Commit Graph

1601 Commits

Author SHA1 Message Date
gabi-simons
d86051805b feat(setup): delete scratch agent after ping-pong, simplify flow
The "Terminal Agent" created for the connection test is now silently
deleted after a successful ping. If the user chooses to chat, a new
agent is auto-created as "{name}'s Terminal" — no name prompt needed.
Condensed the three-line ping section into a single "Connection verified."
status line.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-29 14:10:53 +00:00
gavrielc
5f34e26240 fix(credentials): translate auth errors and require OneCLI for spawn
Two related fixes for the case where credentials aren't usable:

1. Replace Claude Code's "Not logged in / Invalid API key · Please run
   /login" output with a host-aware message. The user can't run /login
   from chat, so the raw text is unhelpful. Provider gains an optional
   isAuthRequired() classifier; the poll-loop substitutes the message
   on both result-text and error paths.

2. Treat OneCLI gateway failure as a transient hard error instead of
   spawning a credential-less container. The catch in container-runner
   now propagates; router and host-sweep wrap wakeContainer to log and
   leave the inbound row pending so the next 60s sweep tick retries.
   Router also stops the typing indicator on failure.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-29 17:02:15 +03:00
Gabi Simons
5dd15c0014 Merge branch 'main' into feat/channel-approval-flow 2026-04-29 16:34:31 +03:00
Gabi Simons
db19837740 feat(permissions): richer channel-approval flow with agent selection and free-text naming
Replace the hardcoded Approve/Ignore card with a multi-step flow:
- Single agent: "Connect to [name]" / "Connect new agent" / "Reject"
- Multiple agents: "Choose existing agent" (follow-up list) / "Connect new agent" / "Reject"
- "Connect new agent" prompts for a free-text name via DM, creates immediately on reply
- Add setMessageInterceptor router hook for capturing free-text replies
- Add resolveChannelName optional method to ChannelAdapter interface

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-29 13:34:10 +00:00
gavrielc
9e45845000 Merge pull request #2104 from alipgoldberg/setup-assistant-green
feat(setup): paint "assistant" green in the agent-name prompt
2026-04-29 15:36:26 +03:00
gavrielc
9a919f4148 Merge branch 'main' into setup-assistant-green 2026-04-29 15:36:14 +03:00
exe.dev user
4608836953 feat(setup): paint "assistant" green in the agent-name prompt
Wraps the word "assistant" in `accentGreen` (#3fba50, added in #2103)
across the six channel adapters that ask "What should your assistant
be called?" — Discord, iMessage, Signal, Slack, Telegram, WhatsApp.
Mirrors the green emphasis on "you" in the display-name prompt: the
green word names the subject of the question (assistant vs operator)
so the operator parses it at a glance.
2026-04-29 12:32:25 +00:00
gavrielc
1bf903a64d Merge pull request #2103 from alipgoldberg/setup-pronoun-green
feat(setup): paint "you" green in the display-name prompt
2026-04-29 15:25:12 +03:00
gavrielc
0044bba0e5 Merge branch 'main' into setup-pronoun-green 2026-04-29 15:25:02 +03:00
exe.dev user
26594d2c54 feat(setup): paint "you" green in the display-name prompt
Adds an `accentGreen` helper (#3fba50) with the same TTY/NO_COLOR/
truecolor gating as the rest of the palette, then wraps the word
"you" in the "What should your assistant call you?" prompt so the
operator parses at a glance who the question is about — the user,
not the assistant. The mirror prompt that asks for the assistant's
name ("What should your assistant be called?") is left for a
follow-up.
2026-04-29 12:16:15 +00:00
gavrielc
01131521ff Merge pull request #2102 from alipgoldberg/setup-color-choices
feat(setup): cyan highlight on active and submitted choices
2026-04-29 15:07:56 +03:00
gavrielc
3742165708 Merge branch 'main' into setup-color-choices 2026-04-29 15:07:00 +03:00
exe.dev user
4c791a41b2 feat(setup): cyan highlight on active and submitted choices
Customize `brightSelect`'s render function so the focused option's
label paints in brand cyan during selection and the submitted answer
paints in dim cyan after the user moves on. Inactive options keep
their default rendering — only the cursor and submitted state pick
up the color, matching the body-text emphasis added in #2101.

Also migrate the one remaining `p.select` call site (the "What next?"
prompt after the first chat) to `brightSelect` so every menu in the
setup flow goes through the same render path. The shape of the call
matches what `brightSelect` already supports — message + options
with value/label/hint — so no feature is lost in the swap.

