salvacybersec/feynman
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

triage remaining tracker fixes

Browse Source
This commit is contained in:
Advait Paliwal
2026-04-09 10:34:29 -07:00
parent 96234425ba
commit bfa538fa00
9 changed files with 157 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
website/src/content/docs/getting-started/configuration.md
View File

@@ -41,6 +41,36 @@ To see all models you have configured:
feynman model list
```
Only authenticated/configured providers appear in `feynman model list`. If you only see OpenAI models, it usually means only OpenAI auth is configured so far.
To add another provider, authenticate it first:
```bash
feynman model login anthropic
feynman model login google
```
Then switch the default model:
```bash
feynman model set anthropic/claude-opus-4-6
```
## Subagent model overrides
Feynman's bundled subagents inherit the main default model unless you override them explicitly. Inside the REPL, run:
```bash
/feynman-model
```
This opens an interactive picker where you can either:
- change the main default model for the session environment
- assign a different model to a specific bundled subagent such as `researcher`, `reviewer`, `writer`, or `verifier`
Per-subagent overrides are persisted in the synced agent files under `~/.feynman/agent/agents/` with a `model:` frontmatter field. Removing that field makes the subagent inherit the main default model again.
## Thinking levels
The `thinkingLevel` field controls how much reasoning the model does before responding. Available levels are `off`, `minimal`, `low`, `medium`, `high`, and `xhigh`. Higher levels produce more thorough analysis at the cost of latency and token usage. You can override per-session:

3
website/src/content/docs/reference/slash-commands.md
View File

@@ -30,6 +30,7 @@ These are the primary commands you will use day-to-day. Each workflow dispatches
| `/log` | Write a durable session log with completed work, findings, open questions, and next steps |
| `/jobs` | Inspect active background work: running processes, scheduled follow-ups, and active watches |
| `/help` | Show grouped Feynman commands and prefill the editor with a selected command |
| `/feynman-model` | Open the model picker for the main default model and per-subagent overrides |
| `/init` | Bootstrap `AGENTS.md` and session-log folders for a new research project |
| `/outputs` | Browse all research artifacts (papers, outputs, experiments, notes) |
| `/search` | Search prior session transcripts for past research and findings |
@@ -37,6 +38,8 @@ These are the primary commands you will use day-to-day. Each workflow dispatches
Session management commands help you organize ongoing work. The `/log` command is particularly useful at the end of a research session to capture what was accomplished and what remains.
The `/feynman-model` command opens an interactive picker that lets you either change the main default model or assign a different model to a bundled subagent like `researcher`, `reviewer`, `writer`, or `verifier`.
## Running workflows from the CLI
All research workflow slash commands can also be run directly from the command line: