Skip to main content
from praisonaiagents import Agent

agent = Agent(
    name="budgeted-agent",
    instructions="Use tools without flooding context.",
)
agent.start("Search the web and keep only the most relevant snippets.")
Per-tool budgets cap how much of each tool’s output enters agent context — noisy tools get tighter limits, critical tools stay protected. The user caps noisy tool output; per-tool budgets truncate oversized results before they fill the context window.

​
How It Works

​
Quick Start

1

Enable context on the agent

from praisonaiagents import Agent, ManagerConfig

agent = Agent(
    name="researcher",
    instructions="Research topics efficiently",
    context=ManagerConfig(default_tool_output_max=10000),
)
2

Set per-tool budgets

agent.context_manager.set_tool_budget("web_search", max_tokens=2000)
agent.context_manager.set_tool_budget("file_read", max_tokens=5000, protected=True)
agent.context_manager.set_tool_budget("code_execute", max_tokens=10000)

agent.start("Summarise the latest WebAssembly news")
3

Truncate output manually

truncated = agent.context_manager.truncate_tool_output(
    "file_read", large_file_content
)
# Appends "...[output truncated]..." when over budget

​
How It Works

Each tool call checks get_tool_budget(tool_name) — falling back to default_tool_output_max when no per-tool rule exists. Protected tools skip pruning during context optimisation.

​
Configuration

​
Via ManagerConfig

from praisonaiagents import Agent, ManagerConfig

agent = Agent(
    name="researcher",
    context=ManagerConfig(
        default_tool_output_max=10000,
        protected_tools=["file_read"],
    ),
)
agent.context_manager.set_tool_budget("web_search", max_tokens=2000)

​
Via environment

export PRAISONAI_CONTEXT_TOOL_OUTPUT_MAX=10000

​
Methods

MethodPurpose
set_tool_budget(name, max_tokens, protected=False)Set limit for one tool
get_tool_budget(name)Read limit (falls back to default)
truncate_tool_output(name, output)Truncate to the tool’s budget
Truncated outputs are persisted to disk so the agent can retrieve them — see Tool Output Store.

​
CLI Usage

praisonai chat
> /context config

# Shows:
#   default_tool_max:       10,000
#   tool_budgets:
#     file_read: 5,000 (protected)
#     web_search: 2,000

​
Best Practices

Web search and file reads return large payloads — cap them at 2,000–5,000 tokens so they do not crowd out conversation history.
Code tools often need full stack traces or build logs — 10,000+ tokens prevents losing error context mid-debug.
protected=True keeps a tool’s output from being pruned during context optimisation, even when the window is tight.
Run /context in chat or call get_stats() on the context manager to see which tools consume the most tokens.

Context Manager

Unified facade for budgeting, compaction, and monitoring.

Tool Output Store

Retrieve full outputs after truncation.