Mike's must-fix. Diagnosed from RAW output of failing queries (not guessed):
- grok xsearch = TIMEOUT: grok-4.20-multi-agent web_search runs past budget on multi-part queries
(286s/280s, rc=124, still searching - 183 thoughts, only progress-noise text); buffered json => total loss.
- gemini search = INTERMITTENT empty turn (a clean re-run gave a real 2.6KB answer in 122s); the wrapper
retried only once, so two empties in a row failed spuriously.
Fixes:
- ask-gemini.sh emit_or_fail: retry up to 3x with 3s/6s backoff (was 1).
- ask-grok.sh xsearch: --output-format streaming-json (salvage partials) + AUTO-FALLBACK to
ask-gemini.sh search when grok doesn't finish (rc!=0 or empty). Validated e2e: grok timed out
(rc=124) -> fell back -> gemini returned a real sourced answer (UniFi Teleport invite-link API).
grok's own multi-agent timeout is an xAI-side limitation; the fallback makes xsearch reliable regardless.
Docs: grok SKILL.md xsearch row + CT_THOUGHTS Thought 2 Resolution.
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>
review/review-files resolve relative paths only against CWD or
$CLAUDETOOLS_ROOT, never a submodule/subdir — so submodule-relative
paths fail with "file not found". Add a [!WARNING] callout to both
SKILL.md files, fix the misleading "absolute or repo-relative" table
wording, and add inline GOTCHA comments at each resolution site in
both scripts. Bitten us repeatedly (latest: GuruConnect review).
Fixes the two Windows pain points when routing code review to the Grok CLI
(native Windows grok.exe driven from Git Bash):
- winpath() (cygpath -w; no-op off Windows) on every path handed to grok.exe
(--prompt-file, --cwd) -> deterministic, space-safe; removes reliance on
MSYS's argv auto-conversion heuristic (the 'confounded by Windows paths').
- review mode resolves to an absolute Windows path (handles absolute/spaced paths).
- NEW review-files [-i instr] <f1> [f2...]: review a set of files together.
- NEW review-diff [-C <repo-dir>] [-i instr] <gitref> [-- <pathspec>]: review a
git diff; -C targets submodules (e.g. guru-rmm). Diff goes via --prompt-file,
not a shell arg -> no 'quote hell'.
Tested: text, review (spaced abs path), review-files (2 tray modules),
review-diff (self-review of these changes). SKILL.md updated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