Reuses `brandBody` from #2101 for the cyan, so the prompt highlight
and the body prose share one definition of the brand body color.
2026-04-29 12:01:35 +00:00
gavrielc
6ef147bc89 Merge pull request #2101 from alipgoldberg/setup-color-body
feat(setup): paint card and log bodies in brand cyan
2026-04-29 14:58:27 +03:00
gavrielc
7d153df710 Merge branch 'main' into setup-color-body 2026-04-29 14:58:02 +03:00
exe.dev user
ab2d509671 feat(setup): paint card and log bodies in brand cyan
Adds a `brandBody` helper in setup/lib/theme.ts that wraps prose in
brand cyan (#2BB7CE), with the same TTY/NO_COLOR/truecolor gating used
by `brand`/`brandBold`/`brandChip`. The helper splits multi-line input
and colors each line independently so the SGR sequence doesn't bleed
across clack's gutter prefix.

Routing:
  - `note()` (the un-dim card wrapper from #2095) now passes
    `brandBody` as its `format` callback, so card bodies render
    cyan line-by-line.
  - Every prose `p.log.{message,info,success,step,warn}` call in the
    setup flow wraps its body argument in `brandBody`. Calls whose
    body is explicitly `k.dim(...)` (failure transcript tails, log
    paths, claude-assist response previews) are left alone — those
    are the "preview/debug" cases the dim-policy comment in
    theme.ts already carves out.
  - Spinner-finish lines in windowed-runner / claude-assist color
    only the message portion; the `(5s)` elapsed suffix stays dim.

Brand cyan accents (chips, wordmark, inline emphasis) are unchanged.
This PR only adds the body color.

A follow-up will add OSC 11 dark/light detection so light-mode
terminals get a brand blue (#2b6fdc) variant — opt-in upgrade with
no regression for the dark-mode default.
2026-04-29 11:43:30 +00:00
gavrielc
57a959028d Merge pull request #2098 from Koshkoshinsk/setup-token-headless
fix claude setup-token flow for headless/remote systems
2026-04-29 14:02:53 +03:00
gavrielc
9f564650c6 Merge branch 'main' into setup-token-headless 2026-04-29 14:02:45 +03:00
gavrielc
2acd71731a Merge pull request #2094 from qwibitai/fix/setup-reuse-existing-env
Detect existing .env and credentials on setup re-run
2026-04-29 14:01:03 +03:00
Daniel M
b7f099db96 Merge branch 'main' into setup-token-headless 2026-04-29 13:59:24 +03:00
gavrielc
c8e960314a Merge remote-tracking branch 'upstream/main' into fix/setup-reuse-existing-env
# Conflicts:
#	setup/channels/imessage.ts
#	setup/channels/telegram.ts
2026-04-29 13:58:21 +03:00
gavrielc
ec3aa0f139 Merge pull request #2096 from qwibitai/fix/password-clear-on-error
Clear password field after validation error
2026-04-29 13:54:36 +03:00
Gabi Simons
d4868a5e01 Merge branch 'main' into fix/password-clear-on-error 2026-04-29 13:35:48 +03:00
Gabi Simons
a014a67556 fix password fields not clearing after validation error
When pasting an invalid token, the old value stayed in the input
field. Pasting a new token appended to the old one instead of
replacing it, causing repeated validation failures.

Add clearOnError: true to all 8 password prompts across setup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-29 10:34:58 +00:00
gavrielc
e0f813603e Merge pull request #2095 from alipgoldberg/setup-undim-cards
fix(setup): stop dimming card bodies in setup flow
2026-04-29 13:29:06 +03:00
Gabi Simons
aa390b3fd0 detect existing .env and credentials on setup re-run
When re-running setup on a machine that already has a .env with
channel tokens or OneCLI config, detect them early and offer to
reuse instead of prompting the user to paste everything again.

- Add detectExistingEnv() to parse .env and group known keys
- Add detectExistingDisplayName() to read display name from v2.db
- Defer display name prompt until actually needed (cli-agent or channel)
- Skip cli-agent and first-chat when groups are already wired
- Add token reuse checks to Telegram, Discord, Slack, Teams, iMessage

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-29 10:20:54 +00:00
exe.dev user
9c8f680ca8 fix: stop dimming setup card bodies
Clack's `p.note` defaults to `format: e => styleText("dim", e)`, which
fades note bodies regardless of the project's stated readability stance
(see comment on `dimWrap` in setup/lib/theme.ts: "prose renders at the
terminal's regular weight"). The dim styling makes body copy hard to
read on dark terminals and visibly washes out brand-colored segments
embedded in cards (e.g. the chip + bold heading rows).

