opencode-reviewer 2.0.0 → 2.0.1

package/README.md

@@ -14,9 +14,8 @@ This plugin is meant to enable you to run sessions with less frequent input in a
 
 ![](./assets/recording.gif)
 
-Targets OpenCode V2 on Linux. Host version numbers do not gate plugin activation;
-the companion protocol and actual scoped API contracts govern review and approval.
-Verified host checks are recorded in the maintainer migration plan.
+For OpenCode V2 on Linux. The plugin checks the server companion's protocol and
+each request's data and scope rather than allowing only specific host versions.
 
 ## Install and config
 
@@ -30,7 +29,7 @@ There is no project-local CLI configuration. OpenCode loads the
   "$schema": "https://opencode.ai/v2/cli.json",
   "plugins": [
     {
-      "package": "opencode-reviewer@2.0.0",
+      "package": "opencode-reviewer@2.0.1",
       "options": {
         "baseURL": "https://openrouter.ai/api/v1",
         "model": "your-model",
@@ -89,7 +88,7 @@ only in this server configuration, not in `cli.json`:
 ```json
 {
   "$schema": "https://opencode.ai/config.json",
-  "plugins": ["opencode-reviewer@2.0.0"],
+  "plugins": ["opencode-reviewer@2.0.1"],
   "permissions": [
     { "action": "shell", "resource": "*", "effect": "ask" },
     { "action": "edit", "resource": "*", "effect": "ask" },
@@ -99,7 +98,7 @@ only in this server configuration, not in `cli.json`:
 }
 ```
 
-Merge these entries with your existing configuration. Rules are ordered; the last
+Merge these entries with your existing configuration. Rules are ordered and the last
 matching rule wins. Reviews run only when OpenCode asks for permission. Existing
 `allow` rules and native autoaccept skip review. See OpenCode's
 [server config](https://opencode.ai/v2/docs/config),
@@ -109,7 +108,7 @@ matching rule wins. Reviews run only when OpenCode asks for permission. Existing
 ## Options reference
 
 These are options inside the plugin's `options` object in global `cli.json`.
-Defaults apply only to omitted options; `null` is invalid. Boolean and integer
+Defaults apply only to omitted options. `null` is invalid. Boolean and integer
 options require JSON booleans and numbers, not quoted strings. Integer ranges are
 inclusive, fractions are invalid, and the maximum safe integer is
 9,007,199,254,740,991. Unknown option names are rejected.
@@ -156,47 +155,49 @@ The sidebar shows Safe, Unsafe, or Analysis unavailable. Explanations support
 Markdown and scrolling. If the sidebar is hidden, use OpenCode's Show sidebar
 command.
 
-The reviewer side panel appears only in the top-level conversation. Browsing its
-subagents, including nested subagents, hides the panel and prevents both normal
-and fast automatic approvals. Reviews may finish while hidden. A Safe report that
-has never started a normal countdown may first become eligible after returning to
-the root and receiving real presentation proof, with a fresh countdown. Leaving
-the root after a countdown starts permanently makes that request manual for the
-running controller, even after returning or disabling/re-enabling review.
-
-Automatic approval requires mouse tracking for the host's painted-panel ownership
-checks. With mouse tracking disabled, reports remain available for manual review.
-The plugin never enables mouse tracking. It preserves sidebar visibility except
-after an explicit approval-notification click, when a root frame confirms the
-sidebar is absent before revealing it.
-
-The category switches are retained, but the current V2 collectors do not support
-skill, MCP or custom-tool reviews. Missing mandatory skill instructions and unproven
-MCP/custom origin or catalog evidence leave these requests manual, not Safe.
-
-Native Code Mode and its tool search remain enabled. Exactly linked native calls
-can be reviewed; ambiguously linked nested calls remain manual. The plugin assumes
-installed plugins preserve native tool meanings, do not replace or alias native
-executors, and do not rewrite commands after evidence capture.
-
-Subagent requests carry the genuine latest root-user prompt. Exact immediate
-delegation is currently unavailable through the supported V2 evidence path and is
-factually omitted, not guessed from older tasks, sibling requests or queued follow-ups.
-Optional context omissions do not alone prevent review when mandatory operation
-evidence is verified. Context cannot override the review contract.
+The reviewer panel appears only in the main conversation. Opening any subagent,
+including a nested one, hides the panel and prevents normal and fast auto-approval.
+Reviews may still finish while hidden. If a Safe report has never started a normal
+countdown, returning to the main conversation can start a fresh one once the host
+confirms the panel is visible. Leaving after a countdown starts cancels auto-approval
+for that request for the rest of that plugin run. Returning or disabling and
+re-enabling review won't restart it.
+
+Auto-approval requires mouse tracking so the host can check that the panel is
+visible and receives clicks. With mouse tracking off, you can still read reports
+and approve requests manually. The plugin doesn't enable mouse tracking or reveal
+a hidden sidebar unless you click an approval notification; it checks that the
+sidebar is absent from the main conversation before showing it.
+
+The skill, MCP and custom-tool options are still present, but these reviews aren't
+supported in V2. The reviewer can't get the required skill instructions or verify
+the source and catalog information for MCP and custom tools. Those requests need
+manual approval; they aren't rated Safe.
+
+Code Mode and its tool search stay enabled. Native tool calls can be reviewed when
+the reviewer can match them exactly to their permission requests. Nested calls
+without an exact match need manual approval. This assumes other installed plugins don't change
+what native tools do, replace or alias their executors, or rewrite commands after
+the reviewer has captured them.
+
+Subagent reviews include the latest user prompt from the main conversation. The
+V2 evidence collector can't get the exact task passed to the requesting subagent,
+so it leaves that out rather than guessing from older tasks, sibling requests or
+queued follow-ups. Missing optional context doesn't prevent review if the required
+operation evidence is verified. Context can't override the review rules.
 
