mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-30 01:32:25 +01:00
feat(harness): authority, turn contract, tools, clean_agent_preview
Chat/agent harness work: request-authority model, turn contract, tool
policy/parsing/execution, clean_agent_preview streaming/thinking, ask_user
persistence, session probes, and scheduler.
Source: vendor/photocraft (ad1cff44) harness files, 3-way merged onto
upstream/dev (a8c147b2). Harness core files were independently developed
in both lineages; resolution policy documented in pr_work/C_conflicts.md
(vendor kept where ahead, upstream kept where vendor is behind; full delta
preserved in pr_work/C_upstream_delta.patch).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
pewdiepie-archdaemon
co-authored by
Claude Opus 5.5
Claude Opus 5.5
parent
a8c147b238
commit
364229f2dc
+76
-13
@@ -70,7 +70,7 @@ def _repair_function_arg_aliases(tool_type: str, args: dict[str, Any]) -> dict[s
|
||||
command = args.get("command")
|
||||
if isinstance(command, str):
|
||||
path, separator, content = command.partition("\n")
|
||||
if separator and path.strip() and content.strip():
|
||||
if separator and path.strip() and content:
|
||||
args["path"] = path.strip()
|
||||
args["content"] = content
|
||||
logger.warning("Normalized legacy `command` write shape to path/content")
|
||||
@@ -494,14 +494,14 @@ FUNCTION_TOOL_SCHEMAS = [
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "youtube_tool",
|
||||
"description": "Read YouTube-specific data without fighting the JS UI. Use for YouTube video comments, transcripts, metadata, or latest video from a channel. For general web lookup use web_search; for interacting with the visible site use private_browser.",
|
||||
"description": "Read YouTube-specific data (comments, transcripts, metadata, or latest video from a channel) without fighting the YouTube JS UI. YOUTUBE ONLY: it accepts only youtube.com or youtu.be links — a video URL, a shorts/live link, or an 11-character video_id, or a channel /@handle/videos URL. It does NOT accept any other website. For a non-YouTube URL do not use this tool: use web_fetch for one specific page or web_search for an open-ended lookup; use private_browser only to drive the visible browser.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"action": {"type": "string", "enum": ["comments", "transcript", "metadata", "latest_channel_video"], "description": "What YouTube data to retrieve. Use latest_channel_video with max_results for latest N uploads from a channel."},
|
||||
"url": {"type": "string", "description": "YouTube video or channel URL"},
|
||||
"video_url": {"type": "string", "description": "YouTube video URL"},
|
||||
"video_id": {"type": "string", "description": "YouTube video id"},
|
||||
"url": {"type": "string", "description": "A youtube.com or youtu.be URL (video, watch?v=, shorts, or a channel /@handle/videos URL). No other hosts."},
|
||||
"video_url": {"type": "string", "description": "A youtube.com or youtu.be video URL"},
|
||||
"video_id": {"type": "string", "description": "The 11-character YouTube video id (e.g. jNQXAC9IVRw)"},
|
||||
"channel_url": {"type": "string", "description": "YouTube channel URL or /@handle/videos URL"},
|
||||
"handle": {"type": "string", "description": "YouTube handle, e.g. @OpenAI"},
|
||||
"max_results": {"type": "integer", "description": "Maximum comments, uploads, or results to return, capped at 50"}
|
||||
@@ -1497,7 +1497,7 @@ FUNCTION_TOOL_SCHEMAS = [
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "generate_image",
|
||||
"description": "Generate an AI image from a text prompt and save it to the gallery. If this tool reports that no image model or endpoint is configured, report that limitation directly; do not substitute Bash, Python, SVG, or another tool.",
|
||||
"description": "Generate a NEW image from a text prompt and place it as a layer in the open editor or save it to the gallery. Use for adding content that is not already in the photo (e.g. 'add a full moon in the sky'). If this tool reports that no image model or endpoint is configured, report that limitation directly; do NOT substitute deterministic editor ops (selection/adjustments/filters), Bash, Python, or SVG.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -1527,6 +1527,75 @@ FUNCTION_TOOL_SCHEMAS = [
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "plan_edit",
|
||||
"description": "Plan a photo-editing program for the currently open image editor. Returns an ordered list of editor ops to run against the canvas. Route object removal, added content, or replaced content to ai_edit_image/generate_image; use deterministic ops only for tone/colour/filter/crop/text/selection edits. If no image provider is configured for a generative request, say so instead of planning a substitute deterministic edit. Use the canonical adjustment/filter shapes (adjustments.apply/applyMasked params {\"type\", \"params\"}; filters.apply/applyMasked params {\"id\"}); never invent adjustment types or filter ids. New ops: photo.autoTone; retouch.skin/blemish/teeth; selection.face/background. Portrait/look-better ('fix the skin', 'fix my teeth') -> selection.face then retouch.skin (and retouch.teeth for teeth) then ONE gentle photo.autoTone; never a timid single step. Low-key/'fix the lighting' on a dark image: at most ONE global lift (prefer photo.autoTone once or shadows-highlights); never stack autoTone/brightness/exposure/levels, and keep highlights <= 0. Temperature sign: moody/cool/cinematic -> white-balance temperature NEGATIVE; warm/golden/sunset -> POSITIVE. Background softer -> selection.background then filters.applyMasked {id:'blur-gaussian'} (never a plain global blur). A vague prompt with no concrete defect ('clean this up') -> return {\"reply\": <question>, \"steps\": [], \"ask_user\": {\"question\":..., \"options\":[...]}} with 2-3 concrete options instead of guessing.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"prompt": {"type": "string", "description": "What the user wants done to the image"},
