dongarandClaude Opus 5.5
b934c46714
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 56s
The executor ended a milestone on any reply without a tool call, and
nothing held a model to the offered tools. Measured on the 4070:
tool_choice "required" is enforced by vLLM (local-fast) and Anthropic,
but qwen3-14b (local-coder) under it cannot stop and writes until the
output ceiling, a known model bug. So enforcement is asked for per
model, and the loop holds the contract itself everywhere.
- The catalog reads supports_tool_choice from LiteLLM's model_info;
BudgetedClient sends tool_choice only to models declared true, as
"required" on the normalized route and {"type": "any"} on the
Anthropic passthrough, and only when tools are offered
- The executor gains an explicit finish tool, the only way to end a
milestone. Finishing with nothing changed is refused once; a prose
reply gets one nudge, then escalates; a call to a tool not offered
counts toward failure_limit, like a failed command; calls after
finish are recorded as not run
- Clients record the model that actually answered. ModelFacts.answered
recognises a proxy fallback, which once credited Claude's answers to
a local model that could not call tools at all
- The context probe reports a fallback instead of trusting it; rerun,
both local models now refuse over-long prompts, as they should
- The capability matrix checks every answer came from the model asked,
that models call only offered tools, and that a declared
supports_tool_choice is true
- Spec A15 and the tuning guide say how enforcement is requested,
declared and backed up
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
90 lines
3.3 KiB
Python
90 lines
3.3 KiB
Python
import json
|
|
|
|
import httpx
|
|
|
|
from nisse_dev.probe import interpret, probe
|
|
|
|
|
|
def test_a_cut_at_the_declared_window_matches() -> None:
|
|
result = interpret(declared=4096, sent=6144, reported=4096, error=None)
|
|
assert result.verdict == "matches"
|
|
assert result.server_window == 4096
|
|
|
|
|
|
def test_a_cut_below_the_declaration_says_what_to_set() -> None:
|
|
# The dangerous case: prompts between the two would be silently cut.
|
|
result = interpret(declared=8192, sent=12288, reported=4096, error=None)
|
|
assert result.verdict == "declared_too_high"
|
|
assert "set max_input_tokens to 4096" in result.message
|
|
|
|
|
|
def test_a_cut_above_the_declaration_is_conservative() -> None:
|
|
result = interpret(declared=4096, sent=6144, reported=5000, error=None)
|
|
assert result.verdict == "declared_conservative"
|
|
|
|
|
|
def test_an_uncut_prompt_means_the_server_allows_more() -> None:
|
|
result = interpret(declared=4096, sent=6144, reported=6100, error=None)
|
|
assert result.verdict == "declared_conservative"
|
|
assert result.server_window is None
|
|
|
|
|
|
def test_a_refusal_is_the_safe_behaviour() -> None:
|
|
result = interpret(declared=4096, sent=6144, reported=None, error="400: too long")
|
|
assert result.verdict == "refuses"
|
|
|
|
|
|
def test_probe_calibrates_then_sends_half_again_the_window() -> None:
|
|
"""Against a fake Ollama: 2 tokens a word, silently cut at 4096."""
|
|
sizes: list[int] = []
|
|
|
|
def handler(request: httpx.Request) -> httpx.Response:
|
|
words = len(json.loads(request.content)["messages"][0]["content"].split())
|
|
sizes.append(words * 2)
|
|
reported = min(words * 2, 4096)
|
|
return httpx.Response(
|
|
200, json={"model": "llama3.2", "usage": {"prompt_tokens": reported}}
|
|
)
|
|
|
|
with httpx.Client(
|
|
base_url="http://litellm", transport=httpx.MockTransport(handler)
|
|
) as http:
|
|
result = probe(http, "llama3.2", declared=4096)
|
|
|
|
assert result.verdict == "matches"
|
|
assert sizes[1] >= 4096 * 1.4 # the probe really exceeded the window
|
|
|
|
|
|
def test_a_fallback_answer_is_never_credited_to_the_model() -> None:
|
|
"""Measured: LiteLLM answered an oversized prompt to local-coder with
|
|
claude-sonnet-5, and the probe called the refusing server roomy."""
|
|
|
|
def handler(request: httpx.Request) -> httpx.Response:
|
|
words = len(json.loads(request.content)["messages"][0]["content"].split())
|
|
model = "local-coder" if words < 1000 else "claude-sonnet-5"
|
|
return httpx.Response(
|
|
200, json={"model": model, "usage": {"prompt_tokens": words * 2}}
|
|
)
|
|
|
|
with httpx.Client(
|
|
base_url="http://litellm", transport=httpx.MockTransport(handler)
|
|
) as http:
|
|
result = probe(http, "local-coder", declared=32768, backing="openai/qwen3-14b")
|
|
|
|
assert result.verdict == "fallback"
|
|
assert "claude-sonnet-5 answered instead of local-coder" in result.message
|
|
|
|
|
|
def test_a_provider_reporting_its_own_model_name_is_not_a_fallback() -> None:
|
|
def handler(request: httpx.Request) -> httpx.Response:
|
|
return httpx.Response(
|
|
200, json={"model": "qwen3-14b", "usage": {"prompt_tokens": 400}}
|
|
)
|
|
|
|
with httpx.Client(
|
|
base_url="http://litellm", transport=httpx.MockTransport(handler)
|
|
) as http:
|
|
result = probe(http, "local-coder", declared=32768, backing="openai/qwen3-14b")
|
|
|
|
assert result.verdict != "fallback"
|