Skip to content

feat: GitHub Intelligence & Technical Architecture Expert#57

Closed
ygd58 wants to merge 13 commits into
NousResearch:mainfrom
ygd58:main
Closed

feat: GitHub Intelligence & Technical Architecture Expert#57
ygd58 wants to merge 13 commits into
NousResearch:mainfrom
ygd58:main

Conversation

@ygd58

@ygd58 ygd58 commented Feb 26, 2026

Copy link
Copy Markdown
Contributor

🚀 Moving beyond Notion: GitHub Architecture Expert

After the feedback that basic Notion tools were already covered, I decided to pivot to a much more critical challenge for developers: Repository Intelligence.

What this PR introduces:

  • Deep Repo Scanning:Hermes can now fetch the entire file tree of any GitHub repository to understand its architecture.
  • Code Contextualization:The agent can read specific source files on the fly to explain "how things work" to the user.
  • Technical Architect Mode:This turns Hermes from a simple assistant into a Technical Lead that can help developers onboard into new codebases instantly.

I'm excited to contribute this "Intelligence" layer to the ecosystem. Ready for review!

Adds a function to fetch model metadata from Hugging Face.
Added operational guidelines for Hugging Face model expertise.
This function executes a Python code snippet in a secure subprocess, capturing output or errors. It includes error handling for timeouts and system errors.
Added operational guidelines for the Autonomous Code Verification Skill.
This skill enables Hermes to autonomously extend its own capabilities by writing new Python tools from scratch, testing them, and registering them without human intervention.
This script fetches current weather data for any city using the Open-Meteo API without requiring an API key. It includes geocoding functionality to convert city names to geographic coordinates.
This file contains a suite of tests for the weather tool, checking various scenarios including valid and invalid city inputs, temperature units, and response structure.
Added documentation for the Adventure Log and self-tool building capabilities of Hermes Agent, including installation instructions and test results.
Introduced a self-tool builder skill for Hermes that enables autonomous tool creation, testing, and registration without human intervention. Includes demo tools and tests.
@ygd58 ygd58 closed this Feb 26, 2026
@andrueandersoncs

Copy link
Copy Markdown

Starting work on issue #57.

Branch: auto/issue-57-surface-longitudinal-rationale-alongside-today-d
Worktree: /Users/andrue/.hermes/worktrees/vantage/issue-57-surface-longitudinal-rationale-alongside-today-d

@andrueandersoncs

Copy link
Copy Markdown

Completed ✅

What changed:

  • New lib/longitudinal-rationale.ts module with deriveLongitudinalRationale() — inspects cross-week adherence history + progress signals and returns a one-line plain-language context sentence
  • Priority-ordered pattern detection: missed-workout pattern → off-plan meal pattern → repeated friction → weight progress trend → strong adherence
  • TodayPlan extended with longitudinalRationale: LongitudinalRationale | null
  • deriveTodayPlan() accepts optional adherenceHistory + progressSummary params
  • TodayScreen loads both signals at mount via useMemo and passes them into deriveTodayPlan()
  • Rationale renders as a small muted line below the ranked directive rationale inside the directive card, hidden when null

Verification:

  • ✅ All 283 tests pass (npm test) including 12 new tests in lib/longitudinal-rationale.test.ts covering all signal branches, edge cases (empty history, sub-threshold), and integration with deriveTodayPlan()
  • npm run build compiles cleanly — no TypeScript errors
  • ✅ Deployed to Railway: https://vantage-production-b8d9.up.railway.app
  • ✅ Dogfood QA: page loads correctly, existing directive display intact, rationale element correctly absent for a new user (graceful degradation), no JS errors in rendered HTML

Shipped in: 223a2ca (main)

Acceptance criteria met:

  • Rationale derived from real adherence/progress signal data ✅
  • Rationale shown only when history is detected (≥ 2 weeks, threshold met) ✅
  • No rationale when insufficient history ✅
  • Existing directive display unchanged ✅

sudo-yf pushed a commit to sudo-yf/hermes-agent that referenced this pull request Apr 5, 2026
Co-authored-by: Nathan Esquenazi <nesquena@gmail.com>
sudo-yf pushed a commit to sudo-yf/hermes-agent that referenced this pull request Apr 5, 2026
CHANGELOG: add v0.30.1 entry covering PRs NousResearch#57-NousResearch#61 (CLI session bridge
fixes: sidebar rendering, profile-aware state.db path, silent SQL error,
show/hide toggle in Settings.

README: add CLI session bridge, token/cost display, subagent cards,
/usage command, skills linked files, show CLI sessions toggle.

Version label: v0.30 -> v0.30.1 in index.html, SPRINTS, CHANGELOG footer.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
EOF
)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants