Skip to content

fix(launcher): detect and display externally-managed gateway as running#1811

Closed
securityguy wants to merge 21 commits intosipeed:mainfrom
securityguy:fix/launcher-detect-external-gateway
Closed

fix(launcher): detect and display externally-managed gateway as running#1811
securityguy wants to merge 21 commits intosipeed:mainfrom
securityguy:fix/launcher-detect-external-gateway

Conversation

@securityguy
Copy link
Copy Markdown
Contributor

@securityguy securityguy commented Mar 19, 2026

Problem

When the picoclaw gateway is managed externally (e.g. via systemd), the launcher had two issues:

  1. Duplicate start: TryAutoStartGateway only checked gateway.cmd, which tracks processes the launcher itself spawned. An external gateway was invisible, so the launcher started a second instance on every launch.

  2. WebUI showed "Gateway Not Running": gatewayStatusData only probed the health endpoint when it owned the process. With gateway.cmd == nil, it returned "stopped" immediately without checking whether the gateway was actually reachable.

Fix

Adds isGatewayHealthy() which probes the configured gateway health endpoint with a 1-second timeout.

  • TryAutoStartGateway: calls isGatewayHealthy() before starting. If the gateway responds, logs "already running externally" and returns.
  • gatewayStatusData: when the launcher has no owned process and its internal state is "stopped", probes the health endpoint. If healthy, reports "running". Launcher-owned transition states (restarting/error) take precedence over the probe.

🤖 Generated with Claude Code

securityguy and others added 21 commits March 15, 2026 20:53
@securityguy @claude
fix(openai_compat): omit empty content when tool_calls present
0142783 
Some providers (via OpenRouter) reject assistant messages with
"content": "" alongside tool_calls. The OpenAI spec permits content to
be absent when tool_calls is set. Switch openaiMessage.Content from
string to *string with omitempty and introduce msgContent() to return
nil when content is empty and tool calls are present.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
feat(openai_compat): add strict_compat option to strip non-standard f…
37d6133 
…ields

Some OpenAI-compatible providers (e.g. OpenRouter routing to strict
backends) reject non-standard fields in the request body such as
reasoning_content in messages and extra_content / thought_signature
in tool calls. Add a per-model strict_compat: true config option that
strips these fields before serialization.

Implementation:
- Add StrictCompat bool to config.ModelConfig
- Add WithStrictCompat option to openai_compat.Provider
- Refactor HTTPProvider constructors into a single NewHTTPProviderWithOptions
  using variadic openai_compat.Option, eliminating the growing list of
  named constructors
- Thread StrictCompat through CreateProviderFromConfig via composed options

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
fix(claude_cli): surface stdout in error when CLI exits non-zero
493e8e8 
When the claude CLI exits with a non-zero status, the previous error
handler only checked stderr. However, the CLI writes its output
(including error details) to stdout, especially when invoked with
--output-format json. This left the caller with only "exit status 1"
and no actionable information.

Now includes both stderr and stdout in the error message so the actual
failure reason is visible in logs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs: document claude-cli and codex-cli providers in README
2ca6110 
Add claude-cli and codex-cli to the supported vendors table and
include vendor-specific configuration examples explaining:
- No API key is required (uses existing CLI subscription)
- The claude-code sentinel model ID skips --model flag so the CLI
  uses its own configured default model

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs: add pending contributions table to README
ab1c122 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs: replace README with minimal dev-fork version
d68d709 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy
Update README.md
ade27cc
@securityguy @claude
feat(channels): support multiple named Telegram bots
c97f6f6 
Add channels.telegram_bots config allowing multiple Telegram bot tokens
to be configured, each mapped to a separate channel (e.g. telegram-amber,
telegram-karen). Each channel can be independently bound to an agent via
the bindings config, enabling distinct AI personas behind separate bots.

Backward compatibility is preserved: the existing channels.telegram
single-entry config continues to work unchanged. On load it is normalized
into telegram_bots as an entry with id "default", which produces the
channel name "telegram" so all existing bindings remain valid.

Key changes:
- config: add TelegramBotConfig struct with ChannelName/AsTelegramConfig
  helpers; add TelegramBots field to ChannelsConfig; normalize legacy
  single entry into list on load
- telegram: add NewTelegramChannelFromConfig constructor accepting
  TelegramConfig + explicit channel name (avoids import cycle)
- channels: add TelegramBotFactory registry; add injectChannelDependencies
  helper to eliminate injection code duplication; add duplicate channel
  name guard in initTelegramBot; update initChannels to iterate over
  TelegramBots; add prefix-based rate limit fallback for named bots

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs(config): add telegram_bots and bindings examples to config.examp…
40ef4a5 
…le.json

Add two disabled example bots (alice, bob) under channels.telegram_bots
and corresponding top-level bindings to illustrate how multiple Telegram
bots map to separate named channels and agents.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy
chore: remove dependabot.yml (dev fork, not needed)
be68a49
@securityguy
Update README.md
64b5b37
@securityguy @claude
feat(providers): add gemini-cli provider
da96f64 
Adds GeminiCliProvider that wraps the Gemini CLI as a subprocess,
following the same pattern as the existing claude-cli and codex-cli
providers.

