Skip to content
cccskills
FreePublished on GitHub

test-claude-locally

Reproduce and verify Weave Router behavior locally with Docker Compose and Claude CLI. Test model routing, response conversion, and streaming against real APIs or a mock service, then inspect logs without changing global Claude Code settings.

OriginalShow the original description

Run the Weave router locally in docker compose and drive it with `claude -p` to reproduce and verify routing/translation behavior for a specific upstream model (e.g. GLM-5.1, DeepSeek, Qwen). Use when verifying a router fix end-to-end, reproducing a prod routing bug, confirming a model's streaming behavior (nudges, tool-call suppression, loop/no-progress breaks), or testing a `/force-model` route — without touching the user's global Claude Code config.

See how to install

Good for

  • Reproducing routing bugs in a local environment
  • Verifying router fixes through Claude CLI
  • Testing streaming behavior with mock responses
  • Checking routes pinned to a specific model
  • Verifying billing gates and content-capture privacy

Files included (2)

  • SKILL.md12.0 KB
  • scripts/mock_openai_upstream.py2.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.


name: test-claude-locally description: Run the local Docker Compose router with a seeded installation and Claude CLI against real or mock upstreams to verify routing and log behavior.

Testing the router locally

For an automated pre-merge regression net (fixture-driven, asserts caching/streaming/decision-headers against real Anthropic), run make smoke — see docs/SMOKE.md. This skill is the interactive counterpart: stand the stack up by hand and drive it with claude -p to reproduce or verify a one-off bug.

Stand up the router in docker compose, point a one-off claude -p session at it via --settings, and read the local server logs to confirm behavior. Two upstream modes: the real provider API (needs a working key + credits) or a mock upstream that emits an exact SSE shape (deterministic, no credits).

Critical gotchas (read first)

  • ~/.claude/settings.json env overrides inherited env vars. Setting ANTHROPIC_BASE_URL in the shell does NOT redirect claude — settings.json wins and the request silently goes to prod. Always redirect with claude --settings <file> (see scripts/local-settings.json). Never edit the user's global ~/.claude.json or ~/.claude/settings.json — that breaks their live session.
  • claude -p is stateless across invocations. A standalone /force-model call does not persist to the next claude -p. Put /force-model <model> as the first line of the SAME prompt that contains the task.
  • The router ignores the request's model field and routes via the cluster scorer. The ONLY way to pin a specific model is /force-model through a Claude Code session (raw curl cannot).
  • Port 8085 conflict. The monorepo's pubsub emulator may already own host port 8085. Drop the router's host binding with a docker-compose.override.yml (see workflow). The server still reaches the emulator over the compose network.
  • No credits / no key = no reproduction. If the real upstream returns an error (e.g. OpenRouter "Insufficient credits"), use the mock-upstream path instead.

Workflow

- [ ] 1. Bring up the stack (handle port 8085)
- [ ] 2. Seed an API key
- [ ] 3. Choose upstream: real provider OR mock
- [ ] 4. Write a one-off local-settings.json
- [ ] 5. Drive with `claude -p --settings`, forcing the target model
- [ ] 6. Read local logs to verify behavior
- [ ] 7. Clean up

1. Bring up the stack

cd <router-repo>
# Drop the pubsub host-port binding to avoid an 8085 conflict:
cat > docker-compose.override.yml <<'EOF'
services:
  pubsub-emulator:
    ports: !reset []
EOF
docker compose up -d --build server   # --build picks up code changes
until curl -sf http://localhost:8080/health >/dev/null; do sleep 2; done

The override file is gitignored-by-intent scaffolding — delete it in cleanup.

2. Seed an API key

docker compose run --rm seed

Copy the rk_... key it prints.

3. Choose the upstream

Real provider — set the provider key in .env.local (e.g. FIREWORKS_API_KEY=...) and restart docker compose up -d server. Confirm the boot log shows <Provider> provider enabled with the real base_url. Use this to confirm a model genuinely produces the behavior.

Mock upstream — for a deterministic, credit-free repro of a precise SSE shape. Point the provider's base URL at a local mock and restart:

python3 scripts/mock_openai_upstream.py >/tmp/mock.log 2>&1 &   # serves :8099
# In docker-compose.override.yml under `server:`, add:
#   environment:
#     FIREWORKS_BASE_URL: http://host.docker.internal:8099/v1
#     FIREWORKS_API_KEY: sk-mock
#   extra_hosts: ["host.docker.internal:host-gateway"]
docker compose up -d server

Edit the mock's emitted chunks to match the upstream shape you're reproducing. Provider→env-var names live in internal/providers/provider.go; base-URL overrides are read in cmd/router/main.go (<PROVIDER>_BASE_URL).

