Implement warmup and fetch retry in the weatherapi adapter

docs/integrations/weatherapi.md

@@ -18,6 +18,17 @@ fail before any HTTP request when the base URL is empty or not absolute.
 
 The HTTP client uses `weather_api.timeout`.
 
+Before fetching bundle sources, the adapter performs a warmup `GET` to
+`/conditions/current` with the same query parameters as the current-conditions
+source request. This is a temporary connectivity check for VPN wake-up behavior
+until the upstream service provides a dedicated health endpoint. A successful
+warmup requires a 2xx response whose body can be read; the adapter does not
+decode or validate the response envelope during warmup.
+
+Warmup attempts, warmup delay, source-fetch retry attempts, and source-fetch
+retry delay are internal adapter defaults. They are not configuration-file
+fields or CLI flags yet. `weather_api.timeout` applies to each HTTP attempt.
+
 ## Response Envelope
 
 Every response used by the adapter must be JSON with a top-level `data` field:
@@ -45,6 +56,12 @@ Malformed JSON envelopes, non-2xx statuses, and response read failures include
 endpoint context in returned errors. Decode errors include source context when
 they fail the fetch; optional malformed sources follow the missing-source policy.
 
+Source-fetch transport failures and retryable HTTP statuses are retried before
+the adapter returns an error. Retryable statuses are `408`, `429`, `500`,
+`502`, `503`, and `504`. Non-retryable statuses, malformed JSON envelopes,
+missing `data`, `data: null` missing-source outcomes, and source decode errors
+are not retried.
+
 ## Query Parameters
 
 The adapter sends these query parameters:
@@ -116,7 +133,10 @@ bundle/debug artifacts, but prompt-facing SPC module output omits geometry.
 
 ## Endpoints Used
 
-The adapter fetches these endpoints once per bundle:
+The adapter warms up `/conditions/current` once before bundle fetching begins,
+with retries if needed. It then fetches these source endpoints once per bundle,
+except when a source request is retried after a transient transport or server
+failure:
 
 - `/observations`
 - `/conditions/current`

docs/troubleshooting.md

@@ -74,7 +74,7 @@ Relevant docs: [CLI reference](cli.md).
 Symptom: generation fails with `fetch /...`, an HTTP status, or request context.
 
 Likely cause: the configured Weather API endpoint is unreachable, returned a
-non-2xx response, or returned an invalid response envelope.
+non-2xx response after retries, or returned an invalid response envelope.
 
 Diagnostic:
 
