Yanis in #general: "Quick question, has anyone tried routing ADK agents through Archestra's LLM Proxy ? I am able to talk to the agent but images/files are not going thro..." | Archestra Community

Messages in #general

Yanis — June 19, 2026

Quick question, has anyone tried routing ADK agents through Archestra's LLM Proxy ? I am able to talk to the agent but images/files are not going through, it seems like they are dropped and the agent only receives text. Anyone has any experience with routing different clients through the LLM proxy ? I am using LiteLLM in order to route through Archestra since ADK does not seem to provide a way to change the `api_base`. But I might be completely wrong in my approach, any help is appreciated. ```import os from google.adk.agents import Agent from google.adk.models.lite_llm import LiteLlm ARCHESTRA_LLM_PROXY_ID = "bc0ecdc9-ff33-43a1-a703-73a1fd1c80fb" ARCHESTRA_MODEL_ROUTER_URL = f"localhost:3000/v1/model-router/{ARCHESTRA_LLM_PROXY_ID}" root_agent = Agent( name="test_agent", model=LiteLlm( model="gemini-2.5-flash", api_base=ARCHESTRA_MODEL_ROUTER_URL, api_key=os.getenv("ARCHESTRA_API_KEY"), ), description=( "Agent to talk to." ), instruction=( "You are a helpful agent who can have a discussion with the user." ), )```

13 replies

joey (archestra team) — June 19, 2026

thanks for the detailed repro - I'm fairly certain this is a bug on our side, not your setup. your ADK/litellm/archestra model-router approach _seems_ correct to me the issue is that our proxy's translator for Gemini (and currently Anthropic/Cohere too) only forwards text content and drops `image_url`/file parts when converting your OpenAI-format request into Gemini's native format. Text-only routing works, which is why chat is fine. I'll push up a PR for this shortly, should be in latest `main` very soon!

joey (archestra team) — June 19, 2026

in your setup, are you running locally off of the latest `main` or running a release (`docker run` / `helm` chart)?

Yanis — June 19, 2026

I am running it locally

joey (archestra team) — June 19, 2026

okay cool, let me test out a fix. thanks again for reporting this 🙏

Yanis — June 19, 2026

Thanks a bunch for the support

joey (archestra team) — June 19, 2026

can you try again on latest `main`?

Yanis — June 19, 2026

Hey Joey, I will

Yanis — June 19, 2026

@user I have tested both the image/file upload feature and the Gateway access grant, they both worth great ! Thanks for the amazing work. Any plans on bringing these to a release ? tilt is great, but it's making my poor mac kneel, i'd love to play around with these features this weekend.

Yanis — June 19, 2026

Also, when sending PDFs/files, LiteLLM was trying to use the OpenAI file API (wouldn't work because I did not specify an openai api key, *and* Archestra would have dropped it anyways.) To ensure that LiteLLM sends everything in base64, all I had to do was change the model from `openai/gemini:gemini-2.5-flash` to `custom_openai/gemini:gemini-2.5-flash`

joey (archestra team) — June 20, 2026

yeah local dev wise there is an upstream next.js dev server bug which is currently causing some performance issues (especially on apple silicon) 😅 (we’re monitoring next for an upstream patch :crossed_fingers:) release wise, I will cut a release right now. Thanks for the feedback about the model router, I’ll take a look and include a patch in the _next_ release

Yanis — June 20, 2026

Thanks ! Just to clarify my last message, pdf/file sending works correctly, there's nothing to fix. However it would indeed be nice if it supported URLs for files too, not just base64.

joey (archestra team) — June 20, 2026

hmm was just checking provider docs - anthropic supports accepting file URLs, Gemini doesn't seem to 🤔 have you come across anything in gemini docs which says otherwise?

joey (archestra team) — June 20, 2026

I mean we _could_ support file URLs for Gemini requests in the :archestra: proxy layer (re-fetch / re-encode the URL), but a bit out of scope for right now 🙂

development

general

social

#general

Jun 18June 19, 2026

Yesterday

Ruoqi11:10 AMOpen in Slack

Hi team — I think I found a prompt-caching bug in the backend and couldn't open a GitHub issue (interactions are restricted to prior contributors), so posting here.

TL;DR: On the Bedrock path, applyPromptCacheBreakpoints attaches ttl:"1h" to cache breakpoints for Claude 4.6 models, but on Bedrock only the 4.5 generation supports the 1-hour TTL — 4.6 is 5-minute only. Bedrock rejects the request (it doesn't silently downgrade), so a Bedrock + Opus/Sonnet 4.6 chat fails.

Where: platform/backend/src/routes/chat/normalization/apply-prompt-cache.ts:24

// comment says "4.5 and newer support a 1-hour cache TTL"

const ONEHOURCACHE_MODEL = /claude-(?:sonnet|haiku|opus)-4-[5-9](?!\d)/;

This matches 4.5–4.9, so 4.6 gets tagged 1h-capable. useOneHour (lines 90-94) then writes ttl:"1h" into the Bedrock cachePoint regardless of provider.

Why it's wrong (Bedrock-specific): AWS's docs list the 1h TTL set by exact version — only Opus/Sonnet/Haiku 4.5; the 4.6 rows say 5-minute only. (Note: on the Anthropic-direct API 4.6 does support 1h, so the bug is specific to the Bedrock path.) Unsupported TTL is a hard error on Bedrock — see the parallel report openclaw/openclaw#21986.

Repro: your own unit test already encodes it — apply-prompt-cache.test.ts:282 uses model: "us.anthropic.claude-opus-4-6-v1:0" and asserts ttl:"1h".

