From 4c6d610263c5badd5c249b89489787002022e729 Mon Sep 17 00:00:00 2001 From: rope Date: Thu, 17 Sep 2026 17:49:24 +0100 Subject: [PATCH] Use ChatGPT Codex for launcher questions --- hosts/FredOS-Mediaserver.nix | 89 +++++++++--------------------------- settings/quickshell.nix | 45 ++++++++---------- 2 files changed, 40 insertions(+), 94 deletions(-) diff --git a/hosts/FredOS-Mediaserver.nix b/hosts/FredOS-Mediaserver.nix index d118aff..3965ab4 100644 --- a/hosts/FredOS-Mediaserver.nix +++ b/hosts/FredOS-Mediaserver.nix @@ -69,45 +69,20 @@ # Instant-answer backend for the quickshell launcher on the desktops: # `printf '%s' "question" | ssh mediaserver qs-ask`. # - # Runs through Claude Code so it draws on fred's existing subscription — - # no API key, no separate billing. The trade is latency: Claude Code boots - # a Node process per question, so this takes ~6s against the raw API's - # ~1s. The launcher therefore shows its Wikipedia answer first and lets - # this one supersede it when it lands. + # Runs through Codex CLI using fred's ChatGPT subscription. Sign in on + # the server as fred with `codex login` once; no API key is needed. + # The launcher shows Wikipedia first and replaces it when this answers. # # Reads the question from stdin — passing it as an ssh argv element would # send it through the remote shell for a second round of word splitting. # - # Every flag here is either isolation or trimming the invocation: - # --safe-mode no CLAUDE.md, skills, hooks, plugins, MCP or - # custom agents. Critical for correctness, not - # just speed: fred's ~/.claude/CLAUDE.md tells - # Claude to answer in caveman mode, which would - # otherwise leak into launcher answers. Auth - # keeps working normally, which is what makes - # the subscription usable here. - # --no-session-persistence writes no transcript, so launcher questions - # never appear in /resume or any project history - # --tools "" no tools at all: nothing to load, and it - # cannot touch the filesystem or network - # --disable-slash-commands no skill resolution - # --strict-mcp-config ignore every MCP config (none supplied) - # --system-prompt replaces the full Claude Code system prompt - # with one line, rather than appending to it - # --permission-mode dontAsk never block waiting on a prompt nobody sees - # --model claude-haiku-4-5 smallest model — a one-line fact needs no more - # - # NOT --bare, which looks like the right flag and is a trap: it skips even - # more, but its auth is "strictly ANTHROPIC_API_KEY or apiKeyHelper (OAuth - # and keychain are never read)" — i.e. it cannot use the subscription. + # Luna at low reasoning effort is enough for a short fact. The CLI runs + # read-only, without web search, shell access, user config, exec rules, + # or session persistence. # # STDOUT is the launcher's channel: the answer, or nothing at all if the - # call fails or the model doesn't know — silence is what the launcher - # reads as "keep the Wikipedia answer". Every reason for that silence goes - # to STDERR instead, which the launcher discards and a human running - # `qs-ask` by hand can read — and to the journal, since over ssh nobody - # ever sees that STDERR. `journalctl -t qs-ask` is the only way to tell a - # blank card caused by UNKNOWN from one caused by a failed call. + # call fails or the model doesn't know — silence means "keep Wikipedia". + # Reasons go to STDERR and the journal (`journalctl -t qs-ask`). (pkgs.writeShellScriptBin "qs-ask" '' # Every line carries this script's pid, because the launcher fires a # fresh call per debounce and concurrent runs otherwise interleave with @@ -124,45 +99,25 @@ [ -z "$q" ] && { log "no question on stdin"; exit 0; } log "ask: $q" - # Claude Code derives its project state (transcripts, auto-memory) from - # the working directory, so run from a dedicated empty one. Combined with - # --no-session-persistence and --safe-mode, a launcher question leaves no - # trace in the real projects' history or memory. + # Keep repository instructions and project files out of this