@synapse-research/synapse 0.2.11 → 0.2.13

package/dist/public/synapse-plugin/skills/synapse/SKILL.md

@@ -1,144 +0,0 @@
----
-name: synapse
-description: Synapse platform overview and router skill. Use it to orient on projects and then hand off to the stage-specific Synapse skills.
-license: AGPL-3.0
-metadata:
-  author: Vincentwei1021
-  version: "0.6.1"
-  category: research
-  mcp_server: synapse
----
-
-# Synapse Skill
-
-Synapse is a research orchestration platform for human researchers and AI agents. This top-level skill is the entry point: use it to understand the product model, check in, inspect project context, and then switch to the stage-specific skill whose prompt boundary best matches the current task.
-
-## Stage Skills
-
-| Skill | When to use it |
-|------|-----------------|
-| **[setup](../setup/SKILL.md)** | Configure MCP, API keys, and project-level `.mcp.json` |
-| **[research](../research/SKILL.md)** | Research questions, literature search, related works, deep research |
-| **[experiments](../experiments/SKILL.md)** | Experiment planning, revision, execution, compute, and result submission |
-| **[autonomy](../autonomy/SKILL.md)** | Autonomous loop and next-experiment proposal work |
-| **[sessions](../sessions/SKILL.md)** | Plugin hooks, session lifecycle, and multi-agent parallel execution |
-
-## Core Workflow
-
-```text
-ResearchProject --> ResearchQuestion --> Experiment --> Report
-       ^                  ^                  ^            ^
-     Human           Human/Agent        Agent executes  Agent writes
-    creates          formulates         and reports     synthesis
-```
-
-Tool families are exposed according to the agent's Synapse roles. Public read/comment/notification/session tools are broadly available, while literature tools usually require `pre_research`, experiment / compute tools require `experiment`, and mutation-heavy research or admin surfaces depend on `research`, `report`, or `admin`.
-
-## Getting Started
-
-### Step 1: Setup and check in
-
-Configure your MCP connection with **[setup](../setup/SKILL.md)**, then call:
-
-```text
-synapse_checkin()
-```
-
-Returns your agent identity, current assignments, and pending work.
-
-### Step 2: Handle active plugin context
-
-The Synapse Claude Code plugin may inject active context during session start, user prompts, sub-agent starts, and task completion. Treat that context as work already assigned by Synapse: do not wait for the user to restate it.
-
-When hook context mentions an active project, assignment, experiment, synthesis task, deep research task, notification, or sub-agent session:
-
-1. Call `synapse_checkin()` to refresh identity, roles, assignments, and notifications.
-2. Use the UUIDs from the hook context with the matching `synapse_get_*` tool.
-3. Continue through the matching stage skill below.
-4. Report durable progress with `synapse_report_experiment_progress` or `synapse_add_comment` when work spans more than a quick read-only lookup.
-5. Finish Synapse-triggered task state with the task-specific completion tool, such as `synapse_submit_experiment_results`, `synapse_save_project_synthesis`, or `synapse_complete_task` for task types that still require explicit completion.
-
-### Step 2b: Empty-project onboarding
-
-If `synapse_checkin()` returns no assignments and no notifications and the user's current project has no related works, no research questions, and no experiments, do not silently pick a direction. Ask the user which path to start with:
-
-1. **Literature-first** — search papers with `synapse_search_papers`, curate with `synapse_add_related_work`, then synthesize a deep research report via `synapse_save_deep_research_report`. Switch to **[research](../research/SKILL.md)**.
-2. **Question-first** — draft one or more `ResearchQuestion` records with `synapse_create_research_question` to frame the project. Switch to **[research](../research/SKILL.md)**.
-3. **Experiment-first** — skip ahead and create the foundational experiment (data preparation + baseline + evaluation script) with `synapse_create_experiment`. Switch to **[experiments](../experiments/SKILL.md)**.
-4. **Autonomous** — hand the project to the CC-client autonomous loop so the agent proposes and runs experiments on its own. Switch to **[autonomy](../autonomy/SKILL.md)**.
-
-Each stage skill repeats this onboarding prompt from its own perspective when entered with empty state.
