mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-30 06:41:51 +00:00
32aea113f0
The contributor PR (#17936) only patched the strip path in `_model_supports_vision()`. The auto-mode router in `agent/image_routing._lookup_supports_vision` still only read models.dev, so a custom-provider model declared as vision-capable would still get its images routed through vision_analyze in the default `agent.image_input_mode: auto` setting. Users had to set both `supports_vision: true` AND `image_input_mode: native` to bypass the text pipeline. Single-knob behavior now: `supports_vision: true` alone is enough in auto mode. The strip path and the routing path consult the same resolver. - Extract override resolution into `_supports_vision_override()` in agent/image_routing.py and wire it into `_lookup_supports_vision()`. - Refactor `run_agent._model_supports_vision` to call the same helper (DRY, single source of truth for the resolution order). - Strict YAML boolean coercion: `supports_vision: "false"` (quoted — a common YAML mistake) no longer coerces to True via bool() truthiness. Recognised tokens: true/false/yes/no/on/off/1/0 plus real bools and 0/1. Unrecognised values return None and fall through to models.dev. - Add @CNSeniorious000 to AUTHOR_MAP for release attribution. Tests: 26 new (TestCoerceCapabilityBool, TestSupportsVisionOverride, TestLookupSupportsVisionOverride, TestAutoModeRespectsOverride). Existing contributor tests + image_routing + vision_native_fast_path + native_image_buffer_isolation all green (92/92).
451 lines
21 KiB
Python
451 lines
21 KiB
Python
"""Tests for agent/image_routing.py — the per-turn image input mode decision."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from agent.image_routing import (
|
|
_coerce_capability_bool,
|
|
_coerce_mode,
|
|
_explicit_aux_vision_override,
|
|
_lookup_supports_vision,
|
|
_supports_vision_override,
|
|
build_native_content_parts,
|
|
decide_image_input_mode,
|
|
)
|
|
|
|
|
|
# ─── _coerce_mode ────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestCoerceMode:
|
|
def test_valid_modes_pass_through(self):
|
|
assert _coerce_mode("auto") == "auto"
|
|
assert _coerce_mode("native") == "native"
|
|
assert _coerce_mode("text") == "text"
|
|
|
|
def test_case_insensitive(self):
|
|
assert _coerce_mode("NATIVE") == "native"
|
|
assert _coerce_mode("Auto") == "auto"
|
|
|
|
def test_invalid_falls_back_to_auto(self):
|
|
assert _coerce_mode("nonsense") == "auto"
|
|
assert _coerce_mode("") == "auto"
|
|
assert _coerce_mode(None) == "auto"
|
|
assert _coerce_mode(42) == "auto"
|
|
|
|
def test_strips_whitespace(self):
|
|
assert _coerce_mode(" native ") == "native"
|
|
|
|
|
|
# ─── _explicit_aux_vision_override ───────────────────────────────────────────
|
|
|
|
|
|
class TestExplicitAuxVisionOverride:
|
|
def test_none_config(self):
|
|
assert _explicit_aux_vision_override(None) is False
|
|
|
|
def test_empty_config(self):
|
|
assert _explicit_aux_vision_override({}) is False
|
|
|
|
def test_default_auto_is_not_explicit(self):
|
|
cfg = {"auxiliary": {"vision": {"provider": "auto", "model": "", "base_url": ""}}}
|
|
assert _explicit_aux_vision_override(cfg) is False
|
|
|
|
def test_provider_set_is_explicit(self):
|
|
cfg = {"auxiliary": {"vision": {"provider": "openrouter", "model": ""}}}
|
|
assert _explicit_aux_vision_override(cfg) is True
|
|
|
|
def test_model_set_is_explicit(self):
|
|
cfg = {"auxiliary": {"vision": {"provider": "auto", "model": "google/gemini-2.5-flash"}}}
|
|
assert _explicit_aux_vision_override(cfg) is True
|
|
|
|
def test_base_url_set_is_explicit(self):
|
|
cfg = {"auxiliary": {"vision": {"provider": "auto", "base_url": "http://localhost:11434"}}}
|
|
assert _explicit_aux_vision_override(cfg) is True
|
|
|
|
|
|
# ─── decide_image_input_mode ─────────────────────────────────────────────────
|
|
|
|
|
|
class TestDecideImageInputMode:
|
|
def test_explicit_native_overrides_everything(self):
