Compare commits
19
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ebb03e7063 | ||
|
|
63701fbebb | ||
|
|
e8a047eb14 | ||
|
|
0279210595 | ||
|
|
25f09e9b52 | ||
|
|
82f2825d3f | ||
|
|
0fec080b4d | ||
|
|
7424c6aefd | ||
|
|
4e3fb88309 | ||
|
|
c8c5ce9015 | ||
|
|
293f51b914 | ||
|
|
70287db150 | ||
|
|
efedba1ff0 | ||
|
|
f35a2d5985 | ||
|
|
19b641a2b6 | ||
|
|
e422e6a13d | ||
|
|
f4d590c40d | ||
|
|
791cb6e524 | ||
|
|
3749df798e |
@@ -0,0 +1,140 @@
|
||||
# Nightly wiki maintenance for the Notes vault (k.renner/notes), replacing the
|
||||
# workstation's wiki-maintenance.timer: distill the raw/ backlog into wiki/,
|
||||
# then audit wiki/. Each agent is its own `claude` run, not a subagent of an
|
||||
# orchestrator, so nothing depends on background tasks in print mode (the
|
||||
# workstation job died on their 600 s ceiling). The pipeline commits and pushes
|
||||
# as Claude Bot; the push webhook then refreshes the wiki-index service.
|
||||
#
|
||||
# The agents and their retrieval scripts address the vault as ~/Notes, so each
|
||||
# agent step links $HOME/Notes to the checkout instead of rewriting them.
|
||||
when:
|
||||
- event: cron
|
||||
cron: wiki-maintenance
|
||||
# Hand-started runs: `woodpecker pipeline create k.renner/homelab --branch master`.
|
||||
# The typesafe_api_key secret is scoped to cron and manual, not deployment.
|
||||
- event: manual
|
||||
|
||||
steps:
|
||||
- name: checkout-notes
|
||||
image: gitea.renner.uno/gitea_admin/ci-claude:2.1.278
|
||||
pull: true
|
||||
environment:
|
||||
WIKI_BOT_TOKEN:
|
||||
from_secret: wiki_bot_token
|
||||
commands:
|
||||
- |
|
||||
set -eu
|
||||
# Token only on the wire, never in .git/config. Secrets set from files carry
|
||||
# a trailing newline (run 10220: "could not read Username"); strip CR/LF.
|
||||
TOKEN=$$(printf '%s' "$$WIKI_BOT_TOKEN" | tr -d '\r\n')
|
||||
git -c http.extraheader="AUTHORIZATION: token $$TOKEN" \
|
||||
clone --depth 50 --branch main https://gitea.renner.uno/k.renner/notes.git notes
|
||||
echo "raw backlog: $$(ls notes/raw/*.md | grep -v _index.md | wc -l) file(s)"
|
||||
|
||||
- name: distill
|
||||
image: gitea.renner.uno/gitea_admin/ci-claude:2.1.278
|
||||
pull: true
|
||||
environment:
|
||||
CLAUDE_CODE_OAUTH_TOKEN:
|
||||
from_secret: claude_code_oauth_token
|
||||
TYPESAFE_API_KEY:
|
||||
from_secret: typesafe_api_key
|
||||
WIKI_INDEX_BASIC_AUTH:
|
||||
from_secret: wiki_index_basic_auth
|
||||
commands:
|
||||
- |
|
||||
set -eu
|
||||
ln -sfn "$$PWD/notes" "$$HOME/Notes"
|
||||
mkdir -p "$$HOME/.config/wiki-index"
|
||||
printf '%s' "$$WIKI_INDEX_BASIC_AUTH" | tr -d '\r\n' > "$$HOME/.config/wiki-index/basic-auth"
|
||||
