agents: review round 2 — split-PR flow, thread recency, mention boundaries, learnings cap, pm model

- publish.sh: resolve_prs matches ai/issue-N AND ai/issue-N-<slug> split branches
  (exact-only silently stalled DELEGATE:@qa and autopilot MERGE_PR on slugged
  work); qa hand-off lists all open PRs; autopilot refuses to merge multi-PR
  issues (drops the label, hands to the human) — merging one of several open
  PRs is half a change deployed. Retro's state=all resolve matches slugs too.
- fetch-thread.sh: paginate and keep the NEWEST 100 comments — a bare limit=100
  kept the OLDEST page and dropped recent decisions on long threads.
- route.sh: word-boundary mention matching ("@internal" no longer routes to
  @intern); a comment with no real agent mention now SKIPS gracefully
  (mode=skip outputs + step guards in agent.yml) instead of a red run.
- run-agent.sh: LEARNINGS.md cap is line-aware and keeps the NEWEST entries
  (retros append at the bottom; the old head -c cut the latest lessons first).
- agents.json/README: @pm gemma4 -> minimax-m3 — the retro rule demands an
  investigating PM, and gemma4 posted 0 tool calls on every run; minimax is the
  model @qa demonstrably uses tools with.
- agent.yml: document the PR-thread concurrency-group caveat.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.gitea/workflows/agent.yml

@@ -11,6 +11,10 @@ jobs:
     # One run at a time PER ISSUE: two quick comments on the same issue would otherwise race —
     # both checking out ai/issue-N, pushing (non-fast-forward loss) and double-posting. Queued
     # runs wait (no cancel) so every trigger is still processed, just serially.
+    # KNOWN CAVEAT: a run triggered on the PR thread groups under the PR number, not the origin
+    # issue (that mapping is only resolved later, in route.sh) — so an issue-thread run and a
+    # PR-thread run for the SAME work item can overlap. Accepted: they post to different threads,
+    # and the branch is only mutated by dev runs, which resume serially per thread.
     concurrency:
       group: ai-agent-${{ github.repository }}-${{ github.event.issue.number }}
       cancel-in-progress: false
@@ -116,6 +120,7 @@ jobs:
         run: bash "$SCRIPTS/route.sh"
 
       - name: Install opencode + provider config (+ Playwright MCP for browser agents)
+        if: steps.prep.outputs.mode != 'skip'
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
           OLLAMA_URL: ${{ secrets.OLLAMA_URL }}
@@ -125,6 +130,7 @@ jobs:
         run: bash "$SCRIPTS/install-opencode.sh"
 
       - name: Install caller-provided skills (from the caller repo's .gitea/agent-skills/)
+        if: steps.prep.outputs.mode != 'skip'
         # Framework skill-plugin hook. A consuming repo can ship its OWN opencode skills under
         # `.gitea/agent-skills/<name>/` (SKILL.md + skill.json + optional setup.sh) — e.g. homelab's
         # "ssh into the deploy host" skill. This installs the ones allowed for the running agent, so
@@ -139,6 +145,7 @@ jobs:
         run: bash "$SCRIPTS/install-caller-skills.sh"
 
       - name: Set up `gitea-api` skill (let agents read/write issues, PRs, Actions across repos)
+        if: steps.prep.outputs.mode != 'skip'
         # Emits an opencode Skill file. The skill uses SELF_TOKEN — the running agent's OWN token
         # (e.g. TOKEN_PM for @pm), injected into the Run-agent step below — so each agent talks to
         # Gitea as itself. This step only writes the doc; permission.skill scopes who may load it.
@@ -147,6 +154,7 @@ jobs:
         run: bash "$SCRIPTS/skill-gitea-api.sh"
 