@@ -83,8 +83,11 @@ weatherreporter generate daily --config ./config.yml --date 2026-05-29
 ```
 
 Safe fix: verify `weather_api.base_url`, network access, and the Weather API
-service response. The adapter fetches `/observations`, `/conditions/current`,
+service response. The adapter first warms up `/conditions/current`, then fetches
-`/forecast/hourly`, `/forecast/narrative`, `/alerts/active`, and `/discussion`.
+`/observations`, `/conditions/current`, `/forecast/hourly`,
+`/forecast/narrative`, `/alerts/active`, `/discussion`,
+`/weatherstories/latest`, and `/outlooks/convective`. Transient VPN wake-up
+failures and retryable upstream statuses are retried automatically.
 
 Relevant docs: [Configuration reference](config.md).
 

internal/adapters/weatherapi/client.go

@@ -24,6 +24,12 @@ import (
 const (
 	convectiveOutlooksEndpoint  = "/outlooks/convective"
 	sourceSPCConvectiveOutlooks = "spc_convective_outlooks"
+
+	defaultWarmupEndpoint  = "/conditions/current"
+	defaultWarmupAttempts  = 3
+	defaultWarmupDelay     = time.Second
+	defaultFetchAttempts   = 2
+	defaultFetchRetryDelay = time.Second
 )
 
 type Client struct {
@@ -35,6 +41,12 @@ type Client struct {
 	precision     int
 	missingSource config.MissingSourceConfig
 	now           func() time.Time
+
+	warmupEndpoint  string
+	warmupAttempts  int
+	warmupDelay     time.Duration
+	fetchAttempts   int
+	fetchRetryDelay time.Duration
 }
 
 type Option func(*Client)
@@ -80,7 +92,12 @@ func New(cfg config.Config, opts ...Option) (*Client, error) {
 			Default: cfg.MissingSource.Default,
 			Sources: cfg.MissingSource.Sources,
 		},
-		now: time.Now,
+		now:             time.Now,
+		warmupEndpoint:  defaultWarmupEndpoint,
+		warmupAttempts:  defaultWarmupAttempts,
+		warmupDelay:     defaultWarmupDelay,
+		fetchAttempts:   defaultFetchAttempts,
+		fetchRetryDelay: defaultFetchRetryDelay,
 	}
 	for _, opt := range opts {
 		opt(client)
@@ -89,6 +106,10 @@ func New(cfg config.Config, opts ...Option) (*Client, error) {
 }
 
 func (c *Client) FetchBundle(ctx context.Context) (*weatherdata.Bundle, error) {
+	if err := c.warmup(ctx); err != nil {
+		return nil, err
+	}
+
 	fetchedAt := c.now()
 	builder := bundleBuilder{
 		client:    c,
@@ -397,24 +418,9 @@ type envelope struct {
 }
 
 func (c *Client) fetch(ctx context.Context, sourceName string, endpoint string, opts queryOptions) (json.RawMessage, weatherdata.Source, error) {
-	reqURL := c.endpointURL(endpoint, opts)
+	reqURL, body, err := c.fetchHTTP(ctx, endpoint, opts)
-	req, err := http.NewRequestWithContext(ctx, http.MethodGet, reqURL.String(), nil)
 	if err != nil {
-		return nil, weatherdata.Source{}, fmt.Errorf("create request for %s: %w", endpoint, err)
+		return nil, weatherdata.Source{}, err
-	}
-
-	resp, err := c.httpClient.Do(req)
-	if err != nil {
-		return nil, weatherdata.Source{}, fmt.Errorf("fetch %s: %w", endpoint, err)
-	}
-	defer resp.Body.Close()
-
-	body, err := io.ReadAll(io.LimitReader(resp.Body, 10<<20))
-	if err != nil {
-		return nil, weatherdata.Source{}, fmt.Errorf("read %s response: %w", endpoint, err)
-	}
-	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
-		return nil, weatherdata.Source{}, fmt.Errorf("fetch %s: unexpected HTTP status %d: %s", endpoint, resp.StatusCode, strings.TrimSpace(string(body)))
 	}
 
 	var env envelope
@@ -440,6 +446,169 @@ func (c *Client) fetch(ctx context.Context, sourceName string, endpoint string,
 	return env.Data, source, nil
 }
 
+func (c *Client) warmup(ctx context.Context) error {
+	endpoint := c.warmupEndpoint
+	if strings.TrimSpace(endpoint) == "" {
+		endpoint = defaultWarmupEndpoint