chmod 600 "$$HOME/.config/wiki-index/basic-auth"
|
||||
"$$HOME/Notes/bin/wiki_rank.py" --probe-index
|
||||
- |
|
||||
set -eu
|
||||
MODEL=$$(sh scripts/ci/pick-model.sh "distill raw source notes into atomic wiki notes: read sources, check the wiki for existing coverage, write or merge notes; careful writing, moderate reasoning")
|
||||
if [ -n "$$MODEL" ]; then echo "distill: selected model $$MODEL"; else echo "distill: using the CLI default model"; fi
|
||||
cd notes
|
||||
cat ../ci/agents/wiki-maintenance/distill.md | claude $${MODEL:+--model $$MODEL} \
|
||||
--agent wiki-distill \
|
||||
--permission-mode acceptEdits \
|
||||
--allowedTools "Read,Edit,Write,Glob,Grep,Bash(/root/Notes/bin/wiki_rank.py:*),Bash(/root/Notes/bin/wiki_ask.py:*),Bash(mv /root/Notes/raw/:*),Bash(mkdir -p /root/Notes/:*)" \
|
||||
--settings ../ci/agents/wiki-maintenance/settings.json \
|
||||
-p
|
||||
|
||||
- name: audit
|
||||
image: gitea.renner.uno/gitea_admin/ci-claude:2.1.278
|
||||
pull: true
|
||||
environment:
|
||||
CLAUDE_CODE_OAUTH_TOKEN:
|
||||
from_secret: claude_code_oauth_token
|
||||
TYPESAFE_API_KEY:
|
||||
from_secret: typesafe_api_key
|
||||
WIKI_INDEX_BASIC_AUTH:
|
||||
from_secret: wiki_index_basic_auth
|
||||
commands:
|
||||
- |
|
||||
set -eu
|
||||
ln -sfn "$$PWD/notes" "$$HOME/Notes"
|
||||
mkdir -p "$$HOME/.config/wiki-index"
|
||||
printf '%s' "$$WIKI_INDEX_BASIC_AUTH" | tr -d '\r\n' > "$$HOME/.config/wiki-index/basic-auth"
|
||||
chmod 600 "$$HOME/.config/wiki-index/basic-auth"
|
||||
- |
|
||||
set -eu
|
||||
MODEL=$$(sh scripts/ci/pick-model.sh "structural audit of ~1700 markdown notes: frontmatter completeness, broken links, orphans; mechanical checks, little reasoning")
|
||||
if [ -n "$$MODEL" ]; then echo "audit: selected model $$MODEL"; else echo "audit: using the CLI default model"; fi
|
||||
cd notes
|
||||
cat ../ci/agents/wiki-maintenance/audit.md | claude $${MODEL:+--model $$MODEL} \
|
||||
--agent wiki-audit \
|
||||
--permission-mode acceptEdits \
|
||||
--allowedTools "Read,Write,Glob,Grep,Bash(/root/Notes/bin/wiki_rank.py:*),Bash(/root/Notes/bin/wiki_ask.py:*)" \
|
||||
--settings ../ci/agents/wiki-maintenance/settings.json \
|
||||
-p
|
||||
|
||||
- name: push-notes
|
||||
image: gitea.renner.uno/gitea_admin/ci-claude:2.1.278
|
||||
pull: true
|
||||
environment:
|
||||
WIKI_BOT_TOKEN:
|
||||
from_secret: wiki_bot_token
|
||||
commands:
|
||||
- |
|
||||
set -eu
|
||||
cd notes
|
||||
git config user.email "claude-bot@renner.uno"
|
||||
git config user.name "Claude Bot"
|
||||
if git diff --quiet && git diff --cached --quiet && [ -z "$$(git ls-files --others --exclude-standard)" ]; then
|
||||
echo "wiki-maintenance: no changes"
