mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
107 lines
4.2 KiB
Python
107 lines
4.2 KiB
Python
"""Regression guard: preserve thinking blocks on DeepSeek's /anthropic endpoint.
|
|
|
|
DeepSeek's ``api.deepseek.com/anthropic`` route speaks the Anthropic Messages
|
|
protocol but, when thinking mode is enabled, requires ``thinking`` blocks from
|
|
prior assistant turns to round-trip on subsequent requests. The generic
|
|
third-party path strips them (signatures are Anthropic-proprietary and other
|
|
proxies cannot validate them), so without a DeepSeek-specific carve-out the
|
|
next tool-call turn fails with HTTP 400::
|
|
|
|
The content[].thinking in the thinking mode must be passed back to the
|
|
API.
|
|
|
|
DeepSeek's compatibility matrix lists ``thinking`` as supported but
|
|
``redacted_thinking`` and ``cache_control`` on thinking blocks as not
|
|
supported. Handling is the same as Kimi's ``/coding`` endpoint: strip
|
|
Anthropic-signed blocks (DeepSeek can't validate them) but preserve unsigned
|
|
blocks that Hermes synthesises from ``reasoning_content``.
|
|
|
|
See hermes-agent#16748.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
|
|
class TestDeepSeekAnthropicPreservesThinking:
|
|
"""convert_messages_to_anthropic must replay DeepSeek thinking blocks."""
|
|
|
|
|
|
|
|
def test_signed_anthropic_thinking_block_is_stripped(self) -> None:
|
|
"""Anthropic-signed blocks (that leaked through) must still be stripped.
|
|
|
|
DeepSeek issues its own signatures and cannot validate Anthropic's —
|
|
the strip-signed / keep-unsigned split matches the Kimi policy.
|
|
"""
|
|
from agent.anthropic_adapter import convert_messages_to_anthropic
|
|
|
|
messages = [
|
|
{"role": "user", "content": "hi"},
|
|
{
|
|
"role": "assistant",
|
|
"content": [
|
|
{
|
|
"type": "thinking",
|
|
"thinking": "anthropic-signed payload",
|
|
"signature": "anthropic-sig-xyz",
|
|
},
|
|
{"type": "text", "text": "hello"},
|
|
],
|
|
},
|
|
{"role": "user", "content": "again"},
|
|
]
|
|
_system, converted = convert_messages_to_anthropic(
|
|
messages, base_url="https://api.deepseek.com/anthropic"
|
|
)
|
|
|
|
assistant_msg = next(m for m in converted if m["role"] == "assistant")
|
|
thinking_blocks = [
|
|
b for b in assistant_msg["content"]
|
|
if isinstance(b, dict) and b.get("type") == "thinking"
|
|
]
|
|
assert thinking_blocks == [], (
|
|
"Signed Anthropic thinking blocks must be stripped on DeepSeek — "
|
|
"DeepSeek cannot validate Anthropic-proprietary signatures."
|
|
)
|
|
|
|
def test_cache_control_stripped_from_thinking_block(self) -> None:
|
|
"""cache_control must still be stripped even when the block is preserved.
|
|
|
|
DeepSeek's compatibility matrix lists cache_control on thinking blocks
|
|
as ignored — cache markers interfere with signature validation on
|
|
upstreams that do check them, so Hermes strips them everywhere.
|
|
"""
|
|
from agent.anthropic_adapter import convert_messages_to_anthropic
|
|
|
|
messages = [
|
|
{"role": "user", "content": "hi"},
|
|
{
|
|
"role": "assistant",
|
|
"reasoning_content": "r1",
|
|
"tool_calls": [
|
|
{
|
|
"id": "call_1",
|
|
"type": "function",
|
|
"function": {"name": "f", "arguments": "{}"},
|
|
}
|
|
],
|
|
},
|
|
{"role": "tool", "tool_call_id": "call_1", "content": "ok"},
|
|
]
|
|
# Inject cache_control on the synthesised thinking block after-the-fact
|
|
# by running conversion once, mutating, then re-running would be
|
|
# indirect. Instead check the simpler invariant: no thinking block in
|
|
# the converted output carries cache_control.
|
|
_system, converted = convert_messages_to_anthropic(
|
|
messages, base_url="https://api.deepseek.com/anthropic"
|
|
)
|
|
for m in converted:
|
|
if not isinstance(m.get("content"), list):
|
|
continue
|
|
for b in m["content"]:
|
|
if isinstance(b, dict) and b.get("type") in {"thinking", "redacted_thinking"}:
|
|
assert "cache_control" not in b
|
|
|
|
|