Demonstrates preference-based routing for personal AI assistants:
Kimi K2.5 handles conversation and agentic tasks, Claude handles
code generation, testing, and complex reasoning — with zero
application code changes and ~48% cost savings.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update all GitHub Actions workflows and Dockerfiles to use Python 3.14
as the default version. Remove the upper bound on requires-python in
model_choice_with_test_harness to allow 3.14+. The CLI's
requires-python stays at >=3.10 for broad compatibility.
* Update GitHub badges after CI workflow consolidation
Fix broken README badges pointing to deleted workflow files (pre-commit.yml,
rust_tests.yml, e2e_tests.yml) and replace with consolidated CI badge. Add
Docker image publish badge and dynamic Trivy security scan badge.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Use existing ADIL_GITHUB_TOKEN secret for security badge
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* Add Trivy Docker image security scan workflow
Scans the Docker image for CRITICAL and HIGH vulnerabilities using Trivy.
Blocks PRs on failures; runs non-blocking on main for visibility. Results
are uploaded to the GitHub Security tab via SARIF.
* Add explicit permissions to Docker security scan workflow
Set minimal permissions: contents read for checkout, security-events
write for SARIF upload to the GitHub Security tab.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix 27 HIGH vulnerabilities found by Trivy Docker scan
- Install supervisor via pip instead of apt to eliminate 22 Debian
python3.13 package vulnerabilities
- Pin urllib3>=2.6.3 to fix CVE-2025-66418, CVE-2025-66471, CVE-2026-21441
- Add ignore-unfixed to Trivy scan to suppress unfixable glibc CVE-2026-0861
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Provides build/test commands, architecture overview, and key conventions
so future Claude Code sessions can be productive immediately.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fixing the README for multi-agent orchestration
* fixed issues where the multi-intent queries weren't being properly handled by GPT-40
* more fixes for the README.md and tracing visuals
* removed remnant Arch README.md
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* init next.js app
* add metadata for keyword selection
* minor heading changes
* updated title and keywords
* updating link to reach planoai.dev
---------
Co-authored-by: Musa <malikmusa1323@gmail.com>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* introduce SEO optimizations for marketing reach
* quality of life updates to Next
* format with biome
* improve wording on home badge
* adding additional keyword based on trends
* add code block and markdown support for blogs
* Update metadata for SEO
* cleaning up plano cli commands
* adding support for wildcard model providers
* fixing compile errors
* fixing bugs related to default model provider, provider hint and duplicates in the model provider list
* fixed cargo fmt issues
* updating tests to always include the model id
* using default for the prompt_gateway path
* fixed the model name, as gpt-5-mini-2025-08-07 wasn't in the config
* making sure that all aliases and models match the config
* fixed the config generator to allow for base_url providers LLMs to include wildcard models
* re-ran the models list utility and added a shell script to run it
* updating docs to mention wildcard model providers
* updated provider_models.json to yaml, added that file to our docs for reference
* updating the build docs to use the new root-based build
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* http-filter: add fully http based demo (remove MCP)
* Fix pre-commit formatting
* add instructions about uv build/sync in cli (#675)
* Musa/demo fix (#676)
* fix demo with travel agent
* Update .gitignore
* remove sse chunk rendering
* ensure that request id is consistent (#677)
* ensure that request id is consistent
* remove test debug/info statements
* Introduce signals change (#655)
* adding support for signals
* reducing false positives for signals like positive interaction
* adding docs. Still need to fix the messages list, but waiting on PR #621
* Improve frustration detection: normalize contractions and refine punctuation
* Further refine test cases with longer messages
* minor doc changes
* fixing echo statement for build
* fixing the messages construction and using the trait for signals
* update signals docs
* fixed some minor doc changes
* added more tests and fixed docuemtnation. PR 100% ready
* made fixes based on PR comments
* Optimize latency
1. replace sliding window approach with trigram containment check
2. add code to pre-compute ngrams for patterns
* removed some debug statements to make tests easier to read
* PR comments to make ObservableStreamProcessor accept optonal Vec<Messagges>
* fixed PR comments
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
Co-authored-by: MeiyuZhong <mariazhong9612@gmail.com>
Co-authored-by: nehcgs <54548843+nehcgs@users.noreply.github.com>
* pass request_id in orchestrator and routing model (#678)
* release 0.4.2 (#679)
* tweaks to web and docs to align to 0.4.2 (#680)
* tweaks to web and docs to align to 0.4.2
* made our release banner clickable
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* Added request id across agents
* fix http_filter agent: request id + pre-commit
---------
Co-authored-by: Adil Hafeez <adil@katanemo.com>
Co-authored-by: Musa <malikmusa1323@gmail.com>
Co-authored-by: Salman Paracha <salman.paracha@gmail.com>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
Co-authored-by: nehcgs <54548843+nehcgs@users.noreply.github.com>
