Skip to content

Commit a0232d4

Browse files
author
SymbolStar
committed
Merge remote-tracking branch 'origin/main' into fix/73542-message-sending-internal-hook
# Conflicts: # src/infra/outbound/deliver.test.ts
2 parents 18e0269 + a002c41 commit a0232d4

10,846 files changed

Lines changed: 822338 additions & 369351 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎.agents/maintainer-notes/telegram.md‎

Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
# Telegram Maintainer Decisions
2+
3+
Use this page during Telegram PR review. These are intentional maintainer decisions, not incidental implementation details.
4+
5+
Verified against Telegram Bot API 10.0, May 8 2026.
6+
7+
## Streaming
8+
9+
- Do not reintroduce `sendMessageDraft` for answer streaming. Telegram drafts are ephemeral 30-second previews in private chats; final delivery still requires a separate `sendMessage`. OpenClaw uses `sendMessage` plus `editMessageText`, then finalizes in place so the user sees one persistent answer.
10+
- Streaming owns one visible preview message. Edit it forward. Do not send an extra final bubble unless the final edit genuinely failed.
11+
- Keep the first-preview debounce. If a provider sends token-sized deltas, coalesce them into cumulative preview text instead of removing the debounce.
12+
- Respect Telegram limits in the Telegram layer. Text over 4096 chars chains into continuation messages. Polls keep the current Bot API 12-option cap.
13+
14+
## Telegram API Ownership
15+
16+
- Prefer grammY primitives and Telegram-native helpers when they model the behavior directly. Avoid custom Bot API wrappers for behavior grammY already owns.
17+
- Throttling is bot-token scoped. All Telegram API clients for the same token share one grammY `apiThrottler()` instance.
18+
- Do not silently retry failed topic sends without topic metadata. A wrong-surface success is worse than a loud Telegram error.
19+
- DM topics and forum topics are distinct. `direct_messages_topic_id` and `message_thread_id` are not interchangeable.
20+
21+
## Context And Authorization
22+
23+
- Reply context comes from OpenClaw-observed messages. Bot API updates expose `reply_to_message`, but there is no arbitrary `getMessage(chat, id)` hydration path later.
24+
- Current local chat context must outrank stale reply ancestry in the prompt. Old replied-to messages should not look like the active conversation.
25+
- Pairing is DM-only. Group and topic authorization need explicit config allowlists.
26+
- Telegram allowlists use numeric sender IDs. Usernames are optional, mutable, and not a reliable arbitrary-user lookup key in the Bot API.
27+
- Group and channel visible replies are policy-controlled. Normal room replies stay private unless `messages.groupChat.visibleReplies: "automatic"` is set or the agent explicitly calls `message.send`.
28+
29+
## Interactive Surfaces
30+
31+
- Native callbacks stay structured. Approval, native command, plugin, select, and multiselect callbacks must not fall through as raw callback text.
32+
- Preserve callback values exactly, including delimiters such as `env|prod`.
33+
- Native slash commands should remain fast-pathable before full workspace and agent-turn setup.
34+
35+
## Review Standard
36+
37+
Telegram behavior PRs need real Telegram proof when they touch transport, streaming, topics, callbacks, authorization, or reply context. Prefer the bot-to-bot QA lane or an equivalent live Telegram probe over synthetic-only validation.