+	}
+	attempts := positiveAttemptCount(c.warmupAttempts)
+	var lastErr error
+	for attempt := 1; attempt <= attempts; attempt++ {
+		if err := ctx.Err(); err != nil {
+			return fmt.Errorf("warm up weather API via %s: %w", endpoint, err)
+		}
+		if err := c.warmupOnce(ctx, endpoint); err != nil {
+			lastErr = err
+		} else {
+			return nil
+		}
+		if attempt == attempts {
+			break
+		}
+		if err := waitForRetry(ctx, c.warmupDelay); err != nil {
+			return fmt.Errorf("warm up weather API via %s after %d attempt(s): %w", endpoint, attempt, err)
+		}
+	}
+	return fmt.Errorf("warm up weather API via %s failed after %d attempts: %w", endpoint, attempts, lastErr)
+}
+
+func (c *Client) warmupOnce(ctx context.Context, endpoint string) error {
+	reqURL := c.endpointURL(endpoint, queryOptions{precision: true})
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, reqURL.String(), nil)
+	if err != nil {
+		return fmt.Errorf("create request for %s: %w", endpoint, err)
+	}
+
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		return fmt.Errorf("fetch %s: %w", endpoint, err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(io.LimitReader(resp.Body, 10<<20))
+	if err != nil {
+		return fmt.Errorf("read %s response: %w", endpoint, err)
+	}
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return fmt.Errorf("fetch %s: unexpected HTTP status %d: %s", endpoint, resp.StatusCode, strings.TrimSpace(string(body)))
+	}
+	return nil
+}
+
+func (c *Client) fetchHTTP(ctx context.Context, endpoint string, opts queryOptions) (*url.URL, []byte, error) {
+	attempts := positiveAttemptCount(c.fetchAttempts)
+	var lastErr error
+	var lastRetryable bool
+	for attempt := 1; attempt <= attempts; attempt++ {
+		if err := ctx.Err(); err != nil {
+			return nil, nil, fmt.Errorf("fetch %s: %w", endpoint, err)
+		}
+		reqURL, body, err := c.fetchHTTPOnce(ctx, endpoint, opts)
+		if err == nil {
+			return reqURL, body, nil
+		}
+		lastErr = err
+		lastRetryable = isRetryableRequestError(err)
+		if !lastRetryable || attempt == attempts {
+			break
+		}
+		if err := waitForRetry(ctx, c.fetchRetryDelay); err != nil {
+			return nil, nil, fmt.Errorf("fetch %s retry delay after attempt %d: %w", endpoint, attempt, err)
+		}
+	}
+	if lastRetryable {
+		return nil, nil, fmt.Errorf("fetch %s failed after %d attempts: %w", endpoint, attempts, lastErr)
+	}
+	return nil, nil, lastErr
+}
+
+func (c *Client) fetchHTTPOnce(ctx context.Context, endpoint string, opts queryOptions) (*url.URL, []byte, error) {
+	reqURL := c.endpointURL(endpoint, opts)
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, reqURL.String(), nil)
+	if err != nil {
+		return nil, nil, fmt.Errorf("create request for %s: %w", endpoint, err)
+	}
+
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		err = fmt.Errorf("fetch %s: %w", endpoint, err)
+		if ctx.Err() != nil {
+			return reqURL, nil, err
+		}
+		return reqURL, nil, retryableRequestError{err: err}
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(io.LimitReader(resp.Body, 10<<20))
+	if err != nil {
+		err = fmt.Errorf("read %s response: %w", endpoint, err)
+		if ctx.Err() != nil {
+			return reqURL, nil, err
+		}
+		return reqURL, nil, retryableRequestError{err: err}
+	}
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		err := fmt.Errorf("fetch %s: unexpected HTTP status %d: %s", endpoint, resp.StatusCode, strings.TrimSpace(string(body)))
+		if isRetryableHTTPStatus(resp.StatusCode) {
+			return reqURL, nil, retryableRequestError{err: err}
+		}
+		return reqURL, nil, err
+	}
+	return reqURL, body, nil
+}
+
+type retryableRequestError struct {
