mirror of
https://github.com/aaronsb/obsidian-mcp-plugin.git
synced 2026-07-22 06:45:14 +00:00
Three defects that each cause an agent to trust a signal further than it holds.
All were surfaced by agents working the same retrieval task and reported
independently, twice each.
Score labels asserted a judgement the number cannot support
interpretScore mapped TF-IDF onto fixed bands — "Good" at >=1.0, "Low" at >0 —
but TF-IDF has no absolute scale; it means different things per query and per
corpus. On a vault where most notes mention the query term the scores compress:
measured, the single best-answering note scored 1.42 ("Good") while five
load-bearing notes scored 0.36-0.45 and were all labelled "Low". An agent
pruning at "Low" would have dropped the entire answer except the anchor. It said
so itself: "the graph was trustworthy; the ranking was not."
The number was never the problem — the adjective was. Scores now render bare,
against this run's top hit ("0.36, 25% of top hit"), which makes the compression
visible instead of hiding it behind a word. Results also carry an explicit
caution not to prune on score.
The graph's blind spot was undocumented, and it is the mirror of search's
The tool descriptions warned that search misses notes written in different
vocabulary. They did not warn that traversal only reaches what someone actually
linked. Both failure modes are real and they are opposite: in the test corpus a
note documenting a fifth consumer of a dependency hub was causally coupled to it
and NOT linked from it, so no traversal from the anchor could reach it — the
shell/ripgrep arm found it by content scan, the graph arm missed it entirely.
Meanwhile that same shell arm silently under-retrieved by 8 files because the
corpus spells the subject two ways, and "a partial match set is indistinguishable
from a complete one".
So they are complements, not substitutes: scan broadly to catch the unlinked,
follow links to catch the differently-worded, trust neither alone. The graph
description now says this, and points at backlinks as the way to find what
depends on a note — which its own text does not know.
"Summary view" read as a truncation warning
Every response closed with "_Summary view. For all metadata fields, use raw:
true._". On tools whose job is faithful retrieval, that reads as a warning that
the content was abridged, and callers spent real attention deciding whether the
note body was a lossy rendering of the argument. Only metadata is abbreviated;
genuine truncation already announces itself (a Pagination section, an explicit
"N more" line). The footer now names what it actually elides.
Also: search-traverse is now described with its cost, not just its brevity — it
returns snippets per node and prunes on scoreThreshold, so it finds WHICH notes
matter but is not the whole argument. Two agents declined to use it because the
description sold the saving without the trade, and chose more calls over less
certainty.
427 tests passing.
|
||
|---|---|---|
| .. | ||
| __mocks__ | ||
| fixtures | ||
| formatters | ||
| security | ||
| validation | ||
| bases-expression-evaluator.test.ts | ||
| bases-yaml.test.ts | ||
| bridge-bootstrap.test.ts | ||
| bridge-self-heal.test.ts | ||
| combine-inline-router.test.ts | ||
| combine-inline.test.ts | ||
| dataview-integration.test.ts | ||
| dispatch-param-guards.test.ts | ||
| file-lock-edit-serialization.test.ts | ||
| fragments-path-scope.test.ts | ||
| fuzzy-match.test.ts | ||
| graph-ignore-exclusion.test.ts | ||
| graph-node-title.test.ts | ||
| graph-search-traversal.test.ts | ||
| graph-search.test.ts | ||
| graph-statistics-vault-wide.test.ts | ||
| list-files-recursive.test.ts | ||
| mcp-server.test.ts | ||
| mcp-session-reinit.test.ts | ||
| network-classifier.test.ts | ||
| network-exposure-integration.test.ts | ||
| patch-operations.test.ts | ||
| read-only-mode.test.ts | ||
| recursive-copy.test.ts | ||
| search-tag-operator.test.ts | ||
| setup.ts | ||
| sse-socket-timeout.test.ts | ||
| test-contract.test.ts | ||
| vault-read-fidelity.test.ts | ||
| vault-rename-extension.test.ts | ||