abmind 0.1.3 → 0.1.4

package/prompts/sleep/08-memory-maintenance.md

@@ -0,0 +1,39 @@
+# Memory Maintenance
+
+Three metadata tasks on existing memories. Process each section independently.
+
+## Task 1: Topic Assignment
+
+Untagged memories:
+${UNTAGGED_MEMORIES}
+
+For each memory, assign the most fitting topic AND 3-5 search keywords:
+```
+abmind edit --memory-id N --topic <topic> --keyword "synonym1, synonym2, synonym3"
+```
+
+Topics: `coding`, `personal`, `work`, `finance`, `health`, `projects`, `tools`, `people`
+
+If a memory spans multiple topics, pick the primary one.
+
+## Task 2: Merge Duplicates
+
+Candidate pairs (similar content, same topic):
+${MERGE_CANDIDATES}
+
+For each pair:
+- If truly duplicate: invalidate the older one (`abmind edit --memory-id <older> --valid-to <today>`)
+- If complementary: keep both
+- If contradictory: invalidate the less confident one
+
+## Task 3: Fill Emotion Context
+
+Memories with emotion tags but missing emotion_context:
+${EMOTION_CONTEXT_GAPS}
+
+For each memory:
+1. Read the content and emotion tags.
+2. Infer WHY the emotion applies in 3-5 words.
+3. Apply: `abmind edit --memory-id N --emotion-context "reason"`
+
+Report counts for each task. If a section has no candidates, say "(none)" and move on.

package/prompts/sleep/{13-consolidation.md → 11-consolidation.md}

@@ -6,6 +6,9 @@ Write a weekly or quarterly summary by consolidating recent daily files.
 
 1. Read recent daily retrospective and summary files.
 2. Identify recurring themes, progress on projects, and shifts in priorities.
-3. Write a consolidated summary to `${CONSOLIDATION_PATH}`.
+3. Write a consolidated summary to `${CONSOLIDATION_OUTPUT_PATH}`.
+4. The first line should be a heading showing the date range covered (e.g. "# Weekly — May 19–25, 2026").
+
+Previous consolidation for reference: `${CONSOLIDATION_PATH}`
 
 Respond with confirmation of the summary written.

package/prompts/sleep/03-extract-from-daily.md

@@ -1,3 +0,0 @@
-# Extract From Daily
-
-This step is code-driven. The orchestrator handles extraction.

package/prompts/sleep/04-retrospective.md

@@ -1,30 +0,0 @@
-# Daily Retrospective + Memory Extraction
-
-Write a daily retrospective based on today's conversations, then extract lasting memories from it.
-
-## Pre-loaded data
-
-Today's clean messages:
-${CLEAN_MESSAGES}
-
-## Task 1: Write Retrospective
-
-Write a retrospective covering:
-
-1. **What happened** — key events, tasks, decisions made today.
-2. **Emotional attribution** — how the user seemed to feel during different interactions. Note shifts in tone or energy.
-3. **Lessons** — what went well, what didn't, what to do differently.
-4. **Recurring errors** — check if any errors appeared multiple times today and were fixed the same way. If so, note: "Recurring: [error] was fixed by [action] — consider adding as auto-fix rule via `abtars-autofix add`."
-5. **Agent notes update** — if anything learned today should persist (user preferences, project context, recurring patterns), update `agent_notes.md` via `abmind edit`.
-
-Write the retrospective to `${RETRO_PATH}`.
-
-## Task 2: Extract Memories from Retrospective
-
-From the retrospective you just wrote, extract lessons, mistakes, and insights as permanent memories:
-
-1. For each candidate, run `abmind recall` with the key phrase to check for duplicates.
-2. If no duplicate exists, store via `abmind store`.
-3. If a mistake repeats a previously stored mistake, store it with escalated emotion score (`-2` from previous).
-
-Respond with a brief confirmation of what was written to the retro file, followed by the count of memories stored.

package/prompts/sleep/07-topic-assignment.md

@@ -1,23 +0,0 @@
-# Topic Assignment
-
-Assign topics to untagged memories.
-
-## Pre-loaded data
-
-Untagged memories:
-${UNTAGGED_MEMORIES}
-
-## Topics
-
-`coding`, `personal`, `work`, `finance`, `health`, `projects`, `tools`, `people`
-
-## Task
-
-For each memory, read its content and assign the most fitting topic AND 3-5 search keywords (synonyms a user might query with):
-```
-abmind edit --memory-id N --topic <topic> --keyword "synonym1, synonym2, synonym3"
-```
-
-If a memory spans multiple topics, pick the primary one.
-
-Respond with the assignments made.

package/prompts/sleep/08-core-promotion.md

@@ -1,26 +0,0 @@
-# Core Promotion
-
-Promote worthy general-tier memories to core tier.
-
-## Pre-loaded data
-
-Promotion candidates (high relevance, frequently recalled):
-${PROMOTION_CANDIDATES}
-
-${CONTRADICTION_WARNINGS}
-
-## Constraints
-
-- Budget: 100 core entries max. Do not exceed.
-- Only promote memories that represent enduring facts, strong preferences, or critical context.
-- Do not promote transient or time-bound information.
-- If a contradiction is flagged: invalidate the older memory (`abmind edit --memory-id <older> --valid-to <today>`) before promoting the newer one.
-
-## Task
-
-For each worthy candidate:
-```
-abmind edit --memory-id N --tier core
-```
-
-Respond with the list of promotions made.

package/prompts/sleep/09-merge.md

@@ -1,19 +0,0 @@
-# Memory Merge
-
-Review near-duplicate memory pairs and merge or invalidate.
-
-## Pre-loaded data
-
-Candidate pairs (similar content, same topic):
-${MERGE_CANDIDATES}
-
-## Rules
-
-- Max 5 merges per run.
-- If both express the same fact: `abmind store --merge --merge-ids A,B`
-- If one contradicts the other: invalidate the older one via `abmind edit --memory-id <older> --valid-to <today>`
-- If they are related but distinct, skip.
-
-## Task
-
-Review each pair and act accordingly. Respond with merges and invalidations performed.

package/prompts/sleep/12-core-knowledge.md

@@ -1,14 +0,0 @@
-# Core Knowledge Review
-
-Review and maintain `agent_notes.md` and `user_profile.md`.
-
-**SOUL.md is read-only** — never modify it. Identity is human-managed.
-
-## Task
-
-1. Read `agent_notes.md` and `user_profile.md`.
-2. Remove entries that are outdated or no longer accurate.
-3. Update entries that have become stale based on recent interactions.
-4. Keep files concise — no redundancy.
-
-Respond with changes made.

package/prompts/sleep/14-emotion-context.md

@@ -1,17 +0,0 @@
-# Emotion Context
-
-Infer emotional context for memories that have emotion tags but no context explaining why.
-
-## Pre-loaded data
-
-Memories with emotion tags but missing emotion_context:
-${EMOTION_CONTEXT_GAPS}
-
-## Task
-
-For each memory:
-1. Read the content and emotion tags.
-2. Infer WHY the emotion applies in 3–5 words (e.g., "frustrated by repeated bug", "proud of shipping fast").
-3. Apply: `abmind edit --memory-id N --emotion-context "reason"`
-
-Respond with the count of contexts added.