|
||||
"state": {"type": "object", "description": "Optional current editor state (layers, selection, document info)"}
|
||||
},
|
||||
"required": ["prompt"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "run_editor_command",
|
||||
"description": "Run a single deterministic operation on the open image editor and return its result. Use catalog ops such as adjustments.*, filters.applyMasked, selection.*, layers.*, document.importImage, layers.placeImage, export.png, screenshot. Do NOT use for AI/masked edits (use ai_edit_image) or new imagery (use generate_image). Canonical shapes: adjustments.apply/applyMasked params = {\"type\": <brightness-contrast|exposure|white-balance|hue-saturation|vibrance|black-white|shadows-highlights|levels|curves|color-balance|photo-filter|selective-color|gradient-map|invert|posterize|threshold|channel-mixer|color-lookup>, \"params\": {...}}; filters.apply/applyMasked params = {\"id\": <blur-gaussian|blur-motion|blur-zoom|sharpen|sharpen-edges|unsharp-mask|noise-add|noise-despeckle|pixelate-mosaic|pixelate-crystallize|stylize-emboss|stylize-find-edges|stylize-solarize|distort-twirl|distort-pinch|distort-spherize|distort-ripple|render-clouds>}. Never nest a numeric bag under {\"adjustments\": {...}} and never invent adjustment types or filter ids (no \"vignette\" or \"clarity\"). Additional canonical ops: photo.autoTone {}; retouch.skin {smooth,opacity,blemish,radius,threshold}; retouch.blemish {radius,threshold}; retouch.teeth {desat,bright}; selection.face {mode}; selection.background {mode,subject,fuzziness}. At most one global brightness/exposure lift (prefer shadows-highlights; keep highlights <= 0). Never stack global lifts.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"op": {"type": "string", "description": "Editor op name from the catalog, e.g. adjustments.applyMasked"},
|
||||
"params": {"type": "object", "description": "Parameters for the op"},
|
||||
"session": {"type": "string", "description": "Editor session id (defaults to the open session)"},
|
||||
"wait": {"type": "boolean", "description": "Wait for the editor result (default true)"}
|
||||
},
|
||||
"required": ["op"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_editor_screenshot",
|
||||
"description": "Capture the open image editor's current canvas as a PNG data URL. Use to inspect the result before choosing the next edit.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"session": {"type": "string", "description": "Editor session id (defaults to the open session)"}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "ai_edit_image",
|
||||
"description": "Apply an AI image edit and place the result as a NEW layer, never overwriting the original. Two modes. mode='instruction' (default): send the WHOLE image with a clear prompt and no mask — use a rephrased instruction that NAMES what must stay unchanged, e.g. 'replace the background with a sunny beach, keep the woman exactly the same'. Use this for background/scene replacement, changing the season or style, adding an object to the scene (a moon, a person), and removing diffuse distractions. mode='masked': masked inpaint on a selected region — use ONLY for an explicit regional removal of a clearly identified object ('remove the person on the left'); select the object first so the mask is tight. NEVER approximate object removal/addition/replacement with selection, adjustment, filter or transform ops; if no image provider is configured, report that instead of substituting a deterministic edit. Other ops: remove-bg, upscale (2x/4x), denoise, enhance-face.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"op": {"type": "string", "enum": ["remove-bg", "upscale", "denoise", "enhance-face", "inpaint", "generative"], "description": "AI edit operation"},
|
||||
"mode": {"type": "string", "enum": ["instruction", "masked"], "description": "instruction = whole-image edit with no mask (background/season/style/add-object/diffuse removal); masked = tight-mask regional removal of a selected object. Default instruction."},
|
||||
"prompt": {"type": "string", "description": "Instruction for inpaint/generative (in instruction mode, name what must stay unchanged)"},
|
||||
"image": {"type": "string", "description": "Optional source (data URL or gallery image id); defaults to the current canvas/screenshot"},
|
||||
"mask": {"type": "string", "description": "Optional base64 PNG mask (white = region to edit); required for mode='masked'"},
|
||||
"scale": {"type": "number", "description": "Upscale factor (2 or 4)"},
|
||||
"strength": {"type": "number", "description": "Denoise strength (0-1)"},
|
||||
"steps": {"type": "integer", "description": "Optional sampler steps. Use 8 for removal/expand edits (default 4 is too weak for those)."},
|
||||
"place": {"type": "boolean", "description": "Place the result as a new layer (default true)"},
|
||||
"model": {"type": "string", "description": "Optional image model id to route this edit to (from GET /api/editor/image-models); omit to use the configured default"},
|
||||
"session": {"type": "string", "description": "Editor session id"}
|
||||
},
|
||||
"required": ["op"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
@@ -2200,13 +2269,7 @@ def function_call_to_tool_block(name: str, arguments: str) -> Optional[ToolBlock
|
||||
elif tool_type == "get_workspace":
|
||||
content = ""
|
||||
elif tool_type == "write_file":
|
||||
body = args.get("content")
|
||||
if isinstance(body, str) and body.strip():
|
||||
content = args.get("path", "") + "\n" + body
|
||||
else:
|
||||
# Preserve missing/empty intent for WriteFileTool instead of folding
|
||||
# all empty shapes into the same path-plus-newline representation.
|
||||
content = json.dumps(args)
|
||||
content = args.get("path", "") + "\n" + args.get("content", "")
|
||||
elif tool_type == "edit_file":
|
||||
content = json.dumps(args)
|
||||
elif tool_type == "apply_patch":
|
||||
|
||||
Reference in New Issue
Block a user