mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-18 04:41:56 +00:00
* feat(video_gen): unified video_generate tool with pluggable provider backends One core video_generate tool, every backend a plugin. Mirrors the image_gen + memory_provider + context_engine architecture: ABC, registry, plugin-context registration hook, and per-plugin model catalogs surfaced through hermes tools. Surface (one schema, every backend): - operation: generate / edit / extend - modalities: text-to-video (prompt only), image-to-video (prompt + image_url), video edit (prompt + video_url), video extend (video_url) - reference_image_urls, duration, aspect_ratio, resolution, negative_prompt, audio, seed, model override - Providers ignore unknown kwargs and declare what they support via VideoGenProvider.capabilities() — backend-specific quirks stay in the backend, the agent learns one tool Backends shipped: - plugins/video_gen/xai/ — Grok-Imagine, full generate/edit/extend + image-to-video + reference images (salvaged from PR #10600 by @Jaaneek, reshaped into the plugin interface) - plugins/video_gen/fal/ — Veo 3.1 (t2v + i2v), Kling O3 i2v, Pixverse v6 i2v with model-aware payload building that drops keys a model doesn't declare Wiring: - agent/video_gen_provider.py — VideoGenProvider ABC, normalize_operation, success_response / error_response, save_b64_video / save_bytes_video, $HERMES_HOME/cache/videos/ - agent/video_gen_registry.py — thread-safe register/get/list + get_active_provider() reading video_gen.provider from config.yaml - hermes_cli/plugins.py — PluginContext.register_video_gen_provider() - hermes_cli/tools_config.py — Video Generation category in hermes tools, plugin-only providers list, model picker per plugin, config write to video_gen.{provider,model} - toolsets.py — new video_gen toolset - tests: 31 new tests covering ABC, registry, tool dispatch, both plugins - docs: developer-guide/video-gen-provider-plugin.md (parallel to the image-gen guide), sidebar + toolsets-reference + plugin guides updated Supersedes: #25035 (FAL), #17972 (FAL), #14543 (xAI), #13847 (HappyHorse), #10458 (provider categories), #10786 (xAI media+search bundle), #2984 (FAL duplicate), #19086 (Google Veo standalone — easy port to plugin interface). Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * feat(video_gen): dynamic schema reflects active backend's capabilities Address the 'capability variance' question — instead of one tool with a static schema that lies about what every backend supports, the video_generate tool now rebuilds its description at get_definitions() time based on the configured video_gen.provider and video_gen.model. The agent sees backend-specific guidance up-front: - 'fal-ai/veo3.1/image-to-video': 'image-to-video only — image_url is REQUIRED; text-only prompts will be rejected' - 'fal-ai/veo3.1' (t2v): no image_url restriction shown - xAI grok-imagine-video: 'operations: generate, edit, extend; up to 7 reference_image_urls' - Backends without edit/extend: 'not supported on this backend — surface that they need to switch backends via hermes tools' This is the same pattern PR #22694 used for delegate_task self-capping — documented in the dynamic-tool-schemas skill. Cache invalidation is free: get_tool_definitions() already memoizes on config.yaml mtime, so a mid-session backend swap rebuilds the schema automatically. Tested: - Empirical FAL OpenAPI schema check confirms image-to-video models require image_url (FAL returns HTTP 422 otherwise) — client-side rejection in FALVideoGenProvider.generate() now prevents the wasted round-trip - Live E2E: fal-ai/veo3.1/image-to-video + prompt-only → clean missing_image_url error; fal-ai/veo3.1 + prompt-only → dispatches - 6 new tests cover the builder (no config / image-only / full-surface / text-only / unknown provider / registry wiring), all passing - 37/37 in the slice, 134/134 in the broader regression set * test(video_gen/xai): full surface integration tests + cleaner schema Verified end-to-end that the xAI plugin handles every documented mode from PR #10600's surface: text-to-video, image-to-video, reference-images-to-video, video edit, video extend (with and without prompt). All five modes route to the correct xAI endpoint (/videos/generations, /videos/edits, /videos/extensions) with the right payload shape (image / reference_images / video keys), and all five client-side rejections fire before the network: edit-without-prompt, extend-without-video_url, image+refs conflict, >7 references, and duration/aspect_ratio clamping. 