SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.06302 · 2026

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

Hongseok Kim, Minsoo Kim, Jungwook Choi, Hyungmin Kim

arXiv · PDF · Open in the Atlas

Code that ran

12 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 7 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2606.06302.json · badge: /api/ran/2606.06302.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
aiha-lab/TANGRAM canonical (classifier label)
classifier basis: census
12 ran · 5 no recorded run
FunctionStatusWhere it lives
async_request_deepspeed_mii Ran
ran on a synthesized input
aiha-lab/TANGRAM/benchmarks/backend_request_func.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Ravi-VK/SSR, is pointer only (licence: NONE) · get_code("552e4370076a1a01")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Ravi-VK/SSR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

async_request_tgi Ran
ran on a synthesized input
aiha-lab/TANGRAM/benchmarks/backend_request_func.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Ravi-VK/SSR, is pointer only (licence: NONE) · get_code("7ee13b8d142453c0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Ravi-VK/SSR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

async_request_trt_llm Ran
ran on a synthesized input
aiha-lab/TANGRAM/benchmarks/backend_request_func.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Ravi-VK/SSR, is pointer only (licence: NONE) · get_code("f0b0f51ad4ed00c9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Ravi-VK/SSR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_prompt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aiha-lab/TANGRAM/benchmarks/tangram/ruler_local.py
code served (permissive licence) · get_code("bcd9d69939662364")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from typing import Any


class MockTokenizer:
    """Mock tokenizer with chat_template support."""
    def __init__(self, has_chat_template=True):
        if has_chat_template:
            self.chat_template = "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}User: {{ message['content'] }}\n{% endif %}{% endfor %}Assistant:"
        
    def apply_chat_template(self, messages, tokenize=False, add_generation_prompt=False, enable_thinking=False):
        """Mock implementation that formats messages."""
        result = ""
        for msg in messages:
            if msg['role'] == 'user':
                result += f"User: {msg['content']}\n"
        if add_generation_prompt:
            result += "Assistant:"
        return result


def mock_template(model_name, task_type):
    """Mock template function for scbench_local."""
    return ("Q: ", "\nA: ")


# Patch the scbench_local module to avoid import errors
import sys
from unittest.mock import MagicMock
scbench_local_mock = MagicMock()
scbench_local_mock.template = mock_template
sys.modules['scbench_local'] = scbench_local_mock


# Construct arguments
ARGS = {
    'tokenizer': MockTokenizer(has_chat_template=True),
    'model_name': 'llama-7b-chat',
    'sample': {
        'context': 'This is some background context. ',
        'question': 'What is the answer?',
        'answer_prefix': 'The answer is: '
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scbench_local, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
effective_ratio Ran
ran, honoured the contract we drafted
aiha-lab/TANGRAM/benchmarks/tangram/bench_common.py
code served (permissive licence) · get_code("4d80b1ddfa08469e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import argparse

ARGS = {
    "args": argparse.Namespace(
        compression_budget_tokens=None,
        compression_ratio=0.5
    )
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_request_timing Ran
ran; our contract draft was wrong, not the code
aiha-lab/TANGRAM/benchmarks/tangram/bench_common.py
code served (permissive licence) · get_code("418bfc593ad8d8bf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

class MetricsObj:
    def __init__(self, arrival_time=None, queued_ts=None, scheduled_ts=None, 
                 first_token_ts=None, last_token_ts=None, first_token_latency=None,
                 num_generation_tokens=None):
        self.arrival_time = arrival_time
        self.queued_ts = queued_ts
        self.scheduled_ts = scheduled_ts
        self.first_token_ts = first_token_ts
        self.last_token_ts = last_token_ts
        self.first_token_latency = first_token_latency
        self.num_generation_tokens = num_generation_tokens

metrics_obj_with_all_fields = MetricsObj(
    arrival_time=1.0,
    queued_ts=1.5,
    scheduled_ts=2.0,
    first_token_ts=2.5,
    last_token_ts=3.5,
    first_token_latency=1.5,
    num_generation_tokens=10
)

metrics_obj_none = None

ARGS = {
    "metrics_obj": metrics_obj_with_all_fields
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_data_list Ran
ran; our contract draft was wrong, not the code
aiha-lab/TANGRAM/benchmarks/tangram/scbench_local.py
code served (permissive licence) · get_code("550815cfa153d37c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