‎.agents/skills/autoreview/SKILL.md‎

Lines changed: 145 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,145 @@
1+
---
2+
name: autoreview
3+
description: "Autoreview closeout: local dirty changes, PR branch vs main, parallel tests."
4+
---
5+
6+
# Autoreview
7+
8+
Run Codex's built-in code review as a closeout check. This is code review (`codex review`), not Guardian `auto_review` approval routing.
9+
10+
Codex native review mode performs best and is recommended. Non-Codex reviewers are fallback/second-opinion paths that receive a generated diff prompt, not the full Codex review-mode runtime.
11+
12+
Use when:
13+
- user asks for Codex review / autoreview / second-model review
14+
- after non-trivial code edits, before final/commit/ship
15+
- reviewing a local branch or PR branch after fixes
16+
17+
## Contract
18+
19+
- Treat review output as advisory. Never blindly apply it.
20+
- Verify every finding by reading the real code path and adjacent files.
21+
- Read dependency docs/source/types when the finding depends on external behavior.
22+
- Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase.
23+
- Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class.
24+
- Keep going until the selected review path returns no accepted/actionable findings.
25+
- If a review-triggered fix changes code, rerun focused tests and rerun the review helper.
26+
- Default to Codex review. If Codex is unavailable or exits with an error, the helper falls back to the first configured CLI from `claude -p`, `pi -p`, `opencode run`, `droid exec`, or `copilot`. Prefer Codex for final closeout because it uses native review mode; non-Codex reviewers use a Codex-inspired generated diff prompt. The helper runs nested Codex review in yolo/full-access mode by default; use `--no-yolo` only when intentionally testing sandbox behavior.
27+
- Stop as soon as the review command/helper exits 0 with no accepted/actionable findings. Do not run an extra direct `codex review` just to get a nicer "clean" line, a second opinion, or clearer closeout wording.
28+
- Treat the helper's successful exit plus absence of actionable findings as the clean review result, even if the underlying Codex CLI output is terse.
29+
- If rejecting a finding as intentional/not worth fixing, add a brief inline code comment only when it explains a real invariant or ownership decision that future reviewers should know.
30+
- Do not push just to review. Push only when the user requested push/ship/PR update.
31+
- For OpenClaw maintainers, keep autoreview validation Crabbox/Testbox-aware when maintainer validation mode is enabled (`OPENCLAW_TESTBOX=1` or `AUTOREVIEW_OPENCLAW_MAINTAINER_VALIDATION=1`). A review pass may inspect files and run cheap non-Node probes, but it must not start local `pnpm`, Vitest, `tsgo`, `npm test`, or `node scripts/run-vitest.mjs` from a Codex/worktree review unless the operator explicitly requested local proof. For runtime proof, use existing evidence or route through Crabbox/Testbox and report the id. Do not apply this rule to ordinary contributors who do not have maintainer Testbox access.
32+
33+
## Pick Target
34+
35+
Dirty local work:
36+
37+
```bash
38+
codex review --uncommitted
39+
```
40+
41+
Use this only when the patch is actually unstaged/staged/untracked in the
42+
current checkout. For committed, pushed, or PR work, point Codex at the commit
43+
or branch diff instead; do not force `--mode local` / `--uncommitted` just
44+
because the helper docs mention dirty work first. A clean `--uncommitted` review
45+
only proves there is no local patch.
46+
47+
Branch/PR work:
48+
49+
```bash
50+
git fetch origin
51+
codex review --base origin/main
52+
```
53+
54+
Do not pass any prompt with `--base`. Some Codex CLI versions reject both inline
55+
and stdin prompt forms, including the helper's `codex review --base <ref> -`,
56+
with `--base <BRANCH> cannot be used with [PROMPT]`. If the helper hits this
57+
error, run plain `codex review --base <ref>` and report that the helper prompt
58+
injection was skipped.
59+
60+
If an open PR exists, use its actual base:
61+
62+
```bash
63+
base=$(gh pr view --json baseRefName --jq .baseRefName)
64+
codex review --base "origin/$base"
65+
```
66+
67+
Committed single change:
68+
69+
```bash
70+
codex review --commit HEAD
71+
```
72+
73+
