will/swarm-master
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(obsidian): refresh automation health reports

Browse Source
This commit is contained in:
William Valentin
2026-05-30 10:04:09 -07:00
parent 759042f49d
commit 987a411bc8
2 changed files with 233 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
swarm-common/obsidian-vault/will/will-shared-zap/Decisions/Runbook Suggestions.md
+229 -7
View File
@@ -1,21 +1,243 @@
# Decision / Runbook Suggestions 2026-05-25 # Decision / Runbook Suggestions 2026-05-30
Generated: 2026-05-25T15:00:25.654Z Generated: 2026-05-30T05:24:51.350Z
Review candidates and promote useful items into durable Decision or Runbook notes. This note is overwritten weekly. Review candidates and promote useful items into durable Decision or Runbook notes. This note is overwritten weekly.
Source: local Obsidian semantic search via Chroma/Ollama embeddings.
## Decision Candidates ## Decision Candidates
_No candidates found._ ### 1. Decisions/Decisions Home.md
- Suggested action: create/update a Decision note.
- Source: [[Decisions/Decisions Home]]
- Query: we decided
- Semantic score: 0.574
- Evidence: # Decisions Home Decision notes preserve context and rationale so future work does not re-litigate old choices. Create notes from [[Decision]]. ## Recent decisions ```dataview TABLE date, status, project FROM "Decisions" WHERE type = "decision" SORT date DESC LIMIT 30 ```
### 2. Templates/Decision.md
- Suggested action: create/update a Decision note.
- Source: [[Templates/Decision]]
- Query: we decided
- Semantic score: 0.561
- Evidence: --- type: decision date: {{date}} status: accepted project: tags: - type/decision --- # Decision: {{title}} ## Context ## Options considered 1. 2. 3. ## Decision ## Consequences - ## Links -
### 3. Runbooks/Promote Session Output to Notes.md
- Suggested action: create/update a Decision note.
- Source: [[Runbooks/Promote Session Output to Notes]]
- Query: we decided
- Semantic score: 0.476
- Evidence: unbooks, projects, and decisions: title-case stable names, e.g. `Swarm Operating Manual.md`. - Avoid names that encode temporary task ids unless the note is specifically about that task. ## Steps 1. Classify the output by destination rules. 2. Search the target folder for an existing note before creating a new one. 3. Summarize durable content into one of these shapes: - Project update: goal, current status, changed artifacts, next actions, blockers. - Runbook: when to use, preconditions, steps, verification, rollback or recovery. - Decision: context, options, decision, consequences, links. - Resource: concise explanation, source links, related projects/runbooks. 4. Add frontmatter consisten
### 4. Templates/Atlas Artifacts/decision-log.md
- Suggested action: create/update a Decision note.
- Source: [[Templates/Atlas Artifacts/decision-log]]
- Query: decision
- Semantic score: 0.542
- Evidence: --- type: atlas-artifact artifact_type: decision project: "{{project}}" status: draft owner: "{{owner}}" created: {{date}} updated: {{date}} source: "{{source}}" reviewer: "{{reviewer|TBD}}" tags: [atlas, artifact, decision] --- # Decision: {{title}} Parent project: [[{{project}}]] Source: {{source}} Supersedes: {{supersedes|N/A}} ## Decision summary One sentence stating the decision. ## Context Why this decision is needed now; include constraints and evidence. ## Options considered | Option | Pros | Cons | Notes | |---|---|---|---| | A | | | | | B | | | | | C | | | | ## Decision Chosen option and rationale. ## Consequences - Positive consequences: ... - Tradeoffs/costs: ... - Follow-up task
### 5. Archive/Archive Home.md
- Suggested action: create/update a Decision note.
- Source: [[Archive/Archive Home]]
- Query: decision
- Semantic score: 0.536
- Evidence: # Archive Inactive notes go here when they are no longer current but may still be useful. Do not delete project history or decisions just because they are old; archive instead.
### 6. Runbooks/Atlas Kanban Durable Project Workflow.md
- Suggested action: create/update a Decision note.
