diff --git a/.feynman/agents/writer.md b/.feynman/agents/writer.md index 3e1a6ab..2590048 100644 --- a/.feynman/agents/writer.md +++ b/.feynman/agents/writer.md @@ -32,6 +32,13 @@ Detailed findings organized by theme or question. Unresolved issues, disagreements between sources, gaps in evidence. ``` +## Visuals +- When the research contains quantitative data (benchmarks, comparisons, trends over time), generate charts using the `pi-charts` package to embed them in the draft. +- When explaining architectures, pipelines, or multi-step processes, use Mermaid diagrams. +- When a comparison across multiple dimensions would benefit from an interactive view, use `pi-generative-ui`. +- Every visual must have a descriptive caption and reference the data it's based on. +- Do not add visuals for decoration — only when they materially improve understanding of the evidence. + ## Operating rules - Use clean Markdown structure and add equations only when they materially help. - Keep the narrative readable, but never outrun the evidence. diff --git a/README.md b/README.md index dab80cb..740b75a 100644 --- a/README.md +++ b/README.md @@ -58,6 +58,7 @@ Four bundled research agents, dispatched automatically or via subagent commands. ## Tools - **[AlphaXiv](https://www.alphaxiv.org/)** — paper search, Q&A, code reading, persistent annotations +- **[Agent Computer](https://agentcomputer.ai)** — secure cloud execution for experiments, replications, and long-running research - **Web search** — Gemini or Perplexity, zero-config default via signed-in Chromium - **Session search** — indexed recall across prior research sessions - **Preview** — browser and PDF export of generated artifacts @@ -81,7 +82,7 @@ feynman search status # web search config ## How it works -Built on [Pi](https://github.com/mariozechner/pi-coding-agent) and [Alpha Hub](https://github.com/getcompanion-ai/alpha-hub). Pi provides the agent runtime — file access, shell execution, persistent sessions, custom extensions. Alpha Hub connects to [alphaXiv](https://www.alphaxiv.org/) for paper search, Q&A, code reading, and annotations. +Built on [Pi](https://github.com/mariozechner/pi-coding-agent), [alphaXiv](https://www.alphaxiv.org/), and [Agent Computer](https://agentcomputer.ai). Pi provides the agent runtime. alphaXiv powers paper search, Q&A, code reading, and annotations. Agent Computer provides secure cloud machines for running experiments and replications. Every output is source-grounded. Claims link to papers, docs, or repos with direct URLs. @@ -96,4 +97,4 @@ cd feynman && npm install && npm run start [Docs](https://feynman.companion.ai/docs) · [MIT License](LICENSE) -Built on [Pi](https://github.com/mariozechner/pi-coding-agent) and [Alpha Hub](https://github.com/getcompanion-ai/alpha-hub). +Built on [Pi](https://github.com/mariozechner/pi-coding-agent), [alphaXiv](https://www.alphaxiv.org/), and [Agent Computer](https://agentcomputer.ai). diff --git a/prompts/audit.md b/prompts/audit.md index d80a61f..d378564 100644 --- a/prompts/audit.md +++ b/prompts/audit.md @@ -7,6 +7,7 @@ topLevelCli: true Audit the paper and codebase for: $@ Requirements: +- Before starting, outline the audit plan: which paper, which repo, which claims to check. Present the plan to the user and confirm before proceeding. - Use the `researcher` subagent for evidence gathering and the `verifier` subagent to verify sources and add inline citations when the audit is non-trivial. - Compare claimed methods, defaults, metrics, and data handling against the actual code. - Call out missing code, mismatches, ambiguous defaults, and reproduction risks. diff --git a/prompts/autoresearch.md b/prompts/autoresearch.md index 0723fc6..68d84d1 100644 --- a/prompts/autoresearch.md +++ b/prompts/autoresearch.md @@ -6,19 +6,46 @@ topLevelCli: true --- Start an autoresearch optimization loop for: $@ -This command uses pi-autoresearch. Enter autoresearch mode and begin the autonomous experiment loop. +This command uses pi-autoresearch. -## Behavior +## Step 1: Gather -- If `autoresearch.md` and `autoresearch.jsonl` already exist in the project, resume the existing session with the user's input as additional context. -- Otherwise, gather the optimization target from the user: - - What to optimize (test speed, bundle size, training loss, build time, etc.) - - The benchmark command to run - - The metric name, unit, and direction (lower/higher is better) - - Files in scope for changes -- Then initialize the session: create `autoresearch.md`, `autoresearch.sh`, run the baseline, and start looping. +If `autoresearch.md` and `autoresearch.jsonl` already exist, ask the user if they want to resume or start fresh. -## Loop +Otherwise, collect the following from the