mcp-gee-sweet 0.8.2.dev45__tar.gz → 0.8.2.dev51__tar.gz

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/.claude/commands/merge-pr.md

@@ -6,6 +6,7 @@ Merge the current branch's PR and clean up its worktree. Uses `--admin` only to
    - Every check in `statusCheckRollup` (in particular "Lint and test") must show success. If anything is failing or still pending, stop and report which — do not merge, and do not wait/poll.
    - `mergeable` must not be `CONFLICTING`.
    - If the branch's second `/`-separated segment is one of the four dev-lane slot names (`ash`, `sky`, `jay`, `kit` — the type prefix in front varies, `feat`/`fix`/`chore`/etc., don't assume `feat`), it must carry the `qa-approved` label (check `gh pr view <number> --json labels`). If it doesn't, stop — that means the paired QA agent (`/team-member`) hasn't signed off yet; don't merge and don't review it yourself here. This check deliberately stays scoped to the four dev-lane names — Aziz's and Amy's branches (`team/aziz`, `docs/amy/issue-<n>`, ...) aren't part of the Dev/QA pairing and go through normal review instead.
+     - **Exception:** a QA-named slot (`sky`/`kit`) authoring its own process/meta PR (e.g. `chore/sky/...`) has no natural QA partner to self-approve — the Dev/QA pairing only exists for the *other* lane's ticket work. There's no label path for this case; stop and ask the user directly whether it's safe to merge without one, same as any missing-label PR. If they confirm (e.g. because it's a prompting/process change with no application-code risk), proceed — that confirmation stands in for the label for this PR only, it doesn't waive the check generally.
 3. Show the user a summary: PR number, title, URL, check status, and review status (expected to be blocked only on the missing-approval requirement). State plainly that merging will use `--admin` to bypass that review gate. Ask for explicit confirmation before proceeding.
 4. On confirmation, squash-merge (matching this repo's existing history — commits land on `develop` as a single `title (#number)` commit): `gh pr merge <number> --admin --squash`. The remote branch is auto-deleted on merge (repo setting), so don't pass `--delete-branch`.
 5. Clean up:
@@ -14,5 +15,6 @@ Merge the current branch's PR and clean up its worktree. Uses `--admin` only to
    - If this session created the current worktree (i.e. it got here via `/start-worktree` or `/next-issue` earlier in this same session), use `ExitWorktree` with `action: "remove"`.
    - Otherwise (worktree predates this session), fall back to manual cleanup from the main checkout: `git worktree remove <path>`, then `git branch -d <branch>`, then `git worktree prune`.
 6. Sweep the other five dev-team lanes for orphaned work on the same ticket. Pull the issue number out of the merged PR's title (e.g. `(#126)`). For each of the other dev-team worktrees (`ash`, `sky`, `jay`, `kit`, `aziz`, `amy`, minus whichever one just merged), run `git -C .claude/worktrees/<name> log --oneline develop..HEAD` and check whether any commit message references that same issue number. A hit means a sibling lane independently started the same ticket and lost the race — since it never became a PR, nothing else would ever clean it up. Don't reset it silently: a squash merge means SHAs (and even diffs) won't match even for genuinely identical content, so show the user the commit list and confirm it's a duplicate before resetting — same idle-reset procedure as step 5 (`git checkout team/<name>`, `git reset --hard origin/develop`, delete the stale branch if it had its own name).
-7. Update the roadmap: from the main checkout on `develop`, `git pull` then check `docs/roadmap.md` for a checkbox line referencing the issue(s) this PR closes (search by issue number). If found, check it off (`- [ ]` → `- [x]`) and append `(PR <number>)` in the existing style (e.g. `(PR #280)`) — see recent `- [x]` entries for the exact convention. If the roadmap has no line item for this issue (not every ticket is roadmap-tracked — chores, follow-up defects, etc.), skip this step silently. Commit directly to `develop` (`docs(roadmap): check off #<issue> (PR <number>)`) and push — `develop`'s branch protection has `enforce_admins: false`, so a direct push by the repo owner is allowed for this kind of small, reversible, docs-only change; don't open a separate PR for it.
-8. Report a summary: the merge commit, the now-merged PR URL, confirmation the worktree was removed, whether any sibling-lane duplicate was found and reset, and whether the roadmap was updated.
+7. From the main checkout on `develop`, `git pull` — unconditionally, even if step 8 turns out to be a no-op. `gh pr merge` merges via the API; it never touches the main checkout's local branch, so skipping this leaves Kai's live-testing home base stale until the next unrelated pull happens to catch it up.
+8. Update the roadmap: check `docs/roadmap.md` for a checkbox line referencing the issue(s) this PR closes (search by issue number). If found, check it off (`- [ ]` → `- [x]`) and append `(PR <number>)` in the existing style (e.g. `(PR #280)`) — see recent `- [x]` entries for the exact convention. If the roadmap has no line item for this issue (not every ticket is roadmap-tracked — chores, follow-up defects, etc.), skip this step silently. Commit directly to `develop` (`docs(roadmap): check off #<issue> (PR <number>)`) and push — `develop`'s branch protection has `enforce_admins: false`, so a direct push by the repo owner is allowed for this kind of small, reversible, docs-only change; don't open a separate PR for it.
+9. Report a summary: the merge commit, the now-merged PR URL, confirmation the worktree was removed, whether any sibling-lane duplicate was found and reset, and whether the roadmap was updated.

