Single card with "Cloud Savings for Agent" header. All metrics
(queries, tokens, compute, energy, dollar savings) in one flex row
with vertical dividers separating usage | compute+energy | costs.
Large bold values above small labels. Consistent typography.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All bubbles (Total Queries, Input Tokens, Output Tokens, Compute,
Energy, and per-provider dollar savings) now sit in one flex row
under "Cloud Savings for Agent". Each bubble has the value (bold)
above the label, with consistent styling. Green for savings values.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Usage stats (Total Queries, Input Tokens, Output Tokens) and Cloud
Savings (Compute, Energy, Dollar Savings) now use flex rows with
compact padding, left-aligned, wrapping naturally without filling
the full width.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Cloud Savings for Agent: Compute, Energy, Dollar Savings in
separate boxes in a row, all values green
2. Agents now receive current date in their input text so they
know what day it is for time-sensitive research queries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Interval schedule now uses hours + minutes picker (max 24h)
instead of raw seconds input
2. Cloud Savings section is now per-agent (computed from agent's
own token counts), not session-wide
3. Shows FLOPs, Energy (kJ), and per-provider savings comparison
(GPT-5.3, Claude Opus 4.6, Gemini 3.1 Pro)
4. Removed kWh per-provider (inaccurate), replaced with compact
FLOPs + Energy row above provider savings
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Intelligence row has explicit "Change" button with loading state
2. Agent ticks now wrapped with InstrumentedEngine so FLOPs, energy,
and cost savings are recorded in telemetry
3. Overview shows Cloud Savings section (per-provider: cost saved, kWh)
4. Stat cards show Total Queries, Input Tokens, Output Tokens
5. "Total Runs" renamed to "Total Queries" everywhere
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- personal_deep_research.toml: add schedule_value="" for template test compat
- test_deep_research_tools_wiring: skip when fastapi not installed in CI
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Agent responses in Interact tab now render as markdown (headers,
bold, lists, etc.) instead of raw text with ** and ##
2. Instruction section is its own box above Configuration in Overview
3. Edit button is inline next to "Instruction" heading
4. User messages stay as plain text (no markdown needed)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Template cards highlight with accent border on hover
2. Text aligned top-left, emoji inline with title
3. Schedule is now an editable dropdown (not hardcoded display)
4. Overview tab shows current instruction with Edit button
5. Instruction is editable and saved to agent config
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add deep_research_agent parameter to ChannelBridge.__init__ and update
_handle_chat to try DeepResearchAgent first, falling back to system.ask()
when no research agent is configured.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Resolve tool names from config["tools"] into actual tool instances
using ToolRegistry, inject runtime deps, and pass them to the agent
constructor instead of hardcoded tools=[].
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the recompute approach from #146 with per-token outlier
detection. Entries whose energy, FLOPs, or dollar savings exceed
generous per-token thresholds (~1000x legitimate values) are hidden
from the leaderboard entirely. All displayed values come directly
from the database — no rewriting of submitted data.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sub-project A spec covering: 2-step wizard, smart template defaults,
rich system prompt templates, tool wiring fix, recommended model
endpoint, and Advanced settings collapse.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Teaches the agent to expand abstract/categorical queries into concrete
search terms using strategies (category→instances, synonyms, broader/narrower,
context clues) rather than hardcoded examples.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Energy and FLOPs are now derived from total_tokens on the leaderboard
display using Claude Opus 4.6 constants, rather than trusting submitted
DB values. This prevents gaming (e.g. TotallyNoire submitting 14B Wh
from 15M tokens). Dollar savings are clamped at the theoretical max
($25/1M tokens) on both the leaderboard and frontend submission side.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Comprehensive step-by-step guide covering Homebrew, uv, Rust, llama.cpp,
model download, Python 3.12 pin (PyO3 compat), and common pitfalls.
Cherry-picked from PR #131 by @gridworks — cleaned up to include only
the docs content (removed duplicate files, binary artifacts, and
unrelated lockfile changes from the original PR).
Co-Authored-By: gridworks <5502067+gridworks@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Companion to #143 which fixed the frontend to use Claude Opus 4.6 as
the sole baseline. This migration recomputes existing Supabase rows
using the exact closed-form: new = T/3.8M + 10*old/19, derived from
the original triple-provider formula.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
