Langfuse aggregates scores by name, so one name may only carry values on
one scale. recall_top_score was emitted for every method, mixing HYBRID's
LR-sigmoid probability and AGENTIC's cross-encoder score (both comparable
in [0, 1]) with KEYWORD's unbounded BM25 and single-route VECTOR's cosine.
A chart on that name averaged the two scales, and in practice a keyword
score can read numerically higher than a calibrated one while meaning less.
Uncalibrated methods now report recall_top_score_raw, leaving
recall_top_score comparable across methods and over time. Every recall
score also carries metadata = {method, calibrated}: a structured field
Langfuse persists and can split on, which the free-text comment could not
serve. The comment stays for reading individual scores.
Breaking for anyone charting recall_top_score for keyword search; 1.2.0 is
four days old, so this is the cheapest moment to correct the naming.
Claude-Session: https://claude.ai/code/session_01UyKinsWs1MgoARPoB9R4NW
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
The examples/langfuse wrapper (everos_langfuse.py) was the interim client-side
instrumentation before EverOS gained native OpenTelemetry export. Now that
[observability] emits real OTLP spans, the wrapper is redundant and its faked
child spans could mislead. Replace it with a minimal, dependency-light example:
enable [observability] in everos.toml, run the server, and drive one
add/flush/search cycle (demo.py, stdlib only) to see native traces in Langfuse.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(examples): make Langfuse wrapper degrade cleanly on a real server
The wrapper synthesized child spans (extraction, embedding, hybrid
recall, rerank, index sync, consolidation) from a mock-only `_detail`
field. Against a real EverOS server that field is absent, so those spans
rendered with placeholder data — hardcoded model names, token=0, fixed
sleep durations — and recall scores fell to 0.
Now the per-stage child spans are emitted only when `_detail` is present
(the mock, or future native in-core instrumentation). Against a live
server only the top-level span per operation is emitted, with real
latency and output — no fabricated data. Recall quality
(recall_top_score / recall_hit) is derived from the real search
response, which already carries a per-hit score, so it works against a
live server today, not just the mock.
Verified: mock path unchanged (full trace tree, real scores); real-ish
path (no `_detail`) emits only top-level spans plus a real recall score.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(examples): count empty recalls as a miss in Langfuse hit-rate
When a search returns nothing scored, record recall_hit=0 (span attribute +
Langfuse score) instead of omitting it, so genuine empty recalls still show
up in recall hit-rate. No top_score is emitted (there is no hit to score).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds examples/langfuse/ — a thin OpenTelemetry wrapper that traces EverOS
memory operations (add / flush+extract / search / reflection) into Langfuse,
with recall quality pushed as Langfuse scores. Pure OTel SDK, no Langfuse
package dependency; runs against a built-in mock or a real EverOS server
(EVEROS_BASE_URL). Additive only, no changes to EverOS core.
Referenced by the upcoming Langfuse docs integration cookbook.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Dani
zhanghui