* fix(opencode): show the session URL on OpenCode 2's native command path
On OpenCode 2 a remote session's URL was invisible. runNativeCommand builds
its bridge client with createV2BridgeClient, which deliberately has no tui
domain, so toastPlannotatorUrl optional-chained to a no-op; both URL delivery
paths (the CLI stderr forwarder and the ready-file poller) route through it.
The V2 client's app.log is console.error, and OpenCode discards a server
plugin's stderr under both default launch modes (packages/cli/src/services/
standalone.ts uses stderr: "ignore" unless OPENCODE_PRINT_LOGS=1). Remote mode
also suppresses the browser, so /plannotator-review showed the user nothing at
all and presented as a hang.
Deliver the URL as a visible transcript notice instead. createSessionUrlNotifier
duck-types ctx.session.synthetic and exposes it to cli-bridge as notifyUrl, a
seam toastPlannotatorUrl prefers over the toast when present; OpenCode 1 clients
carry no notifyUrl and keep their real toast unchanged. The notice is posted
with resume: false, which upstream skips the wake for, so nothing starts a model
turn, and it carries the URL in both text and description because the TUI drops
a synthetic row whose description is empty and renders the description rather
than the text. Everything is guarded: a host without session.synthetic, or a
call with no session, gets no notifier and falls back to today's log-only
behavior, and a rejecting synthetic is caught and leaves the URL retryable by
the other delivery path.
The README's remedy line claimed remote sessions should read the URL from the
OpenCode log, which was never true; it now describes the transcript notice and
names OPENCODE_PRINT_LOGS=1 for older hosts.
Also fixes two bugs in the OpenCode 2 native-command smoke:
- scripts/opencode2-native-commands-smoke.sh looked for a node_modules/.bin/
opencode binary. @opencode-ai/cli publishes opencode2 on every dist-tag, so
the script failed before it started a server. It now tries both names and
reports which it looked for.
- The command-ownership check read /api/command once, immediately after
activation, racing the reclaim schedule whose last tick lands about 15.5s
later. Under PLANNOTATOR_SMOKE_EXPECT_NATIVE=1 that reported a shadowing bug
the reclaim had simply not reached yet. It now polls to a 30s deadline
(PLANNOTATOR_SMOKE_COMMAND_TIMEOUT_MS), still only after /api/plugin reports
the plugin loaded.
AI-assisted (Claude) under maintainer direction.
* fix(opencode): deliver the session URL on OpenCode 2's plan review path too
The first commit fixed only the native command path. The plan path builds its
own client (createV2Client, typed as { app: { agents, log } } with no notifier),
so a remote OpenCode 2 user who reached a review through submit_plan still never
saw the URL: no browser is opened for them and the plugin's console output is
discarded by the host.
The plan path now builds the same bridge client the command path uses, with
toolContext.sessionID, so it carries notifyUrl whenever the host exposes
session.synthetic. That covers both runtimes: the CLI runtime already prefers
notifyUrl inside toastPlannotatorUrl, and the embedded runtime's previously
empty logReady hook is now createPlanReadyNotifier.
That hook still does not log. app.log is console.error, the same stderr
handleServerReady already printed the URL to, so logging there would duplicate
the line in remote mode and add a stray one locally, which is why the hook was
empty. The transcript notice is a different surface, and it is the only one a
remote reviewer can see. Without session.synthetic the hook stays silent exactly
as before.
createV2Client is gone: it duplicated the bridge client's URL-deduped app.log
verbatim, and nothing else used it.
Three tests on the plan path (delivers the notice; stays silent and does not
re-log without synthetic; catches a rejecting notice) plus one that pins the two
wiring seams at source level, since the notifier tests all pass while the plan
path is wired to nothing, which is the shape the bug had.
Also from review: console.error is stubbed across the V2 URL delivery block, so
those tests no longer print URL lines into the suite output. The README bullet
now says the notice covers every way a session opens rather than slash commands
alone.
AI-assisted (Claude) under maintainer direction.