The provider invokes:
  gemini --yolo --output-format json --prompt ""

with the prompt sent via stdin. The --prompt "" flag enables
non-interactive (headless) mode, reading the full prompt from stdin.

Key details:
- Model sentinel: "gemini-cli" skips --model flag (uses CLI default)
- Explicit model: "gemini-cli/gemini-2.5-pro" passes --model gemini-2.5-pro
- System messages prepended to stdin (no --system-prompt flag in gemini)
- Parses JSON response format: {"response": "...", "stats": {"models": {...}}}
- Token usage summed across all models in stats.models (gemini uses
  multiple internal models per request)
- Tool calls extracted from response text using shared extractToolCallsFromText
- New protocol: "gemini-cli" / alias "geminicli"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs: add configuration guide for CLI providers and multi-bot Telegram
2ac7864 
- Add PR sipeed#1633 (gemini-cli provider) to contributions table
- Add configuration guide section covering:
  - claude-cli, codex-cli, and gemini-cli providers with model_list examples
  - Multiple Telegram bots with bindings and per-agent config
  - Agent workspace and personality file notes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
Merge feat/gemini-cli-provider into main
717bb76 
Adds GeminiCliProvider (PR sipeed#1633 against sipeed/picoclaw).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs: use Alice and Bob as example agent names throughout
0c856de 
Replace Amber/Karen with Alice/Bob in all README examples for consistency.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
fix(agent): dispatch per-candidate provider in fallback chain
2a88370 
Previously all agents shared a single LLMProvider instance created from
agents.defaults.model_name. Per-agent model config (agents.list[].model)
only changed the model string passed to Chat() — it never changed which
provider binary was invoked. This caused cross-provider fallback chains
(e.g. gemini-cli falling back to claude-cli) to fail, and made it
impossible to assign different CLI providers to different agents.

Introduces ProviderDispatcher which lazily creates and caches provider
instances keyed by "protocol/modelID". The fallback chain's run closure
now resolves the correct provider via the dispatcher before falling back
to agent.Provider for backward compatibility.

References sipeed#1634

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
Merge fix/provider-dispatch: per-candidate provider dispatch
8938eb7 
Brings in ProviderDispatcher fix (PR sipeed#1637 against sipeed/picoclaw).
References sipeed#1634.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
docs: add PR sipeed#1637 to contributions table
29ec94e 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy
Update README.md
8ac3006
@securityguy @claude
fix(launcher): recognise gemini-cli as a credential-free CLI provider
249a63b 
requiresRuntimeProbe and probeLocalModelAvailability handled claude-cli
and codex-cli but not gemini-cli, causing the launcher to report
"default model has no credentials configured" and skip auto-start when
gemini-cli was set as the default model.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@securityguy @claude
fix(launcher): detect and display externally-managed gateway as running
afa7fe3 
TryAutoStartGateway only checked gateway.cmd, which tracks processes the
launcher itself spawned. A gateway managed externally (e.g. via systemd)
was invisible to this check, causing two problems:
  1. The launcher started a duplicate gateway instance on every launch.
  2. The WebUI showed "Gateway Not Running" even when it was healthy.

Fix: probe the gateway health endpoint in two places:
  - TryAutoStartGateway: skip auto-start if the health endpoint responds.
  - gatewayStatusData: report "running" when the launcher has no owned
    process but the health endpoint is responding. Launcher-owned
    transition states (restarting/error) take precedence over the probe.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
securityguy added a commit to securityguy/picoclaw that referenced this pull request Mar 19, 2026
@securityguy @claude
Merge fix/launcher-detect-external-gateway: detect external gateway
86e68a2 
Brings in launcher external gateway detection fix (PR sipeed#1811 against sipeed/picoclaw).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
securityguy added a commit to securityguy/picoclaw that referenced this pull request Mar 19, 2026
@securityguy @claude
docs: add PRs sipeed#1810 and sipeed#1811 to contributions table
1010821 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@sipeed-bot sipeed-bot Bot added type: bug Something isn't working go Pull requests that update go code labels Mar 19, 2026
This was referenced Mar 20, 2026
Open
Open
@sipeed-bot
Copy link
Copy Markdown

sipeed-bot Bot commented Apr 3, 2026

@securityguy Hi! The external gateway detection fix has been quiet for over 2 weeks. I'm closing it for now. Reopen if you'd like to continue working on this!

@sipeed-bot sipeed-bot Bot closed this Apr 3, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

go Pull requests that update go code type: bug Something isn't working

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@securityguy