feat: Obsidian integration via cli scripts

.opencode/agents/fidelity.md

@@ -13,10 +13,14 @@ Behavior rules:
 - Treat `core/` as the reusable project-independent operating model.
 - Treat `profiles/fidelity/profile.md` as the active Fidelity project profile.
 - Treat `vault/` as the canonical clean knowledge base for humans and AI.
+- Treat `scripts/memory/` as the project-agnostic access layer for note creation, vault search, Base queries, and health checks.
+- Treat `scripts/obsidian/` as the current Obsidian adapter. Do not couple durable memory rules to Obsidian-specific behavior.
 - Treat `ai/inbox/` and generated connector files as raw evidence only, not promoted memory.
 - Keep Obsidian Bases clean: do not let templates in `vault/09-templates/` appear as real daily notes, work items, people, decisions, systems, or workstreams.
 - Role mapping notes such as `vault/04-people/manager.md` are `type: role-map`; actual people profiles are `type: person`.
 - When editing canonical vault notes, update useful metadata at the same time: `updated`, `systems`, `workstreams`, `people`, `related`, `focus`, `work-items`, and `blockers` when applicable.
+- When creating a new typed note, prefer `bash scripts/memory/memory.sh create <type> <slug> [title]`, then inspect and refine the generated Markdown.
+- When checking vault quality, use `bash scripts/memory/memory.sh health` and direct file inspection.
 - Work item notes should preserve Jira ID/title and explicit relationships so standups, Bases, and graph navigation stay useful.
 - Daily notes should include `focus`, `work-items`, and `blockers` when those values are clear.
 - Before answering a prompt that depends on current state, verify the latest relevant files instead of relying only on conversation history.
@@ -44,6 +48,7 @@ Behavior rules:
 - Update preexisting memory when a new prompt clarifies or corrects something already stored.
 - Do not wait for a dedicated sync command if the correct memory update is already obvious.
 - Do not leave behavior-only corrections only in daily logs. If a correction should affect future output, update the tool or instruction that produces that output.
+- If the memory interface or Obsidian adapter fails, continue with direct Markdown operations when safe and do not promote the failure as project memory.
 - Do not over-promote uncertain information. Keep uncertain items in the daily log.
 - When drafting communication, preserve technical meaning and improve clarity in natural US English.
 - When answering Swift/iOS programming questions, use the project-local iOS skills and `vault/03-context/ios/`.

.opencode/agents/workspace.md

@@ -13,12 +13,15 @@ Behavior rules:
 - Load `core/` first for project-independent operating rules.
 - Load the active profile from `AIW_PROJECT_PROFILE` when available; otherwise use the configured project files in this workspace.
 - Treat `vault/` as the canonical clean knowledge base.
+- Treat `scripts/memory/` as the stable memory access layer.
+- Treat tool-specific integrations such as Obsidian as replaceable adapters.
 - Treat profile files as configuration and `ai/inbox/` plus generated connector files as raw evidence.
 - Keep Obsidian Bases clean by excluding templates and typing role maps separately from people.
 - When updating canonical vault notes, maintain relationship metadata and `updated` fields so the vault remains useful to both humans and agents.
 - Before answering current-state questions, inspect current state, active work items, recent logs, and inbox evidence when available.
 - For any meaningful prompt, decide whether it adds, corrects, or invalidates memory.
 - Update the smallest correct canonical file when memory should change.
+- Use the memory interface to create new typed notes and inspect vault health, then edit Markdown directly for precise curation.
 - If the user corrects recurring behavior, update the command, prompt, agent, skill, vault process note, or other control file that enforces that behavior.
 - Keep imported evidence separate from promoted memory.
 - If an integration or sync command fails, do not update project memory from that failure.

.opencode/commands/fidelity-context.md

@@ -9,6 +9,7 @@ Use these files as the baseline context:
 @README.md
 @core/README.md
 @core/memory/operational-memory.md
+@core/integrations/memory-vault-model.md
 @core/integrations/communication-model.md
 @profiles/fidelity/profile.md
 @vault/00-start/start-here.md

.opencode/commands/index.md

@@ -7,6 +7,8 @@ Slash commands available in this workspace.
 ## Generic Commands
 
 - [Workspace Context](workspace-context.md)
+- [Memory Health](memory-health.md)
+- [Memory Create](memory-create.md)
 - [Communication Sync](communication-sync.md)
 - [Archive Import](archive-import.md)
 - [AI Prompt](ai-prompt.md)

.opencode/commands/memory-create.md

@@ -0,0 +1,43 @@
+---
+description: Create a canonical memory note using the project-agnostic memory interface
+---
+
+Create a new canonical memory note from a known type.
+
+Supported types:
+
+- `daily`
+- `work-item`
+- `person`
+- `decision`
+- `system`
+- `workstream`
+- `meeting-note`
+
+User request:
+
+$ARGUMENTS
+
+Read:
+
+@core/integrations/memory-vault-model.md
+@vault/00-start/workspace-architecture.md
+@vault/09-templates/work-item.md
+@vault/09-templates/person.md
+@vault/09-templates/decision.md
+@vault/09-templates/system.md
+@vault/09-templates/workstream.md
+
+Instructions:
+
+- Parse the requested type, slug, and title from `$ARGUMENTS`.
+- Use `bash scripts/memory/memory.sh create <type> <slug> [title]` when type and slug are clear.
+- If type or slug is not clear, do not guess. Explain the expected format.
+- After creation, inspect the generated file and update metadata/content if the user provided enough context.
+- Keep the note in the canonical folder selected by the memory interface.
+
+Return:
+
+1. Created file
+2. Any metadata/content refined
+3. Any missing details the user may want to add

.opencode/commands/memory-health.md

@@ -0,0 +1,27 @@
+---
+description: Check canonical memory health and Obsidian adapter status
+---
+
+Run a lightweight health check for the canonical memory vault.
+
+Read:
+
+@core/integrations/memory-vault-model.md
+@core/integrations/obsidian-model.md
+@vault/00-start/workspace-architecture.md
+
+Run:
+
+!`bash scripts/memory/memory.sh health`
+
+Structured views:
+
+!`for base in work-items people decisions daily systems workstreams; do echo "\n## $base"; bash scripts/memory/memory.sh base-query "$base" paths 2>/dev/null || bash scripts/memory/memory.sh base-query "$base" 2>/dev/null || true; done`
+
+Respond with:
+
+1. Health status
+2. Any issues that should be fixed now
+3. Any optional Obsidian-only improvements
+
+Do not modify project memory unless the user explicitly asks for cleanup.

.opencode/commands/workspace-context.md

@@ -8,6 +8,7 @@ Read core:
 
 @core/README.md
 @core/memory/operational-memory.md
+@core/integrations/memory-vault-model.md
 @core/integrations/communication-model.md
 @core/profiles/create-project-profile.md