       - name: Set up `gitea-admin` skill (@ops only — administer the Gitea instance)
+        if: steps.prep.outputs.mode != 'skip'
         # Instance administration (orgs/users/repos/labels/secrets/scoped tokens). The SKILL.md is
         # written ONLY for @ops (skill-gitea-admin.sh gates on NAME) and permission.skill also denies
         # it to every other agent. It uses SELF_TOKEN (which for @ops is TOKEN_OPS), injected into the
@@ -157,6 +165,7 @@ jobs:
         run: bash "$SCRIPTS/skill-gitea-admin.sh"
 
       - name: Inspect / fetch image attachments (download only for vision agents)
+        if: steps.prep.outputs.mode != 'skip'
         id: imgs
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
@@ -166,6 +175,7 @@ jobs:
         run: bash "$SCRIPTS/fetch-images.sh"
 
       - name: Fetch the full issue thread (shared memory)
+        if: steps.prep.outputs.mode != 'skip'
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
           GT: ${{ secrets.GITEA_TOKEN }}
@@ -173,6 +183,7 @@ jobs:
         run: bash "$SCRIPTS/fetch-thread.sh"
 
       - name: Run agent
+        if: steps.prep.outputs.mode != 'skip'
         id: run
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
@@ -198,6 +209,7 @@ jobs:
         run: bash "$SCRIPTS/run-agent.sh"
 
       - name: Build run report (tool calls + input/output tokens + $ cost) from the event stream
+        if: steps.prep.outputs.mode != 'skip'
         id: log
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
@@ -206,6 +218,7 @@ jobs:
         run: bash "$SCRIPTS/build-activity-log.sh"
 
       - name: Publish — PR (dev agents) or comment (pm), always reply in the issue
+        if: steps.prep.outputs.mode != 'skip'
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
           GT: ${{ secrets.GITEA_TOKEN }}
@@ -232,7 +245,7 @@ jobs:
       # This best-effort step opens a PR for the pushed branch so nothing is silently lost. Runs from
       # $SCRIPTS (outside the workspace) so it works even if the tree was mangled by the agent.
       - name: Rescue — open a PR for pushed work if the run failed
-        if: failure()
+        if: failure() && steps.prep.outputs.mode != 'skip'
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
           GT: ${{ secrets.GITEA_TOKEN }}

.gitea/workflows/scripts/agents.json

@@ -1,6 +1,6 @@
 {
   "pm": {
-    "model": "ollama-cloud/gemma4:cloud",
+    "model": "ollama-cloud/minimax-m3:cloud",
     "vision": true,
     "mode": "comment",
     "skills": [

.gitea/workflows/scripts/fetch-thread.sh

@@ -4,14 +4,25 @@
 # to its real author (@pm/@qa/@junior/…). Strip the hidden `<!-- 🤖 … -->` loop-prevention marker
 # from bodies — it's plumbing, not conversation, and would just waste prompt tokens.
 #
+# PAGINATION: Gitea returns comments ASCENDING and `limit` caps a single page — a bare ?limit=100
+# used to keep the OLDEST 100 comments and silently drop the newest (the exact opposite of what an
+# agent needs on a long thread). Fetch all pages (up to 10 = 500 comments) and keep the LAST 100.
+#
 # Required env (provided by the workflow step): GT NUM GITHUB_SERVER_URL GITHUB_REPOSITORY
 set -eu
 