+	err error
+}
+
+func (e retryableRequestError) Error() string {
+	return e.err.Error()
+}
+
+func (e retryableRequestError) Unwrap() error {
+	return e.err
+}
+
+func isRetryableRequestError(err error) bool {
+	_, ok := err.(retryableRequestError)
+	return ok
+}
+
+func isRetryableHTTPStatus(status int) bool {
+	switch status {
+	case http.StatusRequestTimeout,
+		http.StatusTooManyRequests,
+		http.StatusInternalServerError,
+		http.StatusBadGateway,
+		http.StatusServiceUnavailable,
+		http.StatusGatewayTimeout:
+		return true
+	default:
+		return false
+	}
+}
+
+func waitForRetry(ctx context.Context, delay time.Duration) error {
+	if delay <= 0 {
+		return ctx.Err()
+	}
+	timer := time.NewTimer(delay)
+	defer timer.Stop()
+	select {
+	case <-ctx.Done():
+		return ctx.Err()
+	case <-timer.C:
+		return nil
+	}
+}
+
+func positiveAttemptCount(attempts int) int {
+	if attempts < 1 {
+		return 1
+	}
+	return attempts
+}
+
 func isJSONNull(raw json.RawMessage) bool {
 	return bytes.Equal(bytes.TrimSpace(raw), []byte("null"))
 }

internal/adapters/weatherapi/client_test.go

@@ -80,8 +80,11 @@ func TestFetchBundleFromFixtures(t *testing.T) {
 		"/weatherstories/latest",
 		convectiveOutlooksEndpoint,
 	}
-	if len(requested) != len(wantPaths) {
+	if len(requested) != len(wantPaths)+1 {
-		t.Fatalf("requested paths = %v, want %d source endpoints", requested, len(wantPaths))
+		t.Fatalf("requested paths = %v, want warmup plus %d source endpoints", requested, len(wantPaths))
+	}
+	if !strings.HasPrefix(requested[0], defaultWarmupEndpoint+"?") && requested[0] != defaultWarmupEndpoint {
+		t.Fatalf("first requested path = %q, want warmup endpoint %s", requested[0], defaultWarmupEndpoint)
 	}
 	for _, want := range wantPaths {
 		if !containsPath(requested, want) {
@@ -186,7 +189,7 @@ func TestFetchBundleRecordsSourceHash(t *testing.T) {
 
 func TestHTTPErrorIsActionable(t *testing.T) {
 	server := fixtureServer(t, map[string]handlerOverride{
-		"/conditions/current": {status: http.StatusBadGateway, body: `upstream failed`},
+		"/forecast/hourly": {status: http.StatusBadGateway, body: `upstream failed`},
 	}, nil)
 	client := newTestClient(t, server.URL+"/", nil)
 
@@ -194,15 +197,140 @@ func TestHTTPErrorIsActionable(t *testing.T) {
 	if err == nil {
 		t.Fatal("FetchBundle() error = nil, want HTTP error")
 	}
-	if !strings.Contains(err.Error(), "/conditions/current") || !strings.Contains(err.Error(), "502") {
+	if !strings.Contains(err.Error(), "/forecast/hourly") || !strings.Contains(err.Error(), "502") {
 		t.Fatalf("error = %q, want endpoint and status", err.Error())
 	}
 }
 
+func TestWarmupRetriesBeforeFetchBundle(t *testing.T) {
+	var requested []string
+	var warmupCalls int
+	server := fixtureServer(t, map[string]handlerOverride{
+		defaultWarmupEndpoint: {handler: func(w http.ResponseWriter, r *http.Request) {
+			warmupCalls++
+			if warmupCalls == 1 {
+				w.WriteHeader(http.StatusBadGateway)
+				_, _ = w.Write([]byte("vpn waking up"))
+				return
+			}
+			http.ServeFile(w, r, filepath.Join("testdata", "current.json"))
+		}},
+	}, &requested)
+	client := newTestClient(t, server.URL+"/", nil)
+
+	bundle, err := client.FetchBundle(context.Background())
+	if err != nil {
+		t.Fatalf("FetchBundle() error = %v", err)
+	}
+	if bundle.Current == nil {
+		t.Fatal("Current = nil, want successful fetch after warmup retry")
+	}
+	if warmupCalls != 3 {
+		t.Fatalf("conditions/current calls = %d, want failed warmup, successful warmup, and current source fetch", warmupCalls)
+	}
+	if len(requested) < 2 || !containsPath(requested[:2], defaultWarmupEndpoint) {