4. One-off local settings

cat > /tmp/local-settings.json <<EOF
{ "env": {
  "ANTHROPIC_BASE_URL": "http://localhost:8080",
  "ANTHROPIC_CUSTOM_HEADERS": "X-Weave-Router-Key: rk_REPLACE_ME"
}}
EOF

5. Drive it

cd <scratch-dir-with-files-to-act-on>
env -u CLAUDE_CODE_SESSION_ID -u ANTHROPIC_BASE_URL -u ANTHROPIC_CUSTOM_HEADERS \
  claude -p 'First send exactly: /force-model z-ai/glm-5.1
Then <task that requires tool use>, then stop.' \
  --settings /tmp/local-settings.json --max-turns 10 --verbose

6. Verify via logs

The decision + completion log per action (one ProxyMessages complete) carries the signals you need. Strip ANSI first:

docker compose logs server --since=3m 2>&1 | sed -E 's/\x1b\[[0-9;]*m//g' \
  | grep 'ProxyMessages complete' | grep 'decision_model=z-ai/glm-5.1'

Useful fields: decision_model, decision_provider, upstream_finish_reason, suppressed_tool_calls, text_only_turn_nudged, tool_use_blocks, resp_stop_reason, stop_reason_demoted. Also grep for recovery nudge, tool-call loop, no-progress.

Confirm the model was actually served before drawing conclusions:

docker compose logs server --since=3m 2>&1 | sed -E 's/\x1b\[[0-9;]*m//g' \
  | grep 'ProxyMessages complete' | grep -oE 'decision_model=[^ ]+' | sort | uniq -c

If you only see other models, /force-model didn't take — recheck step 5.

7. Clean up

pkill -f mock_openai_upstream.py 2>/dev/null
rm -f docker-compose.override.yml /tmp/local-settings.json
# `docker compose down` if you want to stop the stack

Testing the balance gate / subscription usage-bypass (managed billing)

For fixes to internal/billing + internal/server/middleware/balance_check.go + the usage-bypass path (internal/proxy/usage_bypass.go), the setup differs from the model-behavior workflow above:

  • The balance gate only attaches in managed mode with billing enabled. Set ROUTER_DEPLOYMENT_MODE=managed on the server service. Billing auto-enables when the router schema's billing tables exist (they do after migrate), logged as Router billing enabled. In default selfhosted mode WithBalanceCheck is never wired and none of this triggers.
  • The Anthropic provider has no ANTHROPIC_BASE_URL override (unlike Fireworks/Together/etc.) — cmd/router/main.go hardcodes anthropic.DefaultBaseURL. To point Anthropic at a mock, temporarily edit that line to config.GetOr("ANTHROPIC_BASE_URL", anthropic.DefaultBaseURL), rebuild, and revert it after testing (don't ship it in the fix PR). The boot log line still prints DefaultBaseURL cosmetically — verify the mock is actually hit via the mock's own logs, not the boot log.
  • Requests must be MainLoop-shaped to reach the usage-bypass decision. Short prompts (small max_tokens, no tools) classify as Probe/Classifier/TitleGen — all hard-pinned, short-circuiting before the usage-bypass and scorer branches. A trivial "say hi" will wrongly hit the refusal path. Use a realistic turn: tools present + max_tokens>=4096 + a normal user message. Confirm turn_type=main_loop in the turnloop classified log before trusting the result.
  • Drive with raw curl on the production router-key path — no claude binary needed, and it lets you pin the requested model (the usage-bypass path serves the requested model verbatim, so no /force-model needed here):
    curl -sS -N -D /tmp/h.txt -X POST http://localhost:8080/v1/messages \
      -H "Authorization: Bearer $RK" \
      -H "X-Weave-Anthropic-Subscription: sk-ant-oat01-anything" \
      -H "anthropic-version: 2023-06-01" -H "Content-Type: application/json" \
      -d '{"model":"claude-sonnet-4-5","max_tokens":4096,"stream":true,"tools":[{"name":"Bash","input_schema":{"type":"object"}}],"messages":[{"role":"user","content":"<realistic multi-sentence task>"}]}'
    
    A fake sk-ant-oat... token is enough for router-side classification; the mock doesn't validate it.
  • Set DB state directly (host psql -h localhost -p 5433 -U router -d router, password router, SET search_path TO router): UPDATE model_router_installations SET usage_bypass_enabled=true WHERE external_id='__router_admin__'; and upsert organization_credit_balance with balance_usd_micros below SubscriptionOverdraftFloorMicros (−5_000_000). Assert no debit via SELECT count(*) FROM organization_credit_ledger WHERE organization_id='__router_admin__'; before/after.
  • Deterministic mock that branches on the requested model is the cleanest way to drive both the serve path and the refusal path from one server: return 200 SSE for one model and 429 for another (the usage-bypass path forwards the requested model verbatim, so branching on model in the request body is reliable).
  • What good looks like: header X-Router-Decision: usage_bypass, the depleted-credits warning injected as content-block index 0 (real content re-indexed to 1), log Balance past subscription overdraft floor: serving subscription-only. Retryable upstream error → log Subscription-only bypass hit retryable error; refusing instead of paid reroute → HTTP 402. No subscription header below floor → insufficient_credits 402 that never logs ProxyMessages start.