-
-### Step 3: Choose the right stage skill
-
-| Current work | Skill to use |
-|--------------|---------------|
-| Understanding project context and project state | Stay here, then call `synapse_get_project_full_context()` |
-| Research questions, literature, deep research | **[research](../research/SKILL.md)** |
-| Experiment drafting, revision, execution, compute, reporting | **[experiments](../experiments/SKILL.md)** |
-| Autonomous next-step proposal, queue-empty behavior, driving the CC-client autonomous loop | **[autonomy](../autonomy/SKILL.md)** |
-| Plugin hook behavior, session tracking, multi-agent parallel dispatch in Claude Code | **[sessions](../sessions/SKILL.md)** |
-
-## Active Trigger Routing
-
-| Trigger or hook context | First action | Then use |
-|-------------------------|--------------|----------|
-| Experiment assignment or assigned experiment UUID | `synapse_get_experiment({ experimentUuid })` | **[experiments](../experiments/SKILL.md)** to start, run, report progress, and submit results |
-| Experiment plan requested | `synapse_get_experiment()` plus `synapse_get_project_full_context()` | **[experiments](../experiments/SKILL.md)** to update the plan |
-| Experiment revision requested | `synapse_get_experiment()` and read relevant comments if needed | **[experiments](../experiments/SKILL.md)** to revise and resubmit/update |
-| Experiment report requested | `synapse_get_experiment()` and inspect completed results | **[experiments](../experiments/SKILL.md)** to write the report/result document |
-| Research question claimed | `synapse_get_research_question()` and `synapse_get_project_full_context()` | **[research](../research/SKILL.md)** |
-| Deep research requested | `synapse_get_project_full_context()`, `synapse_get_related_works()`, then existing report via `synapse_get_deep_research_report()` | **[research](../research/SKILL.md)**; call `synapse_complete_task({ taskType: "deep_research" })` when done |
-| Auto search triggered | `synapse_get_project_full_context()` and inspect existing related works | **[research](../research/SKILL.md)** to search, add related works, and complete the task if required |
-| Synthesis refresh requested | `synapse_get_project_full_context()`, `synapse_get_documents({ type: "project_synthesis" })`, then `synapse_get_document()` if one exists | Save only if new results need analysis; `synapse_save_project_synthesis()` clears the active synthesis task |
-| Autonomous loop or empty queue | `synapse_get_project_full_context()` and `synapse_list_compute_nodes({ researchProjectUuid })` | **[autonomy](../autonomy/SKILL.md)** to drive the CC-client loop |
-| @mention or comment notification | `synapse_get_comments()` for the target when available | Reply with `synapse_add_comment()` using the `@[name](actorType:uuid)` format |
-| Sub-agent start/session context | Use the injected experiment UUID, then `synapse_get_experiment()` | **[sessions](../sessions/SKILL.md)** for hook behavior and **[experiments](../experiments/SKILL.md)** for work execution |
-
-## Minimum Tool Map
-
-| Need | Tools |
-|------|-------|
-| Identity, assignments, notifications | `synapse_checkin`, `synapse_get_notifications`, `synapse_mark_notification_read` |
-| Project context | `synapse_get_research_project`, `synapse_get_project_full_context` |
-| Documents and synthesis | `synapse_get_documents`, `synapse_get_document`, `synapse_save_project_synthesis` |
-| Literature and deep research | `synapse_search_papers`, `synapse_add_related_work`, `synapse_get_related_works`, `synapse_get_deep_research_report` |
-| Research questions | `synapse_get_research_question` and research-question mutation tools when roles allow |
-| Experiments | `synapse_get_assigned_experiments`, `synapse_get_experiment`, `synapse_start_experiment`, `synapse_report_experiment_progress`, `synapse_submit_experiment_results`, `synapse_propose_experiment` |
-| Compute | `synapse_list_compute_nodes`, `synapse_reserve_gpus`, `synapse_get_node_access_bundle` |
-| Collaboration | `synapse_add_comment`, `synapse_get_comments`, `synapse_search_mentionables` |
-| Task cleanup | `synapse_complete_task` except where a task-specific save/submit tool already clears state |
-
-## Execution Rules
-
-1. **Always check in first** -- call `synapse_checkin()` at session start.
-2. **Respond to active Synapse context first** -- when hooks or routed notifications identify a task, handle that task before unrelated work.
-3. **Use UUIDs from context** -- pass experiment, document, project, question, and notification UUIDs directly into the matching `synapse_get_*` tool.
-4. **Keep stage boundaries clean** -- use the research skill for literature/question work, the experiments skill for execution work, and the autonomy skill only when driving the next step yourself.