mcp_gee_sweet-0.8.2.dev51/.claude/commands/retro.md

@@ -0,0 +1,23 @@
+Process the friction and findings from the unit of work you just finished — a PR reviewed, a ticket implemented, a release cut, a doc pass, an orchestration cycle — into a durable form, so the next session in your seat doesn't rediscover the same thing from scratch.
+
+This is discretionary, not a gate. No role's process file requires running this — invoke it when you actually hit friction worth preserving, skip it when a pass was clean. Symmetric with `/team-member`/`/next-issue` on the other end of a work cycle: those are prompts you may follow to *pick up* work; this is the one for *closing out* a piece of it.
+
+**Only process real findings from the work you just did.** Don't invent hypothetical friction to fill out the exercise, and don't pad with things this file already tells you to do routinely (e.g. a QA coverage gap that blocks the PR itself — that's handled inline by `qa.md`/`verify-pr.md`, not a retro item). If nothing survives that filter, say so and stop.
+
+## The two dispositions
+
+For each real finding, decide which bucket it belongs in — most sessions will have some of both:
+
+**Ticket** — a durable product or system finding that needs to be scheduled, prioritized, or fixed by someone later: a bug, a coverage gap, a design inconsistency, tech debt. This repo is issue-first (see the `feedback_ticket_before_editing` convention) — file it with `gh issue create`, pick labels from the existing set (`defect`, `enhancement`, `qa`, `infrastructure`, `documentation`, `backlog`, `decision-needed`, a version label if it's obviously scoped to one), and reference the PR/work that surfaced it. Don't fix it inline just because you noticed it while doing something else — that's scope creep, not this ticket's job, unless the user explicitly asks you to just do it now. Batch multiple findings into one pass at the end rather than filing mid-work. Roadmap grooming (folding the new issue into `docs/roadmap.md`) is Kai's job, not the filer's — leave it for Kai's next grooming pass unless you *are* Kai.
+
+Before filing, triage defect vs. hardening honestly: has a failure actually been observed (a wrong result, a crash, a silently-corrupted state), or are you flagging an input this code merely doesn't validate yet? The latter is real and worth a ticket, but label and word it as hardening, not as a confirmed defect — don't let "I found something" inflate its severity.
+
+**Command decision** — operational knowledge that should change how the *next* session in this same seat behaves: a process gap, a doc gap, a technique that worked (or didn't), a fixture gotcha, a missing step in a skill file. This isn't roadmap-worthy scope, so skip the ticket — edit the relevant process/skill doc directly, right now, and say what you changed. Examples already in this repo: `docs/qa/run.md`'s Playwright limitations list, `docs/qa/retro-v0.8.0.md`'s action items, a role file's own process fixes.
+
+## Your role's details
+
+Read the `## Retro` section in your own role file (`.claude/team-roles/<role>.md`) for the friction categories specific to your seat and which docs each maps to. If that section doesn't exist yet, you're the first to run this from that seat — add one, following the pattern already written for the other roles, and say so in your report.
+
+## Report
+
+State what you filed (issue numbers + one-line summaries) and what you changed directly (files + one-line summaries). Don't just say "processed 3 findings" — name them, the same way you'd report any other work.

mcp_gee_sweet-0.8.2.dev51/.claude/settings.json

@@ -0,0 +1,5 @@
+{
+  "worktree": {
+    "bgIsolation": "none"
+  }
+}

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/.claude/team-roles/amy.md

@@ -12,3 +12,11 @@ Amy keeps documentation accurate, friendly, comprehensive, and fun — README, `
 - **On any other branch (mid-ticket):** report status rather than claiming new work.
 
 Amy has no dedicated MCP server and doesn't need QA-approved sign-off to merge (docs-only PRs aren't gated by `qa-approved`) — normal `/merge-pr` review still applies.
+
+## Retro
+
+Friction Amy typically hits after a doc pass, and where it goes — see `/retro` for the general ticket-vs-command-decision split:
+
+- **Doc-vs-reality drift found while writing** — an existing doc described behavior that turned out wrong once checked against actual code or live tool output. If it points to an actual code bug, file a ticket and route it toward the relevant lane label rather than silently documenting the wrong behavior as if it were intended. If it's purely a documentation accuracy issue within Amy's own scope, just fix it — that's the ticket you're already working, not a new one.
+- **Generated-doc drift** — `docs/tools.md` or `docs/configuration.md` out of sync in a way `scripts/gen_tool_docs.py` doesn't catch (the script's job, not this file's, when it does catch it). File an `infrastructure`-labeled ticket, parallel to #308.
+- **Competitive/positioning claims needing re-verification** and **redundant/overlapping issues** already have their own handling above (step 4's roadmap-Tier-4 routing, step 1's consolidation) — not new retro items, don't re-litigate them here.

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/.claude/team-roles/aziz.md

@@ -15,3 +15,12 @@ Aziz doesn't work a ticket queue — he runs at release cadence: review everythi
 9. **Sign off.** Once every required suite is checked off and documentation review (step 1) is clean, commit the QA docs, push, open a PR, and report to the user that the release is ready to tag (Kai runs `/release` from there).
 
 For a **minor/dev release** that only needs Smoke: same flow, but step 2's audit will usually conclude Smoke alone suffices — Aziz still runs it live and records real results, just against a smaller case set.
+
+## Retro
+
+Friction Aziz typically hits after a release pass, and where it goes — see `/retro` for the general ticket-vs-command-decision split:
+
+- **Release-scope audit surprises** — a merged PR turns out to lack adequate doc/test coverage, or a QA-tier call feels wrong in hindsight once results are in. If it's a gap in one already-merged feature, file a ticket. If it's the scoped-gating process itself (`docs/qa/runs/README.md`) that needs refining, that's a command decision — fix the process doc directly.
+- **Subagent-sharding friction** — a shard's instructions were ambiguous, or two shards' fixture ownership collided. Command decision: refine the sharding instructions in this file or `docs/qa/run.md`'s mutex section, don't just work around it silently next time.
+- **Bugs found during the compile step** are routine, not a retro item — route them to the responsible Dev lane per step 8 above.
+- **This role already has a heavier version of this pattern**: for a full regression run, Aziz writes `docs/qa/retro-vX.Y.Z.md` (see `retro-v0.8.0.md`) with its own "what went well / what didn't / action items" structure. Before filing a one-off ticket or doc edit here, check whether the finding is significant enough to fold into that release-scale retro doc instead — don't duplicate the same finding in two places.