- Source: [[Runbooks/Atlas Kanban Durable Project Workflow]]
- Query: runbook
- Semantic score: 0.652
- Evidence: --- type: runbook system: atlas-kanban status: active owner: Will / Atlas created: 2026-05-14 related: - "[[Atlas Capability Upgrade Program]]" - "[[Kanban Task Graph Templates]]" --- # Atlas Kanban Durable Project Workflow Use this runbook when a request should become durable, reviewable work instead of staying inside one chat thread. ## When to create or reuse a board Create or reuse a Kanban board when any of these are true: - The work spans multiple roles, e.g. research, engineering, ops, review, writing. - The work should survive an interrupted chat, gateway restart, or laptop sleep. - A human may need to unblock, review, approve, or redirect a step. - The output is an artifact, code/co
### 7. Templates/Atlas Artifacts/README.md
- Suggested action: create/update a Decision note.
- Source: [[Templates/Atlas Artifacts/README]]
- Query: procedure
- Semantic score: 0.605
- Evidence: ports: `Projects/<Project Name>/Reports/Test Reports/` - Status reports: `Projects/<Project Name>/Reports/Status/` - Postmortems: `Projects/<Project Name>/Reports/Postmortems/` ## Naming conventions Use lowercase kebab-case filenames with a date prefix where chronology matters. - Plans: `YYYY-MM-DD-<feature>-implementation-plan.md` - Decisions: `YYYY-MM-DD-<decision-topic>.md` - Runbooks: `<system>-<operation>-runbook.md` - Diagrams: `<system>-<view>-diagram.md` - Test reports: `YYYY-MM-DD-<scope>-test-report.md` - Status reports: `YYYY-MM-DD-status-report.md` - Postmortems: `YYYY-MM-DD-<incident-name>-postmortem.md` - Agent audit events: `YYYY-MM-DD-<agent-or-system>-<event-topic>-audit.md`
### 8. Templates/Kanban Task Graph Templates.md
- Suggested action: create/update a Decision note.
- Source: [[Templates/Kanban Task Graph Templates]]
- Query: procedure
- Semantic score: 0.577
- Evidence: cratch` | `1h` | `systematic-debugging`, `hermes-agent` for Hermes | For config/ops changes, comment review-required metadata and block unless the task explicitly authorizes safe immediate completion. | | Verification | `reviewer` or `ops` | `scratch` | `30m` | relevant ops skill | Complete with health checks and residual risks. | | Postmortem | `writer` | `scratch` or `dir:<vault>` | `45m` | `obsidian` | Complete with durable postmortem path. | CLI skeleton: ```bash BOARD=<board> TRIAGE=$(hermes kanban --board "$BOARD" create "triage: <incident>" \ --assignee ops --workspace scratch --priority 10 --max-runtime 30m \ --skill systematic-debugging \ --body "Identify symptoms, affected services
### 9. Projects/Atlas/Safer Autonomy and Permission Tiers.md
- Suggested action: create/update a Decision note.
- Source: [[Projects/Atlas/Safer Autonomy and Permission Tiers]]
- Query: rollback
- Semantic score: 0.571
- Evidence: irreversible effect. - Backup/rollback status. - Why the action is necessary. Prefer Will approval for Tier 3 actions, not just approval from any channel participant. ## Platform guidance ### CLI - Default to fast Tier 0 and Tier 1 execution. - Rely on Hermes shell approvals for dangerous commands; keep `approvals.mode` at `manual` or `smart`. - Do not recommend `--yolo` except for intentionally sandboxed local sessions. - For code/config changes, produce a review handoff with changed files and tests. ### Telegram and Discord gateway Gateway sessions are higher-risk because messages may be terse, mobile, cross-thread, or from multiple people. - Tier 0 is allowed in authorized chats. - Tier 1
### 10. Infrastructure/Automation/n8n Workflows.md
- Suggested action: create/update a Decision note.