|
||||
exit 0
|
||||
fi
|
||||
# The workstation pushes main on its own (notes-push.path), so main moves
|
||||
# while the agents run (run 10241: non-fast-forward). The run's work goes
|
||||
# to a branch and a PR that this step merges through Gitea; a conflict
|
||||
# leaves the PR open for a human and fails the run.
|
||||
BRANCH="wiki-maintenance/$$(date -u +%F)-$$CI_PIPELINE_NUMBER"
|
||||
git checkout -q -b "$$BRANCH"
|
||||
git add -A
|
||||
git commit -q -m "wiki maintenance $$(date -u +%F): distill + audit (CI run $$CI_PIPELINE_NUMBER)"
|
||||
TOKEN=$$(printf '%s' "$$WIKI_BOT_TOKEN" | tr -d '\r\n')
|
||||
git -c http.extraheader="AUTHORIZATION: token $$TOKEN" push origin "HEAD:$$BRANCH"
|
||||
API="https://gitea.renner.uno/api/v1/repos/k.renner/notes"
|
||||
jq -n --arg title "wiki maintenance $$(date -u +%F) (CI run $$CI_PIPELINE_NUMBER)" \
|
||||
--arg body "Nightly distill + audit. Merged by the pipeline; open only if the merge failed." \
|
||||
--arg head "$$BRANCH" '{title: $$title, body: $$body, head: $$head, base: "main"}' > /tmp/pr.json
|
||||
code=$$(curl -s -o /tmp/pr-resp.json -w '%{http_code}' -X POST \
|
||||
-H "Authorization: token $$TOKEN" -H "Content-Type: application/json" --data @/tmp/pr.json "$$API/pulls")
|
||||
echo "POST pull -> HTTP $$code"
|
||||
[ "$$code" -ge 200 ] && [ "$$code" -lt 300 ] || { cat /tmp/pr-resp.json; exit 1; }
|
||||
NUM=$$(jq -r '.number' /tmp/pr-resp.json)
|
||||
# Merge without delete_branch_after_merge: run 10254 got HTTP 500 from that
|
||||
# call although the merge itself had landed. Verify the PR state instead of
|
||||
# trusting the status code, then drop the branch as a separate, best-effort step.
|
||||
code=$$(curl -s -o /tmp/merge-resp.json -w '%{http_code}' -X POST \
|
||||
-H "Authorization: token $$TOKEN" -H "Content-Type: application/json" \
|
||||
--data '{"Do":"merge"}' "$$API/pulls/$$NUM/merge")
|
||||
echo "POST merge #$$NUM -> HTTP $$code"
|
||||
MERGED=$$(curl -s -H "Authorization: token $$TOKEN" "$$API/pulls/$$NUM" | jq -r '.merged')
|
||||
echo "PR #$$NUM merged: $$MERGED"
|
||||
[ "$$MERGED" = "true" ] || { cat /tmp/merge-resp.json; echo "PR #$$NUM left open"; exit 1; }
|
||||
code=$$(curl -s -o /tmp/del-resp.json -w '%{http_code}' -X DELETE -H "Authorization: token $$TOKEN" \
|
||||
"$$API/branches/$$(printf '%s' "$$BRANCH" | sed 's|/|%2F|g')")
|
||||
echo "DELETE branch $$BRANCH -> HTTP $$code (best effort)"
|
||||
@@ -0,0 +1,5 @@
|
||||
You are running as the scheduled wiki-maintenance job in CI. The Notes vault is checked out at ~/Notes (the repository k.renner/notes).
|
||||
|
||||
Run the standard audit pass over ~/Notes/wiki/ and write the dated report to ~/Notes/output/. Do not modify any wiki note. Do not commit or push; the pipeline does that.
|
||||
|
||||
End with two lines: notes scanned, and issues found by category.
|
||||
@@ -0,0 +1,7 @@
|
||||
You are running as the scheduled wiki-maintenance job in CI. The Notes vault is checked out at ~/Notes (the repository k.renner/notes). Do exactly this, nothing else:
|
||||
|
||||
Glob ~/Notes/raw/*.md (top level only, never ~/Notes/raw/_processed/). Distill every file you find into ~/Notes/wiki/ following your process, including the ranker check for every concept. Move each fully processed source to ~/Notes/raw/_processed/. If raw/ has no top-level files besides _index.md, say so and stop.
|
||||
|
||||
Do not commit or push; the pipeline does that after you finish. Do not touch anything outside ~/Notes/wiki/ and ~/Notes/raw/.
|
||||
|
||||
End with one line per file: which wiki notes it produced or merged into, or "nothing distillable".
