# Llm.complete interface may include unannounced max token limitations

**URL:** <https://forum.anna.partners/t/llm-complete-interface-may-include-unannounced-max-token-limitations/321>\
**Category:** Developers\
**Created:** [September 17, 2026, 2:53am UTC](https://forum.anna.partners/t/llm-complete-interface-may-include-unannounced-max-token-limitations/321 "2026-09-17T02:53:47Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Yinghuo\_Mars](https://avatars.discourse-cdn.com/v4/letter/y/839c29/32.png) [@Yinghuo\_Mars](https://forum.anna.partners/u/Yinghuo_Mars)\
**Post date:** [September 17, 2026, 2:53am UTC](https://forum.anna.partners/t/llm-complete-interface-may-include-unannounced-max-token-limitations/321/1 "2026-09-17T02:53:47Z")

</div>

I am now developing `Anna Deck`. While I was trying to let the model `gemini-3.5-flash`(x18) generate a long html file, the output was cut down. Here’s a detailed discription.

## Scenario

I attempted to generate the candidate page in one `llm.complete` call.

The request includes:

- a system prompt requiring only a complete HTML document;
- the user’s page-refinement request;
- the current page HTML;
- a screenshot of the current page.

The expected response is a document starting with `<!doctype html>` and ending with `</html>`.

For the candidate-generation call, I requested:

```auto
maxTokens: 12000
modelPreferences: {
  hints: [{ name: "google/gemini-3.5-flash" }]
}

```

The visible response began in the middle of HTML and ended in the middle of HTML. It did not include either the opening document structure or `</html>`.

The returned usage was:

```auto
{
  "inputTokens": 4976,
  "outputTokens": 4092,
  "totalTokens": 9068
}

```

`stopReason` was still reported as `endTurn`.

## Follow-up Tests

To ensure if there really exists a unvisiable limmition, I ask the model to output a long html with different input `maxToken`. This html contains over 500 paragraphs. The following table shows the final output.

| Requested `maxTokens` | Actual `outputTokens` | Last complete marker | Complete `</html>` |
| --- | --- | --- | --- |
| 4096 | 4092 | `OUTPUT-0075` | No |
| 8192 | 4092 | `OUTPUT-0085` | No |
| 12000 | 4092 | `OUTPUT-0078` | No |
| 16000 | 4092 | `OUTPUT-0076` | No |

## Expected Behavior

I suggest that the platform should take at least one of the following measures to prevent users from encountering this situation again.

1. Honor `maxTokens` values above 4,096 when supported by the selected model;
2. Reject unsupported values with a clear error;
3. Return an explicit effective output limit and a truncation-specific finish reason.

Returning `endTurn` for an incomplete HTML document makes it difficult for developers to distinguish successful completion from output cutting down.

## Environment

Anna version: Local Anna CLI package: `@anna-ai/cli` `0.1.47`  
App source commit: `05071e20d2dcf32a08fdbbbe50f8f3c5c4aa3af0`  
API: `llm.complete` (non-streaming)  
Runtime:

- Browser-hosted Anna App runtime obtained through `window.AnnaAppRuntime.connect()`
- Local app served through `anna-app dev`
- Model preference: `google/gemini-3.5-flash`
- Actual returned model: `google/gemini-3.5-flash`
- Provider metadata returned by the raw response: `openrouter`

The token counts and stopReason shown above are taken directly from the raw response, not from a UI-rendered or truncated view.

---

<div class="post-metadata">

**Author:** ![hunter](https://yyz1.discourse-cdn.com/flex033/user_avatar/forum.anna.partners/hunter/32/8_2.png) [@hunter](https://forum.anna.partners/u/hunter)\
**Post date:** [September 24, 2026, 10:18am UTC](https://forum.anna.partners/t/llm-complete-interface-may-include-unannounced-max-token-limitations/321/2 "2026-09-24T10:18:26Z")

</div>

Hi @Yinghuo_Mars! 👋

First off — thank you for this outstanding report. 🙏 The maxTokens sweep table (4096/8192/12000/16000 → always ~4092) made the diagnosis instant, and your write-up was spot on: there **was** an unannounced 4096 output cap, and `stopReason: "endTurn"` on truncated output was genuinely misleading. We’ve fixed both — and we’re happy to say all **three** of your suggested measures made it in. ✨

## 🚀 Shipping this Friday (Sep 25)

**Platform `1.1.0-beta.179`**

1. ✅ **`maxTokens` above 4096 is now honored.** The effective cap is resolved per call as `min(maxTokens ?? 8192, model output cap, path ceiling)` — the path ceiling is **8192** for `llm.complete` (sync transport budget) and **65536** for `llm.stream`. The default when `maxTokens` is omitted doubles to **8192**.
2. ✅ **The effective limit is explicit.** Every response now carries `_meta.maxTokens: { requested, effective, limitedBy: "request" | "model" | "transport" | "default" }` — no more silent clamping, ever.
3. ✅ **Truncation-specific stop reason.** `stopReason` now maps the provider’s real finish reason: `"endTurn" | "maxTokens" | "contentFilter" | "toolUse"`. Your incomplete-HTML case will report `"maxTokens"`, so you can detect it and continue programmatically. 🎯

Bonus: if your balance can’t cover a large request, you now get a clean `APP_QUOTA_EXCEEDED` (429) **before** the call runs, with `requiredCu` / `remainingCu` / `requestedMaxTokens` in `data` — perfect for an automatic lower-and-retry.

**SDK `@anna-ai/app-runtime 0.17.0`** 🧩

For your exact Anna Deck scenario (`maxTokens: 12000`): with the new SDK, `llm.complete` requests above 8192 are **transparently delivered over the streaming channel** and resolve with the identical single-result shape — your `</html>` will arrive intact, no code changes needed. 🎉

**CLI `@anna-ai/cli 0.1.55`** — full `anna-app dev` parity, including mock mode.

## 📝 Heads-up

- No breaking changes — existing apps keep working unchanged. 🤝
- Calls that were previously silently cut at 4096 can now generate more tokens, so quota spend may rise accordingly. Set `maxTokens` explicitly for a tighter budget.
- `llm.stream` remains the recommended first-class path for long outputs.

The `/developers` docs are being refreshed alongside the release. Reports like this one make the platform better for everyone — please keep them coming, and good luck with Anna Deck! 💚

— The Anna App Platform Team