Add a `note()` helper in setup/lib/theme.ts that wraps `p.note` with a
pass-through formatter, and route every setup-flow `p.note` call site
through it: setup/auto.ts, every setup/channels/*.ts adapter, and the
two setup/lib/claude-* helpers.

Pre-styled segments (brandBold, brandChip, formatPairingCard,
formatCodeCard) now render at full strength instead of being faded
alongside surrounding prose.
2026-04-29 10:20:10 +00:00
exe.dev user
93be2d15f0 fix claude setup-token flow for headless/remote systems
Use script(1) to capture PTY output and extract OAuth token when
browser-based auth isn't available, with fallback code-paste flow.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-29 10:18:38 +00:00
exe.dev user
89738917ae offer to install and authenticate Claude CLI before diagnosis
When setup fails and claude-assist kicks in, instead of silently
skipping when the CLI is missing or unauthenticated, interactively
offer to install it (via install-claude.sh) and sign in (via
claude setup-token) so the user can get diagnostic help immediately.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-29 08:18:29 +00:00
github-actions[bot]
ede6c01da8 chore: bump version to 2.0.15 2026-04-28 19:53:23 +00:00
gavrielc
4d6f9b70f4 Merge pull request #2080 from Koshkoshinsk/circuit-breaker
Add startup circuit breaker for crash loop protection
2026-04-28 22:53:06 +03:00
gavrielc
336e01d2a1 fix circuit-breaker off-by-one, ENOENT, and reset-on-throw + tests
- getDelay indexed by attempt (1-based) into a 0-indexed array, so the
  leading 0 was unreachable and every "after a crash" delay was shifted
  up one slot. Use attempt - 1 so the documented schedule (0s → 0s →
  10s → 30s → 2min → 5min → 15min cap) actually holds.
- enforceStartupBackoff runs before initDb (which creates DATA_DIR), so
  on a fresh checkout fs.writeFileSync hit ENOENT. write() now
  mkdirSync's DATA_DIR first.
- shutdown() didn't run resetCircuitBreaker if teardownChannelAdapters
  threw, so a graceful exit with a teardown error would be counted as a
  crash on the next start. Wrap teardown in try/finally.
- Adds src/circuit-breaker.test.ts: state transitions, full schedule
  (parameterized), reset-window expiry, malformed file, and the
  fresh-install path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-28 22:51:11 +03:00
Daniel Milliner
2bf296b04a add startup circuit breaker and troubleshooting docs
Backs off on rapid restarts to avoid exhausting Discord gateway identify
limits and triggering Cloudflare IP bans. Resets on clean shutdown so only
crashes accumulate the counter. Also adds a troubleshooting section to
CLAUDE.md with the most useful diagnostic locations.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-28 14:07:24 +00:00
gavrielc
ae9bcb7c33 Merge pull request #2075 from qwibitai/fix/slack-setup-wiring
fix(setup): complete Slack setup wiring with welcome DM
2026-04-28 15:37:54 +03:00
Gabi Simons
99869105ba Merge branch 'main' into fix/slack-setup-wiring 2026-04-28 15:35:20 +03:00
Gabi Simons
c5d0243417 fix(setup): add Interactivity & Shortcuts step to Slack setup
Slack interactive buttons (channel approval cards) require Interactivity
to be enabled in the app settings. Without it, button clicks silently
fail to reach the host. Added the step to both the setup wizard
post-install checklist and the add-slack SKILL.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-28 12:19:44 +00:00
Gabi Simons
c36f0c6b36 fix(setup): wire Slack agent during setup like Discord/Telegram
Slack setup previously stopped after installing the adapter, leaving
users to manually discover /init-first-agent. When they DM'd the bot,
the channel-approval flow silently failed because no owner existed.

Now the Slack setup flow matches Discord/Telegram:
- Collects the operator's Slack member ID
- Opens a DM channel via conversations.open (requires im:write scope)
- Runs init-first-agent to establish ownership, wiring, and welcome DM
- Updates post-install note to focus on webhook URL (the only remaining step)

The welcome DM is delivered via chat.postMessage (outbound), which works
before Event Subscriptions are configured. The user sees the greeting
immediately; inbound replies require webhooks.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-28 11:35:51 +00:00
github-actions[bot]
45d3016bce docs: update token count to 133k tokens · 67% of context window 2026-04-28 10:27:34 +00:00
gavrielc
7e37b13aab Fix path traversal in attachment handling on channel-inbound path 2026-04-28 13:26:44 +03:00
dooha333
a80f095174 fix(setup): inject ~/.local/bin into PATH so post-install onecli is reachable
setup/auto.ts spawned register-claude-token.sh via runInheritScript, which
inherits the parent Node process's PATH. When OneCLI was installed earlier
in the same setup run, its installer wrote the binary to ~/.local/bin and
appended a PATH line to the user's shell rc — but rc updates do not reach
an already-running process. The script's first guard, `command -v onecli`,
failed instantly (~3ms), and the auth step reported "Couldn't complete the
Claude sign-in" even though the real blocker was OneCLI not on PATH.