|
||||
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"//": "Permission scope for the wiki-maintenance agents (wiki-distill, wiki-audit) in CI.",
|
||||
"//2": "The step's environment holds a Gitea push token, a TypeSafe key and the wiki-index",
|
||||
"//3": "client credential, so the Read tool is kept away from /proc (env dumps), /root outside",
|
||||
"//4": "the vault symlink target, /etc and the checkout's .git/. The vault itself is the work.",
|
||||
"//5": "Mirrors ci/agents/issue-fix/settings.json; absolute globs because the vault is reached",
|
||||
"//6": "through the ~/Notes symlink the pipeline creates.",
|
||||
"permissions": {
|
||||
"allow": [
|
||||
"Read(//root/Notes/**)",
|
||||
"Edit(//root/Notes/wiki/**)",
|
||||
"Edit(//root/Notes/output/**)",
|
||||
"Edit(//root/Notes/raw/**)",
|
||||
"Bash(/root/Notes/bin/wiki_rank.py:*)",
|
||||
"Bash(/root/Notes/bin/wiki_ask.py:*)",
|
||||
"Bash(mv /root/Notes/raw/:*)",
|
||||
"Bash(mkdir -p /root/Notes/:*)",
|
||||
"Bash(ls:*)",
|
||||
"Bash(date:*)",
|
||||
"Bash(wc:*)",
|
||||
"Bash(head:*)",
|
||||
"Bash(tail:*)"
|
||||
],
|
||||
"deny": [
|
||||
"Read(//proc/**)",
|
||||
"Read(//etc/**)",
|
||||
"Read(//root/.config/**)",
|
||||
"Read(//root/Notes/.git/**)",
|
||||
"Read(//root/Notes/_archive/**)",
|
||||
"Edit(//root/Notes/_archive/**)",
|
||||
"Bash(rm:*)",
|
||||
"Bash(git:*)",
|
||||
"Bash(curl:*)",
|
||||
"Bash(wget:*)"
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -13,7 +13,9 @@ RUN apk add --no-cache \
|
||||
git \
|
||||
jq \
|
||||
openssh-client \
|
||||
openssl
|
||||
openssl \
|
||||
python3 \
|
||||
py3-yaml
|
||||
|
||||
# Install Claude Code, then make the resulting layer byte-stable so that a
|
||||
# rebuild of the SAME version DEDUPS in the Gitea registry instead of orphaning
|
||||
|
||||
@@ -27,6 +27,24 @@ data:
|
||||
PAPERLESS_ALLOWED_HOSTS: "*"
|
||||
PAPERLESS_TIME_ZONE: "Europe/Berlin"
|
||||
PAPERLESS_OCR_LANGUAGE: "deu+eng"
