Its description named core's `hermes auth spotify`; the pinned sha imports core's
plugins.spotify.client, which the Spotify core move removes. A known_issues line points
at the upstream fix (cruzlxyz/hermes-spotify-desktop#2) until the pin can move to it.
The entry declares itself derived from antigravity-subscription-directsdk and
antigravity-oauth, both listed. Its additions (live model discovery, quota
caching, a reset dock) run on the same agy transport, so under rule 16 they go
upstream rather than into a competing listing. Plain delist: no removed.yaml
entry, existing installs keep working. Author notified:
taylorwtf/hermes-antigravity-oauth-plus#1
Pin EaseIT-cz/vornik at cf817ad47d22 (CE release 2026.10.5), plugin 0.11.3.
Since 0.4.0 the plugin adds: forgetting reaches Vornik (/vornik-memory,
/vornik-forget), the Vornik approval transport (Hermes's own approval
prompts answered on the user's paired phone via the local vornikctl, opt-in
with hermes vornik approvals on), and fixes to both. The Disclosure line
covers the new behaviour.
Re-pins LetsFG to 437b91d. The bundled skill and README named three
tools the hosted server has since renamed, and described a booking
approval flow the server no longer has. The banner is the new LetsFG
logo.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
0.4.3 (66a6efcc) -> 0.5.1 (a7303c89, main). The adopted range is
66a6efc..a7303c8:
#8 f936bfe _busy() no longer reads a bare .git/REBASE_HEAD as a rebase in
progress. On git 2.55 a finished `rebase --continue` leaves that
file behind on a clean tree and `rebase --abort`/`--quit` will
not remove it, so the worktree stayed busy for good and the hook
skipped its whole fetch/commit path for it.
#2 280c57c A direct push the remote refuses on policy grounds (branch
protection, a PR-required ruleset, GH013/GH006) no longer
strands a commit: the hook drops only its own unpushed commit,
leaves the edit staged and dirty, stops committing on that
branch and reports it once, instead of re-pushing and re-logging
the same remote error every pass.
#4 a7303c8 A dead cwd fails open instead of refusing the tool call.
capabilities: unchanged -- the same four hooks (pre_tool_call,
post_tool_call, post_llm_call, on_session_end), no tools, no middleware, no
env vars.
description: adds the refusal clause to the existing disclosure -- a branch
whose direct push the remote refuses on policy grounds is never committed to
again, and the edit stays staged and dirty.
Re-pins to 7be60e3, which stops calling the retired managed_uv shim and
reads security.allow_lazy_installs through hermes_cli.config, failing
closed when it is unset, false, malformed or unreadable.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Bumps the entry from 1.3.3 (9cb3c37) to 1.4.2 (0009d8e). The range this pin adopts, in
the plugin repository:
- 0009d8e chore(release): 1.4.2 — two rendering defects, one cause each
- 2d04c2d fix(ui): centre the initials in the profile avatar instead of the line box
- 8b0046a chore(docs): retire the stale refactoring snapshot and the demo's spike artifacts
- 2d70971 fix(tree): key a row by its position, not by its task
- 4ce51a6 chore(release): 1.4.1 — a moved attachment keeps naming a file
- 86a9eb1 fix(move): the target owns the moved attachments' paths
- e1a5258 refactor(shots): the capture flag draws a card, so call it one
- 01b4dac chore(docs): drop the exploratory illustrations the drawn card replaced
- 9cdd7f7 chore(release): 1.4.0 — the tree column, the list view, and the catalogue card
- 1bbe3e7 docs(shots): draw the catalogue card from a script, next to the stills
- da6a70e docs(shots): capture the folded tree and the list view, and stop inheriting the shell's state
- 983b4db feat(view): optional list view beside the timeline (NousResearch#7)
- 409bb43 fix(move): the target assigns the moved rows' own ids (NousResearch#9)
- a849304 fix(bulk): batch assign actually stores; show the assignee on every row (NousResearch#6)
- 427eb1b feat(tree): a collapsible explorer tree in the task column (NousResearch#8)
- baf02f6 feat(detail): move a task to another board from the drawer action menu
- 7b4e1e0 chore(release): 1.3.4 — the websocket gate fails closed, and a finished parent is allowed
- 33213d7 fix(ws): fail closed when the auth gate raises
- fa101a6 fix(reparent): a finished task can take a parent again
Above 4ce51a6, which this PR carried when it was reviewed:
- 86a9eb1 answers the review: a moved attachment kept the source board's absolute
stored_path, which the move's own cleanup then deleted, so it downloaded nothing.
The target now rewrites the path to its own attachments root with the task's new id,
drops rows whose blob is already missing, and the pre-cleanup verification checks each
moved attachment resolves to a file. tests/move_integration.py asserts it — and
tests/run_tests.sh now RUNS that script, which nothing did before.
- 2d70971 + 2d04c2d are two rendering defects found while testing on a real board: rows
were keyed by task id, so a multi-parent task (which legitimately owns several rows)
handed React duplicate keys and folded-away rows were never unmounted; and the profile
initials were off-centre because `text-[8px]` is absent from the desktop's precompiled
stylesheet and a line box was being centred instead of the cap-height ink.
- 8b0046a removes the stale refactoring snapshot and the demo board's own spike artifacts.
Also in this entry:
- `image:` gains a 2:1 banner (1280x640, the shape the other entries use), drawn by
`scripts/card.py` and pinned to this commit like the screenshots.
- a third screenshot: the List view, next to the two that were already there.
- the disclosure names the cross-board move. It writes to another board (the copy is
verified there first) and then deletes the source rows and their links, so a reviewer
should read it as a write, not a read.
Checked before pushing: `hermes plugins validate` passes at this commit (12 checks,
including `security scan — safe` and `desktop surface`), the entry parses, the sha is
40 hex, and all four image URLs answer 200 at the pinned commit. Suite green: 69 node
tests, 11 ESM render checks, 45 pytest, plus the move integration run.