Notes

  • Local cluster version comes from ROUTER_CLUSTER_VERSION in .env.local; it may differ from prod, which is why /force-model (not the scorer) is the reliable way to hit one model.
  • GLM-5.1's primary binding is Together (then Fireworks, then OpenRouter) — see internal/router/catalog/catalog.go.
  • To confirm a deploy contains a given router commit: the prod Cloud Run revision name maps to a monorepo commit; git ls-tree <monorepo-commit> router-internal/router shows the pinned router submodule SHA.

Content-capture and stdout privacy checks

  • Self-hosted capture defaults to off. For a positive control, set WV_CAPTURE_CONTENT=full on the Compose server and leave the seeded installation's content_capture_mode NULL. Deployment off wins over installation full; installation off wins over deployment full.
  • Direct SQL changes to router.model_router_installations.content_capture_mode do not invalidate cached auth. Restart the server after a direct update, or use the admin endpoint that publishes invalidation.
  • For headless requests, x-weave-force-model: <catalog model> pins the target without a slash-command exchange. Supply it alongside X-Weave-Router-Key through the one-off Claude settings. --settings accepts inline JSON as well as a file, allowing locally seeded keys to remain in shell memory.
  • Newer Claude versions may prepend environment context to the main user message. Its last_preview can therefore show environment text rather than the task; title-generation requests may contain the task canary. Add a raw authenticated Messages request when exact preview equality matters.
  • To provoke a real Anthropic 400 through either Messages or Chat Completions, use a tool schema with an invalid nested JSON Schema type, e.g. {"type":"object","properties":{"canary":{"type":"not_a_valid_json_schema_type"}}}. Verify upstream_status=400 and a nonempty error body with capture on before asserting it is blank off. Unknown model pins can fail locally, invalid tool names are sanitized, and invalid caller API keys are ignored on the router-keyed paid-credential path.
  • Search the entire container log for unique off-mode canaries, not only completion records. Include start records and conversation-tail diagnostics. Save logs before recreating the container, which replaces its log history.

Devin Secrets Needed

  • ANTHROPIC_API_KEY for real Anthropic checks. Pass it through the process environment to Compose; do not copy it into tracked files or plaintext test artifacts.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Investigate unexpected Claude Code output by matching a session’s local transcript with production router logs. Identify the serving model and trace response conversion code to explain empty blocks, tool output, or other rendering symptoms.

  • Investigate unexpected output in a specific session
  • Examine an empty thinking block
  • Match displayed content to the serving model and provider
weave-os/router5.6KUpdated Oct 21, 2026

Investigate a Codex CLI session by matching its local conversation record with production router logs. Use the session ID to examine missing reasoning summaries, routing markers, unexpected models, or unusual tool calls and trace relevant code paths.

  • Investigate missing reasoning summaries
  • Confirm which model actually served a turn
  • Trace missing or unexpected routing markers
weave-os/router5.6KUpdated Oct 21, 2026

disable-routing

FreeSummary

Switch Codex from Weave Router back to its normal provider for future sessions. Keep the existing login and router configuration, receive the command result, and retain the option to turn routing on again later.

  • Return Codex to its normal provider
  • Disable routing while keeping router configuration
  • Switch providers without logging out
weave-os/router5.6KUpdated Oct 21, 2026

fm

FreeSummary

Pin the current Codex session to a chosen model through Weave Router. This short alias accepts a model ID, runs the included script, and reports the router’s response while allowing the current turn to continue.

  • Pinning a Codex session to a chosen model
  • Using a short alias for force-model
  • Checking the router’s response after pinning a model
weave-os/router5.6KUpdated Oct 21, 2026

force-model

FreeSummary

Pin the current Codex session to a specific model through Weave Router by providing its model ID. The skill applies the pin, continues the same turn, and reports the router's response.

  • Pinning the current Codex session to a model
  • Specifying a model by its ID
  • Applying a model pin while continuing the same turn
weave-os/router5.6KUpdated Oct 21, 2026

force-parent

FreeSummary

Pin the current parent thread to a chosen AI model through Weave Router while subagents keep automatic model selection. An optional effort setting controls the model's reasoning effort.

  • Keep the parent thread on a chosen model
  • Let subagents keep automatic model selection
  • Specify a model with an optional reasoning effort
weave-os/router5.6KUpdated Oct 21, 2026

See all skills by weave-os

Report a problem with this skill