Fix: narrow the 1h allowlist (Bedrock → 4.5 generation only) and default to the 5-minute TTL for anything not on it, so newer/unknown models degrade to 5m instead of failing. Happy to open a PR with the patch + updated test if you can whitelist my account for contributions — just let me know.

(Found while doing academic research on prompt-caching bugs in OSS LLM apps; full writeup available if useful.)

1 reply

Yanis3:35 PMOpen in Slack

I am using LiteLLM in order to route through Archestra since ADK does not seem to provide a way to change the api_base. But I might be completely wrong in my approach, any help is appreciated.

from google.adk.agents import Agent
from google.adk.models.lite_llm import LiteLlm
ARCHESTRA_LLM_PROXY_ID = "bc0ecdc9-ff33-43a1-a703-73a1fd1c80fb"
ARCHESTRA_MODEL_ROUTER_URL = f"<http://localhost:3000/v1/model-router/{ARCHESTRA_LLM_PROXY_ID}>"

root_agent = Agent(
    name="test_agent",
    model=LiteLlm(
        model="gemini-2.5-flash",
        api_base=ARCHESTRA_MODEL_ROUTER_URL,
        api_key=os.getenv("ARCHESTRA_API_KEY"),
    ),
    description=(
        "Agent to talk to."
    ),
    instruction=(
        "You are a helpful agent who can have a discussion with the user."
    ),
)```

👀1

13 replies

Hamza Nazir4:46 PMOpen in Slack

Hey everyone!

I'm Hamza Nazir, a MERN Stack Developer focused on building full-stack web applications with React, Node.js, Express, and MongoDB.

I joined Archestra to learn, connect with other developers, and contribute to open-source projects. Looking forward to collaborating and building with the community!

:archestra-love:1

2 replies

Read-only live mirror of Archestra.AI Slack

👋Join the discussion withAI enthusiasts!

Thread

Yanis3:35 PMOpen in Slack

I am using LiteLLM in order to route through Archestra since ADK does not seem to provide a way to change the api_base. But I might be completely wrong in my approach, any help is appreciated.

from google.adk.agents import Agent
from google.adk.models.lite_llm import LiteLlm
ARCHESTRA_LLM_PROXY_ID = "bc0ecdc9-ff33-43a1-a703-73a1fd1c80fb"
ARCHESTRA_MODEL_ROUTER_URL = f"<http://localhost:3000/v1/model-router/{ARCHESTRA_LLM_PROXY_ID}>"

root_agent = Agent(
    name="test_agent",
    model=LiteLlm(
        model="gemini-2.5-flash",
        api_base=ARCHESTRA_MODEL_ROUTER_URL,
        api_key=os.getenv("ARCHESTRA_API_KEY"),
    ),
    description=(
        "Agent to talk to."
    ),
    instruction=(
        "You are a helpful agent who can have a discussion with the user."
    ),
)```

👀1

13 replies

joey (archestra team)5:09 PMOpen in Slack

thanks for the detailed repro - I'm fairly certain this is a bug on our side, not your setup.

your ADK/litellm/archestra model-router approach seems correct to me

the issue is that our proxy's translator for Gemini (and currently Anthropic/Cohere too) only forwards text content and drops image_url/file parts when converting your OpenAI-format request into Gemini's native format. Text-only routing works, which is why chat is fine.

I'll push up a PR for this shortly, should be in latest main very soon!

joey (archestra team)5:10 PMOpen in Slack

in your setup, are you running locally off of the latest main or running a release (docker run / helm chart)?

Yanis5:16 PMOpen in Slack

I am running it locally

:thumbsup_all:1

joey (archestra team)5:23 PMOpen in Slack

okay cool, let me test out a fix. thanks again for reporting this 🙏

Yanis5:51 PMOpen in Slack

Thanks a bunch for the support

❤️1

joey (archestra team)7:43 PMOpen in Slack

can you try again on latest main?

Yanis7:58 PMOpen in Slack

Hey Joey, I will

:archestra-love:1

Yanis9:10 PMOpen in Slack

@user I have tested both the image/file upload feature and the Gateway access grant, they both worth great ! Thanks for the amazing work.

Any plans on bringing these to a release ? tilt is great, but it's making my poor mac kneel, i'd love to play around with these features this weekend.

❤️1

Yanis9:26 PMOpen in Slack

Also, when sending PDFs/files, LiteLLM was trying to use the OpenAI file API (wouldn't work because I did not specify an openai api key, and Archestra would have dropped it anyways.) To ensure that LiteLLM sends everything in base64, all I had to do was change the model from openai/gemini:gemini-2.5-flash to custom_openai/gemini:gemini-2.5-flash

joey (archestra team)4:16 AMOpen in Slack

release wise, I will cut a release right now.

Thanks for the feedback about the model router, I’ll take a look and include a patch in the next release

Yanis5:09 AMOpen in Slack

Thanks ! Just to clarify my last message, pdf/file sending works correctly, there's nothing to fix. However it would indeed be nice if it supported URLs for files too, not just base64.

joey (archestra team)5:55 AMOpen in Slack

hmm was just checking provider docs - anthropic supports accepting file URLs, Gemini doesn't seem to 🤔 have you come across anything in gemini docs which says otherwise?

joey (archestra team)6:04 AMOpen in Slack

I mean we could support file URLs for Gemini requests in the :archestra: proxy layer (re-fetch / re-encode the URL), but a bit out of scope for right now 🙂