or with the helper:
74+
75+
```bash
76+
.agents/skills/autoreview/scripts/autoreview --mode commit --commit HEAD
77+
```
78+
79+
Use commit review for already-landed or already-pushed work on `main`. Reviewing
80+
clean `main` against `origin/main` is usually an empty diff after push. For a
81+
small stack, review each commit explicitly or review the branch before merging
82+
with `--base`.
83+
84+
## Parallel Closeout
85+
86+
Format first if formatting can change line locations. Then it is OK to run tests and review in parallel:
87+
88+
```bash
89+
.agents/skills/autoreview/scripts/autoreview --parallel-tests "<focused test command>"
90+
```
91+
92+
Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain. Once that rerun exits cleanly, stop; do not spend another long review cycle on redundant confirmation.
93+
94+
## Context Efficiency
95+
96+
Codex review is usually noisy. Default to a subagent filter when subagents are available. Ask it to run the review and return only:
97+
- actionable findings it accepts
98+
- findings it rejects, with one-line reason
99+
- exact files/tests to rerun
100+
101+
Run inline only for tiny changes or when subagents are unavailable.
102+
103+
## Helper
104+
105+
Bundled helper:
106+
107+
```bash
108+
.agents/skills/autoreview/scripts/autoreview --help
109+
```
110+
111+
The helper:
112+
- chooses dirty `--uncommitted` first
113+
- otherwise uses current PR base if `gh pr view` works
114+
- otherwise uses `origin/main` for non-main branches
115+
- auto-runs `PNPM_CONFIG_PM_ON_FAIL=ignore PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN=false PNPM_CONFIG_OFFLINE=true pnpm run check` in parallel when a repo has `package.json`, `pnpm-lock.yaml`, `node_modules`, and a `check` script; disable with `AUTOREVIEW_AUTO_TESTS=0`
116+
- use `--mode commit --commit <ref>` for already-committed work, especially clean `main` after landing
117+
- should be left in `--mode auto` or forced to `--mode branch` for PR/branch work; do not force `--mode local` after committing
118+
- supports `--reviewer codex|claude|pi|opencode|droid|copilot|auto`; `auto` means Codex first
119+
- supports `--fallback-reviewer auto|claude|pi|opencode|droid|copilot|none`; default is configured CLI fallback
120+
- falls back only when Codex is unavailable or exits nonzero, not when Codex reports findings
121+
- writes only to stdout unless `--output` or `AUTOREVIEW_OUTPUT` is set
122+
- supports `--dry-run`, `--parallel-tests`, and commit refs
123+
- runs nested review with `--dangerously-bypass-approvals-and-sandbox --sandbox danger-full-access` by default
124+
- injects maintainer-only OpenClaw validation policy into native Codex review when `OPENCLAW_TESTBOX=1` or `AUTOREVIEW_OPENCLAW_MAINTAINER_VALIDATION=1`, so local memory-heavy Node/Vitest checks are avoided in favor of Crabbox/Testbox proof
125+
- branch mode may fail on Codex CLI versions that reject `--base` plus the helper's stdin prompt; on that exact parser error, rerun plain `codex review --base <ref>` instead of falling back to a non-Codex reviewer
126+
- keeps accepting `--full-access`; use `--no-yolo` or `AUTOREVIEW_YOLO=0` to opt out
127+
- still accepts legacy `CODEX_REVIEW_*` env vars when the matching `AUTOREVIEW_*` var is unset
128+
- prints `autoreview clean: no accepted/actionable findings reported` when the selected review command exits 0
129+
130+
## Final Report
131+
132+
Include:
133+
- review command used
134+
- tests/proof run
135+
- findings accepted/rejected, briefly why
136+
- the clean review result from the final helper/review run, or why a remaining finding was consciously rejected
137+
138+
Do not run another Codex review solely to improve the final report wording. If the final helper run exited 0 and produced no accepted/actionable findings, report that exact run as clean.
139+
140+
## PR / CI Closeout
141+
142+
- Prefer direct run/job APIs after CI starts: `gh run view <run-id> --json jobs`; use PR rollup only for final mergeability.
143+
- After rebase, compare `origin/main..HEAD`; drop CI-fix commits already upstream before pushing.
144+
- For prompt snapshot CI failures, prove/generate with Linux Node 24 before rerunning the failed job.
145+
- Update PR body once near the final head unless proof labels are missing or stale enough to block CI.

0 commit comments

Comments
 (0)