Matrix image messages used lowercase `[image: ...]` format instead of
the canonical `[IMAGE:...]` marker used by all other channels (Telegram,
Slack, Discord, QQ, LinQ). This caused Matrix image attachments to
bypass the multimodal vision pipeline which looks for `[IMAGE:...]`.
Closes#3486
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace unsafe byte-index string slicing (`&text[..N]`) with
char-boundary-safe alternatives in memory consolidation and security
redaction to prevent panics when multi-byte UTF-8 characters (e.g.
Chinese/Japanese/Korean) span the slice boundary.
Fixes the same class of bug as the prior fix in `execute_one_tool`
(commit 8fcbb6eb), applied to two remaining instances:
- `src/memory/consolidation.rs`: truncation at byte 4000 and 200
- `src/security/mod.rs`: `redact()` prefix at byte 4
Adds regression tests with CJK input for both locations.
Closes#3533
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CLI `cron add` command always routed the second positional argument
through shell security policy validation, which blocked natural language
prompts like "Check server health: disk space, memory, CPU load". This
adds an `--agent` flag to `cron add`, `cron add-at`, `cron add-every`,
and `cron once` so that natural language prompts are correctly stored as
agent jobs without shell command validation.
Closes#3563
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The http_request tool unconditionally blocked all private/LAN hosts with
no opt-out, preventing legitimate use cases like calling a local Home
Assistant instance or internal APIs. This adds an `allow_private_hosts`
config flag (default: false) under `[http_request]` that, when set to
true, skips the private-host SSRF check while still enforcing the domain
allowlist.
Closes#3568
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Comprehensive long-running context upgrades:
- Token-based compaction: replace message-count trigger with token
estimation (~4 chars/token). Compaction fires when estimated tokens
exceed max_context_tokens (default 32K) OR message count exceeds
max_history_messages. Cuts at user-turn boundaries only.
- Persistent sessions: JSONL append-only session files per channel
sender in {workspace}/sessions/. Sessions survive daemon restarts.
Hydrates in-memory history from disk on startup.
- LLM-driven memory consolidation: two-phase extraction after each
conversation turn. Phase 1 writes a timestamped history entry (Daily).
Phase 2 extracts new facts/preferences to Core memory (if any).
Replaces raw message auto-save with semantic extraction.
- New config fields: agent.max_context_tokens (32000),
channels_config.session_persistence (true).
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Upgrade heartbeat system with 4 key improvements:
- Two-phase heartbeat: Phase 1 asks LLM "skip or run?" to save API cost
on quiet periods. Phase 2 executes only selected tasks.
- Structured task format: `- [priority|status] task text` with
high/medium/low priority and active/paused/completed status.
- Decision intelligence: LLM-driven smart filtering via structured prompt
at temperature 0.0 for deterministic decisions.
- Delivery routing: auto-detect best configured channel when no explicit
target is set (telegram > discord > slack > mattermost).
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Validates the aarch64-linux-android release artifact: download, archive
integrity, ELF format, architecture, checksum, and install.sh detection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The auto-generated What's New and Recent Contributors README sections
have been removed, so the sync-readme workflow and its backing script
are no longer needed.
When the crate was renamed from `zeroclaw` to `zeroclawlabs`, users who
installed via install.sh (which uses `cargo install --path`) had the
binary tracked under the old package name. Later running
`cargo install zeroclawlabs` from crates.io fails with:
error: binary `zeroclaw` already exists as part of `zeroclaw v0.1.9`
The installer now detects and removes stale tracking for the old
`zeroclaw` package name before installing, so both install.sh and
`cargo install zeroclawlabs` work cleanly for upgrades.
The tweet was firing on `release: published` immediately when the GitHub
Release was created, but Docker push, crates.io publish, and website
redeploy were still in-flight. This meant users saw the tweet before
they could actually pull the new Docker image or install from crates.io.
Convert tweet-release.yml and sync-readme.yml to reusable workflows
(workflow_call) and call them as the final jobs in both release
pipelines, gated on completion of docker, crates-io, and
redeploy-website jobs.
