jedarden/zai-proxy
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
51 commits 1 branch 0 tags 11 MiB
Commit graph

10 commits

Author SHA1 Message Date
jedarden
e154ebe82d refactor(bf-q8y0): consolidate duplicate getEnvOrDefault parsing logic 
Remove duplicate getEnvOrDefault function from dashboard/logger/logger.go and
use the canonical config.GetEnvOrDefault instead.

Before:
- proxy/config/config.go had GetString()
- dashboard/config/config.go had GetEnvOrDefault()
- dashboard/logger/logger.go had getEnvOrDefault()

After:
- proxy/config/config.go has GetString() (main module canonical)
- dashboard/config/config.go has GetEnvOrDefault() (dashboard module canonical)
- dashboard/logger/logger.go uses config.GetEnvOrDefault()

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-07-02 22:18:44 -04:00
jedarden
0f16d14e80 fix(bf-3ik4): replace zai-proxy.mcp namespace with devpod 
Replace all occurrences of zai-proxy.mcp.svc.cluster.local with
zai-proxy.devpod.svc.cluster.local in documentation files.

Verification:
- No old namespace references remain (grep verified)
- DefaultConfig pattern is correct (shared parsing in config package)
- Dashboard rate tests pass
- Comma-splitting verified working

Fixed files:
- dashboard/README.md
- DEVELOPMENT.md
- docs/notes/CANARY_PROMOTION_CHECKLIST.md
- docs/notes/CANARY_PROMOTION_PROCEDURE.md
- docs/notes/CANARY_ROLLBACK_PROCEDURE.md
- docs/notes/DASHBOARD_API_REFERENCE.md
- docs/notes/DEPLOYMENT.md
- docs/notes/metrics.md
- docs/notes/TROUBLESHOOTING.md

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-07-02 19:25:33 -04:00
jedarden
d442912023 docs(bf-5gbv): update default SCRAPE_TARGETS namespace from mcp to devpod 
Update all documentation that references the old default SCRAPE_TARGETS value:
- docs/notes/ENVIRONMENT_VARIABLES.md: ConfigMap and Deployment examples
- dashboard/README.md: SCRAPE_TARGETS default, kubectl examples, manifests

The default namespace for zai-proxy deployments is now devpod, not mcp.
 2026-07-02 18:36:39 -04:00
jedarden
633df37649 refactor(bf-j6s): update default SCRAPE_TARGETS from mcp to devpod namespace 
- Refactor dashboard/collector/collector.go to use config.GetScrapeTargets()
- Refactor dashboard/api/router.go to use config.GetScrapeTargets()
- Add dashboard/config/config.go with DefaultScrapeTarget set to devpod namespace
- Remove hardcoded mcp namespace defaults from both files

Acceptance: No occurrence of zai-proxy.mcp.svc.cluster.local remains in dashboard Go code, both DefaultConfig structs use devpod default, existing SCRAPE_TARGETS env override unchanged.
 2026-07-02 17:18:32 -04:00
jedarden
225f7cfe51 docs(dashboard): add comprehensive README.md 
- Architecture overview with component diagram
- Quick start for local, frontend dev, Docker, and Kubernetes
- Configuration environment variables reference
- Complete API endpoints documentation (REST + SSE)
- Data model and storage schema explanation
- Development setup and testing instructions
- Troubleshooting guide
- Performance characteristics

Co-Authored-By: Claude <noreply@anthropic.com>
Bead-Id: bf-2o7
 2026-06-21 09:56:17 -04:00
jedarden
c45a974e2e fix(dashboard): remove unused formatRate import in TokenPanel 
tsc -b fails with TS6133 (declared but never read). Breaks Docker build.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-17 10:58:35 -04:00
jedarden
a95bea7c93 chore(dashboard): bump VERSION to 1.1.0 
Adds cache token tracking (tokens_cache_read, tokens_cache_write) and
running window totals strip to TokenPanel.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-17 06:55:49 -04:00
jedarden
9799d75d2b feat(dashboard): add cache token tracking and running totals panel 
Adds cache_read and cache_write token directions throughout the
observability stack so Anthropic prompt-cache billing is visible.

- model/metrics.go: TokensCacheRead, TokensCacheWrite, TokenRateCacheRead,
  TokenRateCacheWrite fields on MetricSnapshot
- collector: reads direction=cache_read/cache_write from
  zai_proxy_tokens_total Prometheus metric
- frontend types.ts: matching TS fields
- TokenPanel: rewritten to show all 4 directions (input, output,
  cache_read, cache_write) on the rate chart; running-total summary
  strip above the chart shows window totals (e.g. "5h window: 1.2M
  input / 340k output / 89k cache_read / 12k cache_write")

Also updates docs/plan/plan.md to accurately document the full
dashboard architecture (backend API, storage schema, SSE hub,
frontend panels, Grafana layer, env vars).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-16 23:08:28 -04:00
jedarden
dee82a76a3 chore: update module paths and add evaluation package 
- proxy/go.mod: github.com/ardenone/zai-proxy → git.ardenone.com/jedarden/zai-proxy
- dashboard/go.mod: github.com/ardenone/ardenone-cluster/containers/zai-proxy-dashboard → git.ardenone.com/jedarden/zai-proxy/dashboard
- Update all Go import paths in proxy/ and dashboard/ to match new module paths
- Add proxy/evaluation/ package (was missing from initial commit)
- Add docs/plan/plan.md with architecture, security model, telemetry design, and migration checklist

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-16 16:03:50 -04:00
jedarden
e7c24a0c08 feat: initial zai-proxy ecosystem repo 
Extracted from ardenone-cluster/containers/zai-proxy and
ardenone-cluster/containers/zai-proxy-dashboard.

- proxy/: OpenAI-compatible ZAI reverse proxy (Go, v1.10.0)
  - Token counting, rate limiting, Prometheus metrics, canary support
- dashboard/: Metrics dashboard backend + React frontend (Go, v1.0.0)
  - Prometheus collector, SQLite storage, SSE live updates
- docs/: Operational notes, research, and plan subdirs

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-16 15:53:52 -04:00