- Source: [[Infrastructure/Automation/n8n Workflows]]
- Query: workaround
- Semantic score: 0.572
- Evidence: Obsidian Notes (wills-portal duplicate) - **ID:** `kHDK9QdUSiAJ8rCM` - **Status:** 🗄️ Archived on 2026-05-12 after SQLite recovery because workflow JSON was empty/unrecoverable. ## Operational notes - n8n DB was recovered on 2026-05-12 from a `SQLITE_CORRUPT: database disk image is malformed` crash loop using SQLite `.recover`, then repaired until `n8n export:workflow --all` succeeded. - Host-side DB backups from the repair were stored under `/home/will/lab/swarm/.n8n-db-backups/` and should remain untracked. - `n8n export:workflow --all` was re-verified on 2026-05-12 and exported 13 workflows successfully. - n8n health after recovery: `http://127.0.0.1:18808/healthz` returns `{"status":"ok
### 11. Infrastructure/Automation/n8n Implementation Handoff.md
- Suggested action: create/update a Decision note.
- Source: [[Infrastructure/Automation/n8n Implementation Handoff]]
- Query: workaround
- Semantic score: 0.547
- Evidence: ssages. - Add clearer classes: `needs_reply`, `FYI`, `receipt`, `newsletter`, `noise`, `action_required`. - Add explicit Obsidian destinations per class. ### Gmail Inbox Monitor + Obsidian Notes - Workflow ID: `whtdorf7yJMVYeHm` - Status: active, OAuth trigger replaced with IMAP fallback on 2026-05-13 - Current behavior: - Original Gmail OAuth trigger failed because the stored Google OAuth client secret is invalid; refresh returns `invalid_client`. - The workflow now uses n8n `Email Trigger (IMAP)` against Gmail with the Hermes Gmail app-password credential `Gmail IMAP (Hermes App Password)`. - Fetches unseen INBOX mail, marks processed mail read, and tracks last message ID. - Local LLM and
### 12. Infrastructure/Automation/Channel Routing Policy.md
- Suggested action: create/update a Decision note.
- Source: [[Infrastructure/Automation/Channel Routing Policy]]
- Query: next time
- Semantic score: 0.486
- Evidence: sons, and draft iteration Prefer Discord when the work is longer than a few turns, technical/investigative, likely to branch into subtopics, or worth separating into a thread. ## Notification split Telegram should carry: - reminders - watchdog alerts - backup failures/staleness - cron failures - important operational summaries - urgent risks - decisions needed to continue - concise completion notices when worth interrupting for Discord should carry: - active debugging work - investigation notes - implementation progress in threads - noisy experiments / test output when a human is actively watching - project planning and architecture discussions - detailed recommendations and multi-option ana
## Runbook Candidates ## Runbook Candidates
_No candidates found._ ### 1. Runbooks/Promote Session Output to Notes.md
- Suggested action: create/update a Runbook note.
- Source: [[Runbooks/Promote Session Output to Notes]]
- Query: we decided
- Semantic score: 0.476
- Evidence: unbooks, projects, and decisions: title-case stable names, e.g. `Swarm Operating Manual.md`. - Avoid names that encode temporary task ids unless the note is specifically about that task. ## Steps 1. Classify the output by destination rules. 2. Search the target folder for an existing note before creating a new one. 3. Summarize durable content into one of these shapes: - Project update: goal, current status, changed artifacts, next actions, blockers. - Runbook: when to use, preconditions, steps, verification, rollback or recovery. - Decision: context, options, decision, consequences, links. - Resource: concise explanation, source links, related projects/runbooks. 4. Add frontmatter consisten
### 2. Templates/Runbook.md
- Suggested action: create/update a Runbook note.
- Source: [[Templates/Runbook]]
- Query: runbook
- Semantic score: 0.674
- Evidence: --- type: runbook system: status: active tags: - type/runbook --- # Runbook - {{title}} ## When to use ## Preconditions - ## Steps 1. 2. 3. ## Verification - ## Rollback - ## Related -
### 3. Runbooks/Runbooks Home.md
- Suggested action: create/update a Runbook note.