Before: gh release create → tweet fires immediately (race condition)
After: gh release create → docker + crates + website → tweet + readme
Add prebuilt binary support for Termux/Android devices:
- Add aarch64-linux-android to stable and beta release matrices with NDK setup
- Detect Termux in install.sh and map to the correct android target
- Add Termux pkg manager support for system dependency installation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove references to --interactive, --security-level, and --onboard
flags that no longer exist in the CLI. Update examples to use current
supported flags.
Closes#3484
Probe /dev/stdin readability before selecting it, and add /proc/self/fd/0
as a fallback for constrained containers where /dev/stdin is inaccessible.
Closes#3482
Add SignalChannel import and match arm in deliver_announcement() so
cron jobs with delivery.channel = "signal" are handled instead of
rejected as unsupported.
Closes#3476
* fix: resolve web dashboard 404 on static assets and SPA fallback
Strip leading slash from asset paths after prefix removal so rust-embed
can find the files. Return 503 with a helpful build hint when index.html
is missing instead of a generic 404.
Closes#3508
* fix: return concrete Response type to fix match arm type mismatch
* feat(channels): add comprehensive channel matrix tests and bump to v0.2.2
Add 50 integration tests covering the full Channel trait contract across
all 16 platforms: identity semantics, threading, draft lifecycle, reactions,
pinning, concurrency, edge cases, and cross-channel routing. Bump version
to 0.2.2.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* style: fix rustfmt formatting in channel matrix tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(lint): remove empty line after doc comment in channel matrix tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(ci): auto-sync README What's New and Contributors on release
Replace hardcoded What's New (v0.1.9b) and Recent Contributors sections
with marker-based auto-sync powered by a new GitHub Actions workflow.
The sync-readme workflow runs on each release and updates both sections
from git history.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(ci): auto-sync What's New and Contributors across all 31 READMEs
Add marker comments to all 30 translated README files and update the
sync script to process all README*.md files on each release. Fix regex
to handle empty markers on first run.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When multiple tool calls execute in a single turn, each tool result was
emitted as a separate role="user" message. Anthropic's API rejects
adjacent messages with the same role, and newer models like
claude-sonnet-4-6 respond with 500 Internal Server Error instead of a
descriptive 400.
Merge consecutive same-role messages in convert_messages() so that
multiple tool_result blocks are combined into one user message, and
consecutive user/assistant messages are also properly coalesced.
Fixes#3493
Multi-platform Docker builds (linux/amd64 + linux/arm64) with fat LTO
and codegen-units=1 consistently exceed 30 minutes. Bump to 60m.
Also skip crates.io publish when the version already exists (the
auto-sync workflow may have published it before the stable release
runs).
Nextcloud Talk bot webhooks send event type "Create" for new chat
messages, but the parser only accepted "message". This caused all
valid messages to be skipped with "skipping non-message event: Create".
Accept both "message" and "Create" as valid event types.
Closes#3491
Uses GitHub Actions cache with SHA-256 hash of tweet content. If the
exact same tweet text was already posted in a previous run, the tweet
is skipped with a warning. Works for both auto-release and manual
dispatch tweets.
Three-layer dedup:
1. feat() commit check — skip if no new features since last release
2. Content hash — skip if identical tweet already posted (cache hit)
3. Beta-to-beta diff — only new features since previous release tag
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The 280-char truncation was blindly chopping the tweet text, cutting
off the GitHub release URL. Now we extract the URL first, truncate
only the body text to fit (accounting for X's 23-char t.co counting),
then re-append the full URL so it always renders correctly.
GITHUB_TOKEN lacks permission to create tags, causing 'Published
releases must have a valid tag' errors. Use RELEASE_TOKEN (same PAT
the beta workflow uses successfully).
Triggers on push to master when Cargo.toml changes. Detects version
bumps by comparing current vs previous commit, checks crates.io to
avoid duplicate publishes, then publishes automatically.
New fast inference providers:
- Cerebras, SambaNova, Hyperbolic
New model hosting platforms:
- DeepInfra, Hugging Face, AI21 Labs, Reka, Baseten, Nscale,
Anyscale, Nebius AI Studio, Friendli AI, Lepton AI
New Chinese AI providers:
- Stepfun, Baichuan, 01.AI (Yi), Tencent Hunyuan
Also fixed missing list_providers() entries for Telnyx and Azure OpenAI.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
