apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-25 00:36:34 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
660 commits 492 branches 66 tags 79 MiB
Commit graph

660 commits

This branch
This branch
All branches
Author SHA1 Message Date
Adil Hafeez
21d4806304 add day time unit for ratelimits 
PR #851 added ratelimit examples using unit: day but the Rust
TimeUnit enum only had second/minute/hour. Adds Day variant and
maps it to per-hour quota (tokens/24).
 2026-03-30 13:38:48 -07:00
Adil Hafeez
d96a2b32f7 use uv run in validate script for local dev 
Falls back to bare python when uv is not available (CI).
 2026-03-30 13:32:50 -07:00
Adil Hafeez
9487c085d7 fix config reference: remove duplicate models, fix validation errors 
PR #851 introduced duplicate openai/gpt-4o entries and set
use_agent_orchestrator: true with multiple endpoints. Fixed by using
groq/llama-3.3-70b-versatile for the routing_preferences example
and setting use_agent_orchestrator: false.
 2026-03-30 13:27:06 -07:00
Adil Hafeez
87343e19d4 Merge remote-tracking branch 'origin/main' into adil/top-level-routing-preferences 2026-03-30 13:23:57 -07:00
Adil Hafeez
5b869648c4 remove random selection policy — consumers can shuffle client-side 
Plano should only handle ranking that requires server-side data
(cost metrics, latency). Random shuffling is trivial for callers.
 2026-03-30 12:33:06 -07:00
Musa
3a531ce22a
expand configuration reference with missing fields (#851) 2026-03-30 12:25:05 -07:00
Adil Hafeez
41e6b489f5 fix pre-commit: black format metrics_server.py, remove trailing newline in config.yaml 2026-03-27 17:45:38 -07:00
Adil Hafeez
3af94d3bce docs: note per-request warning for models with no metric data 2026-03-27 17:33:50 -07:00
Adil Hafeez
a7903d9271 add model_aliases to digitalocean_pricing, use model_id as key, warn on missing data at request time 2026-03-27 17:32:15 -07:00
Adil Hafeez
bd335cd8bd fix DO pricing URL, model_providers name validation, cost_metrics demo endpoint 2026-03-27 17:14:18 -07:00
Adil Hafeez
bd7afd911e add DigitalOcean pricing, startup validation, and demo update 
- MetricsSource::DigitalOceanPricing variant: fetch public DO Gen-AI pricing, normalize as lowercase(creator)/model_id, cost = input + output per million
- cost_metrics endpoint format updated to { "model": { "input_per_million": X, "output_per_million": Y } }
- Startup errors: prefer:cheapest requires cost source, prefer:fastest requires prometheus
- Startup warning: models with no pricing/latency data ranked last
- One-per-type enforcement: digitalocean_pricing; error if cost_metrics + digitalocean_pricing both configured
- cost_snapshot() / latency_snapshot() on ModelMetricsService for startup checks
- Demo config updated to v0.4.0 top-level routing_preferences with cheapest + fastest policies
- docker-compose.yaml + prometheus.yaml + metrics_server.py for demo latency metrics
- Schema and docs updated
 2026-03-27 16:54:37 -07:00
Adil Hafeez
76b1f37052 redesign model_metrics_sources, drop legacy per-provider routing, return ranked model list 2026-03-27 12:37:38 -07:00
Adil Hafeez
b12bf74e5c cargo fmt 2026-03-26 21:02:52 -07:00
Adil Hafeez
2ef938ac5f add top-level routing_preferences with selection_policy and model metrics fetch 2026-03-26 17:35:39 -07:00
Adil Hafeez
406fa92802
release 0.4.14 (#840) 2026-03-20 00:51:37 -07:00
Salman Paracha
69df124c47
the orchestrator had a bug where it was setting the wrong headers for archfc.katanemo.dev (#839) 
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-389.local>
 2026-03-20 00:40:47 -07:00
Adil Hafeez
180a9cb748
separate config generation from process startup in supervisord (#838) 2026-03-19 22:37:56 -07:00
Adil Hafeez
cdad02c5ee
release 0.4.13 (#837) 2026-03-19 19:51:58 -07:00
Adil Hafeez
1ad3e0f64e
refactor brightstaff (#736) 2026-03-19 17:58:33 -07:00
Adil Hafeez
1f23c573bf
add output filter chain (#822) 2026-03-18 17:58:20 -07:00
Adil Hafeez
de2d8847f3
fix CVE-2026-0861: upgrade glibc via apt-get upgrade in Dockerfile (#832) 2026-03-16 13:27:37 -07:00
Adil Hafeez
5388c6777f
add k8s deployment manifests and docs for self-hosted Arch-Router (#831) 2026-03-16 12:05:30 -07:00
Adil Hafeez
f1b8c03e2f
release 0.4.12 (#830) 2026-03-15 13:03:32 -07:00
Salman Paracha
4bb5c6404f
adding new supported models to plano (#829) 
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-389.local>
 2026-03-15 12:37:20 -07:00
Adil Hafeez
5d85829bc2
Improve config validation error messages (#825) 
* improve config validation error messages and update getting started demo

* fix black formatting
 2026-03-15 09:36:58 -07:00
Adil Hafeez
bc059aed4d
Unified overrides for custom router and orchestrator models (#820) 
* support configurable orchestrator model via orchestration config section

* add self-hosting docs and demo for Plano-Orchestrator

* list all Plano-Orchestrator model variants in docs

* use overrides for custom routing and orchestration model

* update docs

* update orchestrator model name

* rename arch provider to plano, use llm_routing_model and agent_orchestration_model