 With streaming enabled, Evaluating and its spinner disappear when a rating arrives.
-The rating remains provisional until the full response is validated. A retry
-clears the preview and restores the loading indicator. Normal auto-approval
-starts only after the full response is validated and rendered on the top-level
-conversation, with matching physical presentation proof.
-
-With `autoApprove: true` and `fastMode: true`, a parsed Safe rating approves the
-current eligible permission immediately, without a countdown or waiting for the
-rest of a streamed report. It still requires native front-of-queue ownership and
-physical presentation on the top-level conversation. Subagent browsing, explicit
-sidebar hiding, covering dialogs and report history prevent fast approval. Without
-streaming, fast mode waits for the full validated response and then skips the countdown.
+The rating is provisional until the full response passes validation. A retry
+clears the preview and brings back the loading indicator. Normal auto-approval
+waits for the full validated report and for the host to confirm that it's displayed
+in the main conversation.
+
+With `autoApprove: true` and `fastMode: true`, a parsed Safe rating can approve the
+request before the streamed report finishes, without a countdown. The request must
+be first in OpenCode's permission queue, and the host must confirm the panel is
+visible in the main conversation. Browsing a subagent, hiding the sidebar or
+covering it with a dialog or report history prevents fast approval. Without
+streaming, fast mode waits for the full validated response, then skips the countdown.
 
 After confirmed fast approval, the live panel shows **Auto-approved; finishing
 report…** and stays ahead of newer requests until its report finishes. Hiding the
@@ -219,13 +220,15 @@ limits and overall timeout still apply. Retried requests can incur additional
 provider charges, and unreported usage remains unknown.
 
 During an auto-approval countdown, click the countdown to allow once immediately,
-or Cancel to leave the request manual. Hiding or covering the panel also cancels
-that request's countdown, except for this plugin's physically proven report-history
-cover on the root route. Browsing any subagent or switching conversations cancels it.
-Returning, remounting or re-enabling cannot revive a canceled request. An uncertain
-approval write also remains manual and is never retried.
+or Cancel to leave the request manual. Hiding or covering the panel cancels the
+countdown too, except when this plugin's report history is displayed in the main
+conversation and passes the host's visibility checks. Browsing any subagent or
+switching conversations cancels it. Returning, reopening the panel or re-enabling
+review won't restart a canceled countdown. If the plugin can't confirm the result
+of an approval attempt, it leaves the request manual and never retries that attempt.
 Cancel before using native Allow always or rejection
 forms; those forms alone do not stop the countdown.
+Cancel remains available during native preparation, until the approval is sent.
 Positive countdowns add a 200 ms initial grace and then update on remaining-time
 boundaries. A zero-second setting still approves without that grace.
 
@@ -234,9 +237,9 @@ descendants. The setting is saved for resume. Both commands are also in the comm
 palette. Disabling stops unapproved reviews and countdowns while native permission
 controls remain available. Already-approved fast-mode reports finish in the background.
 
-After a server reconnect or companion replacement, the old controller stops reviews
-and automatic replies until the plugin is reloaded or OpenCode is restarted. It does
-not mix old permission caches with a new connection.
+If the server reconnects or the companion is replaced, reviews and auto-approval
+stop. Reload the plugin or restart OpenCode to resume. This keeps cached permissions
+from the old connection separate from the new one.
 