|
||||
# OCR concurrency, pinned rather than derived. paperless hands
|
||||
# THREADS_PER_WORKER to ocrmypdf as its job count, and the default is
|
||||
# cpu_count() / TASK_WORKERS. The container has no CPU limit, so
|
||||
# multiprocessing.cpu_count() reports the NODE's cores — 20 on k8s-1 —
|
||||
# and OCR fans out to "Starting processing with 20 workers concurrently".
|
||||
# Twenty pages of a 300dpi colour scan rasterised at once blew past
|
||||
# limits.memory below and the kernel OOMKilled the container (exit 137)
|
||||
# mid-consume. Because celery re-picks the same document on every restart,
|
||||
# that is a crash loop and not a one-off: the pod OOMs ~37s in, before the
|
||||
# webserver ever finishes booting, so it never goes Ready and the archive
|
||||
# stays down.
|
||||
#
|
||||
# TASK_WORKERS is already effectively 1 (20 cores / 1 worker = the 20 jobs
|
||||
# observed); pinning it keeps that explicit so THREADS_PER_WORKER stays the
|
||||
# only knob, and neither value silently changes when this lands on a node
|
||||
# with a different core count.
|
||||
PAPERLESS_TASK_WORKERS: "1"
|
||||
PAPERLESS_THREADS_PER_WORKER: "4"
|
||||
PAPERLESS_CONSUMER_RECURSIVE: "true"
|
||||
PAPERLESS_CONSUMER_DELETE_DUPLICATES: "true"
|
||||
PAPERLESS_CONSUMER_ENABLE_BARCODES: "true"
|
||||
@@ -183,7 +201,7 @@ spec:
|
||||
drop: ["ALL"]
|
||||
containers:
|
||||
- name: paperless
|
||||
image: ghcr.io/paperless-ngx/paperless-ngx:3.2.0 # {"$imagepolicy": "flux-system:paperless-ngx"}
|
||||
image: ghcr.io/paperless-ngx/paperless-ngx:3.2.1 # {"$imagepolicy": "flux-system:paperless-ngx"}
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 8000
|
||||
@@ -273,7 +291,15 @@ spec:
|
||||
cpu: 200m
|
||||
memory: 512Mi
|
||||
limits:
|
||||
memory: 2Gi
|
||||
# Headroom, not the fix — capping OCR jobs in paperless-config
|
||||
# is. Sized from what a healthy pod actually uses: the last
|
||||
# long-lived container held a steady ~1.0Gi working set, so 2Gi
|
||||
# left barely 1Gi for an OCR burst. 3Gi keeps a 4-job burst
|
||||
# clear of the ceiling. The crashlooping containers never showed
|
||||
# this in cadvisor (~820Mi peak) because they lived 37s against
|
||||
# a ~30s scrape interval — the spike fell between samples, so
|
||||
# the OOMKilled status, not the metric, is the reliable signal.
|
||||
memory: 3Gi
|
||||
securityContext:
|
||||
runAsNonRoot: false
|
||||
allowPrivilegeEscalation: true
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
#!/bin/sh
|
||||
# Turn the TypeSafe picker's probability distribution into one model id.
|
||||
#
|
||||
# The judgment (how well each catalog model fits the task) comes from the
|
||||
# model; the policy lives here, in code: among the candidates whose probability
|
||||
# is within MARGIN of the best one, take the most recently released. Several
|
||||
# same-family models (Sonnet 4.5 / 4.6 / 5) split the probability for a
|
||||
# mid-weight task, and the newest of a comparable set is the one to run.
|
||||
#
|
||||
# Usage: choose-model.sh <catalog-table-file> < <systemone-response.json>
|
||||
# The table is fetch-models.sh --table output: id \t name \t released=YYYY-MM-DD ...
|
||||
# Prints the chosen id, or nothing when the answer is NONE / unusable.
|
||||
# Env: CHOOSE_MODEL_MARGIN (default 0.7): candidate if p >= MARGIN * p_best.
|
||||
|
||||
set -eu
|
||||
TABLE_FILE="${1:?usage: choose-model.sh <catalog-table-file> < response.json}"
|
||||
MARGIN="${CHOOSE_MODEL_MARGIN:-0.7}"
|
||||
|
||||
jq -r --rawfile table "$TABLE_FILE" --argjson margin "$MARGIN" '
|
||||
($table | split("\n") | map(select(length > 0) | split("\t")
|
||||
| {key: .[0], value: ((.[2:] | map(select(startswith("released="))) | .[0] // "released=") | ltrimstr("released="))})
|
||||
| from_entries) as $released
|
||||
| (.answers.model.probabilities // {}) | to_entries
|
||||
| map(select(.key != "NONE")) | sort_by(-.value)
|
||||
| if length == 0 then empty
|
||||
else (.[0].value) as $best
|
||||
| map(select(.value >= $margin * $best))
|
||||
| sort_by([($released[.key] // ""), .value])
|
||||
| .[-1].key
|
||||
end' 2>&1
|
||||
@@ -33,6 +33,42 @@ none() { log "$1"; exit 0; } # emit nothing -> caller uses CLI defaul
|
||||
TABLE="$(sh "$HERE/fetch-models.sh" --table || true)"
|
||||
[ -n "$TABLE" ] || none "no catalog available — caller will use the CLI default model"