|
|
cfg = {"agent": {"image_input_mode": "native"}}
|
|
# Non-vision model, aux-vision explicitly configured: native still wins.
|
|
cfg["auxiliary"] = {"vision": {"provider": "openrouter", "model": "foo"}}
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=False):
|
|
assert decide_image_input_mode("openrouter", "some-non-vision-model", cfg) == "native"
|
|
|
|
def test_explicit_text_overrides_everything(self):
|
|
cfg = {"agent": {"image_input_mode": "text"}}
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=True):
|
|
assert decide_image_input_mode("anthropic", "claude-sonnet-4", cfg) == "text"
|
|
|
|
def test_auto_with_vision_capable_model(self):
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=True):
|
|
assert decide_image_input_mode("anthropic", "claude-sonnet-4", {}) == "native"
|
|
|
|
def test_auto_with_non_vision_model(self):
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=False):
|
|
assert decide_image_input_mode("openrouter", "qwen/qwen3-235b", {}) == "text"
|
|
|
|
def test_auto_with_unknown_model(self):
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=None):
|
|
assert decide_image_input_mode("openrouter", "brand-new-slug", {}) == "text"
|
|
|
|
def test_auto_respects_aux_vision_override_even_for_vision_model(self):
|
|
"""If the user configured a dedicated vision backend, don't bypass it."""
|
|
cfg = {"auxiliary": {"vision": {"provider": "openrouter", "model": "google/gemini-2.5-flash"}}}
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=True):
|
|
assert decide_image_input_mode("anthropic", "claude-sonnet-4", cfg) == "text"
|
|
|
|
def test_none_config_is_auto(self):
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=True):
|
|
assert decide_image_input_mode("anthropic", "claude-sonnet-4", None) == "native"
|
|
|
|
def test_invalid_mode_coerces_to_auto(self):
|
|
cfg = {"agent": {"image_input_mode": "weird-value"}}
|
|
with patch("agent.image_routing._lookup_supports_vision", return_value=True):
|
|
assert decide_image_input_mode("anthropic", "claude-sonnet-4", cfg) == "native"
|
|
|
|
def test_auto_uses_text_for_text_only_modalities_even_with_attachment_flag(self):
|
|
registry = {
|
|
"xiaomi": {
|
|
"models": {
|
|
"mimo-v2.5-pro": {
|
|
"attachment": True,
|
|
"modalities": {"input": ["text"]},
|
|
"tool_call": True,
|
|
},
|
|
},
|
|
},
|
|
}
|
|
with patch("agent.models_dev.fetch_models_dev", return_value=registry):
|
|
assert decide_image_input_mode("xiaomi", "mimo-v2.5-pro", {}) == "text"
|
|
|
|
|
|
# ─── _coerce_capability_bool ─────────────────────────────────────────────────
|
|
|
|
|
|
class TestCoerceCapabilityBool:
|
|
def test_real_bool_passes_through(self):
|
|
assert _coerce_capability_bool(True) is True
|
|
assert _coerce_capability_bool(False) is False
|
|
|
|
def test_int_0_and_1(self):
|
|
assert _coerce_capability_bool(1) is True
|
|
assert _coerce_capability_bool(0) is False
|
|
|
|
def test_other_ints_return_none(self):
|
|
assert _coerce_capability_bool(2) is None
|
|
assert _coerce_capability_bool(-1) is None
|
|
|
|
def test_yaml_true_tokens(self):
|
|
for s in ("true", "TRUE", "True", "yes", "on", "1", " true "):
|
|
assert _coerce_capability_bool(s) is True
|
|
|
|
def test_yaml_false_tokens(self):
|
|
for s in ("false", "FALSE", "False", "no", "off", "0", " false "):
|
|
assert _coerce_capability_bool(s) is False
|
|
|
|
def test_quoted_false_does_not_silently_become_true(self):
|
|
# Regression: bool("false") is True in Python. A user writing
|
|
# supports_vision: "false" must NOT enable native vision routing.
|
|
assert _coerce_capability_bool("false") is False
|
|
|
|
def test_unrecognised_strings_return_none(self):