15 new integration tests grouped into four classes (endpoint routing, modalities, validation, clamping). httpx is stubbed via a small fake AsyncClient that records POSTs so the tests assert the actual payload the plugin would send to xAI — not just the success/error envelope. Also cleaned up a description redundancy: when a model's operations match the backend's overall set, we no longer print the duplicate 'operations supported by this model' line. xAI's description now reads: Active backend: xAI . model: grok-imagine-video - operations supported by this backend: edit, extend, generate - modalities supported by this backend: image, reference_images, text - aspect_ratio choices: 16:9, 1:1, 2:3, 3:2, 3:4, 4:3, 9:16 - resolution choices: 480p, 720p - duration range: 1-15s - reference_image_urls: up to 7 images Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * feat(video_gen): collapse surface to t2v + i2v, family-based auto-routing Two design changes per Teknium: 1) Drop edit/extend from the tool surface entirely. Only text-to-video and image-to-video remain. The agent sees a clean tool with two modalities; backend-specific quirks like xAI's edit/extend endpoints stay out of the unified schema. 2) FAL: pick a model FAMILY once, the plugin routes between the family's text-to-video and image-to-video endpoints based on whether image_url was passed. Users no longer pick 'fal-ai/veo3.1' AND 'fal-ai/veo3.1/image-to-video' as separate options — they pick 'veo3.1', and the plugin handles the rest. Catalog rewritten as families: veo3.1 fal-ai/veo3.1 / fal-ai/veo3.1/image-to-video pixverse-v6 fal-ai/pixverse/v6/text-to-video / fal-ai/pixverse/v6/image-to-video kling-o3-standard fal-ai/kling-video/o3/standard/text-to-video / fal-ai/kling-video/o3/standard/image-to-video xAI uses a single endpoint (/videos/generations) for both modes, routed by the presence of the 'image' field in the payload — no edit/extend exposure. Schema changes: - VIDEO_GENERATE_SCHEMA: drop operation, drop video_url. Final params: prompt (required), image_url, reference_image_urls, duration, aspect_ratio, resolution, negative_prompt, audio, seed, model. - VideoGenProvider ABC: drop normalize_operation, VALID_OPERATIONS, DEFAULT_OPERATION. capabilities() drops 'operations' key. - success_response: add 'modality' field ('text' | 'image') so the agent and logs can see which endpoint was actually hit. Dynamic schema builder simplified — no operations bullet, no 'switch backends if you need edit/extend' guidance. When the active backend supports both modalities (the common case), description reads: Active backend: FAL . model: pixverse-v6 - supports both text-to-video (omit image_url) and image-to-video (pass image_url) - routes automatically - aspect_ratio choices: 16:9, 9:16, 1:1 - resolution choices: 360p, 540p, 720p, 1080p - duration range: 1-15s - audio: pass audio=true to enable native audio (pricing tier) - negative_prompt: supported Tests: 51 in the video_gen slice, 216 across the broader image+video sweep, all passing. New FAL routing tests prove pixverse-v6 + no image hits text-to-video endpoint, pixverse-v6 + image_url hits image-to-video endpoint, same for veo3.1 and kling-o3-standard. Docs updated: developer-guide page rewrites the 'model families' pattern as a first-class section so external plugin authors know the convention. toolsets-reference and toolsets.py descriptions match the new surface. Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * feat(video_gen/fal): expand catalog to 6 families, cheap + premium tiers Catalog now covers everything Teknium specced from FAL: Cheap tier: ltx-2.3 fal-ai/ltx-2.3-22b/text-to-video / image-to-video pixverse-v6 fal-ai/pixverse/v6/text-to-video / image-to-video Premium tier: veo3.1 fal-ai/veo3.1 / fal-ai/veo3.1/image-to-video seedance-2.0 bytedance/seedance-2.0/text-to-video / image-to-video kling-v3-4k fal-ai/kling-video/v3/4k/text-to-video / image-to-video happy-horse fal-ai/happy-horse/text-to-video / image-to-video DEFAULT_MODEL moved from veo3.1 (premium) to pixverse-v6 (cheap, sane defaults, both modalities) — better first-run UX for users who haven't explicitly picked a model. New family-entry knob: image_param_key. Kling v3 4K's image-to-video endpoint expects start_image_url instead of image_url; declaring image_param_key='start_image_url' on the family lets _build_payload remap correctly. Other families default to plain image_url. Per-family capability flags reflect each model's docs: - LTX 2.3 + Happy Horse: minimal payloads (no duration/aspect/resolution enum exposed by FAL — let endpoint apply defaults) - Seedance: 6 aspect ratios incl 21:9, durations 4-15, audio supported, negative prompts NOT supported per docs - Kling v3 4K: 16:9/9:16/1:1, 3-15s, audio + negative - Veo 3.1: unchanged, 16:9/9:16, 4/6/8s Tests: +5 covering the new families (full catalog, Kling 4K start_image_url remap, Seedance routing, LTX payload minimality, Happy Horse minimality). 