recall

Previous value: -"2.6: when the answer was stored, as far as you remember. Give after and/or before (a date YYYY-MM-DD, which includes that whole day, or an ISO-8601 timestamp), or ago, plus confidence. The server also searches that period. Among the rows it returns anyway, one found there moves up by at most 3 / 2 / 1 places (sure / likely / vague), and as many extra seats (3 / 2 / 1) hold the best records that search found which the answer does not already hold: one no other search reached, or one the count cut. The returned rows are those of a recall without the cue, reordered, plus at most those seats: no row is removed or re-scored, and which rows pass the quality gate does not change. If the period holds nothing it is widened once, one confidence step. likely widens the period by half its length on each side, vague by its whole length. The response then carries time_cue: the period searched, whether it was widened, how many rows moved and how many seats were used. Pass it only when the request itself says when (a date, a month, \"last week\", \"in the spring\"); omit it when the request names no time, and never fill it with today's date or a guess. A cue whose own period starts within the last 24 hours (today, or later) is not used: the rows are those of a recall without a cue, and time_cue in the response says ignored. A cue that cannot be read returns an error and no messages."New value: +"2.6: when the answer was stored, as far as you remember. Give after and/or before (a date YYYY-MM-DD, which includes that whole day, or an ISO-8601 timestamp), or ago, plus confidence. The server also searches that period. Among the rows it returns anyway, one found there moves up by at most 3 / 2 / 1 places (sure / likely / vague), and as many extra seats (3 / 2 / 1) hold the best records that search found which the answer does not already hold: one no other search reached, or one the count cut. The returned rows are those of a recall without the cue, reordered, plus at most those seats: no row is removed or re-scored, and which rows pass the quality gate does not change. If the period holds nothing it is widened once, one confidence step. likely widens the period by half its length on each side, vague by its whole length. The response then carries time_cue: the period searched, whether it was widened, how many rows moved and how many seats were used, and remainder when the period held more records than the vector search reads and no coarse index could search the rest. Pass it only when the request itself says when (a date, a month, \"last week\", \"in the spring\"); omit it when the request names no time, and never fill it with today's date or a guess. A cue whose own period starts within the last 24 hours (today, or later) is not used: the rows are those of a recall without a cue, and time_cue in the response says ignored. A cue that cannot be read returns an error and no messages."

Added value: +256

Added value: +{
+  "additionalProperties": false,
+  "description": "2.6: when the answer was stored, as far as you remember. Give after and/or before (a date YYYY-MM-DD, which includes that whole day, or an ISO-8601 timestamp), or ago, plus confidence. The server also searches that period. Among the rows it returns anyway, one found there moves up by at most 3 / 2 / 1 places (sure / likely / vague), and as many extra seats (3 / 2 / 1) hold the best records that search found which the answer does not already hold: one no other search reached, or one the count cut. The returned rows are those of a recall without the cue, reordered, plus at most those seats: no row is removed or re-scored, and which rows pass the quality gate does not change. If the period holds nothing it is widened once, one confidence step. likely widens the period by half its length on each side, vague by its whole length. The response then carries time_cue: the period searched, whether it was widened, how many rows moved and how many seats were used. Pass it only when the request itself says when (a date, a month, \"last week\", \"in the spring\"); omit it when the request names no time, and never fill it with today's date or a guess. A cue whose own period starts within the last 24 hours (today, or later) is not used: the rows are those of a recall without a cue, and time_cue in the response says ignored. A cue that cannot be read returns an error and no messages.",
+  "properties": {
+    "after": {
+      "type": "string"
+    },
+    "ago": {
+      "description": "Relative to now: {\"unit\": \"days\" | \"weeks\" | \"months\", \"value\": N} names the unit-long period centred N units ago (a month is 30 days); \"long_ago\" names the oldest third of what this scope holds.",
+      "oneOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "unit": {
+              "enum": [
+                "days",
+                "weeks",
+                "months"
+              ],
+              "type": "string"
+            },
+            "value": {
+              "minimum": 0,
+              "type": "integer"
+            }
+          },
+          "required": [
+            "unit",
+            "value"
+          ],
+          "type": "object"
+        },
+        {
+          "enum": [
+            "long_ago"
+          ],
+          "type": "string"
+        }
+      ]
+    },
+    "before": {
+      "type": "string"
+    },
+    "confidence": {
+      "enum": [
+        "sure",
+        "likely",
+        "vague"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "confidence"
+  ],
+  "type": "object"
+}