|
|
# None == fall through to models.dev, not a silent truthy.
|
|
assert _coerce_capability_bool("maybe") is None
|
|
assert _coerce_capability_bool("") is None
|
|
assert _coerce_capability_bool("definitely") is None
|
|
|
|
def test_other_types_return_none(self):
|
|
assert _coerce_capability_bool(None) is None
|
|
assert _coerce_capability_bool([]) is None
|
|
assert _coerce_capability_bool({}) is None
|
|
assert _coerce_capability_bool(1.5) is None
|
|
|
|
|
|
# ─── _supports_vision_override ───────────────────────────────────────────────
|
|
|
|
|
|
class TestSupportsVisionOverride:
|
|
def test_no_cfg_returns_none(self):
|
|
assert _supports_vision_override(None, "custom", "my-llava") is None
|
|
assert _supports_vision_override({}, "custom", "my-llava") is None
|
|
|
|
def test_top_level_shortcut_wins(self):
|
|
cfg = {"model": {"supports_vision": True}}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is True
|
|
|
|
def test_top_level_false_propagates(self):
|
|
cfg = {"model": {"supports_vision": False}}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is False
|
|
|
|
def test_per_provider_per_model_via_runtime_name(self):
|
|
cfg = {
|
|
"providers": {
|
|
"custom": {"models": {"my-llava": {"supports_vision": True}}},
|
|
},
|
|
}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is True
|
|
|
|
def test_per_provider_per_model_via_config_name(self):
|
|
# Named custom provider — runtime self.provider == "custom", config
|
|
# holds the original name under model.provider.
|
|
cfg = {
|
|
"model": {"provider": "my-vllm"},
|
|
"providers": {
|
|
"my-vllm": {"models": {"my-llava": {"supports_vision": True}}},
|
|
},
|
|
}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is True
|
|
|
|
def test_quoted_false_string_in_yaml_does_not_enable(self):
|
|
# Real-world: user writes supports_vision: "false" (quoted).
|
|
cfg = {"model": {"supports_vision": "false"}}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is False
|
|
|
|
def test_unrecognised_value_falls_through(self):
|
|
cfg = {"model": {"supports_vision": "maybe"}}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is None
|
|
|
|
def test_no_override_returns_none(self):
|
|
cfg = {"model": {"default": "my-llava"}}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is None
|
|
|
|
def test_malformed_sections_are_ignored(self):
|
|
# User accidentally wrote a string where a section was expected —
|
|
# don't blow up, just fall through.
|
|
cfg = {"model": "some-string", "providers": ["not-a-dict"]}
|
|
assert _supports_vision_override(cfg, "custom", "my-llava") is None
|
|
|
|
|
|
# ─── _lookup_supports_vision (override-aware) ────────────────────────────────
|
|
|
|
|
|
class TestLookupSupportsVisionOverride:
|
|
def test_config_override_short_circuits_models_dev(self):
|
|
# Config says True, models.dev says None — config wins.
|
|
cfg = {"model": {"supports_vision": True}}
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert _lookup_supports_vision("custom", "my-llava", cfg) is True
|
|
|
|
def test_config_override_false_beats_vision_capable_models_dev(self):
|
|
# User explicitly disables vision on a models.dev-vision-capable model.
|
|
fake_caps = type("Caps", (), {"supports_vision": True})()
|
|
cfg = {"model": {"supports_vision": False}}
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=fake_caps):
|
|
assert _lookup_supports_vision("anthropic", "claude-sonnet-4", cfg) is False
|
|
|
|
def test_no_override_falls_back_to_models_dev(self):
|
|
fake_caps = type("Caps", (), {"supports_vision": True})()
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=fake_caps):
|
|
assert _lookup_supports_vision("anthropic", "claude-sonnet-4", {}) is True
|
|
|
|
def test_no_override_no_models_dev_entry_returns_none(self):
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert _lookup_supports_vision("custom", "my-llava", {}) is None
|
|
|
|
def test_cfg_none_falls_back_to_models_dev(self):
|
|
# Caller didn't pass cfg at all — old call sites must still work.
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert _lookup_supports_vision("openrouter", "x", None) is None
|
|
|
|
|
|
# ─── decide_image_input_mode with auto + override ────────────────────────────
|
|
|
|
|
|
class TestAutoModeRespectsOverride:
|
|
def test_auto_native_for_custom_with_supports_vision_true(self):
|
|
# The motivating bug: Qwen3.6 on local llama.cpp via provider=custom.
|
|
# Without the override, auto falls back to text. With it, auto picks
|
|
# native — no need to also set agent.image_input_mode: native.
|
|
cfg = {"model": {"supports_vision": True}}
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert decide_image_input_mode("custom", "qwen3.6-35b", cfg) == "native"
|
|
|
|
def test_auto_text_for_custom_with_supports_vision_false(self):
|
|
cfg = {"model": {"supports_vision": False}}
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert decide_image_input_mode("custom", "some-text-only", cfg) == "text"
|
|
|
|
def test_auto_text_for_custom_with_no_override(self):
