mirror of
https://github.com/backnotprop/plannotator.git
synced 2026-09-14 14:17:26 +08:00
feat/opencode2-native-commands
5 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Michael Ramos
|
747b5ea7e6 |
fix(annotate): resolve natural-language arguments or hand off to the agent (#1183)
* fix(annotate): resolve natural-language arguments or hand off to the agent Claude Code skills run the CLI through a bash-substitution prefix that executes before the model sees anything, so any trailing natural language in /plannotator-annotate died with 'File not found: the'. Worse, a non-zero exit from that prefix aborts the whole prompt before the model runs (verified empirically), so the error was never even visible to the agent. Three-tier resolution in the binary's annotate argument handling, shared by every host via packages/shared/annotate-target.ts: 1. Fast path: probe each whitespace-delimited token; exactly one naming an existing file, URL, or folder proceeds with it directly. 2. Ambiguity: two or more tokens resolve; error naming every candidate, never guess. 3. Handoff: nothing resolves; emit an agent-addressed message echoing the words tried and asking the reading agent to interpret the request and re-run with a concrete target, preserving flags. In plain mode it lands on stdout with exit 0, the only combination that reaches the model through the bang prefix; in --json/--hook mode it goes to stderr with exit 1 so machine stdout stays clean. Single-token invocations run the unchanged pipeline first, so bare correct invocations are byte-identical. Strict gates (--require-approval or --result-file) bypass the tolerance entirely: a typo'd path stays a startup failure with exit 2 and no agent-facing prose. The CLI resolution pipeline moves to apps/hook/server/annotate-resolution.ts (returns typed outcomes instead of exiting) so the token fallback can run it once with a selected candidate; OpenCode and Pi wire the same shared selection into their own not-found paths. Skill bodies gain one line telling the agent to re-run with a concrete target when the command reports unresolvable arguments. Closes #1182 Reported-by: @technicalpickles * fix(annotate): harden tolerant resolution per review Review fixes for the three-tier annotate argument handling: - A single unresolvable token now falls through to the legacy pipeline verbatim: 'annotate nope.md' is exit 1 with 'File not found: nope.md' again in every non-strict mode, instead of an exit-0 handoff that fail-opened scripts gating on the exit code. The handoff fires only when two or more words resolve to nothing. - Unrecognized dash-prefixed tokens disable tolerance instead of being skipped, so a typo'd flag ('--no-jna') errors the way it did on base rather than silently fetching via Jina. Known flags are stripped before selection as before. - Token selection now receives the original argv tokens, so a quoted missing path ('my notes.md') is probed as one token and can never be re-split into a silently resolving 'notes.md'. - Bare directory names only count as fast-path candidates when they are the sole argument; a stray word matching a directory (or '.') hands off instead of opening folder mode. Explicit paths like 'src/' keep resolving, and the bare-existence probe fallback is file-only. - The handoff re-run suggestion echoes content flags only (--markdown, --no-jina, --render-html), never transport flags (--gate, --json, --hook). - New subprocess suite (annotate-cli.test.ts) spawns the real CLI entry and pins the contract: single-token typo exit 1, strict invocations (--require-approval and --result-file) exit 2 with empty stdout and no handoff prose, unknown-flag error, quoted-token preservation, and the directory-hijack case. Placeholder dist files are created when a build is absent so the suite runs in CI. - The copilot and gemini annotate command bodies gain the same handoff instruction as the Claude, core, and kiro skills. - AGENTS.md documents the three tiers under Annotate Flow and corrects the strict-section sentences that claimed non-strict behavior was fully unchanged; the marketing annotate doc mentions the tolerant arguments. Refs #1182 |
||
|
Raúl
|
9a450a69e7 |
feat(annotate): preserve notes on structured approval (#1092)
* feat(annotate): add strict atomic result output * feat(annotate): exit 2 for strict-gate usage and publication errors Adopt the grep convention for the strict annotate gate's exit codes: 0 = approved, 1 = negative human outcome (annotated/dismissed under --require-approval), 2 = the gate itself was misconfigured or could not start/deliver a decision. Previously all usage/startup/validation failures shared exit 1 with "reviewer did not approve", so callers could not tell a denied review from a broken gate. - parseStrictAnnotateOptions failures (bad flag combos, strict flags outside annotate --gate --json) now exit 2 - --result-file preflight failures (missing parent, pre-existing or dangling-symlink destination) now exit 2 - post-decision publication failures (destination raced into existence, hard links unavailable, stdout write failure) now exit 2: they deliver no decision record at all, so the code's own fail-closed handling presents them as environment errors, never as a reviewer outcome -- and never approval, since only 0 means approved - decision outcomes keep 0/1 exactly as before; signal deaths keep 128+n - document the contract in AGENTS.md and the annotate-gates guide Claude-Session: https://claude.ai/code/session_01YXkgsNucxDwAL4GdR4XYRk * feat(annotate): preserve notes on structured approval * test(pi): use exact annotate outcome import * fix(annotate): exit 2 for strict-gate startup failures The six startup-failure sites in the annotate path (missing path, unreachable URL, empty folder, ambiguous name, missing/unsupported file, oversized file) run after flag parsing and exited 1. Under --require-approval / --result-file, 1 is the "reviewer requested changes" signal, so a typo'd path made automation misclassify a configuration error as a legitimate rejection. Route those sites through exitAnnotateStartupFailure(), which picks its code from the already-parsed strict options via the new pure helper annotateStartupFailureExitCode(). Non-strict invocations still exit 1 with byte-identical stderr; strict invocations exit STRICT_GATE_ERROR_EXIT_CODE (2). Claude-Session: https://claude.ai/code/session_01H5KQWqXqjrPxyxUNso1QHS * fix(annotate): emit the strict decision on stdout before publishing it writeResultFile ran before the decision JSON reached stdout. On a filesystem without hard links (exFAT, FAT32, most SMB/NFS, some container bind mounts) publication fails deterministically, the catch exited 2 with nothing written anywhere — and the reviewer's autosaved draft had already been deleted by the feedback flow, so their completed decision was lost. Emit the stdout record first, then publish the result file. Exit semantics are unchanged: a publication failure still exits 2, but the decision has reached stdout by then. Only a stdout write failure now leaves no record at all. Correct the docs and comments that claimed exit 2 delivers no decision record: it means the result *file* was not published. Also document the two publication caveats: the 0600 mode is a no-op on Windows, and the atomic link/rename is not followed by a parent-directory fsync, so publication is atomic but not crash-durable. Claude-Session: https://claude.ai/code/session_01H5KQWqXqjrPxyxUNso1QHS * fix(annotate): parse linked docs with the render-side frontmatter rule on export buildCompleteAnnotateFeedback re-parsed each linked document with parseMarkdownToBlocks(entry.markdown) — no options, so frontmatter stripping defaulted on. The render side parses with { frontmatter: shouldStripFrontmatter(path) }. For plain-text linked docs (.yaml/.json/.toml/…) a leading `---` is real content, not frontmatter: a multi-document YAML opens with it. Stripping it on the export side shifted every block id, so ordinary Send Feedback and deny emitted wrong `(line N)` labels — or dropped them entirely when the annotation's block no longer existed. Pass the same shouldStripFrontmatter(filepath) option at the export call site so both sides agree. Claude-Session: https://claude.ai/code/session_01H5KQWqXqjrPxyxUNso1QHS * fix(annotate): carry the message scope through approve-with-notes /api/feedback forwards selectedMessageId and feedbackScope; /api/approve dropped them. Pi resolves the anchor message from those fields, so notes delivered on the approve path anchored to the last message instead of the one the reviewer picked in a multi-message annotate-last session — while Send Feedback in the same session anchored correctly. Forward both fields on the approve path in the Bun and Pi servers, and have the client build the approval body with the same scope resolution Send Feedback uses (extracted as getFeedbackMessageScope so the two can no longer drift). Claude-Session: https://claude.ai/code/session_01H5KQWqXqjrPxyxUNso1QHS * docs(annotate): tell agents an approval may carry notes The skill and slash-command files still described `"decision": "approved"` as "acknowledge and stop", with no mention of the feedback field the gate can now attach — so an agent reading them would silently drop the reviewer's approval notes. Update the Claude core/claude skills, the Copilot commands, the Gemini annotate command, and the annotate command reference so the approved branch names the optional feedback field and says what to do with it: carry it into subsequent work, do not treat it as a change request. Claude-Session: https://claude.ai/code/session_01H5KQWqXqjrPxyxUNso1QHS * docs(annotate): document the real approvedWithNotes default The default annotate.approvedWithNotes template is `{{contextBlock}}{{feedback}}`, not `{{context}}` on its own line, and {{contextBlock}} was missing from the variable table entirely. Show the actual default, add {{contextBlock}} to the variable table, and explain why the default prefers it: it collapses to nothing for message annotations instead of leaving a stray blank line. Claude-Session: https://claude.ai/code/session_01H5KQWqXqjrPxyxUNso1QHS --------- Co-authored-by: Michael Ramos <mdramos8@gmail.com> |
||
|
Kevin
|
0eda139cbe |
Add an option to disable AI features (#1129)
* feat: allow disabling Plannotator AI * fix: enforce disabled AI review endpoints * fix: fully disable AI review surfaces --------- Co-authored-by: Kevin <kcosrdev@gmail.com> |
||
|
Michael Ramos
|
d102c5f709 |
feat(annotate): add --gate, --json, and --silent-approve flags (#570)
Adds an opt-in review gate flow to annotation mode with three composable flags:
- `--gate`: 3-way UX (Approve / Send Annotations / Close)
- `--json`: structured decision output (`{"decision":"approved|annotated|dismissed"}`)
- `--silent-approve`: suppresses plaintext approve marker for naive hooks
Includes shared arg parser, @-reference handling, updated templates across all
harnesses (Claude Code, Copilot, Gemini, OpenCode, Pi), and full documentation.
