Session management lets the orchestrator keep track of recent delegated child sessions so follow-up work can continue in the right specialist context instead of starting from scratch every time.
It is enabled by default. You do not need to add anything to your config unless you want to change how many sessions are remembered.
Delegation works best when specialists can continue a thread they already understand:
Without session management, follow-up delegations usually create fresh child sessions. That works, but the specialist may need repeated context. With session management, the orchestrator can reuse recent child sessions when it makes sense.
When a child task runs, the plugin remembers it under a short alias such as:
exp-1
ora-1
fix-2
The orchestrator sees a compact reminder in its system context, for example:
### Resumable Sessions
- explorer: exp-1 Search routing files
Context read by exp-1: src/router.ts (120 lines), src/routes/api.ts (74 lines)
- oracle: ora-1 Review auth architecture
When a child session reads files through OpenCode's read tool, the reminder can
include a compact list of files that session has already inspected. This helps the
orchestrator choose the right session to resume for related follow-up work.
To keep the prompt small, read context only shows files where at least 10 lines were read, includes line counts, and caps each remembered session to the most recent 8 files by default. Both thresholds are configurable.
On a related follow-up, the orchestrator can reuse that session instead of launching a fresh one. If the remembered child session no longer exists, the plugin drops the stale entry and falls back to a new session automatically.
Session management is intentionally narrow:
task delegations.@agent calls.read tool usage, not
arbitrary filesystem access through shell commands or external MCP tools.This keeps the feature useful for continuity without turning child sessions into long-lived global state.
By default, the plugin remembers 2 recent child sessions per specialist type.
That means the generated starter config can stay clean:
{
"preset": "openai",
"presets": {
"openai": {
"orchestrator": { "model": "openai/gpt-5.5" },
"explorer": { "model": "openai/gpt-5.4-mini" },
"fixer": { "model": "openai/gpt-5.4-mini" }
}
}
}
Session management still works because the runtime falls back to the built-in default.
Only add sessionManager if you want to change the default limits:
{
"sessionManager": {
"maxSessionsPerAgent": 2,
"readContextMinLines": 10,
"readContextMaxFiles": 8
}
}
sessionManager.maxSessionsPerAgent| Type | Default | Range | Meaning |
|---|---|---|---|
| integer | 2 |
1–10 |
Number of recent resumable child sessions remembered per specialist type in the current parent session |
sessionManager.readContextMinLines| Type | Default | Range | Meaning |
|---|---|---|---|
| integer | 10 |
0–1000 |
Minimum number of lines read from a file before it appears in resumable-session context |
Set this lower if you want short config files to appear. Set it higher to keep the prompt focused on substantial file reads.
sessionManager.readContextMaxFiles| Type | Default | Range | Meaning |
|---|---|---|---|
| integer | 8 |
0–50 |
Maximum number of recent read-context files shown per remembered child session |
Set this to 0 to keep session aliases but hide read-context file lists.
Use a higher value if you often run several parallel threads per specialist. Use a lower value if you want fewer aliases in the orchestrator context.
Most users should leave the default alone.
Consider changing it when:
Example with a smaller memory window:
{
"sessionManager": {
"maxSessionsPerAgent": 1,
"readContextMaxFiles": 4
}
}
Example with a larger memory window:
{
"sessionManager": {
"maxSessionsPerAgent": 4,
"readContextMinLines": 5
}
}