- Source: [[Runbooks/Runbooks Home]]
- Query: runbook
- Semantic score: 0.655
- Evidence: # Runbooks Home Runbooks are repeatable operational procedures. Create notes from [[Runbook]]. ## Active runbooks ```dataview TABLE system, status FROM "Runbooks" WHERE type = "runbook" AND status != "archived" SORT system ASC, file.name ASC ```
### 4. Runbooks/Atlas Kanban Durable Project Workflow.md
- Suggested action: create/update a Runbook note.
- Source: [[Runbooks/Atlas Kanban Durable Project Workflow]]
- Query: runbook
- Semantic score: 0.652
- Evidence: --- type: runbook system: atlas-kanban status: active owner: Will / Atlas created: 2026-05-14 related: - "[[Atlas Capability Upgrade Program]]" - "[[Kanban Task Graph Templates]]" --- # Atlas Kanban Durable Project Workflow Use this runbook when a request should become durable, reviewable work instead of staying inside one chat thread. ## When to create or reuse a board Create or reuse a Kanban board when any of these are true: - The work spans multiple roles, e.g. research, engineering, ops, review, writing. - The work should survive an interrupted chat, gateway restart, or laptop sleep. - A human may need to unblock, review, approve, or redirect a step. - The output is an artifact, code/co
### 5. Runbooks/Promote Session Output to Notes.md
- Suggested action: create/update a Runbook note.
- Source: [[Runbooks/Promote Session Output to Notes]]
- Query: runbook
- Semantic score: 0.609
- Evidence: --- title: Promote Session Output to Notes type: runbook system: atlas-swarm status: active tags: - type/runbook - assistant - atlas created: 2026-05-14 updated: 2026-05-14 related: [[Ops Home]], [[Swarm Operating Manual]], [[Project Context Index]], [[Context Pack]] --- # Runbook - Promote Session Output to Notes ## When to use Use this when a chat, agent run, Kanban handoff, or meeting output contains durable knowledge that should be discoverable from Obsidian without rereading the original conversation. Do not use it for transient execution logs, one-off tool output, failed experiments with no lesson, or raw transcripts. ## Preconditions - You know the audience and future use of the note.
### 6. Ops Home.md
- Suggested action: create/update a Runbook note.
- Source: [[Ops Home]]
- Query: runbook
- Semantic score: 0.584
- Evidence: SORT date DESC LIMIT 10 ``` ## Active runbooks ```dataview TABLE system, status FROM "Runbooks" WHERE type = "runbook" AND status != "archived" SORT system ASC, file.name ASC ``` ## Agent workflow Use [[Swarm Operating Manual]] for the full Atlas/Hermes/Obsidian/Kanban workflow, [[Project Context Index]] for active project orientation, [[Context Pack]] for specialist handoffs, and [[Promote Session Output to Notes]] when chat output should become durable notes. Use this pattern when Atlas/Hermes produces useful durable knowledge: - Workflow guide: [[Atlas Discord Telegram Workflow]] - Thread summary → `Resources/` - Active implementation → `Projects/` - Operational procedure → `Runbooks/` -
### 7. Templates/Atlas Artifacts/README.md
- Suggested action: create/update a Runbook note.
- Source: [[Templates/Atlas Artifacts/README]]
- Query: procedure
- Semantic score: 0.605
- Evidence: ports: `Projects/<Project Name>/Reports/Test Reports/` - Status reports: `Projects/<Project Name>/Reports/Status/` - Postmortems: `Projects/<Project Name>/Reports/Postmortems/` ## Naming conventions Use lowercase kebab-case filenames with a date prefix where chronology matters. - Plans: `YYYY-MM-DD-<feature>-implementation-plan.md` - Decisions: `YYYY-MM-DD-<decision-topic>.md` - Runbooks: `<system>-<operation>-runbook.md` - Diagrams: `<system>-<view>-diagram.md` - Test reports: `YYYY-MM-DD-<scope>-test-report.md` - Status reports: `YYYY-MM-DD-status-report.md` - Postmortems: `YYYY-MM-DD-<incident-name>-postmortem.md` - Agent audit events: `YYYY-MM-DD-<agent-or-system>-<event-topic>-audit.md`
### 8. Templates/Kanban Task Graph Templates.md
- Suggested action: create/update a Runbook note.