|
||||
|
||||
# First choice: one TypeSafe (System One) Choice over the catalog. The task and
|
||||
# the catalog rows are state, every model id is an option with its catalog row
|
||||
# as the criterion, and the answer is typed — no prompt, no JSON parsing, and a
|
||||
# request that takes a fraction of a second instead of a claude run. The id is
|
||||
# still validated against the pristine catalog. Falls through to the claude
|
||||
# picker when the key is absent or the request fails.
|
||||
if [ -n "${TYPESAFE_API_KEY:-}" ]; then
|
||||
REQ="$(printf '%s\n' "$TABLE" | jq -R -s --arg task "$GUIDANCE" '
|
||||
split("\n") | map(select(length > 0) | split("\t") | {id: .[0], name: .[1], info: (.[2:] | join(", "))})
|
||||
| {model: "jev-latest",
|
||||
state: {task: $task, models: .},
|
||||
questions: {model: {
|
||||
type: "choice",
|
||||
instructions: "Which model in `models` should run `task`? Match the model to the task: not the largest or newest flagship for trivial or mechanical work, not a minimal model for hard, multi-step or security-sensitive work; prefer a newer model when otherwise comparable. Consider every listed model, including unfamiliar ones. Pick NONE only if no listed model fits.",
|
||||
criteria: ((map({key: .id, value: "\(.name); \(.info)"}) | from_entries) + {NONE: "No listed model fits the task"})}}}')"
|
||||
if [ -n "${PICK_MODEL_TYPESAFE_DRYRUN:-}" ]; then printf '%s\n' "$REQ"; exit 0; fi
|
||||
RESP="$(printf '%s' "$REQ" | curl -sS --max-time 30 -X POST https://api.typesafe.ai/v1/systemone \
|
||||
-H "Authorization: Bearer $TYPESAFE_API_KEY" -H 'Content-Type: application/json' --data-binary @- || true)"
|
||||
# Policy in code (choose-model.sh): among candidates within a margin of the
|
||||
# best probability, the most recently released wins. Same-family models split
|
||||
# the probability for mid-weight tasks (live catalog: Sonnet 4.5 chosen at
|
||||
# 0.23 over Sonnet 4.6).
|
||||
TABLE_FILE="$(mktemp)"
|
||||
printf '%s\n' "$TABLE" > "$TABLE_FILE"
|
||||
CHOICE="$(printf '%s' "$RESP" | sh "$HERE/choose-model.sh" "$TABLE_FILE" | head -1)"
|
||||
rm -f "$TABLE_FILE"
|
||||
TOP="$(printf '%s' "$RESP" | jq -r '(.answers.model.probabilities // {}) | to_entries | sort_by(-.value) | .[0:4] | map("\(.key)=\(.value)") | join(" ")' 2>&1 | head -1)"
|
||||
VALID="$(printf '%s\n' "$TABLE" | sh "$HERE/valid-model.sh" "$CHOICE")"
|
||||
if [ -n "$VALID" ]; then
|
||||
log "typesafe chose '$VALID' (top: ${TOP:-?}) for: $GUIDANCE"
|
||||
printf '%s\n' "$VALID"
|
||||
exit 0
|
||||
fi
|
||||
log "typesafe picker returned '${CHOICE:-<empty>}' (rejected, NONE, or request failed) — falling back to the claude picker"
|
||||
fi
|
||||
|
||||
PROMPT="$(cat <<EOF
|
||||
You are a model-selection agent for an automated CI job. From the models
|
||||
currently available (listed below with their capabilities), choose the single
|
||||
|
||||
@@ -84,9 +84,40 @@ else
|
||||
printf 'FAIL recorded fixture: opus=[%s] haiku=[%s]\n' "$opusline" "$haikuline"; fails=$((fails + 1))
