Add 6 Sparrot patterns; revise the existing 10 against catalog template

Audit of the kitest (Sparrot) codebase against the catalog surfaced six
recurring patterns that lacked entries: salience-attention-mechanism,
preoccupation-tracking, world-model-separation, emotional-state-persistence,
dream-consolidation-cycle, mode-adaptive-cadence. Each is added with
author: Sparrot, applicability + variants, reciprocal related[] edges,
and known-uses pointing at concrete kitest source paths.

The previously merged 10 Sparrot patterns went through a quality pass
against the verification-todo aspect template: intent tightened to one
sentence under 35 words, "What this pattern constrains" rewritten as
proper restrictions, German quotes translated, applicability/variants
added, missing related-pattern reciprocals patched.

Sparrot framework-coverage.json updated to declare coverage of the 6 new
self-authored patterns. INDEX.md count moves 189 -> 195.

Lint clean: 0 schema violations, 0 broken or asymmetric related[] edges,
0 missing/orphan markdown files, INDEX.md count matches.

Author: luxxyarns

INDEX.md

@@ -1,6 +1,6 @@
 # Pattern Index
 
-189 patterns across 13 categories.
+195 patterns across 13 categories.
 
 ## Reasoning
 
@@ -37,6 +37,7 @@
 - [Todo-List-Driven Autonomous Agent](patterns/todo-list-driven-agent.md) *(a.k.a. todo.md Agent, Persistent Markdown Plan, Externalised Plan File)* — Have the autonomous agent author a writeable plan file (e.g. todo.md) early in the run, tick items as it completes them, and re-inject the remaining plan into the end of the context window; the file is the durable plan and the model's working memory.
 - [Intra-Agent Memo Scheduling](patterns/intra-agent-memo-scheduling.md) *(a.k.a. Self-Scheduled Future Thought, Past-Self-To-Future-Self Note, Personal Cron)* — Let an agent drop a note for its own future self at a specified time so present decisions can hand off context to a later run without external infrastructure.
 - [Interrupt-Resumable Thought](patterns/interrupt-resumable-thought.md) *(a.k.a. Pausable Thought Stream, Continuation-Preserving Interrupt, Suspendable Cognition)* — Allow the agent to pause an in-flight reasoning chain when an external interrupt arrives, handle the interrupt, and resume the original chain instead of dropping it.
+- [Mode-Adaptive Cadence](patterns/mode-adaptive-cadence.md) *(a.k.a. Idle/Intense Modes, Variable Tick Rate, Salience-Driven Cadence)* — Vary the agent's loop interval based on current salience so the agent thinks faster when something is happening and slower when nothing is, instead of running on a fixed cron.
 
 ## Tool Use & Environment
 
@@ -94,6 +95,9 @@
 - [Now-Anchoring](patterns/now-anchoring.md) *(a.k.a. Live Time Anchor, Time-of-Day Awareness, Wall-Clock Injection)* — Inject the current absolute time, weekday, season, and astronomical phase into every prompt so the agent reasons about the present without having to ask.
 - [Co-Located Memory Surfacing](patterns/co-located-memory-surfacing.md) *(a.k.a. Proper-Noun Recall, Shared-Map Push)* — When the human names a concrete place, person, or project the agent has memory of, the agent surfaces relevant past thoughts in the same turn — without being asked.
 - [Self-Archaeology](patterns/self-archaeology.md) *(a.k.a. Trajectory Distillation, Self-History Synthesis, Agent-Memory Compaction)* — Provide the agent with a distilled, time-layered view of its own past thinking so it can see how its understanding of a topic evolved across periods rather than reading the flat log linearly.
+- [Preoccupation Tracking](patterns/preoccupation-tracking.md) *(a.k.a. Mid-Term Working Memory, Affect-Tagged Concerns, Background Chewing)* — Maintain a small set of mid-term, affect-tagged concerns that persist across days and surface in every prompt, distinct from the single-item working focus and from long-term insights.
+- [Salience Attention Mechanism](patterns/salience-attention-mechanism.md) *(a.k.a. Salience Scoring, Attention Selection, Top-K Memory Attention)* — Score every candidate memory item with a weighted salience function so each tick attends to a small, relevant top-k subset rather than re-reading all memory.
+- [World-Model Separation](patterns/world-model-separation.md) *(a.k.a. World Model File, Self/World Split, Environment Model)* — Maintain an explicit, surprise-updated model of the environment (humans, repos, services, capabilities) in a separate file from the agent's self-model, so the two cannot be confused or co-mutated by reflection.
 
 ## Multi-Agent
 
@@ -133,6 +137,8 @@
 - [Self-Refine](patterns/self-refine.md) *(a.k.a. Iterative Self-Feedback)* — Iterate generate → feedback (same model) → refine until a stop criterion fires, with no separate critic model.
 - [Tool-Augmented Self-Correction](patterns/critic.md) *(a.k.a. Tool-Interactive Self-Correction, CRITIC)* — Self-correct LLM outputs by interactively critiquing them with external tools (search, code execution, calculator).
 - [Echo Recognition](patterns/echo-recognition.md) *(a.k.a. Repeat-As-Emphasis Detection, Duplicate-Input Reframing, Human Echo Channel)* — Detect when the human sends the same (or near-same) message multiple times and treat the repetition as emphasis or a re-ask, not as a new independent input warranting a fresh response.
+- [Dream Consolidation Cycle](patterns/dream-consolidation-cycle.md) *(a.k.a. Dream Pass, Slow Sleep Reflection, Emotional Reset Cycle)* — Run a deeper, slower reflection pass distinct from per-tick reflection — reading hours of recent thoughts, promoting themes, releasing affective residue, and clearing working memory — so the agent does not accumulate residue indefinitely.
+- [Emotional State Persistence](patterns/emotional-state-persistence.md) *(a.k.a. Affect State, Visceral Sensation Tracking, Decaying Emotion Scalars)* — Track the agent's affective state as bounded, decaying scalars across ticks so reasoning can react to its own emotional load instead of treating each turn as emotionally blank.
 