-5. **Report durable progress** -- use `synapse_report_experiment_progress` and `synapse_add_comment` to keep the team informed.
-6. **Document decisions** -- add comments explaining reasoning on experiments and research questions.
-7. **Use compute correctly** -- call `synapse_list_compute_nodes` before execution decisions, get SSH access via `synapse_get_node_access_bundle`, and never assume local key paths.
-8. **Use sessions intentionally** -- sub-agent sessions are plugin-managed; direct agent sessions are optional.
-
-## Shared References
-
-- **[references/00-common-tools.md](references/00-common-tools.md)** -- full tool inventory by category
-- **[references/01-setup.md](references/01-setup.md)** -- setup reference used by the `setup` skill
-- **[references/02-research-workflow.md](references/02-research-workflow.md)** -- research reference used by the `research` skill
-- **[references/03-experiment-workflow.md](references/03-experiment-workflow.md)** -- experiment reference used by the `experiments` skill
-- **[references/04-autonomous-loop.md](references/04-autonomous-loop.md)** -- autonomy reference used by the `autonomy` skill
-- **[references/05-session-sub-agent.md](references/05-session-sub-agent.md)** -- plugin hooks, session lifecycle, and multi-agent parallel execution reference used by the `sessions` skill
-
-## Status Lifecycles
-
-### Experiment Status Flow
-```text
-draft --> pending_review --> pending_start --> in_progress --> completed
-```
-
-### Research Question Status Flow
-```text
-open --> elaborating --> proposal_created --> completed
-  \                                            /
-   \--> closed <------------------------------/
-```

package/dist/public/synapse-plugin/skills/synapse/package.json

@@ -1,49 +0,0 @@
-{
-  "name": "synapse",
-  "version": "0.7.0",
-  "description": "Synapse research orchestration platform skill for Claude Code. Manage research projects, experiments, literature, and compute resources via MCP tools.",
-  "author": "Vincentwei1021",
-  "license": "AGPL-3.0",
-  "keywords": [
-    "synapse",
-    "skill",
-    "research",
-    "ai-agent",
-    "mcp",
-    "experiments",
-    "compute",
-    "collaboration",
-    "claude-code"
-  ],
-  "synapse": {
-    "category": "research",
-    "mcp_server": "synapse",
-    "files": {
-      "SKILL.md": "SKILL.md",
-      "references/00-common-tools.md": "references/00-common-tools.md",
-      "references/01-setup.md": "references/01-setup.md",
-      "references/02-research-workflow.md": "references/02-research-workflow.md",
-      "references/03-experiment-workflow.md": "references/03-experiment-workflow.md",
-      "references/04-autonomous-loop.md": "references/04-autonomous-loop.md",
-      "references/05-session-sub-agent.md": "references/05-session-sub-agent.md"
-    },
-    "requires": {
-      "mcp": ["synapse"]
-    },
-    "triggers": [
-      "synapse",
-      "checkin",
-      "research project",
-      "experiment",
-      "research question",
-      "compute",
-      "literature",
-      "propose experiment",
-      "session",
-      "sub-agent",
-      "plugin hook",
-      "deep research",
-      "autonomous loop"
-    ]
-  }
-}

package/dist/public/synapse-plugin/skills/synapse/references/00-common-tools.md

@@ -1,107 +0,0 @@
-# MCP Tools Reference
-
-Endpoint: `POST /api/mcp` (HTTP Streamable transport)
-
-Auth: `Authorization: Bearer syn_...`
-
-Tool availability is enforced server-side by the agent's Synapse roles. Public read/comment/notification/session tools are broadly available; literature tools usually require `pre_research`; experiment execution and compute tools require `experiment`; question / project mutation tools depend on `research`, `report`, or `admin`.
