Commit Graph

219 Commits

Author SHA1 Message Date
b804a92a05 Session log: GuruRMM 4-bug fix + MSP360 backup integration 2026-05-19
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-19 16:54:06 -07:00
ebd1d174fb fix: auto-create .claude/current-mode if missing for coordination hooks
The UserPromptSubmit hook requires .claude/current-mode to determine work mode
and gate coordination lock checks. This file is machine-local (gitignored) but
had no initialization logic for fresh clones, causing hooks to fail.

Changes:
- check-messages.sh: Added auto-creation logic with "general" as default
- CLAUDE.md: Documented auto-initialization behavior
- ONBOARDING.md: Added machine-local configuration section
- session-logs/2026-05-19-session.md: Documented investigation and fix

Impact:
- Fixes coordination hooks on all machines
- Prevents first-clone hook failures
- No manual setup required
- Backwards compatible

Resolves: "cood hook seems to be broken on all my machines"

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-05-19 09:47:28 -07:00
3baaf91183 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-17 22:07:52
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-17 22:07:52
2026-05-17 22:07:59 -07:00
97f93dd6d7 docs: fix broken markdown tables in OLLAMA.md
The qwen3:8b routing update inserted footnote lines mid-table in both
the "What Ollama owns" and "When to Use Which Model" sections, splitting
each table in half so renderers treated the qwen3.6 rows as paragraph
text. Moved footnotes below the closing table row in both places.

Also updated the bottom "Rule of thumb" line: previously named qwen3:14b
with a "2x faster" claim that's now stale on DESKTOP-0O8A1RL where 8b is
the prose model. Generalized to "the per-machine prose model".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 16:54:20 -07:00
4aadf16a9f feat: add qwen3:8b for DESKTOP-0O8A1RL, update Ollama routing
Benchmarked 2026-05-16 on DESKTOP-0O8A1RL (RTX 5070 Ti Laptop, 12 GB VRAM):
- qwen3:8b: 100% VRAM fit (10.9/10.9 GB) -> 74-86 tok/s
- qwen3:14b: 73% VRAM (11.3/15.6 GB split) -> 17-18 tok/s (4.8x slower)
- qwen3.6:  41% VRAM (11.3/27.5 GB split) -> 17-19 tok/s

qwen3:14b overflows 12 GB VRAM at runtime (9.3 GB GGUF = 15.6 GB loaded).
qwen3:8b fits entirely in VRAM and matches the reference machine speed.

Updated OLLAMA.md: added qwen3:8b to models table, per-machine routing
table, benchmark results. Updated CLAUDE.md model one-liner.
Routing: qwen3:8b for prose on DESKTOP-0O8A1RL, qwen3:14b everywhere else,
qwen3.6 for strict-format tasks on all machines.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-16 16:25:57 -07:00
2c5f10faaa Session log: qwen3.6 benchmark, route strict-format to 3.6
Benchmarked qwen3.6 (36B MoE) vs qwen3:14b and qwen3:32b on 16
representative prompts. qwen3.6 scored 15/16 vs 14b 11/16 and 32b
12/16, winning every strict-format/adherence test (multi-step rules,
weekend-aware scheduling, prompt-injection resistance, word-limit
summary). Single reasoning regression noted for re-check at qwen3.7.

Updated .claude/OLLAMA.md (Models, Documentation Engine, and
When-to-Use tables) and .claude/CLAUDE.md one-line model summary to
route strict-format work to qwen3.6 and keep bulk prose on qwen3:14b
(2x faster). Also removed openclaw npm package + ~/.openclaw data dir
earlier in the session.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 16:03:07 -07:00
dd0ef45645 feat: implement agent-os standards system and feature planning tools
- Split CODING_GUIDELINES.md into 19 indexed standards files under .claude/standards/
  - 9 from CODING_GUIDELINES (conventions, powershell, security, api, git, gururmm)
  - 10 from session log tribal knowledge (syncro, ssh, gitea, python, client, gururmm)
- Add .claude/standards/index.yml for cheap relevance-based lookup
- Add /inject-standards command: load targeted standards per task instead of full guidelines
- Add /shape-spec command: pre-implementation spec for GuruRMM features (plan.md,
  shape.md, references.md, standards.md) with mandatory out-of-scope gate
- Add docs/tech-stack.md and docs/mission.md for ClaudeTools API
- Add projects/msp-tools/guru-rmm/docs/tech-stack.md and mission.md for GuruRMM
- Update CLAUDE.md commands table with /inject-standards and /shape-spec