 API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-curl -sS -H "Authorization: token $GT" "$API/issues/$NUM/comments?limit=100" 2>/dev/null \
-  | jq -r '.[] |
+: > /tmp/thread_pages.json
+for page in $(seq 1 10); do
+  pg=$(curl -sS -H "Authorization: token $GT" "$API/issues/$NUM/comments?limit=50&page=$page" 2>/dev/null) || pg='[]'
+  n=$(printf '%s' "$pg" | jq 'if type=="array" then length else 0 end' 2>/dev/null || echo 0)
+  [ "${n:-0}" -gt 0 ] && printf '%s\n' "$pg" >> /tmp/thread_pages.json
+  [ "${n:-0}" -lt 50 ] && break
+done
+jq -rs '
+  add // [] | .[-100:] | .[] |
   ( if (.user.login == "ffaerber") then "@ffaerber (the maintainer)"
     else "@" + .user.login end ) as $who |
   "### comment by \($who):\n\(.body | gsub("\\s*<!-- 🤖 agent reply — do not trigger -->"; ""))\n"' \
-  > /tmp/thread.md 2>/dev/null || true
-echo "thread comments fetched: $(grep -c '^### comment by ' /tmp/thread.md 2>/dev/null || echo 0)"
+  /tmp/thread_pages.json > /tmp/thread.md 2>/dev/null || : > /tmp/thread.md
+echo "thread comments fetched: $(grep -c '^### comment by ' /tmp/thread.md 2>/dev/null || echo 0) (newest 100 kept)"