|
||||
fi
|
||||
|
||||
|
||||
# TypeSafe path of pick-model.sh: the request offers exactly the catalog ids plus
|
||||
# NONE as options, carries the task as state, and never sends anything else.
|
||||
printf '%s' '{"data":[{"type":"model","id":"claude-opus-5","display_name":"Claude Opus 5","created_at":"2026-07-24T00:00:00Z","max_input_tokens":1000000,"max_tokens":128000},{"type":"model","id":"claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","created_at":"2025-10-15T00:00:00Z","max_input_tokens":200000,"max_tokens":64000}],"has_more":false}' > "$FX"
|
||||
req="$(FETCH_MODELS_BODY_FILE="$FX" TYPESAFE_API_KEY=dry PICK_MODEL_TYPESAFE_DRYRUN=1 sh "$HERE/pick-model.sh" "a task; with \"quotes\" and $ signs" 2>/dev/null || true)"
|
||||
keys="$(printf '%s' "$req" | jq -r '.questions.model.criteria | keys | join(",")' 2>/dev/null || true)"
|
||||
task="$(printf '%s' "$req" | jq -r '.state.task' 2>/dev/null || true)"
|
||||
if [ "$keys" = "NONE,claude-haiku-4-5-20251001,claude-opus-5" ] && [ "$task" = 'a task; with "quotes" and $ signs' ]; then
|
||||
printf 'ok typesafe request offers catalog ids + NONE and carries the task verbatim\n'
|
||||
else
|
||||
printf 'FAIL typesafe request: keys [%s] task [%s]\n' "$keys" "$task"; fails=$((fails + 1))
|
||||
fi
|
||||
|
||||
# choose-model.sh: newest among comparable candidates, best otherwise, NONE -> nothing.
|
||||
TB="$(mktemp)"
|
||||
printf '%s\n' 'claude-sonnet-4-5 Claude Sonnet 4.5 released=2025-09-29 context=200000' \
|
||||
'claude-sonnet-4-6 Claude Sonnet 4.6 released=2026-02-17 context=200000' \
|
||||
'claude-opus-5 Claude Opus 5 released=2026-07-24 context=1000000' \
|
||||
'claude-haiku-4-5 Claude Haiku 4.5 released=2025-10-15 context=200000' > "$TB"
|
||||
choose() { printf '%s' "$1" | sh "$HERE/choose-model.sh" "$TB" || true; }
|
||||
got="$(choose '{"answers":{"model":{"probabilities":{"claude-sonnet-4-5":0.30,"claude-sonnet-4-6":0.25,"claude-opus-5":0.10,"NONE":0.05}}}}')"
|
||||
if [ "$got" = "claude-sonnet-4-6" ]; then printf 'ok newer sibling within margin wins\n'; else printf 'FAIL comparable: got [%s]\n' "$got"; fails=$((fails + 1)); fi
|
||||
got="$(choose '{"answers":{"model":{"probabilities":{"claude-opus-5":0.90,"claude-haiku-4-5":0.05,"claude-sonnet-4-6":0.04,"NONE":0.01}}}}')"
|
||||
if [ "$got" = "claude-opus-5" ]; then printf 'ok clear best is kept\n'; else printf 'FAIL clear best: got [%s]\n' "$got"; fails=$((fails + 1)); fi
|
||||
got="$(choose '{"answers":{"model":{"probabilities":{"claude-haiku-4-5":0.60,"claude-sonnet-4-5":0.35,"NONE":0.05}}}}')"
|
||||
if [ "$got" = "claude-haiku-4-5" ]; then printf 'ok older best outside margin is kept\n'; else printf 'FAIL margin: got [%s]\n' "$got"; fails=$((fails + 1)); fi
|
||||
got="$(choose '{"answers":{"model":{"probabilities":{"NONE":1.0}}}}')"
|
||||
if [ -z "$got" ]; then printf 'ok NONE yields nothing\n'; else printf 'FAIL NONE: got [%s]\n' "$got"; fails=$((fails + 1)); fi
|
||||
rm -f "$TB"
|
||||
|
||||
if [ "$fails" -eq 0 ]; then
|
||||
echo "All model-selection tests passed."
|
||||
else
|
||||
echo "$fails test(s) FAILED."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
|
||||
Reference in New Issue
Block a user