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/.claude/team-roles/dev.md

@@ -15,3 +15,12 @@ Branch naming for this slot always puts `<name>` as the **second** `/`-separated
 - **On any other branch:** check this branch's PR history: `gh pr list --head <branch> --state all --json number,state,mergedAt`.
   - **A `MERGED` entry exists:** this ticket already shipped and this slot was never reset (e.g. Kai's merge-time cleanup didn't run, or targeted a different branch) — self-heal: `git fetch origin develop`, `git checkout team/<name>`, `git reset --hard origin/develop`, `git branch -D <branch>`. Then treat this slot as idle and fall through to the idle-branch flow above to pick up the next ticket.
   - **No `MERGED` entry (open, closed-without-merge, or no PR at all):** mid-ticket — report status: whether a PR is already open, what CI/QA said if anything, and whether it's waiting on QA or on further work — rather than claiming a new ticket. Don't auto-reset a closed-without-merge branch; that's a judgment call for the user, not this session.
+
+## Retro
+
+Friction Dev (Ash/Jay) typically hits after finishing a ticket, and where it goes — see `/retro` for the general ticket-vs-command-decision split:
+
+- **Design/architecture surprises** — an existing pattern didn't generalize the way expected mid-implementation (a sibling function skipped a step this one needed, a helper needed restructuring to fit a new case). If it's about how future Devs should approach similar work, that's a command decision: add a note to `CLAUDE.md` or a `docs/design/` snapshot. If it's legitimate follow-up scope not worth doing in the current PR, file a ticket instead of expanding this one.
+- **Scope creep discovered while implementing** — related, unshipped bugs or gaps adjacent to the ticket but not part of its acceptance criteria. Ticket, don't fold into the current PR.
+- **Stale or missing `CLAUDE.md` guidance** — instructions that were wrong or absent for a pattern just hit. Command decision: fix `CLAUDE.md` directly, it's this repo's own process doc.
+- **QA-authoring ambiguity** — writing test cases in `docs/qa/tests/` surfaced an unclear tagging rule or fixture assumption in `run.md`/`setup.md`. Command decision: clarify the doc rather than guessing silently and leaving the next Dev to guess the same thing.

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/.claude/team-roles/kai.md

@@ -20,3 +20,11 @@ Why this role split exists: any locally-configured MCP server that runs this pro
    - Release readiness and documentation quality are Aziz's and Amy's territory, not Kai's — when cutting a release, hand off to Aziz (`/team-member Aziz`) for the review/QA-tier/sign-off pass rather than doing it here; route doc gaps found along the way to Amy (`documentation` label) rather than fixing them inline.
 
    Do NOT pick up ticket implementation directly in this session — hand it to a worker session via `start-worktree` (or `next-issue`, which does this automatically), or to a dev-team lane via `/team-member` if the team is active.
+
+## Retro
+
+Friction Kai typically hits during coordination, and where it goes — see `/retro` for the general ticket-vs-command-decision split:
+
+- **Process friction across the team** — another session's role file turned out ambiguous or wrong when actually followed (a stale worktree, a label race, a step that assumed state that wasn't there). Command decision: fix the relevant `.claude/team-roles/*.md` or top-level command file directly — Kai owns the main checkout, so this is usually the right session to make these edits, not a ticket for someone else to eventually pick up.
+- **Roadmap drift** — a shipped PR wasn't checked off in `docs/roadmap.md`, or a version label doesn't match where the work actually landed. Command decision: fix it directly during grooming, it's bookkeeping, not durable design work worth a ticket.
+- **Systemic bugs spotted while merging or triaging that don't belong to the ticket at hand** — file a ticket rather than expanding scope on someone else's PR.

mcp_gee_sweet-0.8.2.dev51/.claude/team-roles/qa.md

@@ -0,0 +1,23 @@
+QA role (Sky / Kit). Reached via `/team-member <name>` after that command's shared isolate + tool-boundary steps.
+
+Find the partner Dev's open PR by matching the branch's second `/`-separated segment against the partner's lowercase name — not a `feat/`-specific prefix, since the Dev's branch type varies: `gh pr list --state open --json number,headRefName,url --jq '[.[] | select((.headRefName | split("/"))[1] == "<partner>")]'`. At most one is expected, since a lane only has one ticket in flight at a time.
+
+- **None found:** self-heal first — `git fetch origin develop`. If this worktree's `HEAD` isn't already `origin/develop`, `git reset --hard origin/develop`: since the partner has no open PR right now, any leftover commits here are a stale copy of a PR this lane previously reviewed (now merged or closed) — this worktree never holds original work of its own, only reset-in copies of a Dev's PR branch, so it's always safe to discard. Then report that Lane {A/B} has nothing to verify right now.
+- **One found:** this is now essentially `/verify-pr`'s steps 4 onward, but simpler — this worktree already IS a dedicated review space, so skip `/verify-pr`'s steps 1–3 (the main-checkout precondition and the `review/<branch>` fetch trick don't apply here):
+  1. `git fetch origin <headRefName> && git reset --hard origin/<headRefName>` in this worktree, staying on `team/<name>` (never create a branch named after the PR here — this slot's identity is `team/<name>`, permanently).
+  2. Tell the user to run `/mcp reconnect` (standalone, on its own line) so this agent's own MCP connection picks up the reset code. Wait for confirmation.
+  3. Run `/code-review` at `high` effort against `origin/develop...HEAD`.
+  4. Scope and run the live QA steps from `/verify-pr` (its steps 6–8: find touched `docs/qa/tests/` cases, cross-check tool coverage, run them live using this worktree's own `mcp-gee-sweet-<name>`-prefixed tools).
+  5. Record `**Result**` entries for every case actually run.
+  6. If anything failed: push the recorded results (`git push origin HEAD:<headRefName>`, with confirmation), comment on the PR summarizing what failed, and stop — tell the user it goes back to the Dev agent.
+  7. If everything passed: push the results, then `gh pr edit <number> --add-label qa-approved`, and report to the user that it's ready for Kai to run `/merge-pr`.
+
+## Retro
+
+Friction QA (Sky/Kit) typically hits after a pass, and where it goes — see `/retro` for the general ticket-vs-command-decision split:
+
+- **Fixture drift/pollution** — the shared spreadsheet/doc accumulates stray objects (charts, temp sheets/rows, leftover permissions) from earlier test runs, breaking `docs/qa/setup.md`'s "Known fixture state" assumptions or blocking visual verification. If a specific test category is the source (e.g. a creation test with no teardown), file a `qa`-labeled ticket against that category rather than just working around it silently. If it's a workaround you need *right now* to finish this pass, that's a command decision — document it in `docs/qa/run.md`'s Playwright-limitations list so the next pass doesn't rediscover it (see the "Chart-covered grid" entry, added 2026-07-15, for the pattern).
+- **Playwright verification gaps** — an element is structurally unreachable or invisible to the browser tools (outside the viewport, canvas-rendered with no accessible geometry, obscured by other content). Command decision: add it to `run.md`'s limitations list along with whatever alternative verification actually worked (e.g. `get_sheet_data(..., include_grid_data=True)`'s `rowMetadata`/`columnMetadata` for pixel-precise dimension checks, when a screenshot can't show it).
+- **Test tag drift** — `⚠️ requires-oauth` or `**Playwright: required**` no longer matches a test case's actual behavior. Small, obvious ones: fix the tag directly in the test file (command decision, mechanical). Larger or systemic drift: don't duplicate #264 (the tracked tag-consistency audit) — add to it instead.
+- **Code-review findings that are minor or systemic rather than PR-blocking** — input-validation gaps, duplicated helpers, style inconsistencies that the new code merely repeats from an existing convention rather than introduces. These are tickets (`enhancement`/`backlog`, or `defect` only if a failure was actually observed), not reasons to withhold `qa-approved` — don't hold one PR hostage to fix a codebase-wide convention. See #323 for the shape this takes (validation + dedup findings from the same review, bundled into one issue since they shared a root cause).
+- **Coverage gaps in the PR itself** (a changed tool with no QA test case at all) are not a retro item — that blocks the pass and is handled inline per this file's step 4 / `verify-pr.md` step 6, not deferred here.