- Source: [[Templates/Kanban Task Graph Templates]]
- Query: procedure
- Semantic score: 0.577
- Evidence: cratch` | `1h` | `systematic-debugging`, `hermes-agent` for Hermes | For config/ops changes, comment review-required metadata and block unless the task explicitly authorizes safe immediate completion. | | Verification | `reviewer` or `ops` | `scratch` | `30m` | relevant ops skill | Complete with health checks and residual risks. | | Postmortem | `writer` | `scratch` or `dir:<vault>` | `45m` | `obsidian` | Complete with durable postmortem path. | CLI skeleton: ```bash BOARD=<board> TRIAGE=$(hermes kanban --board "$BOARD" create "triage: <incident>" \ --assignee ops --workspace scratch --priority 10 --max-runtime 30m \ --skill systematic-debugging \ --body "Identify symptoms, affected services
### 9. Atlas/Operations/2026-05-21 - Hermes Setup Video Follow-up Audit.md
- Suggested action: create/update a Runbook note.
- Source: [[Atlas/Operations/2026-05-21 - Hermes Setup Video Follow-up Audit]]
- Query: procedure
- Semantic score: 0.572
- Evidence: ws captured as a skill Created local skill: ```text ~/.hermes/skills/devops/recurring-hermes-workflows/SKILL.md ``` Purpose: capture the durable workflow pattern from the video and Atlas practice: - periodic report → Hermes cron; - health threshold alert → script-only cron, quiet on success; - durable multi-step project → Kanban; - repeatable procedure → skill plus scripts/references; - user feedback loop → compact durable preferences, not raw rating logs; - avoid adding long procedural recipes to always-injected memory. This prevents future recurring-workflow logic from becoming static-memory bloat. ## Follow-up notes - No urgent migration to VPS is recommended for the current Atlas setup.
### 10. Projects/Atlas/Safer Autonomy and Permission Tiers.md
- Suggested action: create/update a Runbook note.
- Source: [[Projects/Atlas/Safer Autonomy and Permission Tiers]]
- Query: rollback
- Semantic score: 0.571
- Evidence: irreversible effect. - Backup/rollback status. - Why the action is necessary. Prefer Will approval for Tier 3 actions, not just approval from any channel participant. ## Platform guidance ### CLI - Default to fast Tier 0 and Tier 1 execution. - Rely on Hermes shell approvals for dangerous commands; keep `approvals.mode` at `manual` or `smart`. - Do not recommend `--yolo` except for intentionally sandboxed local sessions. - For code/config changes, produce a review handoff with changed files and tests. ### Telegram and Discord gateway Gateway sessions are higher-risk because messages may be terse, mobile, cross-thread, or from multiple people. - Tier 0 is allowed in authorized chats. - Tier 1
### 11. Templates/Atlas Artifacts/runbook.md
- Suggested action: create/update a Runbook note.
- Source: [[Templates/Atlas Artifacts/runbook]]
- Query: rollback
- Semantic score: 0.520
- Evidence: s are referenced but not exposed. - [ ] Verification and rollback/recovery are actionable. - [ ] Last tested date is present. ## Universal reviewer checklist Before accepting this artifact, verify: - [ ] Clear owner, status, date, source, and next action. - [ ] Saved in the correct durable destination and named using the convention. - [ ] Links back to the relevant project note and source task/issue/PR/session/incident. - [ ] Claims are backed by evidence links, command output, or labeled assumptions. - [ ] Risks, rollback, recovery, or revisit triggers are documented where relevant. - [ ] No secrets, tokens, raw PII, private keys, or unredacted credentials are included. - [ ] A new speciali
### 12. Projects/Atlas/Gateway Approval Runbook.md
- Suggested action: create/update a Runbook note.
