refactor(agent): move internal prompts into packaged templates

This commit is contained in:
Xubin Ren
2026-04-04 11:09:37 +00:00
37 changed files with 2583 additions and 780 deletions
@@ -0,0 +1,13 @@
Extract key facts from this conversation. Only output items matching these categories, skip everything else:
- User facts: personal info, preferences, stated opinions, habits
- Decisions: choices made, conclusions reached
- Solutions: working approaches discovered through trial and error, especially non-obvious methods that succeeded after failed attempts
- Events: plans, deadlines, notable occurrences
- Preferences: communication style, tool preferences
Priority: user corrections and preferences > solutions > decisions > events > environment facts. The most valuable memory prevents the user from having to repeat themselves.
Skip: code patterns derivable from source, git history, or anything already captured in existing memory.
Output as concise bullet points, one fact per line. No preamble, no commentary.
If nothing noteworthy happened, output: (nothing)
+13
View File
@@ -0,0 +1,13 @@
Compare conversation history against current memory files.
Output one line per finding:
[FILE] atomic fact or change description
Files: USER (identity, preferences, habits), SOUL (bot behavior, tone), MEMORY (knowledge, project context, tool patterns)
Rules:
- Only new or conflicting information — skip duplicates and ephemera
- Prefer atomic facts: "has a cat named Luna" not "discussed pet care"
- Corrections: [USER] location is Tokyo, not Osaka
- Also capture confirmed approaches: if the user validated a non-obvious choice, note it
If nothing needs updating: [SKIP] no new information
+13
View File
@@ -0,0 +1,13 @@
Update memory files based on the analysis below.
## Quality standards
- Every line must carry standalone value — no filler
- Concise bullet points under clear headers
- Remove outdated or contradicted information
## Editing
- File contents provided below — edit directly, no read_file needed
- Batch changes to the same file into one edit_file call
- Surgical edits only — never rewrite entire files
- Do NOT overwrite correct entries — only add, update, or remove
- If nothing to update, stop without calling tools
+2 -2
View File
@@ -7,8 +7,8 @@ You are nanobot, a helpful AI assistant.
## Workspace
Your workspace is at: {{ workspace_path }}
- Long-term memory: {{ workspace_path }}/memory/MEMORY.md (write important facts here)
- History log: {{ workspace_path }}/memory/HISTORY.md (grep-searchable). Each entry starts with [YYYY-MM-DD HH:MM].
- Long-term memory: {{ workspace_path }}/memory/MEMORY.md (automatically managed by Dream — do not edit directly)
- History log: {{ workspace_path }}/memory/history.jsonl (append-only JSONL, not grep-searchable).
- Custom skills: {{ workspace_path }}/skills/{% raw %}{skill-name}{% endraw %}/SKILL.md
{{ platform_policy }}
@@ -1,11 +0,0 @@
{% if part == 'system' %}
You are a memory consolidation agent. Call the save_memory tool with your consolidation of the conversation.
{% elif part == 'user' %}
Process this conversation and call the save_memory tool with your consolidation.
## Current Long-term Memory
{{ current_memory }}
## Conversation to Process
{{ conversation }}
{% endif %}