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/CLAUDE.md

@@ -32,7 +32,7 @@ Tests live in `tests/` and can be run with `uv run pytest`.
 Logic is split across `src/mcp_gee_sweet/`: `server.py` (MCP setup, tool decorator, resources), `auth.py` (lifespan, `SpreadsheetContext`), and `tools/` (domain-based layout):
 
 - `tools/sheets/data.py` — read/write cell data (`get_sheet_data`, `get_sheet_formulas`, `get_multiple_*`, `find_in_spreadsheet`, `clear_values`, `update_cells`, `batch_update_cells`, `batch_update`)
-- `tools/sheets/structure.py` — sheet structure (`list_sheets`, `copy_sheet`, `duplicate_sheet`, `rename_sheet`, `create_sheet`, `delete_sheet`, `add_rows`, `add_columns`, `delete_rows`, `delete_columns`, `hide_rows`, `unhide_rows`, `hide_columns`, `unhide_columns`, `format_cells`, `merge_cells`, `unmerge_cells`, `freeze`, `update_sheet_properties`, `sort_range`, `add_chart`)
+- `tools/sheets/structure.py` — sheet structure (`list_sheets`, `copy_sheet`, `duplicate_sheet`, `rename_sheet`, `create_sheet`, `delete_sheet`, `add_rows`, `add_columns`, `delete_rows`, `delete_columns`, `hide_rows`, `unhide_rows`, `hide_columns`, `unhide_columns`, `resize_rows`, `resize_columns`, `format_cells`, `update_borders`, `merge_cells`, `unmerge_cells`, `freeze`, `update_sheet_properties`, `sort_range`, `add_chart`)
 - `tools/sheets/helpers.py` — A1 notation helpers (`_parse_a1_notation`, `_column_index_to_letter`, etc.)
 - `tools/drive/files.py` — file/folder operations (`create_spreadsheet`, `import_csv_to_sheet`, `list_spreadsheets`, `list_files`, `search_files`, `create_folder`, `copy_file`, `move_file`, `rename_file`, `delete_file`, `list_shared_with_me`, `list_recent_files`, `get_storage_quota`, etc.)
 - `tools/drive/sharing.py` — permissions (`share_spreadsheet`, `share_file`, `list_permissions`, `update_permission`, `remove_permission`)

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-gee-sweet
-Version: 0.8.2.dev45
+Version: 0.8.2.dev51
 Summary: MCP server for Google Workspace — Sheets, Drive, Docs, and Calendar. 60+ tools for AI clients.
 Project-URL: Homepage, https://github.com/khuisman/mcp-gee-sweet
 Project-URL: Bug Tracker, https://github.com/khuisman/mcp-gee-sweet/issues
@@ -27,7 +27,7 @@ Description-Content-Type: text/markdown
 ![GitHub License](https://img.shields.io/github/license/khuisman/mcp-gee-sweet)
 </div>
 
-An MCP server that gives AI clients reliable, direct access to Google Workspace — Sheets, Drive, Docs, and Calendar. 90 tools across four domains.
+An MCP server that gives AI clients reliable, direct access to Google Workspace — Sheets, Drive, Docs, and Calendar. 101 tools across four domains.
 
 As of mid-2026, Google's own Workspace MCP servers (Developer Preview) cover Gmail, Drive, Calendar, People, and Chat — Sheets and Docs still have no official server at all, and Drive/Calendar coverage there is a fraction of what's here. Stable releases ship to PyPI behind a QA regression gate, with a raw `batch_update` passthrough as an escape hatch for anything a named tool doesn't cover yet. See [Why it exists](https://khuisman.github.io/mcp-gee-sweet/#why-it-exists) for the full, sourced comparison against both the official servers and community alternatives.
 