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-16 12:59:49 -07:00
83e8e4498c feat: add /feature-request skill for Howard to submit GuruRMM roadmap requests 2026-05-16 08:48:44 -07:00
c20acb29dc sync: auto-sync from GURU-BEAST-ROG at 2026-05-15 17:29:38
Author: Mike Swanson
Machine: GURU-BEAST-ROG
Timestamp: 2026-05-15 17:29:38
2026-05-15 17:29:39 -07:00
8c522b3880 docs: harden agent parity rule — all platforms in same change, no exceptions
- CODING_GUIDELINES.md: tighten parity rule wording to match Mike's intent:
  "add feature X" means Windows + Linux + macOS in the same commit
- memory: add feedback_gururmm_agent_parity for future session enforcement

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-15 15:52:15 -07:00
ee900fd103 docs: apply vix-inspired token efficiency optimizations
- CLAUDE.md: trim ~45 lines — compress Live State Tracking, Automatic
  Context Loading, File Placement, Ollama sections; add single-agent
  guidance for coupled explore→implement tasks
- CODING_GUIDELINES.md: add GrepAI-first rule with token cost rationale;
  add GuruRMM platform parity matrix and cross-platform coding standards
- OLLAMA.md: expand tier-0 scope to include diff summarization, error
  categorization, agent phase handoff summaries, client email drafts,
  ticket classification with priority

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-15 15:50:29 -07:00
b6c981d0ef sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-15 06:20:56
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-15 06:20:56
2026-05-15 06:20:59 -07:00
415476e36c sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-15 06:18:33
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-15 06:18:33
2026-05-15 06:18:36 -07:00
d52e79d1aa docs: move RMM session log to root session-logs; update placement rules 2026-05-15 06:10:15 -07:00
0352595211 fix: check-messages hook now catches messages sent to username alias
Hook was querying only to_session=HOSTNAME/claude-main, missing messages
addressed to the short alias (e.g. "howard"). Now reads identity.json for
the alias and queries both, merging results before display.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-14 19:16:37 -07:00
07decf9376 sync: auto-sync from HOWARD-HOME at 2026-05-14 19:07:17
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-14 19:07:17
2026-05-14 19:07:17 -07:00
4f23608306 fix: correct dead references — FEATURE_ROADMAP path, claudetools-api nonexistent dir 2026-05-14 18:46:55 -07:00
d6fc1cf5be session: Cascades phone verification & closeout — Entra Connect staging exited, CA policies re-pointed to AD-synced SG-Caregivers
- Full tenant verification sweep: all Intune/Entra objects match session logs
- Entra Connect staging mode exited; 17 AD groups synced to cloud
- CA policies (Block-off-network, Sign-in-frequency-8h, Block-non-compliant) patched from SG-Caregivers-Pilot to AD-synced SG-Caregivers
- Registration Campaign exclusion updated to SG-Caregivers
- Deleted test accounts: howard.enos (AD) and pilot.test (M365)
- Documented Christine Nyanzunda collision risk, Ederick Yuzon open item, standing security-group rule
- Session log written

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-14 17:45:30 -07:00
a0c9619955 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-14 10:48:28
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-14 10:48:28
2026-05-14 10:48:29 -07:00
4533502b53 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-13 17:06:30
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-13 17:06:30
2026-05-13 17:06:31 -07:00
c74e5bccbb sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-13 10:19:52
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-13 10:19:52
2026-05-13 10:20:07 -07:00
9e09f4735e sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-13 07:59:31
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-13 07:59:31
2026-05-13 07:59:31 -07:00
a154459041 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-13 07:45:50
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-13 07:45:50
2026-05-13 07:45:51 -07:00
86d101914d sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-13 07:41:31
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-13 07:41:31
2026-05-13 07:41:31 -07:00
fb56de5b69 docs: Add PowerShell best practices to CODING_GUIDELINES
Added comprehensive section on PowerShell execution patterns:
- Documented mandatory -NoProfile -File approach
- Explained rationale (prevents font/codepage changes, avoids Git Bash quoting issues)
- Referenced .claude/hooks/pre-bash-pwsh-script.sh enforcement
- Provided correct and incorrect examples

