.gitea/workflows/agent.yml

@@ -169,9 +169,10 @@ jobs:
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           # SELF_TOKEN = the RUNNING agent's OWN token (TOKEN_PM for @pm, TOKEN_OPS for @ops, …).
           # Only this agent's token is placed in its process env, so no agent can act as another.
-          # Powers the gitea-api / gitea-admin skills — each agent calls Gitea as itself. Falls back
-          # to AGENT_TOKEN in repos that haven't been migrated to per-agent tokens (e.g. homelab).
-          SELF_TOKEN: ${{ steps.prep.outputs.name == 'pm' && secrets.TOKEN_PM || steps.prep.outputs.name == 'junior' && secrets.TOKEN_JUNIOR || steps.prep.outputs.name == 'senior' && secrets.TOKEN_SENIOR || steps.prep.outputs.name == 'lead' && secrets.TOKEN_LEAD || steps.prep.outputs.name == 'qa' && secrets.TOKEN_QA || steps.prep.outputs.name == 'ops' && secrets.TOKEN_OPS || secrets.AGENT_TOKEN }}
+          # Powers the gitea-api / gitea-admin skills — each agent calls Gitea as itself. Every
+          # consuming repo now carries the per-agent TOKEN_* secrets (org-level for gitea/*, user-level
+          # for ffaerber/*), so there is no shared-token fallback.
+          SELF_TOKEN: ${{ steps.prep.outputs.name == 'pm' && secrets.TOKEN_PM || steps.prep.outputs.name == 'junior' && secrets.TOKEN_JUNIOR || steps.prep.outputs.name == 'senior' && secrets.TOKEN_SENIOR || steps.prep.outputs.name == 'lead' && secrets.TOKEN_LEAD || steps.prep.outputs.name == 'qa' && secrets.TOKEN_QA || steps.prep.outputs.name == 'ops' && secrets.TOKEN_OPS || '' }}
           NAME: ${{ steps.prep.outputs.name }}
           MODEL: ${{ steps.prep.outputs.model }}
           VISION: ${{ steps.prep.outputs.vision }}
@@ -197,9 +198,6 @@ jobs:
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
           GT: ${{ secrets.GITEA_TOKEN }}
-          # Fallback PAT for triggering comments (delegation/autopilot) + merges in repos without
-          # per-agent tokens. Where per-agent tokens exist, the agent's own token is used instead.
-          AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}
           TOKEN_PM: ${{ secrets.TOKEN_PM }}
           TOKEN_SENIOR: ${{ secrets.TOKEN_SENIOR }}
           TOKEN_JUNIOR: ${{ secrets.TOKEN_JUNIOR }}
@@ -226,9 +224,6 @@ jobs:
         env:
           SCRIPTS: ${{ runner.temp }}/agents-scripts
           GT: ${{ secrets.GITEA_TOKEN }}
-          # Fallback PAT for triggering comments (delegation/autopilot) + merges in repos without
-          # per-agent tokens. Where per-agent tokens exist, the agent's own token is used instead.
-          AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}
           TOKEN_PM: ${{ secrets.TOKEN_PM }}
           TOKEN_SENIOR: ${{ secrets.TOKEN_SENIOR }}
           TOKEN_JUNIOR: ${{ secrets.TOKEN_JUNIOR }}

.gitea/workflows/scripts/publish.sh

@@ -13,10 +13,12 @@ case "$NAME" in
 esac
 [ -z "$TOK" ] && TOK="$GT"
 # Trigger token: comments that must FIRE the next workflow (delegation, autopilot) and PR merges
-# cannot use the built-in GITEA_TOKEN (Gitea won't start new runs from it). Use the agent's own PAT
-# when it has one; otherwise fall back to AGENT_TOKEN (repos without per-agent tokens, e.g. homelab).
+# cannot use the built-in GITEA_TOKEN (Gitea won't start new runs from it) — they need a real PAT.
+# Every agent now has its own token, so TTOK is just the agent's token. If an agent somehow has none
+# (TOK fell back to the built-in GT), TTOK is left empty so the trigger/merge is skipped rather than
+# silently no-op'ing under the built-in token.
 TTOK="$TOK"
-{ [ -z "$TTOK" ] || [ "$TTOK" = "$GT" ]; } && TTOK="${AGENT_TOKEN:-}"
+[ "$TTOK" = "$GT" ] && TTOK=""
 git config user.name  "$NAME"
 git config user.email "$NAME@ffaerber.duckdns.org"
 API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"

README.md

@@ -78,13 +78,14 @@ points `$SCRIPTS` at it. Keep the workflow and its scripts moving together on `m
 | `OLLAMA_URL`, `OLLAMA_CLOUD_API_KEY` | local ornith / Ollama Cloud (gemma4, kimi-k2.7-code, glm-5.2, minimax-m3) |
 | `TOKEN_PM`,`TOKEN_SENIOR`,`TOKEN_JUNIOR`,`TOKEN_LEAD`,`TOKEN_QA` | **primary** — each agent's own Gitea-user PAT. The running agent gets *only its own* token (as `SELF_TOKEN`) so it posts, commits, comments, and (for `@qa` autopilot) merges as itself, and its `gitea-api` skill acts with its own scopes. `TOKEN_QA` needs `write:repository` to merge. |
 | `TOKEN_OPS` | `@ops` only — the admin PAT behind the `gitea-admin` skill (create orgs/users/repos, manage labels & secrets, mint scoped tokens). Injected into the agent process only when the agent is `@ops`. |
-| `AGENT_TOKEN` | **fallback** — an admin PAT used only where per-agent `TOKEN_*` aren't configured (e.g. an un-migrated consuming repo). Covers the two things the built-in `GITEA_TOKEN` can't do: post the delegation/autopilot comment that *fires the next run*, and merge a PR so the push *triggers downstream deploys*. Where per-agent tokens exist, each agent uses its own instead. |
 
 Each agent authenticates as **itself**: the Run-agent step selects that agent's `TOKEN_*` into
-`SELF_TOKEN` (never another agent's), falling back to `AGENT_TOKEN` only when its own token is unset.
-`GITEA_TOKEN` is auto-provided (used for reads, and as the reply identity only when an agent has no
-`TOKEN_*` of its own). Tip: set these once at the **org** level so every repo inherits them via
-`secrets: inherit`.
+`SELF_TOKEN` (never another agent's), and `publish.sh` uses the same token for the delegation/autopilot
+trigger comment and `@qa` merges — the two things the built-in `GITEA_TOKEN` can't do (it won't start
+new runs, and a merge under it won't fire downstream deploys). So **every consuming repo must carry the
+per-agent `TOKEN_*` secrets** (org-level for `gitea/*`, user-level for `ffaerber/*`); there is no shared
+fallback token. `GITEA_TOKEN` is auto-provided (used for reads). Tip: set the `TOKEN_*` once at the
+**org / user** level so every repo inherits them via `secrets: inherit`.
 
 ## Also add to each consuming repo