|
|
# Unchanged baseline: unknown custom model → text.
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert decide_image_input_mode("custom", "unknown", {}) == "text"
|
|
|
|
def test_explicit_aux_vision_override_still_wins(self):
|
|
# If the user has configured a dedicated vision aux backend, respect
|
|
# it even when supports_vision: true is also set.
|
|
cfg = {
|
|
"model": {"supports_vision": True},
|
|
"auxiliary": {"vision": {"provider": "openrouter", "model": "gemini-2.5-pro"}},
|
|
}
|
|
with patch("agent.models_dev.get_model_capabilities", return_value=None):
|
|
assert decide_image_input_mode("custom", "qwen3.6-35b", cfg) == "text"
|
|
|
|
|
|
# ─── build_native_content_parts ──────────────────────────────────────────────
|
|
|
|
|
|
def _png_bytes() -> bytes:
|
|
"""Return a tiny valid 1x1 transparent PNG."""
|
|
return base64.b64decode(
|
|
"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR4nGNgYGBgAAAABQABpfZFQAAAAABJRU5ErkJggg=="
|
|
)
|
|
|
|
|
|
class TestBuildNativeContentParts:
|
|
def test_text_then_image(self, tmp_path: Path):
|
|
img = tmp_path / "cat.png"
|
|
img.write_bytes(_png_bytes())
|
|
parts, skipped = build_native_content_parts("hello", [str(img)])
|
|
assert skipped == []
|
|
assert len(parts) == 2
|
|
assert parts[0]["type"] == "text"
|
|
# User caption is preserved and a per-image path hint is appended so
|
|
# the model can use the local path as a string argument for tools
|
|
# that take ``image_url: str`` (issue #18960).
|
|
assert parts[0]["text"] == f"hello\n\n[Image attached at: {img}]"
|
|
assert parts[1]["type"] == "image_url"
|
|
assert parts[1]["image_url"]["url"].startswith("data:image/png;base64,")
|
|
|
|
def test_empty_text_inserts_default_prompt(self, tmp_path: Path):
|
|
img = tmp_path / "cat.jpg"
|
|
img.write_bytes(_png_bytes())
|
|
parts, skipped = build_native_content_parts("", [str(img)])
|
|
assert skipped == []
|
|
# Even with empty user text, we insert a neutral prompt so the turn
|
|
# isn't just pixels, and the path hint is appended after.
|
|
assert parts[0]["type"] == "text"
|
|
assert parts[0]["text"] == (
|
|
f"What do you see in this image?\n\n[Image attached at: {img}]"
|
|
)
|
|
assert parts[1]["type"] == "image_url"
|
|
|
|
def test_missing_file_is_skipped(self, tmp_path: Path):
|
|
parts, skipped = build_native_content_parts("hi", [str(tmp_path / "missing.png")])
|
|
assert skipped == [str(tmp_path / "missing.png")]
|
|
# Skipped paths are NOT advertised in the path hints — the model
|
|
# would otherwise be told a non-existent file is attached.
|
|
assert parts == [{"type": "text", "text": "hi"}]
|
|
|
|
def test_path_hint_appended(self, tmp_path: Path):
|
|
"""The local path of each attached image is appended to the user
|
|
text part so MCP/skill tools that take ``image_url: str`` can be
|
|
invoked on the same image (issue #18960). Mirrors text-mode
|
|
behaviour (`Runner._enrich_message_with_vision`).
|
|
"""
|
|
img = tmp_path / "scan.png"
|
|
img.write_bytes(_png_bytes())
|
|
parts, _ = build_native_content_parts("attach this", [str(img)])
|
|
text_part = next(p for p in parts if p.get("type") == "text")
|
|
assert "[Image attached at:" in text_part["text"]
|
|
assert str(img) in text_part["text"]
|
|
# User caption is preserved verbatim ahead of the hint.
|
|
assert text_part["text"].startswith("attach this")
|
|
|
|
def test_path_hint_one_per_attached_image(self, tmp_path: Path):
|
|
"""Each successfully attached image gets its own path hint line;
|
|
skipped images do NOT appear in the hints.