@@ -124,7 +124,7 @@ See [Client Setup](https://khuisman.github.io/mcp-gee-sweet/latest/client-setup/
 
 ## Docs
 
-- [Tools](https://khuisman.github.io/mcp-gee-sweet/latest/tools/) — full tool reference (90 tools)
+- [Tools](https://khuisman.github.io/mcp-gee-sweet/latest/tools/) — full tool reference (101 tools)
 - [Authentication](https://khuisman.github.io/mcp-gee-sweet/latest/auth/) — all four auth methods
 - [Configuration](https://khuisman.github.io/mcp-gee-sweet/latest/configuration/) — env vars, caching, tool filtering
 - [Client Setup](https://khuisman.github.io/mcp-gee-sweet/latest/client-setup/) — MCP client config examples

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/README.md

@@ -5,7 +5,7 @@
 ![GitHub License](https://img.shields.io/github/license/khuisman/mcp-gee-sweet)
 </div>
 
-An MCP server that gives AI clients reliable, direct access to Google Workspace — Sheets, Drive, Docs, and Calendar. 90 tools across four domains.
+An MCP server that gives AI clients reliable, direct access to Google Workspace — Sheets, Drive, Docs, and Calendar. 101 tools across four domains.
 
 As of mid-2026, Google's own Workspace MCP servers (Developer Preview) cover Gmail, Drive, Calendar, People, and Chat — Sheets and Docs still have no official server at all, and Drive/Calendar coverage there is a fraction of what's here. Stable releases ship to PyPI behind a QA regression gate, with a raw `batch_update` passthrough as an escape hatch for anything a named tool doesn't cover yet. See [Why it exists](https://khuisman.github.io/mcp-gee-sweet/#why-it-exists) for the full, sourced comparison against both the official servers and community alternatives.
 
@@ -102,7 +102,7 @@ See [Client Setup](https://khuisman.github.io/mcp-gee-sweet/latest/client-setup/
 
 ## Docs
 
-- [Tools](https://khuisman.github.io/mcp-gee-sweet/latest/tools/) — full tool reference (90 tools)
+- [Tools](https://khuisman.github.io/mcp-gee-sweet/latest/tools/) — full tool reference (101 tools)
 - [Authentication](https://khuisman.github.io/mcp-gee-sweet/latest/auth/) — all four auth methods
 - [Configuration](https://khuisman.github.io/mcp-gee-sweet/latest/configuration/) — env vars, caching, tool filtering
 - [Client Setup](https://khuisman.github.io/mcp-gee-sweet/latest/client-setup/) — MCP client config examples

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/docs/configuration.md

@@ -70,7 +70,7 @@ Access logs are emitted at `INFO` level — they appear when `DEBUG_LEVEL` is `D
 
 <!-- Auto-generated by `scripts/gen_tool_docs.py` — do not edit by hand, your changes will be overwritten on the next commit. -->
 