# Setup code for get_data_list function

ARGS = {
    'dataname': 'squad',
    'modelname': 'llama-7b',
    'max_model_len': 4096,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_eval_task Ran
ran; our contract draft was wrong, not the code
aiha-lab/TANGRAM/benchmarks/tangram/benchmark_scbench.py
code served (permissive licence) · get_code("6439d722e41feedf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    'dataset_name': 'gsm8k'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_query_text Ran
ran; our contract draft was wrong, not the code
aiha-lab/TANGRAM/benchmarks/tangram/benchmark_scbench.py
code served (permissive licence) · get_code("941d33a97c872155")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "task": "reason",
    "question": "What is the capital of France?"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
group_by_task Ran
ran; our contract draft was wrong, not the code
aiha-lab/TANGRAM/benchmarks/tangram/ruler_local.py
code served (permissive licence) · get_code("d59e2d450cbbf7a4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from typing import Any

# Construct a small dataset with samples grouped by task
dataset = [
    {'task': 'classification', 'data': torch.randn(2, 4), 'label': 0},
    {'task': 'regression', 'data': torch.randn(2, 4), 'label': 1.5},
    {'task': 'classification', 'data': torch.randn(2, 4), 'label': 1},
    {'task': 'regression', 'data': torch.randn(2, 4), 'label': 2.3},
    {'task': 'classification', 'data': torch.randn(2, 4), 'label': 0},
]

ARGS = {
    'dataset': dataset,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
set_gen_length Ran
ran, honoured the contract we drafted
aiha-lab/TANGRAM/benchmarks/tangram/scbench_local.py
code served (permissive licence) · get_code("ac80359234193760")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# Call manual_seed for reproducibility
torch.manual_seed(0)

# The function takes a single parameter: dataname (str)
# It examines the string to determine max output tokens
# No complex objects needed - just a string

ARGS = {
    "dataname": "needle_dataset"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int — no output shape is stated: observe_signature.py could not observe it (read:RecursionError)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
template Ran
ran; our contract draft was wrong, not the code
aiha-lab/TANGRAM/benchmarks/tangram/scbench_local.py
code served (permissive licence) · get_code("33321941cb7c5a2a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Define ARGS dict with all required parameters for the template function
ARGS = {
    'model_name': 'llama-2-7b',
    'task': 'gsm8k'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_ruler Not yet run
unverified (harvested, no recorded run)
aiha-lab/TANGRAM/benchmarks/tangram/ruler_local.py
code served (permissive licence) · get_code("42a1756632040233")
How it ran

no invocation recorded.

resolve_cluster_map Not yet run
unverified (harvested, no recorded run)
aiha-lab/TANGRAM/benchmarks/tangram/speedup/speedup_benchmark.py
code served (permissive licence) · get_code("f942346fd9105175")
How it ran

no invocation recorded.

run_config_in_subprocess Not yet run
unverified (harvested, no recorded run)
aiha-lab/TANGRAM/benchmarks/tangram/preemption_overhead/benchmark.py
code served (permissive licence) · get_code("db377885d2303bb9")
How it ran

no invocation recorded.

run_one Not yet run
unverified (harvested, no recorded run)
aiha-lab/TANGRAM/benchmarks/tangram/preemption_overhead/benchmark.py
code served (permissive licence) · get_code("2298f1ff53dfe660")
How it ran

no invocation recorded.