Added value: +{
+  "default": false,
+  "description": "2.6 recall trace: true adds `trace` to the response — which rows each stage (retrieval arms, fusion, quality gate, autocut, final order, count cut, reserved seats) kept, dropped or reordered, and why, with ranks and scores. It carries references only, never stored text, and is not stored on the server. trace_version identifies its shape. False (the default) returns the response unchanged.",
+  "type": "boolean"
+}

Previous value: -"Normalized content strings to exclude from results (starts-with match). Used to prevent duplication with conversation context already known to the caller."New value: +"Normalized content strings to exclude from results (starts-with match). Used to prevent duplication with conversation context already known to the caller. bug-399: the starts-with rule holds only at or above 32 characters. A shorter entry has to EQUAL the stored content (after the normalization this parameter already asks for: stripped and lower-cased) — a short prefix would otherwise suppress every memory beginning with it, inside the retrievers and with nothing in the response reporting the exclusion. Size entries at or above that length when you mean a prefix."

Previous value: -"Per-retriever search depth, not a pure response cap (CSC #716): the value is handed to each retrieval channel (vector / episode FTS / keyword) as its top-K, so lowering it shrinks the candidate pool itself — rows beyond the depth are unreachable at any gate value, and score normalization / autocut operate on the smaller pool, which can also reorder what remains. Fewer rows than this may be returned. (Agent-facing cap; the library layer accepts up to the scan window for direct callers.)"New value: +"Per-retriever search depth, not a pure response cap: the value is handed to each retrieval channel (vector / episode FTS / keyword) as its top-K, so lowering it shrinks the candidate pool itself — rows beyond the depth are unreachable at any gate value, and score normalization / autocut operate on the smaller pool, which can also reorder what remains. Fewer rows than this may be returned. (Agent-facing cap; the library layer accepts up to the scan window for direct callers.)"

Added value: +{
+  "default": "",
+  "description": "Opaque session identity you declare — a partition hint, NOT authentication. It scopes this process's per-session state: the degraded-recall advisory's \"already told you\" memory, and which no-persist pause applies to this call. It does NOT filter stored data (use agent_id / project_id / channel for that), and it never reaches the database. Omit it to share one bucket with every other caller that omits it, which is the behaviour that predates this parameter.",
+  "type": "string"
+}

Previous value: -"Deep recall — disable time and completion decay for exhaustive search"New value: +"Deep recall — halves the quality gate (and the calibrated fused gate), so weaker matches are admitted. It also disables time and completion decay, which are inert unless CPERSONA_CONFIDENCE_ENABLED=true, and it does NOT widen the scan window (CPERSONA_MAX_MEMORIES) — deep is about how weak a match may be, not how far back the search reaches."

Previous value: -"Max memories to return (agent-facing cap; the library layer accepts up to the scan window for direct callers)"New value: +"Per-retriever search depth, not a pure response cap (CSC #716): the value is handed to each retrieval channel (vector / episode FTS / keyword) as its top-K, so lowering it shrinks the candidate pool itself — rows beyond the depth are unreachable at any gate value, and score normalization / autocut operate on the smaller pool, which can also reorder what remains. Fewer rows than this may be returned. (Agent-facing cap; the library layer accepts up to the scan window for direct callers.)"

Added value: +{
+  "description": "v2.4.17 γ filter. Omit → no filter (all projects). '' → global pool only. 'X' → 'X' bucket ∪ global pool. Threaded through cascade / RRF / vector / FTS / keyword paths.",
+  "type": "string"
+}

Added value: +{
+  "default": "",
+  "description": "v2.4.20 per-user source filter. Empty (default) = no filter. Non-empty = prefix match against json_extract(source, '$.id'), e.g. 'discord:12345' to restrict to one Discord user, or 'discord:' to scope to all Discord-sourced memories. Episodes are skipped when set (no per-user source tagging).",
+  "type": "string"
+}

Added value: +{
+  "description": "Normalized content strings to exclude from results (starts-with match). Used to prevent duplication with conversation context already known to the caller.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}