-By default all 100 tools are registered. Use `ENABLED_TOOLS` (or `--include-tools` on the CLI) to restrict the server to exactly the tools you need. This reduces the AI's context window cost — each registered tool is a name the model must reason about on every call.
+By default all 103 tools are registered. Use `ENABLED_TOOLS` (or `--include-tools` on the CLI) to restrict the server to exactly the tools you need. This reduces the AI's context window cost — each registered tool is a name the model must reason about on every call.
 
 ```bash
 # Environment variable

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/docs/qa/run.md

@@ -36,6 +36,7 @@ When a test case is tagged `**Playwright: required**`, after the tool call the c
 
 - **Footer / header content** — Google Docs renders headers and footers outside the main document canvas. For short documents `window.scrollTo` does not bring the footer into the viewport. When a test involves `create_footer` or `create_header`, use the API response as confirmation; a Playwright snapshot of the body is still useful but will not show the footer content.
 - **Permission changes** — sharing confirmations are not visible in the Drive UI without navigating to the file's "Share" dialog. Use `list_permissions` API response as the confirmation source for share tests.
+- **Chart-covered grid (Sales sheet)** — repeated `add_chart` test runs leave floating chart objects on the Sales sheet (they're never cleaned up between runs), and as of 2026-07-15 there were ~12 stacked overlapping charts covering roughly rows 1–22. This blocks visual verification of anything in that region — row-height/column-width changes (`resize_rows`/`resize_columns`), cell formatting, etc. are not visible in a screenshot, and Playwright's accessibility snapshot doesn't expose per-cell grid geometry either (only the charts' own accessible text). When a test in that area needs precise confirmation, use `get_sheet_data(..., range=<affected range>, include_grid_data=True)` instead — the raw response includes `rowMetadata`/`columnMetadata` with each row/column's actual `pixelSize`, which is more precise than a screenshot anyway. Longer term, `add_chart` QA test cases should delete the chart they create at the end of each run (see `docs/qa/tests/sheets_charts.md`) so the fixture doesn't accumulate; that cleanup is not yet in place.
 
 ### Coordinating Playwright across parallel shards
 

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/docs/qa/tests/sheets_mgmt.md

@@ -642,6 +642,174 @@ Tests marked **⚠️ destructive** rename or delete sheets — reset fixtures a
 
 ---
 
+## `resize_rows` / `resize_columns`
+
+### TC-S73: Resize a single row to an explicit pixel height ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Set row 5 (0-based index 4) on the Sales sheet in {SPREADSHEET_ID} to 60 pixels tall"
+
+**Checks**
+- `updateDimensionProperties` request sent with `dimension: ROWS`, `startIndex: 4`, `endIndex: 5`
+- `properties.pixelSize: 60`, `fields: pixelSize`
+- Row 5 visibly taller in the Sheets UI
+
+**Result (2026-07-15) ✅ PASS** `resize_rows(spreadsheet_id, sheet="Sales", start_row=4, pixel_size=60)` → `{"replies":[{}]}`, no error. Playwright was skipped for this run — the shared fixture's Sales sheet currently has ~12 overlapping chart objects left over from other QA passes, which visually cover rows 1–22 and make row-height differences unreadable in a screenshot. Verified precisely instead via `get_sheet_data(..., range="A1:E6", include_grid_data=True)`, which returns `rowMetadata[].pixelSize` — confirmed row index 4 read back 60 immediately after this call (before being overwritten by TC-S74/TC-S75 below).
+
+---
+
+### TC-S74: Resize a range of rows ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Set rows 3 through 5 (0-based indices 2–4) on the Sales sheet in {SPREADSHEET_ID} to 40 pixels tall"
+
+**Checks**
+- `startIndex: 2`, `endIndex: 5` in the request (inclusive end_row=4 translated to exclusive 5)
+- All three rows resize in the UI
+
+**Result (2026-07-15) ✅ PASS** `resize_rows(spreadsheet_id, sheet="Sales", start_row=2, end_row=4, pixel_size=40)` → `{"replies":[{}]}`, no error. Confirmed via `get_sheet_data(..., range="A1:E6", include_grid_data=True)`: `rowMetadata` for row indices 2 and 3 both read back `pixelSize: 40` after the full test sequence (index 4 was subsequently auto-resized by TC-S75, as expected).
+
+---
+
+### TC-S75: Auto-resize rows to fit content ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Auto-fit the height of row 5 (0-based index 4) on the Sales sheet in {SPREADSHEET_ID} to its content"
+
+**Setup:** Row 5 previously set to an oversized pixel height (e.g. TC-S73).
+
+**Checks**
+- `autoResizeDimensions` request sent with `dimensions.dimension: ROWS`, `startIndex: 4`, `endIndex: 5`
+- Row 5 shrinks back to content-fit height in the Sheets UI
+
+**Result (2026-07-15) ✅ PASS** `resize_rows(spreadsheet_id, sheet="Sales", start_row=4, auto_resize=True)` → `{"replies":[{}]}`, no error. Confirmed via `get_sheet_data(..., range="A1:E6", include_grid_data=True)`: row index 4's `pixelSize` read back as `21` (Sheets' default/content-fit height for plain text), down from the `40` set by TC-S74 moments earlier — confirms `autoResizeDimensions` fired and took effect.
+
+---
+
+### TC-S76: Resize rows — neither pixel_size nor auto_resize given returns error
+
+**Prompt**
+> "Resize row 0 on the Sales sheet in {SPREADSHEET_ID} without specifying a size or auto-fit"
+
+**Checks**
+- Response contains `error` field
+- No `batchUpdate` call made
+
+**Result (2026-07-15) ✅ PASS** `resize_rows(spreadsheet_id, sheet="Sales", start_row=0)` → `{"error":"Specify pixel_size or set auto_resize=True"}`. Returned before any batchUpdate call.
+
+---
+
+### TC-S77: Resize rows — both pixel_size and auto_resize given returns error
+
+**Prompt**
+> "Resize row 0 on the Sales sheet in {SPREADSHEET_ID} to 50 pixels and also auto-fit it"
+
+**Checks**
+- Response contains `error` field
+- No `batchUpdate` call made
+
+**Result (2026-07-15) ✅ PASS** `resize_rows(spreadsheet_id, sheet="Sales", start_row=0, pixel_size=50, auto_resize=True)` → `{"error":"Specify only one of pixel_size or auto_resize"}`. Returned before any batchUpdate call.
+
+---
+
+### TC-S78: Resize rows — sheet not found returns error
+
+**Prompt**
+> "Set row 0 to 50 pixels tall on a sheet called 'NoSuchSheet' in {SPREADSHEET_ID}"
+
+**Checks**
+- Response contains `error` field
+
+**Result (2026-07-15) ✅ PASS** `resize_rows(spreadsheet_id, sheet="NoSuchSheet", start_row=0, pixel_size=50)` → `{"error":"Sheet 'NoSuchSheet' not found"}`.
