add optional system prompt environment injection

Agents can have their custom system prompt. Environment system prompt gets added regardless.
Making this optional would reduce tokens and increase prompt adherence if this info is not needed for the agent to fulfill its task.

if (process.env.OPENCODE_NO_ENV_PROMPT !== 'true') {
  system.push(...(await SystemPrompt.environment()))
}

Or even better: per agent in config, as system prompts can be defined there anyways:

 "agent": {
    "build": {
      "mode": "primary",
      "model": "anthropic/claude-sonnet-4-20250514",
      "prompt": "{file:./prompts/build.txt}",
      "envinfo": false
      ...
   }
}

Yes, this is very important to keep a clean context window.

The environent information is injected AFTER a custom Agent prompt, which puts limits on how you can end it.

I think, what makes much more send is having a placerholder in the prompt that gets replaced if it's present. Similar to arguments with / commands.

that's an interesting idea, kinda like it

The environent information is injected AFTER a custom Agent prompt

Still getting my bearings, but shouldn't any system prompt be added separately:

    const result = await generateObject({
      model: openai('gpt-4o'),
      system: `You are a SQL (postgres) ...`, // SYSTEM PROMPT AS ABOVE - OMITTED FOR BREVITY
      prompt: `Generate the query necessary to retrieve the data the user wants: ${input}`,
      schema: z.object({
        query: z.string(),
      }),
    });

Also rather than optionally inject a hardcoded system prompt wouldn't it be better to allow users to define a SYSTEM.md per agent, say for the hypothetical IDE agent:

agent/ide.md
agent/ide/SYSTEM.md
agent/ide/create-ticket.md
...

This suggests there are three prompt types: Primary, System and Sub-Agents

The environent information is injected AFTER a custom Agent prompt

Still getting my bearings, but shouldn't any system prompt be added separately:
const result = await generateObject({
  model: openai('gpt-4o'),
  system: `You are a SQL (postgres) ...`, // SYSTEM PROMPT AS ABOVE - OMITTED FOR BREVITY
  prompt: `Generate the query necessary to retrieve the data the user wants: ${input}`,
  schema: z.object({
    query: z.string(),
  }),
});
Also rather than optionally inject a hardcoded system prompt wouldn't it be better to allow users to define a SYSTEM.md per agent, say for the hypothetical IDE agent:

agent/ide.md
agent/ide/SYSTEM.md
agent/ide/create-ticket.md
...
This suggests there are three prompt types: Primary, System and Sub-Agents

AFAIK, the system prompt for an agent can be defined already and is used as it. The issue is how it's merged with environment specific stuff, which you have no control over.

AFAIK, the system prompt for an agent can be defined already and is used as it.

Thanks. I see that Modes is now deprecated in favor of an agent option mode, and a mode did have a prompt option (which was the system prompt). However, agent docs say that mode has one option:

https://opencode.ai/docs/agents#mode:

The mode option can be set to primary, subagent, or all. If no mode is specified, it defaults to all.

So no more mode#prompt?

+1 on this. My use case is a research-only agent (web search, no local tools) where the environment block is pure noise. A per-agent config field like context: false would be ideal — simple and backwards-compatible.

docs: add empty system prompt to codex command for speed (#1300)

Hi, any updates regarding this request? Would be super helpful.

To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.

Navigation Menu

add optional system prompt environment injection #1894

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

add optional system prompt environment injection #1894

Description

Activity

calvinalkan commented on Oct 1, 2025

rekram1-node commented on Oct 1, 2025

taqtiqa-mark commented on Oct 14, 2025

calvinalkan commented on Oct 14, 2025

taqtiqa-mark commented on Oct 14, 2025

hmblair commented on Mar 2, 2026

konstantinoskalyfommatos commented on Apr 4, 2026

github-actions commented on Jun 4, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions