mirror of
https://github.com/hanzoai/insights.git
synced 2026-10-30 16:15:31 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
43 lines
1.7 KiB
Python
43 lines
1.7 KiB
Python
"""Per-span self-time annotation for full-trace payloads.
|
|
|
|
Self-time is the part of a span's duration not covered by its children — computed as an
|
|
interval union so overlapping or parallel children are only subtracted once. For a leaf
|
|
it equals the span's own duration; for a parent it is the unaccounted gap ("where did
|
|
the wall-clock actually go"), which is invisible from duration_nano alone.
|
|
"""
|
|
|
|
import datetime as dt
|
|
from collections import defaultdict
|
|
|
|
_MICROSECOND = dt.timedelta(microseconds=1)
|
|
|
|
|
|
def annotate_self_time(spans: list[dict]) -> None:
|
|
"""Set `self_time_nano` on every span dict, in place.
|
|
|
|
Expects the full span set of a trace (children grouped by `parent_span_id`);
|
|
`timestamp` / `end_time` must still be datetimes. On a truncated trace the values
|
|
overstate self-time for spans whose children were cut.
|
|
"""
|
|
children_by_parent: dict[str, list[dict]] = defaultdict(list)
|
|
for span in spans:
|
|
children_by_parent[span["parent_span_id"]].append(span)
|
|
|
|
for span in spans:
|
|
start, end = span["timestamp"], span["end_time"]
|
|
intervals = sorted(
|
|
(max(child["timestamp"], start), min(child["end_time"], end))
|
|
for child in children_by_parent.get(span["span_id"], [])
|
|
if child["timestamp"] < end and child["end_time"] > start
|
|
)
|
|
|
|
covered_ns = 0
|
|
cursor = start
|
|
for child_start, child_end in intervals:
|
|
child_start = max(child_start, cursor)
|
|
if child_end > child_start:
|
|
covered_ns += ((child_end - child_start) // _MICROSECOND) * 1000
|
|
cursor = child_end
|
|
|
|
span["self_time_nano"] = max(span["duration_nano"] - covered_ns, 0)
|