- Source: [[Projects/Atlas/Gateway Approval Runbook]]
- Query: rollback
- Semantic score: 0.515
- Evidence: nsitive effect: `<effect>`. Backup/rollback status: `<status>`. Reason: `<why>`. I will not proceed without exact approval." ### Safe completion reply "Done: `<what changed>`. Verified by `<check>`. I did not `<explicit non-actions if ambiguity/risk existed>`." ## Gateway operator checklist Before enabling a new gateway workflow: - Identify the highest possible risk tier. - Define allowed channels/users and target resources. - Decide whether Tier 2 actions can use `/approve` or must block into Kanban. - Ensure Tier 3 cannot run from vague chat approval. - Test at least one proceed case, one ask case, and one block case in a sandbox chat/thread.
### 13. Infrastructure/Automation/n8n Workflows.md
- Suggested action: create/update a Runbook note.
- Source: [[Infrastructure/Automation/n8n Workflows]]
- Query: workaround
- Semantic score: 0.572
- Evidence: Obsidian Notes (wills-portal duplicate) - **ID:** `kHDK9QdUSiAJ8rCM` - **Status:** 🗄️ Archived on 2026-05-12 after SQLite recovery because workflow JSON was empty/unrecoverable. ## Operational notes - n8n DB was recovered on 2026-05-12 from a `SQLITE_CORRUPT: database disk image is malformed` crash loop using SQLite `.recover`, then repaired until `n8n export:workflow --all` succeeded. - Host-side DB backups from the repair were stored under `/home/will/lab/swarm/.n8n-db-backups/` and should remain untracked. - `n8n export:workflow --all` was re-verified on 2026-05-12 and exported 13 workflows successfully. - n8n health after recovery: `http://127.0.0.1:18808/healthz` returns `{"status":"ok
### 14. Infrastructure/Automation/n8n Implementation Handoff.md
- Suggested action: create/update a Runbook note.
- Source: [[Infrastructure/Automation/n8n Implementation Handoff]]
- Query: workaround
- Semantic score: 0.547
- Evidence: open('/tmp/n8n-api-cred.json')); c=c[0] if isinstance(c,list) else c; print(c['data']['value'])") rm -f /tmp/n8n-api-cred.json docker exec n8n-agent rm -f /tmp/n8n-api-cred.json /tmp/n8n-api-cred.log # Example: list workflows curl -sS -H "X-N8N-API-KEY: $API_KEY" http://127.0.0.1:18808/api/v1/workflows?limit=100 ``` Do NOT print the API key in logs or output. Inspect workflow inventory from SQLite copy: ```bash tmp=/tmp/n8n-check-$(date +%s) mkdir -p "$tmp" docker cp n8n-agent:/home/node/.n8n/database.sqlite "$tmp/database.sqlite" sqlite3 "$tmp/database.sqlite" "select name, active, isArchived from workflow_entity order by name;" ``` Check logs without printing secrets: ```bash docker logs n
### 15. Resources/Swarm Operating Manual.md
- Suggested action: create/update a Runbook note.
- Source: [[Resources/Swarm Operating Manual]]
- Query: workaround
- Semantic score: 0.545
- Evidence: es in the correct repo or workspace. - Reviewer: checks usability, safety, diffs, tests, and whether acceptance criteria were met before changes are treated as complete. ## Where durable state lives - `Projects/`: active implementation programs, project specs, project status, and project-specific context. - [[Project Context Index]]: one-row orientation for active projects, including board, repo/workspace path, status, commands, runbooks, and owner/reviewer. - `Runbooks/`: repeatable operational procedures. - `Decisions/`: important product, architecture, or workflow choices. - `Resources/`: stable summaries, manuals, research notes, and references. - `Templates/`: reusable note and handoff
### 16. Templates/Atlas Artifacts/reviewer-checklist.md
- Suggested action: create/update a Runbook note.