56/56 in the slice green. Note: I did NOT add the FAL-hosted xAI Grok-Imagine variant. Hermes already has a direct xAI plugin that talks to xAI's own API; routing the same model through FAL's wrapper would duplicate the surface without adding capabilities. Users on FAL who want Grok-Imagine should use the xAI plugin directly; flag if you want both routes available. * test(video_gen): tool-surface routing matrix — every model x modality End-to-end matrix test driven through _handle_video_generate() — the actual function the agent's video_generate tool call lands in. Writes config.yaml, invokes the registered handler with a raw args dict, then asserts the outbound HTTP/SDK call hit the right endpoint with the right payload shape. Parametrized over FAL_FAMILIES.keys() so the matrix auto-discovers new families as they're added (add a family to FAL_FAMILIES and you get both modalities tested for free). Coverage: - All 6 FAL families x {text-only, text+image} = 12 cases - xAI x {text-only, text+image} = 2 cases - tool-level model= arg overrides config = 2 cases For each case, verifies: - result['success'] is True - result['modality'] matches input shape ('text' if no image_url, 'image' otherwise) - outbound endpoint URL matches the family's text_endpoint or image_endpoint - text-only payloads carry no image-shaped keys - text+image payloads carry the family's image key (image_url for most, start_image_url for kling-v3-4k, wrapped 'image' object for xAI) All 16 cases passing. Confirms the tool surface routes every (provider, model, modality) combination correctly with zero leakage. * feat(video_gen): keep video_gen out of first-run setup, surface in status Two changes: 1. video_gen joins _DEFAULT_OFF_TOOLSETS, so it is NOT pre-selected in the first-run toolset checklist. Video gen is niche, paid, and slow — most users don't want it nagging them during initial setup. Anyone who wants it opts in via 'hermes tools' -> Video Generation, which already routes to the provider+model picker. 2. The 'hermes setup' status panel learns about video_gen — but only shows the row when a plugin reports available. Users without FAL_KEY/XAI_API_KEY see nothing about video gen; users with one of those keys see 'Video Generation (FAL) ✓' as confirmation it's wired. Verified live: - Fresh install (no creds): zero video_gen mentions in wizard. - With FAL_KEY: status row appears with active backend name. - 160/160 in the setup + tools_config + video_gen test slice. Rationale: image_gen is on by default because it's a featured creative tool used in casual chat (telegrams, etc). Video gen is heavier — long wait, paid per-second pricing. Default-off matches user intent better. --------- Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
191 lines
6.2 KiB
Python
191 lines
6.2 KiB
Python
"""Integration tests for the xAI video gen plugin's simplified surface.
|
|
|
|
xAI exposes only text-to-video and image-to-video through the unified
|
|
``video_generate`` tool. We assert the endpoint hit and the payload shape
|
|
because routing is the part most likely to break silently.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
import pytest
|
|
|
|
from agent import video_gen_registry
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _reset_registry():
|
|
video_gen_registry._reset_for_tests()
|
|
yield
|
|
video_gen_registry._reset_for_tests()
|
|
|
|
|
|
class _FakeResponse:
|
|
def __init__(self, status: int = 200, payload: Optional[Dict[str, Any]] = None):
|
|
self.status_code = status
|
|
self._payload = payload or {}
|
|
self.text = json.dumps(self._payload)
|
|
|
|
def raise_for_status(self):
|
|
if self.status_code >= 400:
|
|
import httpx
|
|
raise httpx.HTTPStatusError("err", request=None, response=self) # type: ignore
|
|
|
|
def json(self):
|
|
return self._payload
|
|
|
|
|
|
class _FakeAsyncClient:
|
|
def __init__(self):
|
|
self.posts: List[Dict[str, Any]] = []
|
|
|
|
async def __aenter__(self):
|
|
return self
|
|
|
|
async def __aexit__(self, *args):
|
|
return None
|
|
|
|
async def post(self, url, headers=None, json=None, timeout=None):
|
|
self.posts.append({"url": url, "json": json})
|
|
return _FakeResponse(200, {"request_id": "req-123"})
|
|
|
|
async def get(self, url, headers=None, timeout=None):
|
|
return _FakeResponse(200, {
|
|
"status": "done",
|
|
"video": {"url": "https://xai-cdn/out.mp4", "duration": 8},
|
|
"model": "grok-imagine-video",
|
|
})
|
|
|
|
|
|
@pytest.fixture
|
|
def xai_provider(monkeypatch):
|
|
monkeypatch.setenv("XAI_API_KEY", "test-key")
|
|
|
|
import plugins.video_gen.xai as xai_plugin
|
|
|
|
captured: Dict[str, _FakeAsyncClient] = {}
|
|
|
|
def _client_factory():
|
|
captured["client"] = _FakeAsyncClient()
|
|
return captured["client"]
|
|
|
|
monkeypatch.setattr(xai_plugin.httpx, "AsyncClient", _client_factory)
|
|
|
|
async def _no_sleep(*a, **k):
|
|
return None
|
|
|
|
monkeypatch.setattr(asyncio, "sleep", _no_sleep)
|
|
|
|
provider = xai_plugin.XAIVideoGenProvider()
|
|
return provider, captured
|
|
|
|
|
|
def _last_post(captured) -> Dict[str, Any]:
|
|
return captured["client"].posts[-1]
|
|
|
|
|
|
class TestXAIEndpoint:
|
|
"""xAI uses one endpoint — ``/videos/generations`` — for both modes."""
