multi-agent-mux/.agents/reports/canary-projects-multi-agent-mux-creator-cline/report-5157a4a7.md

Code Review: .agents/skills/lib.sh — agy TOS-seeding fix + send_keys_safe cline/claude paste-check skip

Job ID: 5157a4a7 Reviewer: cline Diff reviewed: 3846d99..f2e23c1 (working tree, git diff HEAD)

Scope

The diff (git diff HEAD -- .agents/skills/lib.sh, +66/-12) contains two hunks in .agents/skills/lib.sh:

1. Hunk 1 — provision_isolation() agy-arm: adds seeding for ~/.gemini/antigravity, ~/.gemini/config, macOS Library/Preferences plists, Library/Application Support/Antigravity, Library/Group Containers/group.com.google.gemini, and a Linux/Unix else branch seeding XDG config/data dirs. This is the change directly described in the task goal.
2. Hunk 2 — send_keys_safe(): skips the strict paste-visibility check (step 3) for sessions whose name matches cline or claude, while still running the step-4 submission-verification retry loop.

The working-tree diff matches the diff quoted in the brief byte-for-byte.

"No other files changed" check

git status --short:

• M .agents/skills/lib.sh — the only tracked-file modification.
• ?? .agents/skills/multi-agent-mux-delegate-job/multi-agent-mux-delegate-job.<pid>_<n>.tmp — untracked, transient atomic-write temp copy of the job-runner orchestrator script (same artifact observed in prior review passes), not a code change.

Confirmed: no files other than .agents/skills/lib.sh contain reviewable changes.

Lint / Syntax

• bash -n .agents/skills/lib.sh → SYNTAX OK.
• shellcheck is not installed in this environment; manual review of the new lines found no quoting, unbound-variable, or word-splitting issues.

Hunk 1 — provision_isolation agy TOS seeding

Correctness & scoping

• Correctly scoped to the agy) case arm of provision_isolation. agy uses the home isolation lever (isolation_lever → home, isolation_env_prefix → HOME=<root>), so seeding into $root/.gemini/... and $root/Library/... is the right target for a redirected HOME.
• All source paths are guarded with existence checks ([ -d ... ] / [ -f ... ]) before ln -sfn, matching the established pattern in the surrounding code, so the function is a no-op for paths that don't exist on a given machine.
• mkdir -p is called for each new parent dir ($root/Library/Preferences, $root/Library/Application Support, $root/Library/Group Containers, $root/.config, $root/.local/share) before creating the symlink, so ln -sfn never fails on a missing parent.
• The Linux else branch correctly resolves XDG_CONFIG_HOME/XDG_DATA_HOME with ${VAR:-$HOME/...} defaults and tries both Antigravity and antigravity casings via elif, mirroring the case-sensitivity reality of XDG dirs across distros.
• The two new ~/.gemini/antigravity and ~/.gemini/config blocks are placed after the existing antigravity-cli file loop and before the uname Darwin/Linux branch, which is the correct location (they apply on both platforms; the uname branch is platform-specific).

Live path verification (this machine = macOS Darwin)

All newly-referenced source paths were checked against the real $HOME:

Path	Exists?
~/.gemini/antigravity	✅ dir
~/.gemini/config	✅ dir
~/Library/Keychains	✅ dir (pre-existing seed target)
~/Library/Preferences/com.google.antigravity.plist	✅ file
~/Library/Preferences/com.google.GeminiMacOS.plist	✅ file
~/Library/Preferences/com.google.GeminiMacOS.shareddata.plist	✅ file
~/Library/Application Support/Antigravity	✅ dir
~/Library/Group Containers/group.com.google.gemini	✅ dir

Functional smoke test

Ran provision_isolation agy <tmp_root> against the live machine state. Result:

• Return code 0.
• Seeded list printed: .gemini/antigravity-cli/antigravity-oauth-token,.gemini/antigravity-cli/installation_id,.gemini/antigravity-cli/settings.json,.gemini/antigravity,.gemini/config,Library/Keychains,Library/Preferences/com.google.antigravity.plist,Library/Preferences/com.google.GeminiMacOS.plist,Library/Preferences/com.google.GeminiMacOS.shareddata.plist,Library/Application Support/Antigravity,Library/Group Containers/group.com.google.gemini
• Every entry under <tmp_root> is a correct symlink (ls -laR) pointing at the real source path; no dangling links, no leading comma in the output (because earlier .gemini/* segments fire first on this machine).

Cosmetic nit (carried forward, inert)

Three Darwin-branch lines build seeded as seeded="$seeded,<path>" (lines 1240, 1246, 1251) without the ${seeded:+$seeded,} guard used everywhere else in this function (including the two .gemini/* blocks added in this same diff, just above). If none of the earlier seed steps fired (e.g. a fresh machine with no ~/.gemini/* files and no Keychains dir, but an existing Antigravity Preferences plist), seeded would start with a leading comma (e.g. ,Library/Preferences/com.google.antigravity.plist).