Closes #570
For provenance purposes, this commit was AI assisted.
|
||
|
Michael Ramos
|
1800c24d80 |
feat(gemini): add Gemini CLI plan review integration
* feat(gemini): add Gemini CLI plan review integration Adds a new `apps/gemini-hook/` adapter that enables Plannotator plan review for Gemini CLI users via the BeforeTool hook system. The adapter reads the plan file from disk (Gemini provides a path, not inline content), delegates to the shared @plannotator/server for the browser-based review UI, and translates the decision back into Gemini's hook output format. Requires an upstream fix (google-gemini/gemini-cli#21802) that makes `decision = "allow"` user policies work for exit_plan_mode, allowing hooks to replace the built-in TUI approval dialog. Includes: - apps/gemini-hook/server/index.ts — stdin/stdout adapter - apps/gemini-hook/hooks/ — policy TOML + settings snippet - scripts/install.sh — Gemini binary download, policy install, settings config For provenance purposes, this commit was AI assisted. * refactor(gemini): use single binary with auto-detection instead of separate app Removes apps/gemini-hook/ — the plannotator binary now auto-detects Gemini CLI from stdin (plan_path = file on disk) vs Claude Code (plan = inline content) and branches input parsing + output formatting. Config fixtures live in apps/gemini/ (policy TOML + settings snippet). Install script gates on ~/.gemini existing so Claude-only users are unaffected. For provenance purposes, this commit was AI assisted. * test(gemini): add manual sandbox script for Gemini CLI integration Three modes: - --simulate: pipes BeforeTool JSON to hook, tests approve/deny output - (default): runs local patched Gemini build - --nightly: installs Gemini nightly and runs it Backs up and restores ~/.gemini config on exit. For provenance purposes, this commit was AI assisted. * feat(gemini): add slash commands, marketing tab, and docs for Gemini CLI - Add /plannotator-review and /plannotator-annotate slash commands (.toml) - Install Gemini slash commands in all three install scripts (sh, ps1, cmd) - Add Gemini tab to marketing landing page with icon - Add Gemini CLI to top-level README install section - Create apps/gemini/README.md with full setup and usage docs - Remove stale dev:gemini script and regenerate bun.lock For provenance purposes, this commit was AI assisted. * fix(gemini): merge hook into existing settings.json instead of printing instructions When ~/.gemini/settings.json already exists, use node to JSON-merge the BeforeTool hook config rather than asking the user to do it manually. Falls back to instructions only if node is unavailable. For provenance purposes, this commit was AI assisted. * fix(gemini): handle plan_filename rename and fix scoping bug Gemini CLI nightly renamed plan_path to plan_filename in exit_plan_mode. Accept both field names for forward/backward compatibility. Reconstruct full plan path from transcript_path + session_id + plans/ + filename. Also hoist planFilename variable out of try block so it's accessible in the deny output path (was causing ReferenceError). For provenance purposes, this commit was AI assisted. * fix(gemini): dim approve button when annotations exist for Gemini CLI Gemini's hook runner ignores systemMessage on the allow path, so approve-with-feedback is silently dropped — same limitation as Claude Code. Extend the existing UI gate to also apply for gemini-cli origin. For provenance purposes, this commit was AI assisted. * fix(gemini): add AGENT_CONFIG entry and fix sandbox simulate mode Register "gemini-cli" in AGENT_CONFIG so the UI shows "Gemini CLI" with proper badge styling instead of generic "Coding Agent" fallback. Update sandbox simulate mode to match production input format: use plan_filename instead of plan_path, include transcript_path, and simulate the Gemini directory structure for path reconstruction. For provenance purposes, this commit was AI assisted. |