-
----
-
-## Public Context
-
-| Tool | Description |
-|------|-------------|
-| `synapse_checkin` | Agent check-in. Returns identity, roles, assignments, notifications, and project summaries. |
-| `synapse_list_research_projects` | List visible research projects. |
-| `synapse_get_research_project` | Get project details. |
-| `synapse_get_project_full_context` | Get the canonical project context snapshot: questions, experiments with UUIDs, related-work paper titles, document references, synthesis hints, and compute availability summary. |
-| `synapse_get_activity` | Get the project activity stream. |
-| `synapse_get_documents` | List project documents. |
-| `synapse_get_document` | Read a document in full. |
-| `synapse_add_comment` | Add a durable comment. Prefer `research_question`, `experiment`, or `document` targets. |
-| `synapse_get_comments` | Read the full discussion thread for an entity. |
-| `synapse_get_notifications` | Fetch notifications. Unread notifications auto-mark as read unless `autoMarkRead: false`. |
-| `synapse_mark_notification_read` | Explicitly mark a notification read when needed. Usually optional because `synapse_get_notifications` handles unread notifications by default. |
-| `synapse_search_mentionables` | Search people / agents before composing an `@mention`. |
-| `synapse_get_project_groups` | List project groups and summary metrics. |
-| `synapse_get_project_group` | Read a single project group with its projects. |
-| `synapse_get_group_dashboard` | Get aggregated project-group dashboard data. |
-
----
-
-## Research Questions
-
-Usually requires a research-oriented role.
-
-| Tool | Description |
-|------|-------------|
-| `synapse_get_research_questions` | List research questions for a project. |
-| `synapse_get_research_question` | Read one research question in detail. |
-| `synapse_get_available_research_questions` | List claimable questions (`status=open`). |
-| `synapse_claim_research_question` | Claim a question for elaboration. |
-| `synapse_release_research_question` | Release a previously claimed question. |
-| `synapse_update_research_question_status` | Move a question through `open -> elaborating -> proposal_created -> completed` as appropriate. |
-
----
-
-## Experiments And Compute
-
-Requires the `experiment` tool family.
-
-| Tool | Description |
-|------|-------------|
-| `synapse_get_assigned_experiments` | List experiments assigned to the current agent. |
-| `synapse_get_experiment` | Read one experiment in full. |
-| `synapse_create_experiment` | Create a new experiment outside autonomous loop. Defaults to `pending_review`; can also create a `draft` for further refinement. |
-| `synapse_update_experiment_status` | Move an experiment between `draft`, `pending_review`, and `pending_start` during planning or revision. Can also set `liveStatus` / `liveMessage`. |
-| `synapse_update_experiment_plan` | Flesh out or revise an experiment plan: title, description, linked research question, priority. |
-| `synapse_start_experiment` | Move an experiment into execution. Optionally reserve GPUs inline. |
-| `synapse_reserve_gpus` | Reserve GPUs before starting when you want explicit control over allocation. |
-| `synapse_report_experiment_progress` | Report live progress to the experiment card and timeline. Supports `liveStatus` such as `queuing`, `checking_resources`, or `running`. |
-| `synapse_submit_experiment_results` | Finish an experiment and submit structured results. |
-| `synapse_save_experiment_report` | Create or update the dedicated experiment result document after completion. |
-| `synapse_propose_experiment` | Propose the next experiment during autonomous loop execution. Human-review mode creates `pending_review`; full-auto mode creates `pending_start` and auto-assigns it back to the agent. |
-| `synapse_list_compute_nodes` | List pools, nodes, GPUs, and access details. |
-| `synapse_get_node_access_bundle` | Get managed SSH access details and `privateKeyPemBase64`. |
-| `synapse_sync_node_inventory` | Sync node instance metadata and GPU inventory. |
-| `synapse_report_gpu_status` | Report GPU lifecycle or telemetry updates. |
-| `synapse_get_repo_access` | Get repository credentials and the experiment's base branch when a project is repo-backed. |
-
----
-
-## Literature And Related Works
-
-Usually requires `pre_research`.
-
-| Tool | Description |
-|------|-------------|
-| `synapse_search_papers` | Search papers via DeepXiv hybrid search with arXiv fallback. |
-| `synapse_read_paper_brief` | Fast paper summary. |
-| `synapse_read_paper_head` | Section map plus section TLDRs. |
-| `synapse_read_paper_section` | Read a single section in full. |
-| `synapse_read_paper_full` | Read the full paper as Markdown. Use sparingly. |
-| `synapse_add_related_work` | Add a paper to a project's related works. Duplicate adds are skipped. |
-| `synapse_get_related_works` | List all papers already collected for a project. |
-| `synapse_get_deep_research_report` | Load the current literature-review document, if one exists. |
-| `synapse_save_deep_research_report` | Create or update the literature-review document and increment its version on update. |
-| `synapse_complete_task` | Clear the active `auto_search` or `deep_research` task after a Synapse-triggered run finishes. |
-
----
-
-## Sessions
-
-| Tool | Description |
-|------|-------------|
-| `synapse_list_sessions` | List sessions for the current agent. |
-| `synapse_get_session` | Read one session. |
-| `synapse_create_session` | Create a session for direct work. For Claude sub-agents, let the plugin hooks manage sessions automatically. |
-| `synapse_close_session` | Close a session. |
-| `synapse_reopen_session` | Reopen a closed session instead of creating a duplicate. |
-| `synapse_session_heartbeat` | Keep a session active. |
-
----
-
-## Compatibility Note
-
-Legacy `ExperimentDesign` / `ExperimentRun` surfaces still exist in the repository for compatibility, but this Claude plugin intentionally centers the current `ResearchQuestion -> Experiment` workflow.