invocation. work="$HOME/.cache/qs-ask" ${pkgs.coreutils}/bin/mkdir -p "$work" || { log "cannot create $work"; exit 0; } cd "$work" || { log "cannot enter $work"; exit 0; } - # MAX_THINKING_TOKENS=0 is the single biggest win here, worth ~2.4x. - # Measured: Haiku defaults to extended thinking, and it spent 225 output - # tokens and 1.9s deliberating before emitting an 80-character answer - # about the height of a tower. With thinking off: 43 output tokens, - # time-to-first-text 2657ms -> 1122ms, wall clock 5.7s -> 2.4s, same - # answer. A one-line lookup has nothing to reason about. - # - # --name is not cosmetic: without it Claude Code fires a second, - # concurrent `source=generate_session_title` request to invent a title - # for a session --no-session-persistence then throws away. It costs no - # wall time (both requests dispatch ~1ms apart), but it spent 507 input - # tokens against 153 for the real question. Naming the session up front - # removes it: one request instead of two, 660 input tokens -> 153. - # - # For the record, two things that are NOT the bottleneck, both measured: - # process startup (0.12s boot + 28ms to fire the request, so keeping a - # warm process saves nothing) and prompt size (184 input tokens). - ans=$(printf '%s' "$q" | ${pkgs.coreutils}/bin/env MAX_THINKING_TOKENS=0 \ - ${pkgs.claude-code}/bin/claude -p \ - --safe-mode \ - --no-session-persistence \ - --tools "" \ - --disable-slash-commands \ - --strict-mcp-config \ - --permission-mode dontAsk \ - --output-format text \ - --model claude-haiku-4-5 \ - --name qs-ask \ - --system-prompt 'Answer the question in one or two short sentences, under 240 characters. Lead with the specific fact asked for, including units. The query is often bare keywords rather than a question ("shadow hunter knife classic wow"); treat that as a request for the key facts about that thing, not as unanswerable. No preamble, no caveats, no markdown, no follow-up offers. Reply with exactly UNKNOWN only when you genuinely do not know, or the answer depends on live data you do not have.' \ + ans=$(printf 'Answer the question in one or two short sentences, under 240 characters. Lead with the specific fact asked for, including units. The query is often bare keywords rather than a question ("shadow hunter knife classic wow"); treat that as a request for the key facts about that thing. No preamble, caveats, markdown, or follow-up offers. Do not use tools. Reply with exactly UNKNOWN only when you genuinely do not know, or the answer depends on live data you do not have.\n\nQuestion: %s\n' "$q" | \ + ${pkgs.coreutils}/bin/timeout 30s ${pkgs.codex}/bin/codex exec \ + --model gpt-5.6-luna \ + --config model_reasoning_effort=low \ + --config web_search=disabled \ + --disable shell_tool \ + --sandbox read-only \ + --skip-git-repo-check \ + --ephemeral \ + --ignore-user-config \ + --ignore-rules \ + - \ 2>/dev/null) \ - || { log "claude exited non-zero (auth expired? run 'claude' once to log in)"; exit 0; } + || { log "codex exited non-zero (check 'codex login status' as fred)"; exit 0; } ans=$(printf '%s' "$ans" | ${pkgs.coreutils}/bin/tr -d '\r' | ${pkgs.gnused}/bin/sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//') diff --git a/settings/quickshell.nix b/settings/quickshell.nix index 2ae4905..8f88bdc 100644 --- a/settings/quickshell.nix +++ b/settings/quickshell.nix @@ -344,19 +344,16 @@ in 'https://en.wikipedia.org/w/api.php?action=query&format=json&generator=search&gsrlimit=3&prop=extracts&exintro&explaintext&redirects=1' ''; - # Launcher LLM answers, via the mediaserver. The API key lives on the - # server ONLY — the desktops just pipe a question over the same SSH - # path the server monitor already uses, so no laptop ever holds a - # credential and there's one place to rotate it. The remote end is - # `qs-ask` in hosts/FredOS-Mediaserver.nix. + # Launcher LLM answers, via the mediaserver. Codex uses fred's ChatGPT + # login there; desktops only pipe questions over the existing SSH path. + # The remote end is `qs-ask` in hosts/FredOS-Mediaserver.nix. # # The query goes over STDIN, not as an argv element: `ssh host cmd arg` # re-parses arg through the remote shell, so a question containing # quotes would break. stdin sidesteps remote quoting entirely. # - # Prints nothing when the key is missing, the server is unreachable, the - # call fails, or the model says it doesn't know — each of those falls - # through to the Wikipedia answer. + # Prints nothing when login is missing, the server is unreachable, the + # call fails, or the model says it doesn't know; Wikipedia then remains. askFetchScript = pkgs.writeShellScript "ask-fetch" '' q="$1" [ -z "$q" ] && exit 0 @@ -367,8 +364,7 @@ in ''; # Launcher weather. Neither of the other two answer paths can serve - # this: qs-ask runs with no tools at all, so Claude has no live data and - # correctly refuses, and Wikipedia answers "weather in kristiansand" + # this: qs-ask has no live data, and Wikipedia answers "weather in kristiansand" # with the city's founding date. open-meteo needs no key — geocode the # place name, then read current conditions at those coordinates. # @@ -2025,8 +2021,8 @@ in // the slow paths count: Wikipedia lands inside the debounce // and would just flicker the spinner. readonly property bool answerPending: askProc.running || wxProc.running - readonly property string pendingSource: wxProc.running ? "open-meteo" : "Claude" - // Claude answered the current query, so the slower-arriving + readonly property string pendingSource: wxProc.running ? "open-meteo" : "ChatGPT" + // ChatGPT answered the current query, so the slower-arriving // Wikipedia result must not overwrite it. property bool askWon: false property var answerCache: ({}) @@ -2116,10 +2112,8 @@ in } } - // Claude, tried first. The script is the feature gate: with - // no API key it exits immediately and prints nothing, which - // is the same signal as a failed call — so the Wikipedia - // path stays the default with zero configuration. + // ChatGPT, tried alongside Wikipedia. Without a Codex login + // the script prints nothing and Wikipedia remains visible. Process { id: askProc stdout: StdioCollector { @@ -2172,7 +2166,7 @@ in return; } answerQuery = q; - // Weather takes the open-meteo path alone: Claude has no + // Weather takes the open-meteo path alone: ChatGPT has no // network to look it up with, Wikipedia answers with the // city's founding date, and the cache has no notion of // age so it must not serve a temperature twice. @@ -2191,10 +2185,7 @@ in return; } // Both at once. Wikipedia fills the card in well under a - // second; Claude takes ~6s through Claude Code and - // supersedes it on arrival. Racing them beats chaining: - // Claude-then-fallback would leave the card blank for - // six seconds on every question. + // second; ChatGPT supersedes it when Codex finishes. askWon = false; killAsk(); askProc.command = [Commands.askFetch, q]; @@ -2218,7 +2209,7 @@ in fact: text.slice(0, 400), lead: "", url: "", // nothing to open - source: "Claude" + source: "ChatGPT" }; cacheAnswer(res); // Typing may have moved on while the call was out. @@ -2365,7 +2356,7 @@ in : "https://en.wikipedia.org/wiki/" + encodeURIComponent(title.replace(/ /g, "_")), source: "Wikipedia" }; - // Claude already answered this query — don't overwrite + // ChatGPT already answered this query — don't overwrite // the better answer in the cache or on screen. if (askWon) return; cacheAnswer(res); @@ -2801,7 +2792,7 @@ in anchors.rightMargin: 14 spacing: 4 - // Article title — Wikipedia only; a Claude + // Article title — Wikipedia only; a ChatGPT // answer has no page behind it. Row { spacing: 8 @@ -2842,12 +2833,12 @@ in // Always say who answered — the two sources // carry very different trust. The spinner - // runs for as long as Claude's ~6s call is + // runs for as long as the Codex call is // out, which is the only cue that a // Wikipedia answer already on screen is // still provisional — and that a card that - // never changes was Claude declining, not - // Claude being slow. + // never changes was ChatGPT declining or + // the call failing. Row { spacing: 5 SIcon {