Use the session key directly as the PostHog trace ID so feedback and generation events share the same trace. Extract non-assistant messages from conversations for $ai_input.
Add extractUsageFromMessages and normalizeOutputForPostHog to pull actual
token counts and cost from OpenClaw per-message usage metadata, and convert
Anthropic-style tool call blocks to OpenAI format for PostHog AI observability.
Integrate gateway daemon restart (stop → install → start) into both the
update and start web runtime commands so the gateway stays in sync with
runtime upgrades.
Switch TraceContextManager from runId to sessionId-based indexing so
tool spans share the same trace_id as their parent generation. Extract
tool names from agent_end messages for the PostHog Tools tab. Guard
against sending $0 cost and null token counts.
Integrate PostHog LLM Analytics via a bundled OpenClaw plugin that captures
$ai_generation, $ai_span, and $ai_trace events with configurable privacy
mode (content redaction on by default). Add like/dislike feedback buttons
to the web chat UI backed by a /api/feedback route. Extend the CLI with
`telemetry privacy on|off` subcommands and fix command delegation so
telemetry subcommands aren't forwarded to OpenClaw. Harden the web runtime
installer to auto-flatten pnpm standalone deps and dereference dangling
symlinks, preventing "Cannot find module 'next'" crashes in dev. Move
plugin installation before onboard in bootstrap so the gateway starts
with plugins.allow already configured.
