Per the 5070 handoff (DSCA33-45-HOFFMAN-RECOVERY): the lost DSCA33/45 specs are
recoverable from Hoffman, not John. Wired the mined dsca33-45-templates.json (56
models) into the renderer:
- datasheet-exact.js: load DSCA3345_TEMPLATES; for family DSCA, the Hoffman-mined
template takes PRECEDENCE over the stale staged-extraction entry (which shadowed 25
models with accOut "?"/no accHeader). Emit the verbatim 2-line accHeader for these
families (Vin (mVAC)/Iin (AAC)/Frequency (Hz), Output (VDC)/(mADC)). Per-model
`validated` GATE: a DSCA33/45 model renders only after byte-matching its Hoffman
original; until then it returns null (skipped) so an unverified render can never
overwrite a pristine live original. DSCA_VALIDATE_MODE env opens the gate for the
validation harness only. Exposed rendersWithoutSpecs().
- render-datasheet.js: allow a null-specs render for DSCA33/45 (their spec files were
lost; template-driven) instead of bailing on missing specs.
- derive-dsca-slotmaps.js: DSCA_TPL env to target the 3345 templates; derived 43 slot
maps into them (22 models need none, 8 DSCA33 still below threshold).
- validate-dsca3345.js (new): renders each model's _srcSerial, fetches the live
Hoffman original (GET TestReportDataFiles/{serial}, deployed uploader token — no
vault needed), content-normalized compare; --apply marks validated.
STATUS: gate is CLOSED — 0 models validated, all DSCA33/45 still render null, nothing
published, no risk. Final-Test block + accuracy headers now byte-match the Hoffman
originals for all 56 models; the remaining blocker is accuracy-DATA numeric quirks that
must match to pass the gate:
- DSCA33 calc column stored in A but displayed in mADC (x1000); measured stored in
mA (not scaled) — an original-software unit quirk.
- sign conventions differ per layout (DSCA33 stim/calc/meas unsigned, error signed;
DSCA45 stim unsigned, calc/meas/error signed).
- DSCA45 frequency-input stim formatting.
These need per-layout reverse-engineering against the originals (the validation harness
is the oracle). 8 DSCA33 models (DSCA33-02/03/03A/04/04A/05/05A/1642) also lack a slot
map (below threshold). DSCA33-1948 + DSCA45-1746 (24 units) have no Hoffman original.
Cleanups: deleted superseded memory project_dsca33_45_spec_gap; struck the obsolete
"ask John" TODO 2 from the handoff note.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The DSCA33/DSCA45 main spec files lost in the cryptolocker wipe are recoverable:
the original software published correct certs to the Hoffman product API before
the wipe and our null-skipping renderer never overwrote them. Mine per-model
Final-Test templates (names + specs + verbatim accuracy headers) straight from
those originals instead of requesting spec files from Dataforth/John.
- dsca33-45-templates.json: 56 models (DSCA33 34/35, DSCA45 22/23); only
DSCA33-1948 + DSCA45-1746 (24 units) lack an original.
- mine-hoffman-dsca.py: the re-runnable miner.
- DSCA33-45-HOFFMAN-RECOVERY handoff for the AD2 session (incl. the gate:
validate each render vs its Hoffman original before enabling live rendering).
- memories: Hoffman recovery (supersedes the spec-gap "need John" note) and the
AD2 SSH MTU-blackhole root cause/fix; errorlog entries (syncro jq, ssh correction).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Mike's correction: web search (grok xsearch + gemini search) carries at least as much weight as
live API probing - the searches gave the real leads this session (connector proxy, teleport setting
path); blind endpoint-probing is "highly suspect" (mostly 404s). And the search bots MUST be properly
fixed - both returned empty repeatedly on UniFi research despite the same-day partial grok fix.
- docs/CT_THOUGHTS.md: Thought 2 (HIGH PRIORITY) - web-search reliability must-fix, with the observed
failures + a proper-fix investigation plan (capture failing-query JSON; max-turns/streaming-json/
retry; cross-fallback grok<->gemini; 5/5 acceptance).
- memory feedback_web_search_over_probing: lead with web search/docs; probe only to CONFIRM a
hypothesis, never as primary discovery. Reading our own config is fine; guessing paths is not.
- errorlog correction logged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
New backend reaching ANY of the ~36 ACG UniFi consoles remotely via api.ui.com with the
account key (vault services/unifi-site-manager) - no UOS server, no LAN/VPN. Mapped the API
surface empirically (key live), corroborated by grok+gemini web search:
- Tier 1 (Site Manager): fleet/devices/sites/isp commands - inventory, site health (counts,
IPS, ISP/ASN), and WAN/ISP time-series (latency/throughput/downtime).