|
|
"""
|
|
good = tmp_path / "good.png"
|
|
good.write_bytes(_png_bytes())
|
|
missing = tmp_path / "missing.png" # never created
|
|
parts, skipped = build_native_content_parts(
|
|
"see attached", [str(good), str(missing)]
|
|
)
|
|
assert skipped == [str(missing)]
|
|
text_part = next(p for p in parts if p.get("type") == "text")
|
|
assert text_part["text"].count("[Image attached at:") == 1
|
|
assert str(good) in text_part["text"]
|
|
assert str(missing) not in text_part["text"]
|
|
|
|
def test_multiple_images(self, tmp_path: Path):
|
|
img1 = tmp_path / "a.png"
|
|
img2 = tmp_path / "b.png"
|
|
img1.write_bytes(_png_bytes())
|
|
img2.write_bytes(_png_bytes())
|
|
parts, skipped = build_native_content_parts("compare these", [str(img1), str(img2)])
|
|
assert skipped == []
|
|
image_parts = [p for p in parts if p.get("type") == "image_url"]
|
|
assert len(image_parts) == 2
|
|
# Both paths surface in the text part, one per line.
|
|
text_part = next(p for p in parts if p.get("type") == "text")
|
|
assert text_part["text"].count("[Image attached at:") == 2
|
|
assert str(img1) in text_part["text"]
|
|
assert str(img2) in text_part["text"]
|
|
|
|
def test_mime_inference_jpg(self, tmp_path: Path):
|
|
# Real JPEG bytes (SOI marker FF D8 FF): sniffing now wins over suffix.
|
|
img = tmp_path / "photo.jpg"
|
|
img.write_bytes(b"\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01" + b"\x00" * 32)
|
|
parts, _ = build_native_content_parts("x", [str(img)])
|
|
url = parts[1]["image_url"]["url"]
|
|
assert url.startswith("data:image/jpeg;base64,")
|
|
|
|
def test_mime_inference_webp(self, tmp_path: Path):
|
|
# Real WEBP bytes (RIFF....WEBP): sniffing now wins over suffix.
|
|
img = tmp_path / "pic.webp"
|
|
img.write_bytes(b"RIFF\x24\x00\x00\x00WEBPVP8 " + b"\x00" * 32)
|
|
parts, _ = build_native_content_parts("", [str(img)])
|
|
url = parts[1]["image_url"]["url"]
|
|
assert url.startswith("data:image/webp;base64,")
|
|
|
|
def test_mime_sniff_overrides_misleading_extension(self, tmp_path: Path):
|
|
"""Discord-style bug: file is named .webp but contains PNG bytes.
|
|
Anthropic rejects on MIME mismatch (HTTP 400) so we MUST sniff.
|
|
Regression guard for the user-reported Discord PNG-as-WEBP failure.
|
|
"""
|
|
img = tmp_path / "discord_cached.webp"
|
|
img.write_bytes(_png_bytes()) # bytes are PNG, suffix lies
|
|
parts, _ = build_native_content_parts("", [str(img)])
|
|
url = parts[1]["image_url"]["url"]
|
|
assert url.startswith("data:image/png;base64,"), (
|
|
f"Expected MIME sniffing to detect PNG bytes regardless of .webp suffix, got: {url[:60]}"
|
|
)
|
|
|
|
|
|
# ─── Oversize handling ───────────────────────────────────────────────────────
|
|
|
|
|
|
class TestLargeImageHandling:
|
|
"""Large images attach at native size; shrink is handled reactively at
|
|
retry time in ``run_agent._try_shrink_image_parts_in_messages`` rather
|
|
than proactively here.
|
|
"""
|
|
|
|
def test_large_image_passes_through_unchanged(self, tmp_path: Path):
|
|
"""A multi-MB image is attached as-is — no resize, no skip."""
|
|
from agent import image_routing as _ir
|
|
|
|
img = tmp_path / "medium.png"
|
|
# 200 KB of real bytes; not huge but enough to verify no size gate fires.
|
|
img.write_bytes(b"\x89PNG\r\n\x1a\n" + b"X" * 200_000)
|
|
url = _ir._file_to_data_url(img)
|
|
assert url is not None
|
|
assert url.startswith("data:image/png;base64,")
|
|
# Base64 expansion means output is ~4/3 of input, plus header.
|
|
assert len(url) > 200_000
|
|
|
|
def test_missing_file_returns_none(self, tmp_path: Path):
|
|
from agent import image_routing as _ir
|
|
missing = tmp_path / "does_not_exist.png"
|
|
assert _ir._file_to_data_url(missing) is None
|
|
|
|
def test_build_native_parts_no_provider_kwarg(self, tmp_path: Path):
|
|
"""build_native_content_parts takes text + paths, no provider kwarg."""
|
|
from agent import image_routing as _ir
|
|
|
|
img = tmp_path / "cat.png"
|
|
img.write_bytes(_png_bytes())
|
|
parts, skipped = _ir.build_native_content_parts("hi", [str(img)])
|
|
assert skipped == []
|
|
assert len(parts) == 2
|
|
assert parts[0]["type"] == "text"
|
|
assert parts[1]["type"] == "image_url"
|