* feat(opencode): restore the slash commands on OpenCode 2
OpenCode's V2 plugin API gained native command execution upstream
(anomalyco/opencode issue #2185, PR #44765): ctx.command.transform lets a
plugin add a command whose execute callback fully owns the invocation. That
shape currently ships on the beta and dev dist-tags of @opencode-ai/plugin
while next and latest still carry the older context, so the capability is
duck-typed at runtime and never imported. On a host that exposes it the V2
adapter registers /plannotator-review, /plannotator-annotate and
/plannotator-last and runs the same handleCliCommand machinery OpenCode 1
uses, passing the raw argument tail straight through to the CLI. On a host
without it nothing new is registered and behavior is byte-identical to before.
Also wires ctx.session.switchAgent (same API generation, same probe) so an
agent switch chosen in the review UI is applied instead of only warned about,
and accepts both agent.list() response shapes: the HTTP client types it as a
{ location, data } envelope while the in-process plugin domain answers with a
bare array, where reading .data threw and silently emptied the agent list.
The shared command stubs get model-mediated fallback bodies for OpenCode 2
hosts on the stale channels. They carry no shell interpolation on purpose:
OpenCode 1 evaluates a template's !`...` before the V1 plugin's
command.execute.before hook can clear the parts, so a bang template there
would launch a second Plannotator session on every OC1 invocation. A source
level test pins that.
AI-assisted (Claude) under maintainer direction.
* fix(opencode): probe the command draft and reclaim the names from the stubs
Review found the capability probe was wrong in the direction that matters.
ctx.command.transform exists on pre-#44765 hosts too: our own pinned
@opencode-ai/plugin@0.0.0-next-16775 declares CommandDraft as
{ list, get, update, remove } with no add. The probe therefore returned true on
next and latest, draft.add was undefined, and because transforms are stored and
replayed the TypeError landed in the batched reload flush and aborted it before
commit, plausibly taking every command registration on the host down with it.
Capability is now read from the draft handed to the callback, which is the only
witness, and the registration call is wrapped so no transform rejection can fail
plugin setup.
The stubs also shadowed the native definitions on new hosts. Command definitions
land in a name-keyed map where add is Map.set, transforms replay in registration
order, and OpenCode's own ConfigCommandPlugin activates in the post group after
package plugins while scanning the exact directory the installer writes the
three stubs to. A setup-time registration is therefore always overwritten on a
normal install. The plugin now re-registers the same transform once activation
settles, so its definitions are last in the replay order, and calls
ctx.command.reload() explicitly because a late registration only adds its reload
to the already-flushed boot batch. Ownership is read back from
ctx.command.list() by description, which is why the native descriptions and the
stub frontmatter are deliberately distinct. If the reclaim cannot run the stubs
keep the names and the commands still work through their fallback bodies.
Also: a failing switchAgent no longer costs the reviewer their feedback on the
command path, feedback is delivered as "queue" rather than replaying the
invocation's admission mode minutes later when a steer would land mid-turn, and
the agent-list comment no longer asserts a bare-array response that could not be
reproduced upstream (accepting both shapes is still right, since reading .data
blindly throws into a catch that degrades silently).
Tests: the real old-host draft shape registers nothing and throws nothing, the
shadowing contest is modelled against upstream's replay semantics, the OpenCode 1
parts-clearing invariant is pinned for all three commands in both plan-agent and
manual mode now that the stubs carry real instructions, and the V2 smoke asserts
the plugin did not activate as failed and that all three commands resolve. The
smoke now also installs the stubs into its sandbox config dir so the contest
actually happens there. scripts/opencode2-native-commands-smoke.sh runs the same
smoke against a dev-channel build with native commands required; CI cannot,
because it pins a next build.
AI-assisted (Claude) under maintainer direction.
* fix(opencode): keep the reclaim ticking and stop an unbuilt checkout failing setup
The reclaim ended the loop when the draft-probe flag read false, but that flag
only flips when the transform replays, which under boot batching is the flush
after every plugin has loaded. Plannotator loads before the post-group config
plugins, so the first tick legitimately reads false and the loop exited for
good: the reclaim was inert in exactly the shape production has. The tick is
skipped now instead, with a test that flips the flag between ticks.
The V1 entry called resolveBundledHtmlPath synchronously during plugin
construction, outside the .catch that was there to absorb a missing asset, so an
unbuilt checkout threw out of construction before any code path that needs the
HTML. The Test workflow runs bun test with no build step, so the new OpenCode 1
interception tests failed there. Both preloads are guarded; the lazy getters
still raise a clear error if something actually needs the file.