Patch process.env.PATH at the top of main() so every subsequent shell-out
sees ~/.local/bin. Idempotent — no-op if already present. Also drops a
duplicate `pollHealth` import that was lurking in the import block.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 11:31:29 +00:00
github-actions[bot]
f8c3d02348 docs: update token count to 133k tokens · 66% of context window 2026-04-26 21:39:26 +00:00
github-actions[bot]
b808ab4fd2 chore: bump version to 2.0.14 2026-04-26 21:39:18 +00:00
gavrielc
b9b186c9cf Merge pull request #2023 from KeXin95/fix/custom-anthropic-base-url
feat: pass ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN into agent containers
2026-04-27 00:39:07 +03:00
gavrielc
b44bcf5dcf Merge branch 'main' into fix/custom-anthropic-base-url 2026-04-27 00:38:53 +03:00
gavrielc
be86bd3c2d fix(setup): remove duplicate pollHealth import in auto.ts
Slipped through during the #2035 rebase resolution — both #2030's import
and ours landed in the merge. TypeScript dedups by symbol so it didn't
fail the typecheck, but it's noise and would've eventually tripped a
linter rule.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 00:35:55 +03:00
gavrielc
6591062fbb refactor: route custom Anthropic endpoint through OneCLI vault
The original approach passed ANTHROPIC_AUTH_TOKEN into the container
as an env var and disabled the proxy for the custom host (NO_PROXY) —
which works, but bypasses OneCLI entirely for that credential. The
container holds the raw secret, the gateway loses audit/rotation, and
we lose the rest of the vault's protections for this cohort.

OneCLI-native version: store the token as a generic secret with header
injection (--header-name Authorization --value-format 'Bearer {value}'
+ host-pattern matching the base URL hostname). The container only
needs ANTHROPIC_BASE_URL plus a placeholder ANTHROPIC_AUTH_TOKEN — the
proxy rewrites the Authorization header on the wire.

setup/lib/setup-config.ts — adds --anthropic-auth-token alongside the
existing --anthropic-base-url.

setup/auto.ts — runAuthStep short-circuits the auth-method prompt when
both NANOCLAW_ANTHROPIC_BASE_URL and NANOCLAW_ANTHROPIC_AUTH_TOKEN are
set: creates the OneCLI generic secret, writes ANTHROPIC_BASE_URL to
.env (so the runtime reads it), and appends `import './claude.js';` to
src/providers/index.ts (so the provider only registers when the user
has configured a custom endpoint — no branching for everyone else).

src/providers/claude.ts — drops ANTHROPIC_AUTH_TOKEN/NO_PROXY
passthrough. Reads ANTHROPIC_BASE_URL from .env, sets a placeholder
ANTHROPIC_AUTH_TOKEN in container env so the SDK includes an
Authorization header for OneCLI to overwrite.

src/providers/index.ts — removes the unconditional import; setup
appends it on demand.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 00:34:31 +03:00
KeXin95
26fc3ff322 feat: pass ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN into agent containers
Users with a custom Anthropic-compatible endpoint (ANTHROPIC_BASE_URL) were
getting 401s because the OneCLI proxy injects ANTHROPIC_API_KEY=placeholder
and forwards to api.anthropic.com, overriding the custom endpoint and key.

Add a claude provider host config that reads ANTHROPIC_BASE_URL,
ANTHROPIC_AUTH_TOKEN, and CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC from .env
and passes them into the container. Also sets NO_PROXY for the custom host so
the OneCLI proxy doesn't intercept those requests.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 00:32:16 +03:00
gavrielc
4ebf56e2a3 Merge pull request #2035 from qwibitai/feat/setup-advanced-settings
feat(setup): advanced settings flow with remote OneCLI support
2026-04-27 00:15:05 +03:00
gavrielc
7693a20970 feat(setup): validate onecli api token starts with oc_
Matches the OneCLI CLI's own format expectation ("oc_... format" per
`onecli auth login --help`) so a malformed token gets caught at setup
time rather than at first vault call.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 00:13:07 +03:00
gavrielc
e706dcac00 feat(setup): default OneCLI remote URL to https://app.onecli.sh
Replaces the example.internal placeholder with the hosted gateway URL
so the advanced screen and --help suggest the canonical destination
out of the box.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 00:13:07 +03:00