+		t.Fatalf("initial requests = %v, want warmup endpoint retries", requested)
+	}
+}
+
+func TestWarmupFailureStopsBeforeSourceFetches(t *testing.T) {
+	var requested []string
+	server := fixtureServer(t, map[string]handlerOverride{
+		defaultWarmupEndpoint: {status: http.StatusBadGateway, body: `vpn unavailable`},
+	}, &requested)
+	client := newTestClient(t, server.URL+"/", nil)
+	client.warmupAttempts = 2
+
+	_, err := client.FetchBundle(context.Background())
+	if err == nil {
+		t.Fatal("FetchBundle() error = nil, want warmup failure")
+	}
+	if !strings.Contains(err.Error(), "warm up weather API") ||
+		!strings.Contains(err.Error(), defaultWarmupEndpoint) ||
+		!strings.Contains(err.Error(), "2 attempts") ||
+		!strings.Contains(err.Error(), "502") {
+		t.Fatalf("error = %q, want warmup endpoint, attempts, and status", err.Error())
+	}
+	if got := countPath(requested, defaultWarmupEndpoint); got != 2 {
+		t.Fatalf("warmup requests = %d, want 2; all requests = %v", got, requested)
+	}
+	if containsPath(requested, "/observations") {
+		t.Fatalf("requested paths = %v, want warmup failure before source fetches", requested)
+	}
+}
+
+func TestFetchRetriesRetryableStatus(t *testing.T) {
+	var hourlyCalls int
+	server := fixtureServer(t, map[string]handlerOverride{
+		"/forecast/hourly": {handler: func(w http.ResponseWriter, r *http.Request) {
+			hourlyCalls++
+			if hourlyCalls == 1 {
+				w.WriteHeader(http.StatusBadGateway)
+				_, _ = w.Write([]byte("temporary upstream failure"))
+				return
+			}
+			http.ServeFile(w, r, filepath.Join("testdata", "hourly.json"))
+		}},
+	}, nil)
+	client := newTestClient(t, server.URL+"/", nil)
+
+	bundle, err := client.FetchBundle(context.Background())
+	if err != nil {
+		t.Fatalf("FetchBundle() error = %v", err)
+	}
+	if bundle.Hourly == nil {
+		t.Fatal("Hourly = nil, want successful fetch after retry")
+	}
+	if hourlyCalls != 2 {
+		t.Fatalf("hourly calls = %d, want 2", hourlyCalls)
+	}
+}
+
+func TestFetchDoesNotRetryNonRetryableStatus(t *testing.T) {
+	var hourlyCalls int
+	server := fixtureServer(t, map[string]handlerOverride{
+		"/forecast/hourly": {handler: func(w http.ResponseWriter, r *http.Request) {
+			hourlyCalls++
+			w.WriteHeader(http.StatusNotFound)
+			_, _ = w.Write([]byte("not found"))
+		}},
+	}, nil)
+	client := newTestClient(t, server.URL+"/", nil)
+
+	_, err := client.FetchBundle(context.Background())
+	if err == nil {
+		t.Fatal("FetchBundle() error = nil, want non-retryable status error")
+	}
+	if hourlyCalls != 1 {
+		t.Fatalf("hourly calls = %d, want no retry", hourlyCalls)
+	}
+}
+
+func TestFetchDoesNotRetryMalformedEnvelope(t *testing.T) {
+	var hourlyCalls int
+	server := fixtureServer(t, map[string]handlerOverride{
+		"/forecast/hourly": {handler: func(w http.ResponseWriter, r *http.Request) {
+			hourlyCalls++
+			w.WriteHeader(http.StatusOK)
+			_, _ = w.Write([]byte(`not-json`))
+		}},
+	}, nil)
+	client := newTestClient(t, server.URL+"/", nil)
+
+	_, err := client.FetchBundle(context.Background())
+	if err == nil {
+		t.Fatal("FetchBundle() error = nil, want envelope decode error")
+	}
+	if hourlyCalls != 1 {
+		t.Fatalf("hourly calls = %d, want no retry", hourlyCalls)
+	}
+}
+
 func TestRequiredHourlyForecast(t *testing.T) {
+	var requested []string
 	server := fixtureServer(t, map[string]handlerOverride{
 		"/forecast/hourly": {status: http.StatusOK, body: `{"data": null}`},
-	}, nil)
+	}, &requested)
 	client := newTestClient(t, server.URL+"/", nil)
 
 	_, err := client.FetchBundle(context.Background())
@@ -212,6 +340,9 @@ func TestRequiredHourlyForecast(t *testing.T) {