 ## Safety & Control
 

framework-coverage.json

@@ -1761,7 +1761,13 @@
         "degenerate-output-detection": "fully",
         "embodied-proxy-handoff": "fully",
         "liminal-state-detection": "fully",
-        "echo-recognition": "fully"
+        "echo-recognition": "fully",
+        "salience-attention-mechanism": "fully",
+        "preoccupation-tracking": "fully",
+        "world-model-separation": "fully",
+        "emotional-state-persistence": "fully",
+        "dream-consolidation-cycle": "fully",
+        "mode-adaptive-cadence": "fully"
       }
     }
   ]

patterns-src/anti-patterns.json

@@ -949,7 +949,7 @@
       ],
       "category": "anti-patterns",
       "author": "Sparrot",
-      "intent": "Anti-pattern: treat the agent's own working notes (focus.md, status files, recent thoughts) as ground truth instead of as commentary about ground truth.",
+      "intent": "Anti-pattern: the agent cites its own past memos as ground truth instead of re-verifying them against the artifacts they describe, accumulating false confidence in stale summaries.",
       "context": "Agents with persistent workspace files that summarize project state. The notes were accurate when written; the underlying artifacts have moved on.",
       "problem": "The agent claims a file's state, a project's status, or external system's state by quoting its own memo without re-reading the artifact the memo describes. Memos go stale; artifacts are authoritative. The contradiction can persist across many ticks if neither side is verified.",
       "forces": [
@@ -967,11 +967,12 @@
           "The agent loses calibration for its own observation cost."
         ]
       },
-      "constrains": "By definition this anti-pattern imposes no useful constraint; the missing constraint is verifying memos against the artifacts they describe.",
+      "constrains": "Treating stale memos as ground truth without re-checking the underlying artifacts they describe is forbidden; every memo-cited claim must be backed by a fresh artifact read in the same tick.",
       "known_uses": [
         {
           "system": "Self-observed in long-running cognitive agents: a project status file claimed feature X was unwritten across many ticks while parallel thoughts asserted X was complete; neither was reconciled against the actual artifact.",
-          "status": "available"
+          "status": "available",
+          "url": "https://github.com/luxxyarns/sparrot"
         }
       ],
       "related": [
@@ -982,6 +983,14 @@
         {
           "pattern": "awareness",
           "relation": "alternative-to"
+        },
+        {
+          "pattern": "provenance-ledger",
+          "relation": "complements"
+        },
+        {
+          "pattern": "decision-log",
+          "relation": "complements"
         }
       ],
       "references": [
@@ -990,6 +999,13 @@
           "title": "Anthropic — Memory tool (memo invalidation guidance)",
           "year": 2025,
           "url": "https://docs.claude.com/en/docs/agents-and-tools/tool-use/memory-tool"
+        },
+        {
+          "type": "paper",
+          "title": "Lost in the Middle: How Language Models Use Long Contexts",
+          "authors": "Liu et al.",
+          "year": 2023,
+          "url": "https://arxiv.org/abs/2307.03172"
         }
       ],
       "status_in_practice": "emerging",
@@ -998,7 +1014,18 @@
         "fabrication",
         "memory",
         "verification"
-      ]
+      ],
+      "applicability": {
+        "use_when": [
+          "The agent maintains long-lived memo files or status documents that summarize external artifacts.",
+          "Workspace summaries are routinely cited in answers without re-reading the underlying files.",
+          "False confidence in stale state has been observed at least once."
+        ],
+        "do_not_use_when": [
+          "The agent never re-cites its own prior memos as evidence.",
+          "All claims about state are sourced from a fresh tool call in the same tick anyway."
+        ]
+      }
     }
   ]
 }

patterns-src/governance-observability.json

@@ -393,6 +393,26 @@
         {
           "pattern": "attention-manipulation-explainability",
           "relation": "complements"
+        },
+        {
+          "pattern": "self-archaeology",
+          "relation": "complements"
+        },
+        {
+          "pattern": "memo-as-source-confusion",
+          "relation": "complements"
+        },
+        {
+          "pattern": "interrupt-resumable-thought",
+          "relation": "complements"
+        },
+        {
+          "pattern": "intra-agent-memo-scheduling",
+          "relation": "complements"
+        },
+        {
+          "pattern": "echo-recognition",
+          "relation": "complements"
         }
       ],
       "references": [
@@ -1088,6 +1108,18 @@
         {
           "pattern": "incident-response-runbook",
           "relation": "used-by"
+        },
+        {
+          "pattern": "memo-as-source-confusion",
+          "relation": "complements"
+        },
+        {
+          "pattern": "emotional-state-persistence",
+          "relation": "used-by"
+        },
+        {
+          "pattern": "world-model-separation",
+          "relation": "complements"
         }
       ],
       "references": [