* regenerate rendered config reference
 2026-03-15 09:36:11 -07:00
Adil Hafeez
785bf7e021
add build-cli and build-brightstaff skills (#824) 2026-03-13 00:28:35 -07:00
Adil Hafeez
2f52774c0e
Add Claude Code skills and streamline CLAUDE.md (#823) 
* add claude code skills and streamline CLAUDE.md

* remove claude code attribution from PR skill

* update pr skill
 2026-03-13 00:18:41 -07:00
Adil Hafeez
5400b0a2fa
add instructions on hosting arch-router locally (#819) 2026-03-11 15:28:50 -07:00
Adil Hafeez
b4313d93a4
Run demos without Docker (#809) 2026-03-11 12:49:36 -07:00
Musa
6610097659
Support for Codex via Plano (#808) 
* Add Codex CLI support; xAI response improvements

* Add native Plano running check and update CLI agent error handling

* adding PR suggestions for transformations and code quality

* message extraction logic in ResponsesAPIRequest

* xAI support for Responses API by routing to native endpoint + refactor code
 2026-03-10 20:54:14 -07:00
Adil Hafeez
5189f7907a
add k8s deploy guide (#816) 2026-03-10 12:27:31 -07:00
Adil Hafeez
97b7a390ef
support inline routing_policy in request body (#811) (#815) 2026-03-10 12:23:18 -07:00
Adil Hafeez
028a2cd196
add routing service (#814) 
fixes https://github.com/katanemo/plano/issues/810
 2026-03-09 16:32:16 -07:00
Adil Hafeez
b9f01c8471
support native mode in planoai logs command (#807) 2026-03-05 18:34:06 -08:00
Adil Hafeez
065328e11c
release 0.4.11 (#806) 2026-03-05 13:58:19 -08:00
Adil Hafeez
780a0af132
Use editable install to fix sdist build failure (#805) 2026-03-05 13:50:50 -08:00
Adil Hafeez
a1508f4de1
fix pypi publish: use wheel-only build, remove build hook (#804) 2026-03-05 12:54:40 -08:00
Adil Hafeez
8f7a8a8a17
fix sdist build: use build hook to bundle config files (#803) 
* fix sdist build: use build hook to bundle config files

* copy hatch_build.py in Dockerfile
 2026-03-05 12:40:50 -08:00
Adil Hafeez
c13ce19293
release 0.4.10 (#802) 2026-03-05 12:17:45 -08:00
Adil Hafeez
36cbe3f589
show download progress bar instead of curl output (#801) 2026-03-05 12:09:25 -08:00
Adil Hafeez
abb89382f7
fix gzip hard link error in WASM plugin upload (#800) 2026-03-05 08:49:04 -08:00
Adil Hafeez
f63d5de02c
Run plano natively by default (#744) 2026-03-05 07:35:25 -08:00
Adil Hafeez
198c912202
allow otel collector endpoint to be set from config (#794) 
Co-authored-by: Adil Hafeez <adil.hafeez10@t-mobile.com>
 2026-03-01 04:05:45 -08:00
Musa
15c6c62df0
fix: strip trailing 'Copy code' from clipboard when copying code blocks (#788) 
Co-authored-by: Claude <noreply@anthropic.com>
 2026-02-27 13:11:26 -08:00
Adil Hafeez
d9404afa4d
release 0.4.9 (#785) 2026-02-26 16:18:02 -08:00
Salman Chishti
5082f087c6
Upgrade GitHub Actions to latest versions (#782) 
Signed-off-by: Salman Muin Kayser Chishti <13schishti@gmail.com>
 2026-02-26 12:17:32 -08:00
Salman Chishti
e2380063f7
Upgrade GitHub Actions for Node 24 compatibility (#781) 
Signed-off-by: Salman Muin Kayser Chishti <13schishti@gmail.com>
 2026-02-26 10:45:03 -08:00
Musa
2bde21ff57
add Custom Trace Attributes to extend observability (#708) 
* add custom trace attributes

* refactor: prefix custom trace attributes and update schema handlers tests configs

* refactor: rename custom_attribute_prefixes to span_attribute_header_prefixes in configuration and related handlers

* docs: add section on custom span attributes

* refactor: update tracing configuration to use span attributes and adjust related handlers

* docs: custom span attributes section to include static attributes and clarify configuration

* add custom trace attributes

* refactor: prefix custom trace attributes and update schema handlers tests configs

* refactor: rename custom_attribute_prefixes to span_attribute_header_prefixes in configuration and related handlers

* docs: add section on custom span attributes

* refactor: update tracing configuration to use span attributes and adjust related handlers

* docs: custom span attributes section to include static attributes and clarify configuration

* refactor: remove TraceCollector usage and enhance logging with structured attributes

* refactor: custom trace attribute extraction to improve clarity

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-25 16:27:20 -08:00
Adil Hafeez
70ad56a258
remove exposed example passwords from documentation (#779) 
* remove exposed example passwords from documentation

Replace hardcoded example password (MyPass#123/MyPass%23123) and
project-specific Supabase references (postgres.myproject) with
generic placeholders in docs.

https://claude.ai/code/session_01H5wj3VH1Jh28kzepEwdDCx

* remove hardcoded FlightAware AeroAPI key from flights.py

https://claude.ai/code/session_01H5wj3VH1Jh28kzepEwdDCx

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2026-02-25 13:14:36 -08:00