.gitea/workflows/scripts/publish.sh

@@ -44,8 +44,14 @@ trig() { if [ -z "$TTOK" ]; then echo "no trigger token — cannot fire on #$1";
 # Origin issue for this run (route.sh resolves it from the branch on PR threads), and a resolver for
 # the open PR built from its branch (ai/issue-<issue>). Lets @pm/@qa cross between the issue and PR.
 ISSN="${ISSNUM:-$NUM}"
-resolve_pr() { curl -sS "${hdr[@]}" "$API/pulls?state=open&limit=50" \
-  | jq -r --arg br "ai/issue-$ISSN" 'if type=="array" then (map(select(.head.ref==$br))|.[0].number // empty) else empty end' 2>/dev/null; }
+# All OPEN PRs belonging to this issue, oldest→newest. Matches ai/issue-N AND the ai/issue-N-<slug>
+# split branches AGENTS.md tells devs to use — an exact-only match silently stalled the flow on
+# slugged branches (DELEGATE:@qa found "no open PR"; autopilot MERGE_PR couldn't merge).
+resolve_prs() { curl -sS "${hdr[@]}" "$API/pulls?state=open&limit=50" \
+  | jq -r --arg br "ai/issue-$ISSN" 'if type=="array" then
+      ([ .[] | select(.head.ref==$br or (.head.ref|startswith($br+"-"))) | .number ] | sort | join(" "))
+    else "" end' 2>/dev/null; }
+resolve_pr() { resolve_prs | awk '{print $NF}'; }   # newest open PR (empty if none)
 # Remove the 'autopilot' label from an issue by resolving its ID first (Gitea's DELETE label
 # endpoint is by ID, not name). Arg $1 = issue number. Used as the autopilot kill switch.
 del_autopilot_label() {
@@ -194,9 +200,13 @@ if [ "$MODE" != "pr" ]; then
   # (@qa never merges — it approves and hands back here.) Merge with the PAT (TTOK), not the built-in
   # token, so the push to main fires the deploy. TOKEN_PM must carry write:repository.
   if [ "$NAME" = "pm" ] && [ "$AUTOPILOT" = "true" ] && grep -qiE '^[[:space:]]*MERGE_PR[[:space:]]*$' /tmp/agent_out.md; then
-    PRN=$(resolve_pr)
+    PRS=$(resolve_prs); PRN=${PRS##* }; CNT=$(echo "$PRS" | wc -w)
     if [ -z "$PRN" ]; then
       echo "MERGE_PR but no open PR found for issue #$ISSN"
+    elif [ "$CNT" -gt 1 ]; then
+      # Split-PR work: auto-merging just one of several open PRs is half a change deployed.
+      del_autopilot_label "$ISSN"
+      post_to "$ISSN" "⚠️ This issue has $CNT open PRs (#${PRS// /, #}) — autopilot only merges single-PR work. Removed the autopilot label; @ffaerber please review and merge them in order."
     else
       echo "@pm autopilot: merging PR #$PRN (issue #$ISSN)"
       mc=$(curl -sS -o /tmp/merge_resp.txt -w '%{http_code}' -X POST \
@@ -221,7 +231,7 @@ if [ "$MODE" != "pr" ]; then
   # pm → qa → merge), and run-agent.sh injects LEARNINGS.md into every future prompt — closing the loop.
   if [ "$NAME" = "pm" ] && grep -qiE '^[[:space:]]*RETRO[[:space:]]*$' /tmp/agent_out.md; then
     PRN=$(curl -sS "${hdr[@]}" "$API/pulls?state=all&limit=50" \
-      | jq -r --arg br "ai/issue-$ISSN" 'if type=="array" then ([.[]|select(.head.ref==$br)] | sort_by(.number) | last | .number // empty) else empty end' 2>/dev/null)
+      | jq -r --arg br "ai/issue-$ISSN" 'if type=="array" then ([.[]|select(.head.ref==$br or (.head.ref|startswith($br+"-")))] | sort_by(.number) | last | .number // empty) else empty end' 2>/dev/null)
     rbody=$(printf 'Retrospective for issue #%s%s.\n\nRead the FULL issue thread%s using the gitea-api skill (issue comments%s and the PR diff). Identify what went wrong, slow, or needed human correction — missed wiring, review misses, bounced rounds, unclear delegation, missing context.\n\nThen APPEND the distilled learnings to `LEARNINGS.md` at the repo root (create it with a short header if missing). Rules for entries:\n- 3 to 6 bullets max, each ONE line: `symptom -> rule for next time`.\n- Concrete and checkable (name the file/step/marker), not generic advice.\n- Do not repeat an existing bullet; refine it instead.\n- Do not rewrite unrelated parts of the file.\n\nThese learnings are injected into every future agent prompt, so quality over quantity.' \
       "$ISSN" "${PRN:+ / PR #$PRN}" "${PRN:+ and PR #$PRN thread}" "${PRN:+, PR comments}")
     rnum=$(curl -sS -X POST "${hdr[@]}" "$API/issues" \
@@ -242,8 +252,10 @@ if [ "$MODE" != "pr" ]; then
   # the PR. Chain terminates: normal → @pm tells the creator (no marker); autopilot → @pm merges above.
   if [ -n "$target" ] && [ "$target" != "$NAME" ]; then
     if [ "$target" = "qa" ]; then
-      PRN=$(resolve_pr)
-      if [ -n "$PRN" ]; then
+      PRS=$(resolve_prs); PRN=${PRS##* }; CNT=$(echo "$PRS" | wc -w)
+      if [ -n "$PRN" ] && [ "$CNT" -gt 1 ]; then
+        trig "$ISSN" "@qa please review the $CNT open PRs for issue #$ISSN (#${PRS// /, #}) — put your recommendations on each PR; approve only when ALL are good."
+      elif [ -n "$PRN" ]; then
         trig "$ISSN" "@qa please review PR #$PRN for issue #$ISSN — put your recommendations on the PR, or approve."
       else
         echo "DELEGATE:@qa but no open PR yet for issue #$ISSN — not firing"