+
+---
+
+### TC-S79: Resize a single column to an explicit pixel width ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Set column B (0-based index 1) on the Sales sheet in {SPREADSHEET_ID} to 200 pixels wide"
+
+**Checks**
+- `updateDimensionProperties` request sent with `dimension: COLUMNS`, `startIndex: 1`, `endIndex: 2`
+- `properties.pixelSize: 200`, `fields: pixelSize`
+- Column B visibly wider in the Sheets UI
+
+**Result (2026-07-15) ✅ PASS** `resize_columns(spreadsheet_id, sheet="Sales", start_column=1, pixel_size=200)` → `{"replies":[{}]}`, no error. Playwright skipped — see "Chart-covered grid" note in `docs/qa/run.md`. Verified via `get_sheet_data(..., range="A1:E6", include_grid_data=True)`: column index 1's `pixelSize` read back `200` immediately after this call (before being overwritten by TC-S81 below).
+
+---
+
+### TC-S80: Resize a range of columns ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Set columns C through E (0-based indices 2–4) on the Sales sheet in {SPREADSHEET_ID} to 50 pixels wide"
+
+**Checks**
+- `startIndex: 2`, `endIndex: 5` in the request
+- All columns in range resize in the UI
+
+**Result (2026-07-15) ✅ PASS** `resize_columns(spreadsheet_id, sheet="Sales", start_column=2, end_column=4, pixel_size=50)` → `{"replies":[{}]}`, no error. Confirmed via `get_sheet_data(..., range="A1:E6", include_grid_data=True)`: column indices 2, 3, and 4 all read back `pixelSize: 50`.
+
+---
+
+### TC-S81: Auto-resize columns to fit content ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Auto-fit the width of column B (0-based index 1) on the Sales sheet in {SPREADSHEET_ID} to its content"
+
+**Setup:** Column B previously set to an oversized pixel width (e.g. TC-S79).
+
+**Checks**
+- `autoResizeDimensions` request sent with `dimensions.dimension: COLUMNS`, `startIndex: 1`, `endIndex: 2`
+- Column B shrinks back to content-fit width in the Sheets UI
+
+**Result (2026-07-15) ✅ PASS** `resize_columns(spreadsheet_id, sheet="Sales", start_column=1, auto_resize=True)` → `{"replies":[{}]}`, no error. Confirmed via `get_sheet_data(..., range="A1:E6", include_grid_data=True)`: column index 1's `pixelSize` read back `28` (content-fit for the short numeric values in column B), down from the `200` set by TC-S79 — confirms `autoResizeDimensions` fired and took effect.
+
+---
+
+### TC-S82: Resize columns — neither pixel_size nor auto_resize given returns error
+
+**Prompt**
+> "Resize column 0 on the Sales sheet in {SPREADSHEET_ID} without specifying a size or auto-fit"
+
+**Checks**
+- Response contains `error` field
+- No `batchUpdate` call made
+
+**Result (2026-07-15) ✅ PASS** `resize_columns(spreadsheet_id, sheet="Sales", start_column=0)` → `{"error":"Specify pixel_size or set auto_resize=True"}`. Returned before any batchUpdate call.
+
+---
+
+### TC-S83: Resize columns — both pixel_size and auto_resize given returns error
+
+**Prompt**
+> "Resize column 0 on the Sales sheet in {SPREADSHEET_ID} to 100 pixels and also auto-fit it"
+
+**Checks**
+- Response contains `error` field
+- No `batchUpdate` call made
+
+**Result (2026-07-15) ✅ PASS** `resize_columns(spreadsheet_id, sheet="Sales", start_column=0, pixel_size=100, auto_resize=True)` → `{"error":"Specify only one of pixel_size or auto_resize"}`. Returned before any batchUpdate call.
+
+---
+
+### TC-S84: Resize columns — sheet not found returns error
+
+**Prompt**
+> "Set column 0 to 100 pixels wide on a sheet called 'NoSuchSheet' in {SPREADSHEET_ID}"
+
+**Checks**
+- Response contains `error` field
+
+**Result (2026-07-15) ✅ PASS** `resize_columns(spreadsheet_id, sheet="NoSuchSheet", start_column=0, pixel_size=100)` → `{"error":"Sheet 'NoSuchSheet' not found"}`.
+
+---
+
 ## `format_cells`
 
 ### TC-S33: Apply bold and background color to a range ⚠️ destructive
@@ -761,6 +929,99 @@ Tests marked **⚠️ destructive** rename or delete sheets — reset fixtures a
 
 ---
 
+## `update_borders`
+
+### TC-S85: Apply a solid border around all four edges of a range ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Add a black solid border around all four edges of A1:D5 on the Sales sheet"
+
+**Checks**
+- `updateBorders` request sent with `top`, `bottom`, `left`, `right` all `style="SOLID"`
+- `color` set to black on each edge
+- `range` covers A1:D5
+- No error in response
+
+**Result (2026-07-16) ✅ PASS (API-verified, not visual)** The Sales sheet's A1:D5 region is fully covered by the known stacked-chart fixture pollution (see `run.md`'s "Chart-covered grid" entry), so a screenshot can't show the border. Used `get_sheet_data(range="A1:D5", include_grid_data=True)` instead: perimeter cells (row 1 all columns = top; row 5 all columns = bottom; column A all rows = left; column D all rows = right) all show `{"style": "SOLID", "color": {}}` (empty color = black), exactly matching the request. No error in the batchUpdate response.
+
+---
+
+### TC-S86: Apply dashed inner gridlines inside a range ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Add dashed inner horizontal and vertical borders inside A1:C3 on the Sales sheet"
+
+**Checks**
+- `updateBorders` request includes `innerHorizontal` and `innerVertical`, both `style="DASHED"`
+- `top`/`bottom`/`left`/`right` are not set
+- No error in response
+
+**Result (2026-07-16) ✅ PASS (API-verified, not visual)** Same chart-coverage limitation as TC-S85 — verified via `get_sheet_data(range="A1:C3", include_grid_data=True)`. Interior cell edges between rows/columns show `DASHED`, while the pre-existing perimeter `SOLID` borders from TC-S85 (which this call's request did not include top/bottom/left/right keys for) were left completely untouched — confirming the tool only sends the edges it was given and doesn't clobber unspecified ones. No error in response.
+
+---
+
+### TC-S87: Clear an existing border edge with style NONE ⚠️ destructive
+
+**Prompt**
+**Playwright: required**
+> "Remove the border from the right edge of A1:D5 on the Sales sheet"
+
+**Checks**
+- `updateBorders` request includes `right.style="NONE"`
+- No error in response
+
+**Result (2026-07-16) ✅ PASS (API-verified, not visual)** Same chart-coverage limitation. Verified via `get_sheet_data(range="D1:D5", include_grid_data=True)`: the `right` border is absent from every cell in column D after the call, while `top`/`bottom` borders from TC-S85 remain — confirming only the targeted edge was cleared. No error in response.
+
+---
+
+### TC-S88: update_borders — no border params returns error
+