package/dist/public/synapse-plugin/skills/synapse/references/01-setup.md

@@ -1,112 +0,0 @@
-# Setup: MCP Configuration
-
-## Overview
-
-Configure the Synapse MCP server so your AI agent can communicate with the platform.
-
----
-
-## 1. Create an API Key
-
-API keys are created in the Synapse web UI.
-
-**Steps:**
-
-1. Open Synapse in a browser (for example `http://localhost:3000`)
-2. Navigate to **Agents** in the sidebar
-3. Create or open the agent Claude Code should use
-4. Generate / copy the agent's API key
-5. Save the key immediately because it is shown only once
-
-The API key is prefixed with `syn_` (for example `syn_PXPnHpnmmYk8...`).
-
-If you do not have an API key yet:
-
-> I need a Synapse API key to connect to the platform. Please create one on the Agents page and share the key with me.
-
----
-
-## 2. MCP Server Configuration
-
-Synapse MCP uses the HTTP Streamable transport. Place this in `.mcp.json` at the project root or globally at `~/.claude/.mcp.json`.
-
-The plugin bundle also ships the same template at `public/synapse-plugin/.mcp.json` so teams can copy a project-level config into place instead of rewriting it from scratch.
-
-Replace `<BASE_URL>` with the Synapse address (for example `https://synapse.example.com` or `http://localhost:3000`).
-
-```json
-{
-  "mcpServers": {
-    "synapse": {
-      "type": "http",
-      "url": "<BASE_URL>/api/mcp",
-      "headers": {
-        "Authorization": "Bearer <your-api-key>"
-      }
-    }
-  }
-}
-```
-
-Restart Claude Code after configuration so MCP picks up the new server.
-
-### Optional: Project Filtering
-
-Scope the agent to specific projects using headers:
-
-| Header | Format | Effect |
-|--------|--------|--------|
-| `X-Synapse-Project` | UUID or comma-separated UUIDs | Only these projects |
-| `X-Synapse-Project-Group` | Group UUID | All projects in the group |
-
-```json
-{
-  "mcpServers": {
-    "synapse": {
-      "type": "http",
-      "url": "<BASE_URL>/api/mcp",
-      "headers": {
-        "Authorization": "Bearer syn_xxx",
-        "X-Synapse-Project": "project-uuid-1,project-uuid-2"
-      }
-    }
-  }
-}
-```
-
----
-
-## 3. Verify Connection
-
-Call check-in to verify the connection:
-
-```text
-synapse_checkin()
-```
-
-A successful response includes your agent identity, roles, current assignments, notification count, and project summaries.
-
-If it fails, check:
-- Is the API key correct and does it start with `syn_`?
-- Is the URL reachable?
-- Did you restart Claude Code?
-- Does the agent have the roles needed for the tools you expect to use (`pre_research`, `research`, `experiment`, `report`, `admin`)?
-
----
-
-## Environment Variables
-
-For agents running outside Claude Code, set:
-
-| Variable | Description |
-|----------|-------------|
-| `SYNAPSE_URL` | Base URL of the Synapse instance |
-| `SYNAPSE_API_KEY` | Agent API key (`syn_...`) |
-
----
-
-## Next Steps
-
-- [00-common-tools.md](00-common-tools.md) — Full tool reference
-- [02-research-workflow.md](02-research-workflow.md) — Research questions and literature
-- [03-experiment-workflow.md](03-experiment-workflow.md) — Experiment planning, execution, and reports

package/dist/public/synapse-plugin/skills/synapse/references/02-research-workflow.md

@@ -1,145 +0,0 @@
-# Research Workflow
-
-This guide covers the pre-experiment research phase: understanding project context, working with research questions, and managing literature / deep research outputs.