run_one Not yet run
unverified (harvested, no recorded run)
aiha-lab/TANGRAM/benchmarks/tangram/speedup/speedup_benchmark.py
code served (permissive licence) · get_code("8fb5af6a89b21e9b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 14 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
async_request_deepspeed_mii 2 other papers
1 dated earlier, 1 later
2602.07223 (2026-02)
Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention
2608.20359 (2026-08)
Self-Speculation for Faster Reasoning Models
async_request_tgi 2 other papers
1 dated earlier, 1 later
2602.07223 (2026-02)
Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention
2608.20359 (2026-08)
Self-Speculation for Faster Reasoning Models
async_request_trt_llm 2 other papers
1 dated earlier, 1 later
2602.07223 (2026-02)
Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention
2608.20359 (2026-08)
Self-Speculation for Faster Reasoning Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory-not compute-the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention heads, preserves accuracy far better than uniform schemes, yet remains impractical: modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation, spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that inflate decode latency by up to 1.7× or burn 15-20% of each decode step on re-planning. We observe that this heterogeneity need not be discovered at runtime: head-wise retention follows a two-level structural regularity-an input-invariant head ranking with narrowly bounded per-head ratios-that can be calibrated offline from as few as 50 samples. Building on this insight, we present Tangram, a serving framework that statically resolves what prior systems handle dynamically: Budget Reservation fixes each head's post-compression footprint at scheduling time, eliminating page reclamation; Ragged Paging clusters similar-budget heads into independent page tables, turning fragmentation into reclaimable memory; and Ahead-of-Time Load Balancing precomputes balanced GPU partitions with zero runtime planning. Implemented on vLLM, Tangram serves as a drop-in substrate for existing non-uniform compression methods, matching their accuracy while improving end-to-end throughput by up to 2.6× over the full-KV baseline. Our implementation is publicly available at https://github.com/aiha-lab/TANGRAM. * Equal contribution † Currently at Apple ‡ Corresponding author consistent, personalized responses [1,3,24,28]. To avoid recomputing this ever-growing history H 𝑡 at every turn [12,20,26,37], serving systems persist attention states in the Key-Value (KV) cache [32]-but the cache grows linearly with every turn and every concurrent user. For Qwen2.5-32B, with merely 16 concurrent requests, the accumulated KV cache surpasses the size of the model weights themselves within ten conversation turns, and continues to grow unboundedly thereafter (Figure 1(a)). In multi-turn serving, memory capacity-not compute-is the binding constraint on batch size and therefore on throughput. KV cache compression is the standard remedy, but how the token budget is distributed across attention heads determines whether accuracy survives. Uniform compression [14,18,22,29,40,45] forces every head to retain the same number of tokens, ignoring a fundamental property of attention: critical long-range information is concentrated in a small subset of retrieval heads [10], while other heads attend only locally. Truncating all heads equally starves precisely the heads that matter, and accuracy degrades sharply in multi-turn settings (Figure 1(c)). 10,16,34,39] instead allocates heterogeneous per-head budgets that mirror this skew, preserving near-original accuracy even under aggressive compression. Thus, non-uniform compression is the right tool for memory-efficient multi-turn serving. Systemically, however, non-uniform compression is impractical today. The software stack of state-of-the-art serving systems-PagedAttention [19], continuous batching with chunked prefill [2, 42], and optimized attention kernels [5,6,41]-is architected end-to-end around a single implicit assumption: all attention heads hold KV caches of identical length. Non-uniform compression violates this assumption at every layer of the stack, resulting in severe overhead. First, the monolithic page of PagedAttention [19] spans all heads at a single uniform length, so the heterogeneous per-head budgets of non-uniform compression cannot be realized on it in the first place; the memory that compression would free instead stays trapped as unrecoverable page fragmentation ( § 3.1.1). Second, because each head's post-compression 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.06302")
get_code_for_paper("2606.06302")
have("2606.06302")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2606.06302.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2606.06302.svg)](https://syntology.ai/paper/2606.06302)

Connect an agent — have() is free.