+**Checks (unit test)**
+- Calling `update_borders` with no edge params returns `{"error": ...}`
+- No batchUpdate API call made
+
+**Result (2026-07-16) ✅ PASS** `test_no_params_returns_error` passes.
+
+---
+
+### TC-S89: update_borders — border spec missing style returns error
+
+**Checks (unit test)**
+- An edge dict without a `"style"` key returns `{"error": ...}` before any API call
+
+**Result (2026-07-16) ✅ PASS** `test_missing_style_returns_error` passes.
+
+---
+
+### TC-S90: update_borders — invalid style value returns error
+
+**Checks (unit test)**
+- An unrecognized `style` value (e.g. `"SQUIGGLY"`) returns `{"error": ...}` listing valid styles, before any API call
+
+**Result (2026-07-16) ✅ PASS** `test_invalid_style_returns_error` passes.
+
+---
+
+### TC-S91: update_borders — sheet not found returns error
+
+**Checks (unit test)**
+- Sheet name not in spreadsheet → `{"error": "Sheet 'X' not found"}`
+
+**Result (2026-07-16) ✅ PASS** `test_returns_error_when_sheet_not_found` passes.
+
+---
+
+### TC-S92: update_borders — non-string style value returns error, does not crash
+
+**Checks (unit test)**
+- Calling `update_borders` with an edge dict whose `"style"` value is not a string (e.g. `top={"style": 5}` or `top={"style": None}`) returns `{"error": ...}`, same as the existing "invalid style" and "missing style" cases.
+
+**Result (2026-07-16) ✅ PASS — fix verified** Originally failed: validation only checked `"style" not in border` (key presence) before calling `.upper()`, so a non-string style (e.g. `top={"style": 5}`) reached `border["style"].upper()` and crashed with an unhandled `AttributeError` instead of a clean error. Fixed by adding `if not isinstance(border["style"], str): return {"error": ...}` before the `.upper()` call. Verified three ways: unit test `test_non_string_style_returns_error` passes (covers both `5` and `None`); confirmed live against the real `update_borders` MCP tool with `top={"style": 5}` and `top={"style": null}` — both return `{"error": "Border spec for 'top' has a non-string 'style' value"}` with no crash. TC-S92 closed.
+
+---
+
 ## `freeze`
 
 ### TC-S42: Freeze the header row ⚠️ destructive

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/docs/roadmap.md

@@ -105,7 +105,7 @@ No new tools. Stabilize on what Tier 1 shipped before starting Tier 2 feature wo
 **Sheets**
 - [ ] `update_borders` — border style, width, color on a range ([#122](https://github.com/khuisman/mcp-gee-sweet/issues/122)) _(freema/mcp-gsheets)_
 - [x] `hide_rows` / `hide_columns` / unhide — toggle row or column visibility ([#123](https://github.com/khuisman/mcp-gee-sweet/issues/123)) _(freema/mcp-gsheets)_ (PR #311)
-- [ ] `resize_rows` / `resize_columns` — set pixel height/width, or auto-fit to content ([#124](https://github.com/khuisman/mcp-gee-sweet/issues/124)) _(freema/mcp-gsheets)_
+- [x] `resize_rows` / `resize_columns` — set pixel height/width, or auto-fit to content (PR #321) ([#124](https://github.com/khuisman/mcp-gee-sweet/issues/124)) _(freema/mcp-gsheets)_
 - [ ] `add_data_validation` / `get_data_validation` — dropdowns, checkboxes, value constraints ([#125](https://github.com/khuisman/mcp-gee-sweet/issues/125)) _(freema/mcp-gsheets)_
 - [x] `update_sheet_properties` — tab color, hide/show gridlines (PR #301) ([#126](https://github.com/khuisman/mcp-gee-sweet/issues/126)) _(freema/mcp-gsheets)_
 - [x] `duplicate_sheet` — copy a sheet within the same spreadsheet (PR #286) ([#127](https://github.com/khuisman/mcp-gee-sweet/issues/127))
@@ -119,7 +119,7 @@ No new tools. Stabilize on what Tier 1 shipped before starting Tier 2 feature wo
 - [ ] `list_all_events` — query all subscribed calendars in parallel _(decision needed — also tracked in Decisions Needed)_ ([#194](https://github.com/khuisman/mcp-gee-sweet/issues/194))
 
 **Docs**
-- [ ] `insert_page_break` — explicit page break at an index ([#148](https://github.com/khuisman/mcp-gee-sweet/issues/148))
+- [x] `insert_page_break` — explicit page break at an index ([#148](https://github.com/khuisman/mcp-gee-sweet/issues/148)) (PR #314)
 - [x] `merge_table_cells` — merge cells in an existing table (distinct from write-time colspan) ([#150](https://github.com/khuisman/mcp-gee-sweet/issues/150)) (PR #310)
 - [ ] Comments API — list, add, resolve doc comments ([#151](https://github.com/khuisman/mcp-gee-sweet/issues/151))
 - [ ] `create_named_range` / `create_bookmark` — anchor points for internal links ([#152](https://github.com/khuisman/mcp-gee-sweet/issues/152))

{mcp_gee_sweet-0.8.2.dev45 → mcp_gee_sweet-0.8.2.dev51}/docs/tools.md

@@ -2,7 +2,7 @@
 
 <!-- Auto-generated by `scripts/gen_tool_docs.py` — do not edit by hand, your changes will be overwritten on the next commit. -->
 
-100 tools. All tool names are lowercase with underscores — use these exact strings with `ENABLED_TOOLS` or `--include-tools`.
+103 tools. All tool names are lowercase with underscores — use these exact strings with `ENABLED_TOOLS` or `--include-tools`.
 
 ## Sheets — data
 
@@ -38,7 +38,10 @@
 | `unhide_rows` | Unhide previously hidden rows in a sheet. | `spreadsheet_id`, `sheet`, `start_row`, `end_row?` |
 | `hide_columns` | Hide columns in a sheet from view. | `spreadsheet_id`, `sheet`, `start_column`, `end_column?` |
 | `unhide_columns` | Unhide previously hidden columns in a sheet. | `spreadsheet_id`, `sheet`, `start_column`, `end_column?` |
+| `resize_rows` | Set an explicit pixel height for rows, or auto-fit them to content. | `spreadsheet_id`, `sheet`, `start_row`, `end_row?`, `pixel_size?`, `auto_resize?` |
+| `resize_columns` | Set an explicit pixel width for columns, or auto-fit them to content. | `spreadsheet_id`, `sheet`, `start_column`, `end_column?`, `pixel_size?`, `auto_resize?` |
 | `format_cells` | Apply formatting to a cell range (background color, font, alignment, number format). | `spreadsheet_id`, `sheet`, `range`, `bold?`, `italic?`, `strikethrough?`, `font_size?`, `font_color?`, `background_color?`, `horizontal_alignment?`, `vertical_alignment?`, `number_format_type?`, `number_format_pattern?` |
+| `update_borders` | Apply or clear borders on the edges of a cell range. | `spreadsheet_id`, `sheet`, `range`, `top?`, `bottom?`, `left?`, `right?`, `inner_horizontal?`, `inner_vertical?` |
 | `merge_cells` | Merge a range of cells into one cell. | `spreadsheet_id`, `sheet`, `range`, `merge_type?` |
 | `unmerge_cells` | Unmerge all merged cells in a range. | `spreadsheet_id`, `sheet`, `range` |
 | `freeze` | Freeze rows and/or columns in a sheet. | `spreadsheet_id`, `sheet`, `rows?`, `columns?` |