-
----
-
-## Research Questions
-
-Research questions are the starting point of every project. They define what the project investigates.
-
-### Viewing Questions
-
-```text
-synapse_get_research_questions({ researchProjectUuid: "..." })
-synapse_get_research_question({ researchQuestionUuid: "..." })
-```
-
-### Claiming And Working On Questions
-
-```text
-# Find open questions
-synapse_get_available_research_questions({ researchProjectUuid: "..." })
-
-# Claim one
-synapse_claim_research_question({ researchQuestionUuid: "..." })
-
-# Update status as you progress
-synapse_update_research_question_status({ researchQuestionUuid: "...", status: "elaborating" })
-```
-
-### Status Flow
-
-```text
-open --> elaborating --> proposal_created --> completed
-  \                                            /
-   \--> closed <------------------------------/
-```
-
-- `open`: available for agents to claim
-- `elaborating`: agent is investigating and formulating next steps
-- `proposal_created`: follow-up experiments were created from this question
-- `completed`: the question has been answered well enough for the current project scope
-
----
-
-## Literature And Related Works
-
-Use literature search to ground research questions in existing work. These tools usually require a `pre_research`-capable agent.
-
-### Search Papers
-
-```text
-synapse_search_papers({ query: "transformer attention mechanisms", limit: 10 })
-```
-
-Uses DeepXiv hybrid search over arXiv with API fallback. Results include title, authors, abstract, URLs, and other metadata.
-
-### Progressive Paper Reading
-
-Read papers at different levels of detail to manage token budget:
-
-```text
-# Quick summary
-synapse_read_paper_brief({ arxivId: "2401.12345" })
-
-# Paper structure with section TLDRs
-synapse_read_paper_head({ arxivId: "2401.12345" })
-
-# One section in full
-synapse_read_paper_section({ arxivId: "2401.12345", sectionName: "Experiments" })
-
-# Complete paper markdown
-synapse_read_paper_full({ arxivId: "2401.12345" })
-```
-
-### Add Related Work To A Project
-
-```text
-synapse_add_related_work({
-  researchProjectUuid: "...",
-  title: "Attention Is All You Need",
-  url: "https://arxiv.org/abs/1706.03762",
-  authors: "Vaswani et al.",
-  arxivId: "1706.03762"
-})
-```
-
-### View Project Related Works
-
-```text
-synapse_get_related_works({ researchProjectUuid: "..." })
-```
-
----
-
-## Deep Research Reports
-
-Generate or retrieve literature-review documents for a project:
-
-```text
-# Get existing report
-synapse_get_deep_research_report({ researchProjectUuid: "..." })
-
-# Save or update report (auto-increments version)
-synapse_save_deep_research_report({
-  researchProjectUuid: "...",
-  title: "Literature Review: Transformer Efficiency",
-  content: "# Literature Review\n\n..."
-})
-```
-
-If the work was triggered by Synapse's Deep Research or Auto Search UI, finish by clearing the active task:
-
-```text
-synapse_complete_task({ researchProjectUuid: "...", taskType: "deep_research" })
-```
-
----
-
-## Typical Research Flow
-
-1. `synapse_checkin()` to see assignments and available projects
-2. `synapse_get_research_project()` or `synapse_get_project_full_context()` to understand the project
-3. `synapse_claim_research_question()` if you are taking ownership of a question
-4. `synapse_search_papers()` to find relevant prior work
-5. `synapse_read_paper_brief()` / `head()` / `section()` to inspect papers progressively
-6. `synapse_add_related_work()` for papers worth keeping in project context
-7. `synapse_save_deep_research_report()` to synthesize findings into a durable document
-8. `synapse_update_research_question_status()` to reflect progress
-9. `synapse_add_comment({ targetType: "research_question", ... })` to document reasoning
-10. `synapse_complete_task()` if this was a Synapse-triggered deep research / auto-search task
-11. Move on to experiment planning or execution
-
----
-
-## Documents
-
-Projects accumulate documents as research progresses:
-
-```text
-synapse_get_documents({ researchProjectUuid: "...", type: "project_synthesis" })
-synapse_get_document({ documentUuid: "..." })
-```
-
-Document types include experiment result docs (soft-linked to experiments) and project synthesis docs (rolling summaries updated automatically as experiments complete).