.gitea/workflows/scripts/route.sh

@@ -31,11 +31,22 @@ name=""
 # load-bearing for the flow's trigger comments: "@pm — @qa approved …" must route to @pm (pm is
 # checked first), while "@junior please address @qa's review …" must route to the dev (devs are
 # checked before qa). If you add an agent or reword a trigger in publish.sh, re-check this order.
+# WORD-BOUNDARY match, not substring: "@internal" or "x@internet.com" must NOT route to @intern
+# (the workflow gate can only do contains(), so this is where its false positives get filtered).
 for a in pm junior senior lead qa ops intern; do
-  case "$scan" in *"@$a"*) name=$a; break;; esac
+  if printf '%s' "$scan" | grep -qE "(^|[^[:alnum:]_])@$a([^[:alnum:]_-]|\$)"; then name=$a; break; fi
 done
 if [ -z "$name" ]; then
-  if [ -z "$CID" ]; then name=pm; else echo "no known agent mentioned"; exit 1; fi
+  if [ -z "$CID" ]; then
+    name=pm
+  else
+    # Not an agent task (e.g. the gate's contains() matched "@internal"). Skip GRACEFULLY: emit
+    # mode=skip so every later step no-ops — a red run for a non-agent comment is just noise.
+    echo "no known agent mentioned (word-boundary) — skipping run"
+    { echo "name=none"; echo "model=none"; echo "vision=false"; echo "mode=skip"; echo "skills=[]";
+      echo "branch=main"; echo "new=false"; echo "autopilot=false"; echo "issnum=$NUM"; } >> "$GITHUB_OUTPUT"
+    exit 0
+  fi
 fi
 model=$(jq -r --arg a "$name" '.[$a].model'  /tmp/agents.json)
 vision=$(jq -r --arg a "$name" '.[$a].vision' /tmp/agents.json)

.gitea/workflows/scripts/run-agent.sh

@@ -109,8 +109,18 @@ fi
 # TEAM LEARNINGS — distilled from past retros (see the RETRO flow in publish.sh). Lives at the
 # CALLER repo root as LEARNINGS.md, maintained by retro PRs. Injected into EVERY agent's prompt
 # (capped) so past mistakes actually change future behavior — this is the feedback loop.
+# Cap is LINE-aware and keeps the NEWEST entries: retros append at the bottom, so a byte-cap from
+# the top would silently drop the latest lessons first (and cut mid-bullet).
 LEARN=""
-[ -s LEARNINGS.md ] && LEARN=$(head -c 4000 LEARNINGS.md)
+if [ -s LEARNINGS.md ]; then
+  if [ "$(wc -l < LEARNINGS.md)" -gt 80 ]; then
+    LEARN=$(printf '%s\n_(older learnings truncated — full list in LEARNINGS.md)_\n%s' \
+      "$(head -n 3 LEARNINGS.md)" "$(tail -n 70 LEARNINGS.md)")
+  else
+    LEARN=$(cat LEARNINGS.md)
+  fi
+  LEARN=$(printf '%s' "$LEARN" | head -c 8000)
+fi
 [ -n "$LEARN" ] && LEARN="
    TEAM LEARNINGS (distilled from past retros in this repo — APPLY them; they exist because a
    previous task went wrong without them):

README.md

@@ -7,7 +7,7 @@ Shared **AI dev-team** workflow for Gitea Actions, reusable across repos. It giv
 
 | Agent | Model | Vision | Mode | Skills | Role |
 |-------|-------|:------:|------|--------|------|
-| `@pm` | `ollama-cloud/gemma4:cloud` | yes | comment | `gitea-api` | Product manager & orchestrator — plans, picks the dev, hands finished PRs to `@qa`, reports back to the issue creator (autopilot: merges approved PRs itself). Issue thread only; never edits files, never reads the PR diff. |
+| `@pm` | `ollama-cloud/minimax-m3:cloud` | yes | comment | `gitea-api` | Product manager & orchestrator — plans, picks the dev, hands finished PRs to `@qa`, reports back to the issue creator (autopilot: merges approved PRs itself). Issue thread only; never edits files, never reads the PR diff. |
 | `@junior` | `ollama-cloud/kimi-k2.7-code:cloud` | no | pr | — | Junior dev — small, low-risk changes (mostly YAML/compose/config). Text-only, cannot read images. Defers complex or image tasks to `@senior` or `@lead`. |
 | `@senior` | `ollama-cloud/glm-5.2:cloud` | no | pr | `gitea-api` | Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only). |
 | `@lead` | `anthropic/claude-opus-4-8` | yes | pr | `gitea-api` | Tech lead — the hardest problems, architecture, and final calls. |