mirror of
https://github.com/morluto/rea.git
synced 2026-11-10 16:57:19 +00:00
morluto
cb4e5cfbff
* refactor(analysis): centralize resource budgets and recovery facts * feat(analysis): expose ASAR and Ghidra runtime admission controls * feat(artifacts): expose reader admission and preserve limited recognition * feat(javascript): expose recoverable semantic precision budgets * feat(web): add recoverable source-map budgets and compact retained views * feat(web): make historical capture decoding budgets recoverable * fix(desktop): enforce selected view policies across capture and export * feat(runtime): make Frida and LLDB retention budgets selectable * feat(native): expose diagnostic budgets and preserve exhaustion causes * feat(managed): expose recoverable snapshot and representation budgets * feat(metadata): make Go and Rust inspection budgets recoverable * feat(wasm): expose representation and producer admissions * feat(evm): expose per-call worker resource budgets * feat(android): make resource and string-pool omissions recoverable * feat(producers): expose command and recorded-capture budgets * docs(analysis): record recovery contracts and integrated validation * fix(docs): link calibration oracle from published verification pages * fix(docs): restore desktop task anchors and receipt links * test(analysis): align fixtures with selectable budget contracts * fix(analysis): remove source-location projector dependency cycle * test(analysis): refresh budget recovery and verifier regressions * test(analysis): preserve format and publication recovery expectations * test(windows): align conformance with owned runtime admission * fix(desktop): preserve selected alias kinds in exported state * test(analysis): align provider fixtures with recoverable budgets * test(desktop): validate emitted alias metadata structurally * fix(ghidra): classify bounded Windows endpoint refusals * test(cli): assert selectable artifact admission recovery * fix(cli): preserve capture provenance in environment builds
46 lines
1.8 KiB
Python
46 lines
1.8 KiB
Python
"""Join serial observer receipts with exact tokenization of every logical call.
|
|
|
|
Requires tiktoken 0.12.0 for comparison with the retained measurements.
|
|
Token counts exclude chat framing, catalogs, adapters, retained delivery and
|
|
model reasoning. Artifact and repository path spelling can affect tokens.
|
|
"""
|
|
|
|
import argparse
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import tiktoken
|
|
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument('receipts', type=Path)
|
|
parser.add_argument('output', type=Path)
|
|
options = parser.parse_args()
|
|
encoding = tiktoken.get_encoding('cl100k_base')
|
|
rows = []
|
|
for path in sorted(options.receipts.rglob('*.metrics.json')):
|
|
metrics = json.loads(path.read_text())
|
|
key = str(path.relative_to(options.receipts)).removesuffix('.metrics.json')
|
|
# The observer argv ends with the selected configuration file.
|
|
config = json.loads(Path(metrics['argv'][-1]).read_text())
|
|
reply = json.loads(Path(config['reply_receipt']).read_text())
|
|
assert metrics['exit_code'] == 0 and metrics['stop_reason'] is None, path
|
|
assert metrics['cleanup'] == 'group_empty' and reply['success'], path
|
|
tokens = sum(
|
|
len(encoding.encode(json.dumps(call[field], ensure_ascii=False, separators=(',', ':'))))
|
|
for call in reply['calls']
|
|
for field in ['request', 'reply']
|
|
)
|
|
rows.append({
|
|
'key': key,
|
|
'calls': reply['call_count'],
|
|
'tokens_cl100k_base': tokens,
|
|
'seconds': metrics['elapsed_seconds'],
|
|
'cpu': metrics['cpu_seconds_waited_subtree'],
|
|
'peak_mib': metrics['peak_process_group_rss_bytes_sampled'] / 1024**2,
|
|
'delivered': reply['package_uris_delivered_final'],
|
|
'cleanup': metrics['cleanup'],
|
|
'scope': reply['boundary'],
|
|
})
|
|
assert rows, 'No *.metrics.json receipts found'
|
|
options.output.write_text(json.dumps(rows, indent=2) + '\n')
|