Using agy as a provider for my harness

I find the Gemini Flash 3.6 a very interesting model. It is reasonably competent but most importantly super duper fast. Additionally I already pay for the Google AI Pro account so I have a nice amount of free tokens.

Unfortunately, I am a single harness kind of person, all my engineering, clawing and so on is done in my harness https://term-llm.com/

Ever since agy was released I have been keen to add it as a provider to my harness, I already do so for claude -p and cursor-agent and grok, all have their own quirks, but were reasonably straight forward to get going.

agy though has been a real tricky one. I felt extremely uneasy going with approaches I have seen out there. Ripping the OAuth keys out of the binary is wrong, parsing internal Sqlite database feels wrong.

A few weeks ago a new release of agy was made with --output-format=stream-json so I was very excited to easily wire this into my harness.

The gaps

Sadly, it is not easy.

The general pattern I (and others) have used for “binary as a endpoint” is:

  • Disable the native tools that the agy harness provides
  • Wire up an MCP with tools that my harness provides

Sadly there are 2 huge gaps as of release 1.1.10

  1. You can not disable native tools AND enable an MCP see this issue.

Native tools + MCP - works
tools: [] + inheritMcp: true - due to a bug MCP unavailable

  1. MCP has a non configurable knob where if an MCP tool returns 4096 bytes or more, the harness will put the result in a file, which is not desirable.

The workaround

agy vial localharness makes calls to daily-cloudcode-pa.googleapis.com term-llm adds a TLS intercepting request filter, via HTTP_PROXY. With this proxy in place I can:

  1. remove all native tools (so only MCP tools remain)
  2. undo spill over truncation which is not configurable

I now added Gemini 3.6 Flash to my rotation of LLMs I use for code reviews and quick prototyping.

Looking forward to the 2 tiny changes needed in agy that will let me remove the proxy.

You can’t use Antigravity in another harness. By doing this, you are likely to get banned with no refunds on your Google AI Pro account.

Antigravity explicitly specifies that you can’t use the Agy provider in other harnesses

This is simply using the built in supported, --output-format=stream-json which the agy team released and working around 2 bugs that will be eventually fixed in the harness.

Oh, ok, I see now.

I didn’t realize Antigravity has an SDK now