Files
fidelity-ai-workspace/core/memory/operational-memory.md
david.delagneau 374991a568 Refactor workspace structure and documentation
- Deleted obsolete files: obsidian-vault.md, onboarding.md, workspace-model.md
- Updated opencode.json to remove references to deleted files.
- Revised profile.md to clarify the status of legacy paths and communication evidence.
- Adjusted prompts to reflect new file paths and improve clarity.
- Enhanced daily logs with focus, work-items, and blockers properties.
- Updated work-item notes to include systems, workstreams, people, and related properties.
- Improved context maintenance guidelines to ensure accurate and durable project knowledge.
- Refined base filters to exclude template files and ensure only relevant notes are displayed.
- Updated daily templates to ensure proper formatting and consistency.
- Modified workflows to align with the new vault structure and improve context synchronization.
2026-04-16 16:28:30 -06:00

3.3 KiB

Operational Memory

Definition

Operational memory is a versionable file-based system where the agent decides whether each interaction introduces, corrects, or invalidates knowledge, then updates the smallest correct canonical file.

The goal is not transcript storage. The goal is a curated working memory that improves future reasoning, communication, and execution.


Memory Classes

daily

Use for same-day progress, findings, evolving reproduction notes, and work that may change soon.

Default path pattern:

vault/06-daily/YYYY-MM-DD.md

state

Use for current priorities, active blockers, near-term constraints, and communication needs that affect the next few days.

Default paths:

vault/01-current/current-work.md
vault/01-current/work-items.md

work-items

Use for canonical memory about active tickets, tasks, stories, investigations, or other units of work.

Default path pattern:

vault/02-work-items/<id-or-slug>.md

stable-context

Use for durable project knowledge that should survive beyond the current work window.

Default path pattern:

vault/03-context/<domain>/*.md

people

Use for repeated collaborators, role mappings, manager/stakeholder context, and communication preferences.

Default path pattern:

vault/04-people/*.md

decisions

Use for confirmed decisions with ongoing impact.

Default path pattern:

vault/05-decisions/*.md

tooling-behavior

Use when a user correction changes how the workspace should behave in the future.

Default path patterns:

.opencode/commands/*.md
.opencode/agents/*.md
.opencode/skills/*/SKILL.md
prompts/*.md
vault/00-start/*.md
vault/03-context/process/*.md

Raw evidence stays outside vault/; promoted memory is written to vault/.


Promotion Rules

Promote information when it is:

  • explicit enough to preserve safely
  • relevant to the current project or workflow
  • likely to matter in a future session
  • useful for standups, status updates, debugging, planning, or decision making

Do not promote:

  • tool failures
  • sync attempts
  • empty inbox states
  • generic chat noise
  • unverified guesses
  • duplicate paraphrases of existing memory

If confidence is mixed, prefer the daily log and preserve uncertainty.


Correction Rules

When new information supersedes old memory:

  • update the existing canonical file directly
  • do not leave stale and corrected versions side by side
  • preserve qualifiers when the fact remains partially confirmed
  • update indexes when adding new stable context files

The agent should behave like a senior engineer maintaining project notes, not like a transcript accumulator.


Self-Maintenance Rules

When the user corrects recurring output or behavior, update the operational surface that controls that behavior.

Examples:

  • standup format correction -> update prompts/standup.md and the standup command
  • communication freshness correction -> update the communication sync command/plugin
  • prompt-engineering correction -> update the AI prompt command or skill
  • memory routing correction -> update memory rules and context-maintenance guidance

The daily log may preserve evidence, but reusable behavior must live in the command, prompt, skill, agent, or knowledge file that enforces it.