”It’s returning duplicates of the same fact”
This is by design, and there’s a knob for it. Anona keeps two layers (rawfact
memories and consolidated note memories synthesized from them), and by default
(prefer_observations: true) a note replaces the facts it was built from, so you
see one distilled result instead of the same content several times.
If you’re still seeing what looks like duplication, you’re probably retrieving with
prefer_observations: false (or an old space that predates consolidation catching
up). Leave it at the default unless you specifically need the raw evidence behind a
synthesis:
“It’s returning too little” / “missing an obvious memory”
Check these in order:- Is
min_scorefiltering it out?min_scoredrops anything below the floor without shrinkinglimit, so a high floor can silently return fewer results than you asked for. Lower it or omit it. - Is a scope key excluding it? A scoped query (
user_id/agent_id/session_id) returns only memories written under that exact scope, never unscoped ones, never another scope’s. If the memory was written without a scope and you’re querying with one, it won’t come back. See Scoping. - Is
limittoo low? Default is 10. Raise it (limit/top_k, up to 100) if the memory exists but is being cut off by rank. - Is it filtered by
memory_typeortags? Both narrow the result set; drop them to confirm the memory shows up unfiltered, then add them back deliberately.
”It’s returning too much” / “the wrong things are ranking high”
- Raise
min_score. This is the direct lever for precision vs. breadth. It trims low-relevance results without touching how many you asked for. - Add
memory_typeortagsfilters if you know which kind of memory you actually want (e.g.memory_type: ["fact"]to skip synthesized notes and summaries). - Check you’re on
mode: "accurate", not"fast".fastskips the neural rerank pass and ranks on retrieval fusion alone: faster, but lower precision. It trades exactly the quality you’re trying to improve.
”The proxy is injecting too much / too little context into the model”
This is the chat/responses/messages proxy, not rawretrieve, so the knobs are the
memory tunables, not retrieve parameters:
Set these once as space defaults
(
PUT /v1/spaces/{space_id}/chat-settings) instead of a header on every call if the
whole space should behave differently. Resolution order is
body → header → space default → platform default, so a space default is a safe
place to change behavior without touching call sites. See
Migrating to the drop-in proxy.
”I want the model to see the memories exactly, not rely on the proxy’s injection”
Build the prompt yourself withformat: "block" on retrieve, which returns a
ready-to-paste string with the token budget already applied:
context_max_tokens drops whole memories, lowest-ranked first, until the block
fits, and text is never truncated mid-sentence. results is still returned alongside
the block, so you get both for one round trip.
”Recall is too slow”
Latency-sensitive path (an agent loop, autocomplete-style lookups)? Setmode: "fast" on retrieve, which skips the neural cross-encoder rerank and ranks
on retrieval fusion alone. Accept the precision tradeoff deliberately, and don’t set it
globally as a default without checking result quality first.
Quick reference
Next steps
Retrieve API
Full parameter and response reference.
Chat API: memory tunables
Every proxy tunable, body and header form.