The smoke's failed-plugin guard read entry.state.status, but Plugin.Info carries
status and error at the top level, so a failed activation slipped through.
Reads the top level first and keeps the nested one as a fallback.
Comment corrections: State.batch clears its active flag before flushing, so a
late transform registration materializes on its own; the explicit reload() is
redundant-but-defensive rather than required. The reclaim schedule is a list of
deltas the loop awaits in turn, so the ticks land near 0.3s, 1.5s, 5.5s and
15.5s, not at the raw numbers.
AI-assisted (Claude) under maintainer direction.
Two agent command-surface cleanups. Both remove only the command entry points; all underlying infrastructure stays.
1. /plannotator-status (Pi): removed — it echoed phase/plan-file/progress on
demand, but that state is already shown ambiently (status bar + live
checklist widget). The phase/checklist state machine is untouched.
2. /plannotator-archive (all agents): removed the command/skill entry points
across every surface — Claude/Codex/Kiro skills, Pi, OpenCode (handler +
dispatch + cli-bridge + embedded + stub), Droid, the Kiro agent prompt, all
three installers, docs, marketing, and the CI deprecated-command guard. The
installers also gained a stale-skill cleanup so upgraders drop a previously
installed plannotator-archive skill.
Kept (infrastructure) — archive browsing stays available in-review via the
sidebar: the `plannotator archive` CLI subcommand (apps/hook/server), the
mode:"archive" server path + /api/archive endpoints, ArchiveBrowser/useArchive,
the sidebar Archive tab, sessions.ts "archive" mode, and ~/.plannotator/plans
storage.
Verified: bun test scripts/install.test.ts → 72 pass; pi-extension typecheck +
build:opencode pass; repo-wide residual scan clean; KEEP-set integrity
confirmed; one orphaned import (opencode commands.ts) caught in self-review and
removed.
Registers submit_plan tool and slash commands without modifying prompts
or agent permissions. Fills the gap between manual (commands only) and
plan-agent (full automation) for users who want to manage prompts and
permissions themselves.
* Wire PLANNOTATOR_PASTE_URL through opencode/pi servers and Landing demo link
OpenCode plugin only read PLANNOTATOR_SHARE_URL; add a getPasteApiUrl helper
and thread it into plan/annotate/archive server starts. Pi extension's
serverReview gains the same shareBaseUrl/pasteApiUrl env-var pair already
used by serverPlan/serverAnnotate. Landing.tsx now accepts a shareBaseUrl
prop for self-hosters' demo link. Paste-service CORS defaults grow a
comment clarifying that self-hosters must override ALLOWED_ORIGINS.
* Embed custom paste origin in short URL fragment
When PLANNOTATOR_PASTE_URL is set to a non-default paste service, the
generated short link now includes a base64url-encoded paste param in the
fragment (#key=...&paste=...). The share portal and importFromShareUrl
extract it on load so they can fetch from the right paste backend without
needing a server — fixing broken short links for self-hosters who use a
custom paste service but keep the hosted share portal.
Backward compatible: links without a paste param continue to use the
default or server-provided paste API URL as before.
For provenance purposes, this commit was AI assisted.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* docs: add /plannotator-last to READMEs and marketing docs
* feat: add /plannotator-last to install scripts
* fix: sync review command wording in install scripts with plugin
The plugin's plannotator-review.md was updated in #293 to handle
LGTM approvals but the install scripts still had the old wording.
* feat: add Plan Diff marketing dialog, Pi origin support, and docs
- Add PlanDiffMarketing first-run dialog announcing the Plan Diff feature
with per-origin video demo URLs (Claude Code, OpenCode, Pi)
- Add 'pi' as a first-class origin with display name and violet badge
- Add Plan Diff blog post (plan-diff-see-what-changed.md)
- Add brief Plan Diff mentions across READMEs and marketing docs
* polish: tighten blog post copy and reduce em dash usage
* fix: move PlanDiffMarketing to plan-diff/ and fix stale useEffect deps
* add plan diff preview screenshot for marketing dialog
Add PLANNOTATOR_SHARE_URL env var so users can point share links at
their own self-hosted portal instance instead of share.plannotator.ai.
