# fx — automated, selectable fix sources for f()

`fx` automates the `[LEARN] ... Enter a fix:` prompt in `f()` by gathering
candidate fixes from a directory of small, pluggable scripts and letting
you pick one (or auto-picking) before it's piped into `f`'s stdin.

**Zero changes to `../../src/f.sh`.** `f()`'s `read -r n` already doesn't
care whether that line comes from a human or a program — `fx` just
decides what to type there.

## Usage

```sh
. ../../src/f.sh
. fx.sh
fx some-command --that --might --fail
```

Set `FX_AUTO=1` to skip the picker and take the top-ranked candidate
automatically. Without it, `fx` uses `fzf` if installed, or a plain
numbered prompt otherwise.

## Default sources (`sources.d/`, run in filename order)

| File | What it offers |
|---|---|
| `10-known.sh` | Fixes already taught for a command that *starts* the same way, since `f()`'s own lookup only matches the exact string. |
| `20-history.sh` | The closest-looking command you've actually run before, read from `$HISTFILE`. |
| `30-selfdiag.sh` | Re-runs the command once, and if the tool's own error output suggests a corrected invocation (git's `--set-upstream` hint, etc.), emits a **function that re-derives the suggestion live on every future call** — not a frozen snapshot. This distinction matters: an earlier version of this source cached the literal suggested line and it silently broke on the second branch it saw (`git ls-remote` showed the second branch never got pushed). Re-diagnosing on every call is what makes one taught fix generalize correctly. |
| `40-pathfuzzy.sh` | If the first word isn't a real command, offers a **function** (not an alias — aliases don't expand in non-interactive shells without `shopt -s expand_aliases`) wrapping the closest-spelled real command, using transposition-aware edit distance so `gti` scores closer to `git` than to unrelated same-length commands like `ftp`. |
| `50-thefuck.sh` | Bridges to `thefuck --yes`, if installed, as one more opinion. Note `--yes` executes its own suggestion, so this candidate is often already-applied by the time you see it. Wrapped in `timeout 5` — fuzz-testing found it hanging past 3s on a majority of unmatched inputs with no fast-fail path of its own. |
| `70-local-llm.sh` | Off by default (no-ops unless a local Ollama or LM Studio server responds on its usual port). The one source with real reasoning capability, for failures none of the deterministic sources above can characterize — see "Known gaps" below for a concrete real-world case. |
| `80-remote-api.sh` | Off by default (no-ops unless `FX_REMOTE_API_URL`/`KEY`/`MODEL` are all set). Same reasoning capability as `70-local-llm.sh`, over a paid remote API instead — the last-resort tier, both in cost and in filename order. |
| `90-team-shared.sh` | Off by default (no-ops unless `FX_TEAM_URL` is set) — see below, this one *is* the extension example. |

## Adding a custom source

Drop a new executable file into `sources.d/`. Nothing else to register.

Contract:
- invoked as `sourcefile "$CMD"` where `$CMD` is the whole failing command line
- may read `$FX_OUTPUT` — captured stdout+stderr of one real attempt (empty if `FX_NO_PROBE` is set)
- prints zero or more candidate fix lines to stdout, one per line
- non-zero exit or no output = "no opinion," silently skipped
- filename prefix (`NN-name`) sets consideration/display order — lower runs first

`90-team-shared.sh` is a real, working example of this contract: it pulls
a shared `p`-format corrections file from `$FX_TEAM_URL` and offers
exact-key matches. It's a template, not a dependency — treat a URL you
point it at the same way you'd treat an rc file you `source`: a match
becomes `eval`'d code the moment you select it.

## Known gaps

Every deterministic/heuristic source (`10`-`50`) fixes one of two shapes:
the **command name** is wrong (`40-pathfuzzy.sh`), or the **tool itself**
already said what the right invocation is (`30-selfdiag.sh`). Neither
covers the shape where the command name and structure are entirely
correct, but one **argument value** is wrong for reasons that require
outside knowledge to diagnose.

Concrete, real case, not hypothetical: testing against a live third-party
system (an independently-built local service stack) from WSL,
`curl http://127.0.0.1:7778/...` failed — not because `curl` or the URL
*syntax* was wrong, but because WSL2's NAT networking means `127.0.0.1`
from inside WSL doesn't reach the Windows host; the actual gateway IP
(`cat /etc/resolv.conf`'s `nameserver` line) does. No source here fixes
this: `pathfuzzy` only touches the command name, `selfdiag` needs the
tool's own output to suggest the correction (a bare "Connection refused"
doesn't), and `known`/`history` need this exact case taught before it can
help. This is precisely what `70-local-llm.sh`/`80-remote-api.sh` exist
for — handed the command plus `$FX_OUTPUT`, a model that knows WSL2's
networking quirks could plausibly reason its way to the fix. Neither tier
was configured during that test, so `fx` correctly stayed silent instead
of guessing.

A related, categorically different case from the same session: three of
that stack's five services turned out to be bound to `127.0.0.1` only
(reachable from the Windows host itself, confirmed working there;
unreachable from WSL at any IP, connection times out rather than
refuses). No source in this directory — including the LLM tiers — can fix
that, because the packet never reaches the process at all. That's a
server-side bind-address decision, not a client-side command to correct.
Worth naming as its own category: not every "why did this fail" question
is a `fx` question. Some are infrastructure decisions to leave alone
(this one was, deliberately) and document, not to work around.

## Known cost

`fx` runs the command once itself before consulting sources (so
`30-selfdiag.sh` has real output to read). That's one extra execution
beyond what plain `f()` does. Set `FX_NO_PROBE=1` to skip it for
commands with side effects you don't want repeated — the output-aware
source just has no opinion in that case, and the others still work.