 	if !strings.Contains(err.Error(), "hourly forecast data") {
 		t.Fatalf("error = %q, want hourly context", err.Error())
 	}
+	if got := countPath(requested, "/forecast/hourly"); got != 1 {
+		t.Fatalf("hourly requests = %d, want no retry; all requests = %v", got, requested)
+	}
 }
 
 func TestNullAlertsMeansNoActiveAlerts(t *testing.T) {
@@ -420,6 +551,43 @@ func TestContextCancellation(t *testing.T) {
 	}
 }
 
+func TestRetryDelayRespectsContextCancellation(t *testing.T) {
+	var cancel context.CancelFunc
+	var hourlyCalls int
+	server := fixtureServer(t, map[string]handlerOverride{
+		"/forecast/hourly": {handler: func(w http.ResponseWriter, r *http.Request) {
+			hourlyCalls++
+			if cancel != nil {
+				cancel()
+			}
+			w.WriteHeader(http.StatusBadGateway)
+			_, _ = w.Write([]byte("temporary upstream failure"))
+		}},
+	}, nil)
+	client := newTestClient(t, server.URL+"/", nil)
+	client.fetchRetryDelay = time.Hour
+
+	ctx, cancelFunc := context.WithCancel(context.Background())
+	cancel = cancelFunc
+	defer cancelFunc()
+
+	start := time.Now()
+	_, err := client.FetchBundle(ctx)
+	elapsed := time.Since(start)
+	if err == nil {
+		t.Fatal("FetchBundle() error = nil, want cancellation during retry delay")
+	}
+	if !strings.Contains(err.Error(), context.Canceled.Error()) {
+		t.Fatalf("error = %q, want context cancellation", err.Error())
+	}
+	if elapsed > time.Second {
+		t.Fatalf("FetchBundle() elapsed = %s, want prompt cancellation", elapsed)
+	}
+	if hourlyCalls != 1 {
+		t.Fatalf("hourly calls = %d, want retry delay cancellation before second attempt", hourlyCalls)
+	}
+}
+
 func TestHTTPTimeout(t *testing.T) {
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		time.Sleep(50 * time.Millisecond)
@@ -432,12 +600,14 @@ func TestHTTPTimeout(t *testing.T) {
 	if err != nil {
 		t.Fatalf("New() error = %v", err)
 	}
+	client.warmupDelay = 0
+	client.fetchRetryDelay = 0
 
 	_, err = client.FetchBundle(context.Background())
 	if err == nil {
 		t.Fatal("FetchBundle() error = nil, want timeout error")
 	}
-	if !strings.Contains(err.Error(), "/observations") {
+	if !strings.Contains(err.Error(), defaultWarmupEndpoint) {
 		t.Fatalf("error = %q, want endpoint context", err.Error())
 	}
 }
@@ -464,8 +634,9 @@ func TestSaveBundle(t *testing.T) {
 }
 
 type handlerOverride struct {
-	status int
+	status  int
-	body   string
+	body    string
+	handler http.HandlerFunc
 }
 
 func fixtureServer(t *testing.T, overrides map[string]handlerOverride, requested *[]string) *httptest.Server {
@@ -485,6 +656,10 @@ func fixtureServer(t *testing.T, overrides map[string]handlerOverride, requested
 			*requested = append(*requested, r.URL.String())
 		}
 		if override, ok := overrides[r.URL.Path]; ok {
+			if override.handler != nil {
+				override.handler(w, r)
+				return
+			}
 			w.WriteHeader(override.status)
 			_, _ = w.Write([]byte(override.body))
 			return
@@ -510,6 +685,8 @@ func newTestClient(t *testing.T, baseURL string, sourcePolicies map[string]confi
 	if err != nil {
 		t.Fatalf("New() error = %v", err)
 	}
+	client.warmupDelay = 0
+	client.fetchRetryDelay = 0
 	return client
 }
 
@@ -532,6 +709,16 @@ func containsPath(requested []string, path string) bool {
 	return false
 }
 
+func countPath(requested []string, path string) int {
+	var count int
+	for _, rawURL := range requested {
+		if strings.HasPrefix(rawURL, path+"?") || rawURL == path {
+			count++
+		}
+	}
+	return count
+}
+
 func sourceByName(t *testing.T, sources []weatherdata.Source, name string) weatherdata.Source {
 	t.Helper()
 	for _, source := range sources {