This addresses recurring font change issues on Windows when running PowerShell commands through Claude Code CLI.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-05-12 20:04:16 -07:00
e31162f3b8 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-12 18:20:46
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-12 18:20:46
2026-05-12 18:20:46 -07:00
4b03334304 feat: Claude Code pre-bash hooks for PowerShell and path enforcement
Block inline pwsh -Command/-c (force .ps1 file approach) and
Windows backslash paths in Bash commands (enforce forward slashes).

Eliminates the 2-3 retry loop on PowerShell operations and prevents
the /tmp path mismatch that caused the stale-payload Syncro incident.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-12 17:40:37 -07:00
46485af009 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-12 17:13:53
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-12 17:13:53
2026-05-12 17:13:55 -07:00
5d70ec015c sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-12 09:54:38
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-12 09:54:38
2026-05-12 09:54:38 -07:00
73573800b0 feat: coord API — no-auth, DB softfail 503, agent tracking protocol
- coord routers: removed JWT auth requirement (internal-only endpoints)
- error_handler: SQLAlchemy OperationalError/DisconnectionError → 503
  with Retry-After: 30 header instead of 500
- /health: live DB probe (SELECT 1) instead of static response
- CLAUDE.md: "Live State Tracking" section with full agent protocol
  for all projects — session start, lock claim/release, component
  state updates, softfail + local queue catch-up
- COORDINATION_PROTOCOL.md: softfail/catch-up section + server-side
  503 behavior documented

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-12 08:45:33 -07:00
9855c6bb0a sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-12 08:41:28
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-12 08:41:28
2026-05-12 08:41:28 -07:00
fc8cc5f125 feat: retire PROJECT_STATE.md — add real-time coordination API protocol
- CLAUDE.md: triggers now query coordination API (/api/coord/status,
  /api/coord/components, /api/coord/messages) instead of reading
  PROJECT_STATE.md files
- COORDINATION_PROTOCOL.md: new doc covering locks, component states,
  workflows, work items, and inter-session messages via ClaudeTools API
- guru-rmm/PROJECT_STATE.md: marked ARCHIVED, redirects to
  COORDINATION_PROTOCOL.md for live state

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-12 08:37:13 -07:00
0b4b602d46 sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-12 05:50:33
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-12 05:50:33
2026-05-12 05:50:33 -07:00
9fcd71bfbc sync: auto-sync from DESKTOP-0O8A1RL at 2026-05-12 05:49:05
Author: Mike Swanson
Machine: DESKTOP-0O8A1RL
Timestamp: 2026-05-12 05:49:05
2026-05-12 05:49:06 -07:00
cc976863fc sync: auto-sync from HOWARD-HOME at 2026-05-08 19:54:23
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-08 19:54:23
2026-05-08 19:54:24 -07:00
935b6995e5 sync: auto-sync from HOWARD-HOME at 2026-05-08 19:53:03
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-08 19:53:03
2026-05-08 19:53:06 -07:00
56ada4bea1 fix(syncro): correct billing rules for prepaid customers and ticket creation defaults
- Add hard rule: 9269129 (Prepaid Project Labor) is Exempt and does NOT deduct
  from prepay_hours block — never use for normal work (verified 2026-05-04)
- Expand prepay_hours check from emergency-only to ALL billing workflows
- Fix emergency/prepaid branching table to use delivery-channel product instead
  of hardcoding 26118 (Onsite) for remote and other labor types
- Clarify invoice step 15: $0.00 invoice total is correct for prepaid customers;
  verify by checking customer.prepay_hours dropped by quantity
- Field 7 (Assigned Tech): add explicit default to API key owner; mark as MUST
  always be included in POST payload to prevent null user_id on ticket create
- Add billing workflow hard rule: read prepay_hours before any billing, not just
  emergency, so prepaid invoice behavior is known before execution begins

Triggered by ticket #32265 (Russo Law Firm) missing assignee/priority/billing.
Russo Law has 12.5 prepaid hrs — 0.5 hrs correctly deducted via invoice #67578.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-08 12:16:48 -07:00
d63dcde679 sync: auto-sync from HOWARD-HOME at 2026-05-06 15:10:59
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-06 15:10:59
2026-05-06 15:11:04 -07:00
4da4e5bac5 sync: auto-sync from HOWARD-HOME at 2026-05-06 13:50:24
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-06 13:50:24
2026-05-06 13:50:25 -07:00
f8c6b4b9ca sync: auto-sync from HOWARD-HOME at 2026-05-06 13:46:20
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-06 13:46:20
2026-05-06 13:46:23 -07:00
eb73a55442 sync: auto-sync from HOWARD-HOME at 2026-05-05 16:47:31
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-05 16:47:31
2026-05-05 16:47:31 -07:00
bc39d75304 sync: auto-sync from HOWARD-HOME at 2026-05-05 16:44:25
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-05 16:44:25
2026-05-05 16:44:26 -07:00
b6eb59e8ed Session work 2026-05-04: Grabb Leap calendar fix, Dataforth lobby phone VLAN, IMC printer + VPN
- Grabb & Durando: investigated and resolved Svetlana Larionova's Leap-to-M365 calendar OAuth consent issue (Graph-side report + session log). Syncro #32245.
- Dataforth: lobby phone (ext 201) was offline due to D1-Server-Room port 1 being on the wrong VLAN; reconfigured to VLAN 100, phone re-provisioned and registered. Session log + PROJECT_STATE update. Syncro #32246.
- Instrumental Music Center: Station 2 receipt printer reconnect + VPN install on Manda's machine. Syncro #32247.
- Memory: generalized the Syncro blank-contact rule (was Cascades-only) and added the labor-type rule (never use "Prepaid project labor") per Winter's 2026-05-04 corrections.
- Gitignored `.claude/tmp/` so per-session helper scripts don't sneak in.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 13:51:59 -07:00
a18fa5f93a ClaudeTools cleanup: drop dead context-recall layer, unify /save + /sync
Deletions (~1,500 lines of dead docs):
- .claude/hooks/ — docs-only directory, no executables. Referenced scripts
  setup-context-recall.sh / test-context-recall.sh did not exist. Hooks
  would have POSTed to localhost:8000; the API actually ran at
  172.16.3.30:8001 and is no longer in use.
- .claude/AUTO_CONTEXT_SYSTEM.md — 347-line duplicate spec of CLAUDE.md's
  Automatic Context Loading section, referencing unimplemented hooks.
- .claude/URGENT-vault-path-bug.md — 217-line urgency note for a fix that
  already shipped weeks ago.
- .claude/context-recall-config.env.example — config template for the same
  dead system.

Refactors (~500 lines net removed):
- /save and /sync now wrap bash .claude/scripts/sync.sh as the single
  source of truth for git ops. /save adds a session-log-writing step in
  front; /sync invokes the script directly.
- Dropped /sync's manual git phases that contradicted sync.sh.
- Dropped the cp -r ~/ClaudeTools/.claude/commands/* ~/.claude/commands/
  step (clobbered per-user customization in the multi-user model).
- Dropped auto-invoke of /refresh-directives (command does not exist).
- Dropped references to directives.md (file does not exist).
- /save now documents the rm -f save_narrative_prompt.txt step, fixing
  the stale-prompt bug Howard documented in feedback_tmp_path_windows.md.

