art-dag/celery
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Rename content_hash/output_hash to cid throughout

Browse Source 
Refactor to use IPFS CID as the primary content identifier:
- Update database schema: content_hash -> cid, output_hash -> output_cid
- Update all services, routers, and tasks to use cid terminology
- Update HTML templates to display CID instead of hash
- Update cache_manager parameter names
- Update README documentation

This completes the transition to CID-only content addressing.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
gilesb
2026-01-12 08:02:44 +00:00
parent 494a2a8650
commit 92d26b2b72
22 changed files with 981 additions and 988 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
tasks/execute.py
View File

@@ -81,8 +81,8 @@ def execute_step(
# Get L1 cache manager (IPFS-backed)
cache_mgr = get_cache_manager()
# Check if already cached (by cache_id as content_hash)
cached_path = cache_mgr.get_by_content_hash(step.cache_id)
# Check if already cached (by cache_id as cid)
cached_path = cache_mgr.get_by_cid(step.cache_id)
if cached_path:
logger.info(f"Step {step.step_id} already cached at {cached_path}")
@@ -141,14 +141,14 @@ def execute_step(
try:
# Handle SOURCE nodes
if step.node_type == "SOURCE":
content_hash = step.config.get("content_hash")
if not content_hash:
raise ValueError(f"SOURCE step missing content_hash")
cid = step.config.get("cid")
if not cid:
raise ValueError(f"SOURCE step missing cid")
# Look up in cache
path = cache_mgr.get_by_content_hash(content_hash)
path = cache_mgr.get_by_cid(cid)
if not path:
raise ValueError(f"SOURCE input not found in cache: {content_hash[:16]}...")
raise ValueError(f"SOURCE input not found in cache: {cid[:16]}...")
output_path = str(path)
complete_task(step.cache_id, worker_id, output_path)
@@ -165,7 +165,7 @@ def execute_step(
for item_id in step.config.get("items", []):
item_cache_id = input_cache_ids.get(item_id)
if item_cache_id:
path = cache_mgr.get_by_content_hash(item_cache_id)
path = cache_mgr.get_by_cid(item_cache_id)
if path:
item_paths.append(str(path))
@@ -190,7 +190,7 @@ def execute_step(
input_cache_id = input_cache_ids.get(input_step_id)
if not input_cache_id:
raise ValueError(f"No cache_id for input step: {input_step_id}")
path = cache_mgr.get_by_content_hash(input_cache_id)
path = cache_mgr.get_by_cid(input_cache_id)
if not path:
raise ValueError(f"Input not in cache: {input_cache_id[:16]}...")
input_paths.append(Path(path))
@@ -276,7 +276,7 @@ def execute_step(
"step_id": step.step_id,
"cache_id": step.cache_id,
"output_path": str(cached_file.path),
"content_hash": cached_file.content_hash,
"cid": cached_file.cid,
"ipfs_cid": ipfs_cid,
"filter_count": len(filter_chain),
}
@@ -298,7 +298,7 @@ def execute_step(
if not input_cache_id:
raise ValueError(f"No cache_id for input step: {input_step_id}")
path = cache_mgr.get_by_content_hash(input_cache_id)
path = cache_mgr.get_by_cid(input_cache_id)
if not path:
raise ValueError(f"Input not in cache: {input_cache_id[:16]}...")
@@ -336,7 +336,7 @@ def execute_step(
"media_type": output_def.media_type,
"index": output_def.index,
"path": str(cached_file.path),
"content_hash": cached_file.content_hash,
"cid": cached_file.cid,
"ipfs_cid": ipfs_cid,
})
else:
@@ -347,7 +347,7 @@ def execute_step(
"media_type": "video/mp4",
"index": 0,
"path": str(cached_file.path),
"content_hash": cached_file.content_hash,
"cid": cached_file.cid,
"ipfs_cid": ipfs_cid,
})
@@ -362,7 +362,7 @@ def execute_step(
"name": step.name,
"cache_id": step.cache_id,
"output_path": str(cached_file.path),
"content_hash": cached_file.content_hash,
"cid": cached_file.cid,
"ipfs_cid": ipfs_cid,
"outputs": outputs,
}