user before doing anything else: +- What to optimize (test speed, bundle size, training loss, build time, etc.) +- The benchmark command to run +- The metric name, unit, and direction (lower/higher is better) +- Files in scope for changes +- Maximum number of iterations (default: 20) + +## Step 2: Environment + +Ask the user where to run: +- **Local** — run in the current working directory +- **New git branch** — create a branch so main stays clean +- **Virtual environment** — create an isolated venv/conda env first +- **Cloud** — delegate to a remote Agent Computer machine via `/delegate` + +Do not proceed without a clear answer. + +## Step 3: Confirm + +Present the full plan to the user before starting: + +``` +Optimization target: [metric] ([direction]) +Benchmark command: [command] +Files in scope: [files] +Environment: [chosen environment] +Max iterations: [N] +``` + +Ask the user to confirm. Do not start the loop without explicit approval. + +## Step 4: Run + +Initialize the session: create `autoresearch.md`, `autoresearch.sh`, run the baseline, and start looping. Each iteration: edit → commit → `run_experiment` → `log_experiment` → keep or revert → repeat. Do not stop unless interrupted or `maxIterations` is reached. diff --git a/prompts/compare.md b/prompts/compare.md index d015724..1df9315 100644 --- a/prompts/compare.md +++ b/prompts/compare.md @@ -7,8 +7,10 @@ topLevelCli: true Compare sources for: $@ Requirements: +- Before starting, outline the comparison plan: which sources to compare, which dimensions to evaluate, expected output structure. Present the plan to the user and confirm before proceeding. - Use the `researcher` subagent to gather source material when the comparison set is broad, and the `verifier` subagent to verify sources and add inline citations to the final matrix. - Build a comparison matrix covering: source, key claim, evidence type, caveats, confidence. +- Generate charts with `pi-charts` when the comparison involves quantitative metrics. Use Mermaid for method or architecture comparisons. - Distinguish agreement, disagreement, and uncertainty clearly. - Save exactly one comparison to `outputs/` as markdown. - End with a `Sources` section containing direct URLs for every source used. diff --git a/prompts/deepresearch.md b/prompts/deepresearch.md index 8feaffb..fd8f4b8 100644 --- a/prompts/deepresearch.md +++ b/prompts/deepresearch.md @@ -40,6 +40,8 @@ Write the plan to `outputs/.plans/deepresearch-plan.md` as a self-contained arti Also save the plan with `memory_remember` (type: `fact`, key: `deepresearch.plan`) so it survives context truncation. +Present the plan to the user and ask them to confirm before proceeding. If the user wants changes, revise the plan first. + ## 2. Scale decision | Query type | Execution | @@ -107,6 +109,8 @@ Detailed findings organized by theme or question. Unresolved issues, disagreements between sources, gaps in evidence. ``` +When the research includes quantitative data (benchmarks, performance comparisons, trends), generate charts using `pi-charts`. Use Mermaid diagrams for architectures and processes. Every visual must have a caption and reference the underlying data. + Save this draft to a temp file (e.g., `draft.md` in the chain artifacts dir or a temp path). ## 6. Cite diff --git a/prompts/draft.md b/prompts/draft.md index 3750323..503c6cb 100644 --- a/prompts/draft.md +++ b/prompts/draft.md @@ -7,8 +7,10 @@ topLevelCli: true Write a paper-style draft for: $@ Requirements: +- Before writing, outline the draft structure: proposed title, sections, key claims to make, and source material to draw from. Present the outline to the user and confirm before proceeding. - Use the `writer` subagent when the draft should be produced from already-collected notes, then use the `verifier` subagent to add inline citations and verify sources. - Include at minimum: title, abstract, problem statement, related work, method or synthesis, evidence or experiments, limitations, conclusion. - Use clean Markdown with LaTeX where equations materially help. +- Generate charts with `pi-charts` for quantitative data, benchmarks, and comparisons. Use Mermaid for architectures and pipelines. Every figure needs a caption. - Save exactly one draft to `papers/` as markdown. - End with a `Sources` appendix with direct URLs for all primary references. diff --git a/prompts/lit.md b/prompts/lit.md index 6dc773e..e688afb 100644 --- a/prompts/lit.md +++ b/prompts/lit.md @@ -8,8 +8,9 @@ Investigate the following topic as a literature review: $@ ## Workflow -1. **Gather** — Use the `researcher` subagent when the sweep is wide enough to benefit from delegated paper triage before synthesis. For narrow topics, search directly. -2. **Synthesize** — Separate consensus, disagreements, and open questions. When useful, propose concrete next experiments or follow-up reading. -3. **Cite** — Spawn the `verifier` agent to add inline citations and verify every source URL in the draft. -4. **Verify** — Spawn the `reviewer` agent to check the cited draft for unsupported claims, logical gaps, and single-source critical findings. Fix FATAL issues before delivering. Note MAJOR issues in Open Questions. -5. **Deliver** — Save exactly one literature review to `outputs/` as markdown. Write a provenance record alongside it as `.provenance.md` listing: date, sources consulted vs. accepted vs. rejected, verification status, and intermediate research files used. +1. **Plan** — Outline the scope: key questions, source types to search (papers, web, repos), time period, and expected sections. Present the plan to the user and confirm before proceeding. +2. **Gather** — Use the `researcher` subagent when the sweep is wide enough to benefit from delegated paper triage before synthesis. For narrow topics, search directly. +2. **Synthesize** — Separate consensus, disagreements, and open questions. When useful, propose concrete next experiments or follow-up reading. Generate charts with `pi-charts` for quantitative comparisons across papers and Mermaid diagrams for taxonomies or method pipelines. +4. **Cite** — Spawn the `verifier` agent to add inline citations and verify every source URL in the draft. +5. **Verify** — Spawn the `reviewer` agent to check the cited draft for unsupported claims, logical gaps, and single-source critical findings. Fix FATAL issues before delivering. Note MAJOR issues in Open Questions. +6. **Deliver** — Save exactly one literature review to `outputs/` as markdown. Write a provenance record alongside it as `.provenance.md` listing: date, sources consulted vs. accepted vs. rejected, verification status, and intermediate research files used. diff --git a/prompts/review.md b/prompts/review.md index 1239537..9f0d238 100644 --- a/prompts/review.md +++ b/prompts/review.md @@ -7,6 +7,7 @@ topLevelCli: true Review this AI research artifact: $@ Requirements: +- Before starting, outline what will be reviewed and the review criteria (novelty, empirical rigor, baselines, reproducibility, etc.). Present the plan to the user and confirm before proceeding. - Spawn a `researcher` subagent to gather evidence on the artifact — inspect the paper, code, cited work, and any linked experimental artifacts. Save to `research.md`. - Spawn a `reviewer` subagent with `research.md` to produce the final peer review with inline annotations. - For small or simple artifacts where evidence gathering is overkill, run the `reviewer` subagent directly instead. diff --git a/prompts/watch.md b/prompts/watch.md index cac8267..30c8d08 100644 --- a/prompts/watch.md +++ b/prompts/watch.md @@ -7,8 +7,8 @@ topLevelCli: true Create a research watch for: $@ Requirements: +- Before starting, outline the watch plan: what to monitor, what signals matter, what counts as a meaningful change, and the check frequency. Present the plan to the user and confirm before proceeding. - Start with a baseline sweep of the topic. -- Summarize what should be monitored, what signals matter, and what counts as a meaningful change. - Use `schedule_prompt` to create the recurring or delayed follow-up instead of merely promising to check later. - Save exactly one baseline artifact to `outputs/`. - End with a `Sources` section containing direct URLs for every source used. diff --git a/src/pi/launch.ts b/src/pi/launch.ts index 6dbee8f..bcf649e 100644 --- a/src/pi/launch.ts +++ b/src/pi/launch.ts @@ -12,6 +12,10 @@ export async function launchPiChat(options: PiRuntimeOptions): Promise { throw new Error(`Promise polyfill not found: ${promisePolyfillPath}`); } + if (process.stdout.isTTY) { + process.stdout.write("\x1b[2J\x1b[3J\x1b[H"); + } + const child = spawn(process.execPath, ["--import", promisePolyfillPath, piCliPath, ...buildPiArgs(options)], { cwd: options.workingDir, stdio: "inherit", diff --git a/website/src/pages/index.astro b/website/src/pages/index.astro index e5925fc..2b043f9 100644 --- a/website/src/pages/index.astro +++ b/website/src/pages/index.astro @@ -111,11 +111,15 @@ import Base from '../layouts/Base.astro';

Tools

-
+
-
AlphaXiv
+
AlphaXiv

Paper search, Q&A, code reading, persistent annotations

+
+
Agent Computer
+

Secure cloud execution for experiments and replications

+
Web search

Gemini or Perplexity, zero-config default

@@ -134,7 +138,7 @@ import Base from '../layouts/Base.astro';
-

Built on Pi and Alpha Hub. MIT licensed. Open source.

+

Built on Pi, alphaXiv, and Agent Computer. MIT licensed. Open source.

Get started GitHub