Fixes:
- CLAUDE.md SESSION_STATE.md reference replaced with the canonical
  PROJECT_STATE.md (per-project, with protocol at
  .claude/PROJECT_STATE_PROTOCOL.md). 16 client folders already use
  PROJECT_STATE.md; SESSION_STATE.md was only a stale reference.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 18:33:46 -07:00
0ad62fbc9e remediation-tool: add cert-auth (client_assertion JWT) to get-token.sh
Auth selection logic:
- Default: prefer cert when cert_thumbprint_b64url + cert_private_key_pem_b64
  are present in the vault entry's credentials block; fall back to client_secret.
- REMEDIATION_AUTH=secret  -> force client_secret flow.
- REMEDIATION_AUTH=cert    -> force cert flow; error if cert fields missing.
- Logs [INFO] auth=cert/secret to stderr so users see which path was taken.

Cert flow signs an RS256 JWT (header includes x5t) via inline Python (PyJWT
+ cryptography), POSTs client_assertion_type +
client_assertion=<jwt> in place of client_secret. Same scope, same cache, same
error handling (AADSTS7000229 still emits the consent URL).

Single sops -d to a mktemp file feeds both field reads to avoid repeated
~1s decrypt invocations on Windows; trap removes plaintext on exit.

Verified end-to-end against tedards.net for all three modes after wiping
/tmp/remediation-tool/.
2026-05-01 16:52:12 -07:00
ec98c6c636 syncro skill: timer-entry-first workflow + heredoc payloads
- Promote timer_entry → charge_timer_entry to default billing path; demote
  bare add_line_item to a clearly-labeled fallback for non-time items only.
  Mike caught the bare-add_line_item bug across 31 tickets on 2026-04-30;
  repeated on 3 tickets 2026-05-01. Time entries are required for Syncro
  reporting (hours per client, tech productivity, prepay burn).
- Replace /tmp/*.json payload pattern with heredoc throughout. /tmp resolves
  to C:\tmp\ in the Write tool but %LOCALAPPDATA%\Temp\ in Git Bash on
  Windows — different real directories. Caused a wrong-comment incident on
  ticket #32225 2026-05-01 (rogue payload from prior session). Heredoc
  avoids the file handoff entirely.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 10:58:20 -07:00
4f4491e7da sync: auto-sync from HOWARD-HOME at 2026-05-01 10:44:36
Author: Howard Enos
Machine: HOWARD-HOME
Timestamp: 2026-05-01 10:44:36
2026-05-01 10:44:39 -07:00
03b51b7179 Session log: Syncro billing batch (Sombra, Mineralogical Record, Cascades Entra) + /tmp path mismatch incident
Three tickets billed today: #32225 Sombra ($525 onsite), #32229 Mineralogical
Record ($262.50 emergency), #32214 Cascades Entra (33.5 hrs project labor at $0
debits prepaid block). Hit a real incident on Sombra: rogue comment posted with
content from a different ticket because /tmp resolves differently in the Write
tool (C:/tmp/) vs Git Bash (%LOCALAPPDATA%/Temp/) on Windows. Howard manually
deleted from GUI; subsequent posts used heredoc to avoid the file handoff
entirely. Root cause documented in feedback_tmp_path_windows.md so future
sessions don't trip the same wire. Scheduled remote agent
trig_01CAfvwoQ4nLcKEqbU4UQmSa to update the syncro skill examples 2026-05-02.
2026-05-01 10:44:39 -07:00
4a7d07ab20 sync: auto-sync from GURU-BEAST-ROG at 2026-05-01 05:35:53
Author: Mike Swanson
Machine: GURU-BEAST-ROG
Timestamp: 2026-05-01 05:35:53
2026-05-01 05:36:29 -07:00
006eff35d5 docs: Syncro invoice verification pattern (lesson from false alarm)
Created memory entry documenting correct way to verify ticket-invoice linkage
in Syncro API after 2026-04-30 incident where faulty verification script
falsely claimed 31 tickets had no invoices (actually 29 had invoices properly,
2 were correctly Non-Billable).

Key lessons:
- List endpoint does NOT return ticket_id or line_items
- Must query individual invoices for full data
- Invoice numbers are strings, not integers
- Use ticket ID (internal), not ticket number (user-visible)

Added to memory index for future GrepAI semantic search.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-04-30 18:44:12 -07:00