|
|
|
|
def test_text_to_video_hits_generations(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
result = provider.generate("a dog on a skateboard")
|
|
assert result["success"] is True
|
|
assert _last_post(captured)["url"].endswith("/videos/generations")
|
|
assert result["modality"] == "text"
|
|
|
|
def test_image_to_video_hits_generations(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
result = provider.generate(
|
|
"animate this",
|
|
image_url="https://example.com/cat.png",
|
|
)
|
|
assert result["success"] is True
|
|
assert _last_post(captured)["url"].endswith("/videos/generations")
|
|
assert result["modality"] == "image"
|
|
|
|
|
|
class TestXAIPayload:
|
|
def test_text_payload_has_no_image_field(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
provider.generate("a dog at sunset")
|
|
payload = _last_post(captured)["json"]
|
|
assert payload["prompt"] == "a dog at sunset"
|
|
assert "image" not in payload
|
|
assert "reference_images" not in payload
|
|
|
|
def test_image_payload_has_image_field(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
provider.generate("animate this", image_url="https://example.com/cat.png")
|
|
payload = _last_post(captured)["json"]
|
|
assert payload["image"] == {"url": "https://example.com/cat.png"}
|
|
|
|
def test_reference_images_payload(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
provider.generate(
|
|
"keep this character",
|
|
reference_image_urls=[
|
|
"https://example.com/a.png",
|
|
"https://example.com/b.png",
|
|
],
|
|
)
|
|
payload = _last_post(captured)["json"]
|
|
assert payload["reference_images"] == [
|
|
{"url": "https://example.com/a.png"},
|
|
{"url": "https://example.com/b.png"},
|
|
]
|
|
|
|
|
|
class TestXAIValidation:
|
|
def test_missing_prompt_rejects(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
result = provider.generate("")
|
|
assert result["success"] is False
|
|
assert result["error_type"] == "missing_prompt"
|
|
# Never hit the network
|
|
assert "client" not in captured or not captured["client"].posts
|
|
|
|
def test_image_plus_refs_rejects(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
result = provider.generate(
|
|
"x",
|
|
image_url="https://example.com/i.png",
|
|
reference_image_urls=["https://example.com/r.png"],
|
|
)
|
|
assert result["success"] is False
|
|
assert result["error_type"] == "conflicting_inputs"
|
|
assert "client" not in captured or not captured["client"].posts
|
|
|
|
def test_too_many_references_rejects(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
result = provider.generate(
|
|
"x",
|
|
reference_image_urls=[f"https://example.com/r{i}.png" for i in range(8)],
|
|
)
|
|
assert result["success"] is False
|
|
assert result["error_type"] == "too_many_references"
|
|
|
|
|
|
class TestXAIClamping:
|
|
def test_duration_clamped_to_15(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
provider.generate("x", duration=30)
|
|
assert _last_post(captured)["json"]["duration"] == 15
|
|
|
|
def test_duration_clamped_when_refs_present(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
provider.generate(
|
|
"x",
|
|
duration=15,
|
|
reference_image_urls=["https://example.com/r.png"],
|
|
)
|
|
# refs present caps to 10
|
|
assert _last_post(captured)["json"]["duration"] == 10
|
|
|
|
def test_invalid_aspect_ratio_soft_clamps(self, xai_provider):
|
|
provider, captured = xai_provider
|
|
provider.generate("x", aspect_ratio="21:9")
|
|
assert _last_post(captured)["json"]["aspect_ratio"] == "16:9"
|