Threads the base URL through the same path as sharingEnabled: env var →
server options → API response → editor state → useSharing hook →
generateShareUrl(). Includes self-hosting guide and documentation.
Closes#12
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Add Windows PowerShell install script (install.ps1)
- Install slash commands for both Claude Code and OpenCode
- Update OpenCode README with install script instructions
- Simplify UpdateBanner to use same install command for both platforms
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Allow users to specify which browser opens plan files via environment variable.
Default behavior unchanged - only activates when env var is set.
- macOS: Set to app name ("Google Chrome") or path
- Linux/Windows: Set to executable path
Closes#42
Users need to clear both ~/.cache/opencode and ~/.bun/install/cache
for a complete reset when stuck on old versions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Refactor: shared server package with PLANNOTATOR_REMOTE env var
- Create packages/server/ with shared server implementation
- Add PLANNOTATOR_REMOTE=1 env var for devcontainer/SSH mode
- Deprecate SSH_CONNECTION detection (still works with warning)
- Both Claude Code and OpenCode now use identical server logic
- OpenCode gains Obsidian/Bear integrations and remote detection
- Update documentation with environment variables section
Fixes#27🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Remove PLANNOTATOR_ORIGIN env var, fix onReady callback timing
- Remove PLANNOTATOR_ORIGIN hack from Claude Code hook (hardcode "claude-code")
- Fix onReady callback to pass port directly (was referencing undefined server)
- Create tests/manual/test-server.ts for testing either origin
- Update test-hook-2.sh to use new test server with opencode origin
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add devcontainer test setup, reduce logging verbosity
- Add tests/devcontainer/ with devcontainer.json for testing remote mode
- Add tests/opencode-local/ for local OpenCode testing
- Update package.json build script for proper bundling
- Remove verbose multi-line error messages, keep useful errors
- Clean up unused deprecationWarned variable
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add devcontainer support and documentation
- Add PLANNOTATOR_REMOTE env var for container/remote detection
- Remove console logging (silent operation)
- Add devcontainer.md with full setup instructions
- Add devcontainer section to OpenCode plugin README
- Add port-only test setup to reproduce common misconfiguration
- Update test devcontainers to forward port 4096 for opencode web
- Bump version to 0.4.1
Fixes#27🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Update CLAUDE.md: legacy SSH detection, not deprecated
Removed incorrect mention of deprecation warning - SSH_TTY/SSH_CONNECTION
detection is silent by design.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix OpenCode agent switching after plan approval
After approving a plan, the conversation context stayed in "plan" mode
even though the TUI showed "build". This caused edits to fail because
the plan agent has edit permissions denied.
The fix uses session.prompt() to inject a message with agent: "build",
which triggers a new agentic loop with proper build agent permissions.
Fixes#29🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Users may be stuck on old plugin versions due to OpenCode's caching.
Added note to both READMEs with the rm command to clear the cache.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add Obsidian integration for auto-saving approved plans
- Auto-detect Obsidian vaults from system config
- Settings UI with vault dropdown and folder config
- Save plans with YAML frontmatter (created, source, tags)
- Extract tags heuristically from H1 title and code fence languages
- Human-readable filenames: "Title - Jan 2, 2026 2-30pm.md"
- Cross-platform support (macOS, Windows, Linux)
- Add local test script for hook simulation
* Add backlinks and improve filename generation
- Add [[Plannotator Plans]] backlink to saved notes for graph connectivity
- Extract title from H1 for human-readable filenames
- Format: "Title - Jan 2, 2026 2-30pm.md"
- Add bulk test script for ~/.claude/plans
- Add fix script to add backlinks to existing vault files
* Add Obsidian integration docs to README, landing page, and plugins
- Root README: Quick note about Obsidian support after video table
- apps/hook README: Detailed setup and example file format
- apps/opencode-plugin README: Feature list and setup instructions
- Landing page: New "Save to Obsidian" feature card
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add Obsidian Integration section to README
* Screenshot Obsidian settings
Added an implementation plan section for user authentication.
* Update README with Obsidian auto-save feature
Added information about auto-saving approved plans to Obsidian.
* Update README with Obsidian integration link
Added link to details about Obsidian integration.
* Update README to include Obsidian auto-saving feature
Clarified the new feature for saving to Obsidian with a link.
---------
Michael Ramos