- Tier 2 (CLOUD CONNECTOR -> console LOCAL Network API = UOS PARITY): the `net` command proxies
/v1/connector/consoles/<id>/proxy/network/api/s/<site>/stat/{device,sta}, returning the SAME
ace_stat depth as the UOS Mongo path - per-radio cu_total airtime/channel/bw/tx_power/num_sta/
satisfaction and per-client rssi/signal/noise/satisfaction/rates. Verified live on Brooklyn/
Skybar (standalone UDM, WAN-firewalled): `net brooklyn radios` + `net brooklyn clients` work.
This achieves parity with (and broader coverage than) the UOS server for non-UOS consoles.
Added references/site-manager-api.md (full catalog + 3 tiers), a Plane 3 note in SKILL.md, and
updated the reference memory. Read-only; POST actions (device restart, client block) exist, not wired.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Root-caused the long-standing `ask-grok.sh xsearch` "no result (stopReason=)"
failure by reading Grok's bundled docs (~/.grok/docs/user-guide + README) instead
of probing:
- web_search runs a SEPARATE multi-agent model (grok-4.20-multi-agent), so the
wrapper's blanket --no-subagents strangled it -> indefinite hang, 0 bytes. Scoped
--no-subagents OFF xsearch; use --yolo (documented headless tool-run posture).
- xsearch prompt mandated X/Twitter search on every call (slow multi-agent) and the
budget was 240s -> still timed out. Now web-primary (X only when relevant), 300s.
Validated end-to-end through the wrapper: 23s, correct answer + 3 sources.
Model: pin -m grok-build (xAI flagship, 512k, the documented default) for the
reasoning modes (text/verify/review*) so quality is deterministic and not at the
mercy of the runtime default (this machine drifted to grok-composer-2.5-fast, a fast
Cursor coding model). xsearch + image/video keep the runtime default. Validated text
mode on grok-build (13s).
Doc accuracy (SKILL.md): corrected the model facts (default, the separate web_search
model, --effort unsupported on grok-build per supports_reasoning_effort:false);
documented the xsearch subagent exception. Fixed a stale in-script comment claiming
--rules/--disallowed-tools "tripped the CLI" (both are valid headless flags).
memory: add feedback_interview_ai_read_docs (read bundled docs / interview the model
before probing) + index; errorlog correction.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
onboarding-diagnostic.ps1: add a PowerShell-version guard. The probe is PS3+ by
design (Get-CimInstance, [ordered], ConvertTo-Json); on stock PS2 (Win7 SP1 /
2008 R2 without WMF) it crashed with cryptic [ordered] errors and emitted empty
DIAG-JSON (first hit: AMT-PC). Now on PS<3 it emits a legible, parseable result
inside the DIAG-JSON markers (hand-built JSON) with a WMF 5.1 / KB3191566
remediation hint instead. Parses clean. True PS2-native probe stays an RMM Thought.
memory: add feedback_windows_quote_stripping (+ index) consolidating the two
recent embedded-double-quote incidents (PowerShell->curl.exe CommandLineToArgvW,
RMM->cmd.exe shutdown /c) into one root cause + fix, so future ref= entries land.
errorlog: the two self-logged entries from #32333 (preview-skip friction,
AMT-PC/Scileppi conflation correction).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Merge duplicate DM memories into canonical feedback_dm_wrapping_commands_to_mike
(points at the productized discord-dm skill; keeps UA/Cloudflare-1010 + 50109
gotchas); git rm the session-created feedback_dm_wrapped_command_lines duplicate.
- feedback_365_remediation_tool: record that Exchange Operator HAS Graph Mail.Send/
Mail.ReadWrite (corrects an earlier "suite has no Mail.Send") + the EXO-vs-Graph
token-audience gotcha + Get-MessageTraceV2 + fresh-onboard EXO 401 propagation.
- Remove a duplicate MEMORY.md index line --apply-safe added from a false-orphan.
- Log the memory-dream false-orphan/dup-index defect to errorlog for skill linting.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Triggered by ~1h lost on 2026-06-12 when the IX WHM access method was forgotten and
password auth no longer worked. CLAUDE.md Key rules now mandates vaulting via the vault
skill + thorough documentation for any credential surfaced in a session.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two sweeps:
1. .30 is a PHYSICAL box (Lenovo ThinkCentre M83, Ubuntu 26.04), not a Jupiter
VM — the VM was decommissioned 2026-06-12. Fixed inventory tables and the
gururmm-build system page (overview, index, jupiter, gururmm-build,
POWER_FAILURE_RUNBOOK).
2. Windows build chain: Beast (GURU-BEAST-ROG, tailnet 100.101.122.4, i9-14900K)
is PRIMARY; Pluto (172.16.3.36) is FALLBACK. Verified against build-windows.sh
(`attempt_build beast || attempt_build pluto`). Fixed overview, index,
projects/gururmm (build-host table + flow + host detail), systems/pluto, and
the reference_pluto_build_server memory.
Submodule advanced: build-pipeline doc comments corrected to match.
