: 3rem 0;
437437
}
438438

439439
.section-label {
@@ -470,6 +470,10 @@
470470
margin-top: 3.5rem;
471471
}
472472

473+
.features-grid > .feature-card:last-child:nth-child(3n + 1) {
474+
grid-column: 2;
475+
}
476+
473477
.feature-card {
474478
padding: 2rem;
475479
background: var(--bg-card);
@@ -635,10 +639,6 @@
635639
}
636640

637641
/* ─── Comparison Table ───────────────────────────────────────── */
638-
.comparison {
639-
border-top: 1px solid var(--border);
640-
}
641-
642642
.comparison-table {
643643
width: 100%;
644644
margin-top: 3rem;
@@ -1352,28 +1352,6 @@ <h2 class="section-title">llmock vs MSW</h2>
13521352
</div>
13531353
</section>
13541354

1355-
<!-- ═══ Real-World Usage ═════════════════════════════════════════ -->
1356-
<section class="reveal">
1357-
<div class="container">
1358-
<h2>Real-World Usage</h2>
1359-
<p>
1360-
<a href="https://github.com/CopilotKit/CopilotKit" target="_blank">CopilotKit</a> uses
1361-
llmock across its test suite to verify AI agent behavior across multiple LLM providers
1362-
without hitting real APIs. The tests cover streaming text, tool calls, and multi-turn
1363-
conversations across both v1 and v2 runtimes.
1364-
</p>
1365-
<p>
1366-
See the
1367-
<a
1368-
href="https://github.com/CopilotKit/CopilotKit/search?q=llmock&amp;type=code"
1369-
target="_blank"
1370-
>CopilotKit test suite</a
1371-
>
1372-
for real-world examples of llmock in action.
1373-
</p>
1374-
</div>
1375-
</section>
1376-
13771355
<!-- ═══ Claude Code Integration ═══════════════════════════════════ -->
13781356
<section id="claude-code" class="reveal">
13791357
<div class="container">
@@ -1435,6 +1413,25 @@ <h3>Copy to Project</h3>
14351413
</div>
14361414
</section>
14371415

1416+
<!-- ═══ Real-World Usage ═════════════════════════════════════════ -->
1417+
<section class="reveal">
1418+
<div class="container">
1419+
<h2 class="section-title">Real-World Usage</h2>
1420+
<p class="section-desc">
1421+
<a href="https://github.com/CopilotKit/CopilotKit" target="_blank">CopilotKit</a> uses
1422+
llmock across its test suite to verify AI agent behavior across multiple LLM providers
1423+
without hitting real APIs. The tests cover streaming text, tool calls, and multi-turn
1424+
conversations across both v1 and v2 runtimes. See the
1425+
<a
1426+
href="https://github.com/CopilotKit/CopilotKit/search?q=llmock&amp;type=code"
1427+
target="_blank"
1428+
>CopilotKit test suite</a
1429+
>
1430+
for real-world examples.
1431+
</p>
1432+
</div>
1433+
</section>
1434+
14381435
<!-- ═══ Footer ═══════════════════════════════════════════════════ -->
14391436
<footer>
14401437
<div class="container">

0 commit comments

Comments
 (0)