- Source: [[Templates/Atlas Artifacts/reviewer-checklist]]
- Query: root cause
- Semantic score: 0.486
- Evidence: parent project note. - [ ] The artifact links to source Kanban task, issue, PR, session, or incident when available. - [ ] Superseded/replaced artifacts are linked when relevant. ## Content quality - [ ] Purpose, audience, owner, status, and next action are clear. - [ ] Claims are backed by command output, source links, or explicitly labeled assumptions. - [ ] Risks, rollback, recovery, or revisit triggers are documented where relevant. - [ ] The artifact is concise enough to use but complete enough to orient a new specialist. ## Safety and durability - [ ] No secrets, tokens, private keys, raw PII, or unredacted credentials are included. - [ ] Runtime churn/log dumps are summarized or linke
## Raw Summary ## Raw Summary
- Total candidates: 0 - Total candidates: 33
- Decision candidates: 0 - Decision candidates: 12
- Runbook candidates: 0 - Runbook candidates: 16
swarm-common/obsidian-vault/will/will-shared-zap/Resources/Obsidian Automation Health.md
+4 -4
View File
@@ -1,12 +1,12 @@
# Obsidian Automation Health # Obsidian Automation Health
Updated: 2026-05-29T19:00:03.775Z Updated: 2026-05-30T17:00:59.527Z
## Status ## Status
- Overall: Needs attention - Overall: OK
- Obsidian REST: OK - Obsidian REST: OK
- Reindex trigger: {"error":{"message":"500 - \"{\\n \\\"error\\\": \\\"reindex failed\\\",\\n \\\"exit_code\\\": 3,\\n \\\"stderr\\\": \\\"\\\"\\n}\"","name":"AxiosError","stack":"AxiosError: Request failed with status code 500\n at settle (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/axios@1.13.5/node_modules/axios/lib/core/settle.js:19:12)\n at RedirectableRequest.handleResponse (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/axios@1.13.5/node_modules/axios/lib/adapters/http.js:746:9)\n at - Reindex trigger: {"status":"ok","mode":"incremental","vault_path":"/home/will/lab/swarm/swarm-common/obsidian-vault/will/will-shared-zap","note_count":184,"added":0,"changed":1,"removed":0,"chunks_indexed":1,"vector_count":436,"state_file":"/home/will/.hermes/data/rag-search/obsidian_index_state.json","chroma_path":"/home/will/.hermes/data/rag-search/chroma","progress_file":"/home/will/.hermes/data/rag-search/obsidian_reindex_progress.json","progress_log_tail":"{\"status\": \"preparing\", \"mode\": \"incremental
- RAG/embedding check: {"ok":false,"status":"failed","exitCode":1,"output":"{\n \"checks\": {\n \"obsidian_semantic\": {\n \"error\": \"HTTPError: HTTP Error 503: Service Unavailable\",\n \"ok\": false\n },\n \"ollama\": {\n \"embedding_dim\": 768,\n \"error\": null,\n \"model\": \"nomic-embed-text\",\n \"ok\": true\n }\n },\n \"durationMs\": 3069,\n \"failed\": [\n \"obsidian_semantic\"\n ],\n \"ok\": false,\n \"status\": \"failed\"\n}","durationMs":3113} - RAG/embedding check: {"ok":true,"status":"ok","exitCode":0,"output":"{\n \"checks\": {\n \"obsidian_semantic\": {\n \"collection\": \"obsidian\",\n \"last_full_index\": \"2026-05-22T18:26:30.248050\",\n \"last_incremental_index\": \"2026-05-30T10:00:54.083813\",\n \"note_count\": 184,\n \"ok\": true,\n \"result_count\": 1,\n \"search_ok\": true,\n \"status\": \"ok\",\n \"vector_count\": 436\n },\n \"ollama\": {\n \"embedding_dim\": 768,\n \"error\": null,\n \"model\": \"nomic-embed-text\",\n \"ok\": true\n }\n },\n \"durationMs\": 5305,\n \"failed\": [],\n \"ok\": true,\n \"status\": \"ok\"\n}","durationMs":5377}
This note is automatically overwritten by n8n. This note is automatically overwritten by n8n.