• Impact: the sole consumer, create_session.sh:339, does [x for x in os.environ.get('ISOLATION_SEEDED', '').split(',') if x], which filters falsy split segments — so a leading empty element is silently dropped. No functional bug today. Style consistency nit only; does not block.

local in case branch (bash semantics)

The Linux else branch declares local xdg_config=... / local xdg_data=... inside a case arm. In bash, local is dynamically scoped and valid anywhere inside a function body regardless of case/if nesting, so this is well-formed (and bash -n confirms). No issue.

Hunk 2 — send_keys_safe() cline/claude paste-check skip

local was_popup=0
if [[ "$sess" =~ "cline" ]] || [[ "$sess" =~ "claude" ]]; then
  # Skip strict paste check due to scrollout false-positives, proceed to C-m loop
  true
else
  sleep 0.5
  local pane_content
  pane_content=$(_pane_capture "$sess")
  ...paste-visibility checks (return 3 on miss)...
fi

Scope observation

The stated task goal is the agy TOS-seeding fix (Hunk 1). Hunk 2 is a separate change to the paste-submission verification logic for cline/claude sessions and is unrelated to agy onboarding. However, the brief explicitly asks to review the cumulative git diff, so it is in scope for this review. It is not a blocker (see analysis below), but it is noted that this hunk is outside the narrow task-goal description.

Analysis

• Consistent with existing convention: three lines above (unchanged, pre-existing context), the function already special-cases if [[ "$sess" =~ "agy" ]] to skip all verification and return 0 unconditionally. The new cline/claude branch is less aggressive — it only skips step 3 (paste-visibility check) and still runs the step-4 submission-verification retry loop (marker-left-tail / pane-changed / spinner-token checks) below. It is more conservative than the precedent it sits next to, not a new pattern.
• Session-name matching is safe under this project's naming convention: session names embed the agent name as a suffix (e.g. ...-creator-claude, ...-creator-cline, ...-creator-agy), matching the pattern already relied upon by the pre-existing agy check, so substring matching on cline/claude is not expected to produce false hits from unrelated workspace/repo names.
• =~ with quoted RHS: [[ "$sess" =~ "cline" ]] — quoting the RHS of =~ makes bash treat it as a literal substring match rather than a regex (shellcheck SC2076-class nit; [[ "$sess" == *cline* ]] would be the idiomatic form). This exactly mirrors the pre-existing, unchanged agy check one line above, so it is a style-consistency choice, not a regression.
• Variable scoping: splitting the old local pane_content was_popup=0 into local was_popup=0 (outer) and local pane_content (inner, else-only) is correct — was_popup is referenced unconditionally later in the retry loop (lines 1653, 1655), pane_content only inside the branch that declares it. No unbound-variable risk.
• Trade-off (named explicitly): skipping the paste-visibility check for claude/cline means a genuine paste failure (not just a scrollback false-positive) for those two agents is no longer caught at step 3 (return 3); it now depends entirely on the step-4 retry-loop heuristics (spinner tokens, marker leaving the tail, pane-content diff) to detect submission. This is a reasonable, bounded trade-off given the stated motivation (documented false positives breaking real pastes for these TUIs), and it downgrades detection rather than removing it. It would benefit from a live smoke test (send a real multi-line prompt to a claude/cline-suffixed session and confirm it submits) which cannot be performed in this non-interactive review environment — but nothing here indicates the fix is wrong or requires a redesign.
• bash -n passes; no unbound-variable or quoting issues found in this hunk.

Regression / loss check

• No existing functionality removed: the agy early-return shortcut (line 1619-1622) is unchanged; the else (non-cline/claude/agy) path retains the original strict paste-visibility check verbatim.
• The two .gemini/* blocks added in Hunk 1 are additive and guarded by existence checks; they cannot break the prior antigravity-cli file loop above them.
• No imports/variables orphaned by these changes.
• No tests exist that exercise the agy arm of provision_isolation (the only provision_isolation test, test_comp_create_isolation_folder_setup, exercises the claude arm), so there is no test regression to report — and no new test was added for the agy arm. This is a pre-existing test-coverage gap, not introduced by this diff; flagging for awareness, not as a blocker.

Verdict

Both hunks are correctly scoped (only .agents/skills/lib.sh, only their respective functions), syntactically valid (bash -n clean), and internally consistent with existing patterns in the same file. Hunk 1 is the agy TOS/onboarding seeding fix directly matching the task goal; it was functionally smoke-tested against live machine state and produces correct symlinks and a well-formed seeded list. Hunk 2 is a targeted flakiness fix for cline/claude paste submission that follows the file's existing per-agent-shortcut convention and is more conservative than the precedent it sits next to; its only real risk (masked true paste failures for claude/cline) is a bounded, intentional trade-off that would ideally get a live smoke test, but nothing here indicates the fix is wrong or requires a redesign. The two cosmetic nits (Darwin seeded guard inconsistency; =~ quoted-RHS style) are inert and do not block.

[VERDICT: PASS]