 ### Report history
 
@@ -247,6 +250,8 @@ PageUp/PageDown scroll. Close or Escape closes history. Repeating the command
 returns to the newest report. History remains available with review disabled or
 invalid reviewer configuration. The history command preserves a hidden sidebar;
 clicking an approval notification reveals it and selects that permission's live or saved report.
+Keyboard browsing also works with mouse tracking off; that does not grant
+automatic-approval history cover.
 
 Each entry shows the original report, available usage, model, provider and outcome:
 **Auto approved**, **Manually approved**, **Cancelled**, or **Rejected**. Cancelled
@@ -256,20 +261,27 @@ native Allow once replies whose submitting client cannot be identified. History
 keeps the latest completed report, which can differ from the report that caused
 approval in another window.
 
-Normal-mode history cover preserves an ongoing countdown only on
-the root route, with physical proof of the history heading/footer and rendered
-report. A newly completed Safe review may become eligible under that same proof.
-Native dialogs, including the command palette, still cancel an active countdown;
-opening history afterward cannot restart it. Fast mode has no history-cover
-exception. Browsing saved reports never approves a request or replays notifications.
-
-Reports are saved only after a qualifying permission resolution. Saved reports
-can contain private text and are retained in OpenCode's local state directory
-unless deletion ownership is proven. A conversation deletion does not authorize
-purging reports without proven server/scope ownership. Uncertain offline deletions
-retain history; a missing list entry or bare 404 is not enough. Windows using the
-same state directory share this history, partitioned by host directory and root
-conversation. Uncommitted reports can be lost on shutdown or prolonged storage failure.
+In normal mode, opening report history can leave a countdown running in the main
+conversation. The host must confirm that the history heading and footer are visible
+and the review report is rendered. A newly completed Safe review can become eligible
+for a countdown under the same checks. OpenCode dialogs, including the command palette, still cancel an
+active countdown; opening history afterward won't restart it. History blocks fast
+approval. Browsing saved reports doesn't itself approve requests or replay notifications.
+
+Reports are saved only after a permission resolution that qualifies for history.
+They can contain private text and are kept under OpenCode's local state base:
+`$XDG_STATE_HOME`, or `~/.local/state` when unset. Safely accessible history stays
+under `opencode/opencode-reviewer/`. If the host directory is unsuitable for private
+storage, the plugin uses its private, plugin-owned sibling
+`opencode-reviewer-state/opencode-reviewer/` without changing host-directory permissions.
+An existing safe sibling database remains in use across restarts. Conversation
+enable/disable settings stay in the original OpenCode state directory.
+The plugin deletes them only when it can verify that a deleted conversation belongs
+to the matching server and scope. If that can't be verified after an offline
+deletion, it keeps the history; a missing list entry or bare 404 isn't enough.
+Windows using the same state directory share history, grouped by host directory
+and main conversation. Reports not yet saved can be lost on shutdown or during a
+prolonged storage failure.
 
 ### Usage totals
 
@@ -432,7 +444,8 @@ Use Node.js 24.15.0+ within 24.x, or 22.22.2+ within 22.x, and npm.
 Run `npm ci --ignore-scripts`, then `npm run check` for typechecking, source tests,
 pure-helper tests and the build. `npm run test:helpers` runs the helper checks
 without building or starting OpenCode. Pull-request CI checks both Node versions
-and runs a separate representative Linux OpenCode 2.0.26 fixture profile.
+and runs a separate representative Linux fixture profile on stock OpenCode
+2.0.26 and 2.0.27.
 After building, run `node scripts/test-runtime.mjs --profile ci` for that same
 profile. Use `node scripts/test-runtime.mjs --list` for the complete runtime
 inventory or `node scripts/test-runtime.mjs --plan --profile ci` for a

package/THIRD_PARTY_NOTICES.md

@@ -31,8 +31,10 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 https://github.com/anomalyco/opencode/tree/v2.0.26/packages/theme
 
-The pinned theme helper is bundled in the terminal payload. Solid and OpenTUI
-remain host-provided external dependencies.
+The pinned theme syntax helper is bundled unchanged in the terminal payload.
+A build-time adapter replaces its public barrel with a syntax-only re-export;
+unused theme parsers, schemas and their Effect dependency are not bundled.
+Solid and OpenTUI remain host-provided external dependencies.
 
 License source: https://github.com/anomalyco/opencode/blob/v2.0.26/LICENSE