fix(agents): rename xai provider key to xai-oc to avoid opencode catalog collision (#118)
ci / lint (pull_request) Successful in 17s
ci / lint (pull_request) Successful in 17s
opencode ships a built-in `xai` model-catalog entry (a real @ai-sdk/xai integration with Responses-API support). Naming our custom OpenAI-compatible shim `xai` too made opencode's --auto permission-check path assume the catalog's provider object once a `permission` block is present (always, in this pipeline) and call .responses(), which our shim doesn't implement — crashing every @lead/@ops run with "Z.responses is not a function". Reproduced locally with the production config shape on opencode 1.17.13; renaming the provider key to xai-oc (model id xai-oc/grok-4.5) fixes it reliably across repeated fresh-state runs.
This commit is contained in:
@@ -25,7 +25,7 @@
|
|||||||
"desc": "Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."
|
"desc": "Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."
|
||||||
},
|
},
|
||||||
"lead": {
|
"lead": {
|
||||||
"model": "xai/grok-4.5",
|
"model": "xai-oc/grok-4.5",
|
||||||
"vision": true,
|
"vision": true,
|
||||||
"mode": "pr",
|
"mode": "pr",
|
||||||
"skills": [
|
"skills": [
|
||||||
@@ -43,7 +43,7 @@
|
|||||||
"desc": "QA / reviewer — reviews PRs: reads the diff, drives a headless browser (Playwright) to verify behavior, posts specific recommendations on the PR and the pass/fail verdict on the issue. Never edits code, never merges."
|
"desc": "QA / reviewer — reviews PRs: reads the diff, drives a headless browser (Playwright) to verify behavior, posts specific recommendations on the PR and the pass/fail verdict on the issue. Never edits code, never merges."
|
||||||
},
|
},
|
||||||
"ops": {
|
"ops": {
|
||||||
"model": "xai/grok-4.5",
|
"model": "xai-oc/grok-4.5",
|
||||||
"vision": false,
|
"vision": false,
|
||||||
"mode": "comment",
|
"mode": "comment",
|
||||||
"skills": [
|
"skills": [
|
||||||
|
|||||||
@@ -38,7 +38,7 @@ COST=${COST:-0}; INP=${INP:-0}; OUT=${OUT:-0}; CR=${CR:-0}; CW=${CW:-0}; RE=${RE
|
|||||||
IN_TOTAL=$(( INP + CR + CW )) # total input context processed
|
IN_TOTAL=$(( INP + CR + CW )) # total input context processed
|
||||||
# Cost label: ollama / ollama-cloud models are SUBSCRIPTION-billed (GPU-time against the plan, no
|
# Cost label: ollama / ollama-cloud models are SUBSCRIPTION-billed (GPU-time against the plan, no
|
||||||
# $/token price exists), so a "$0.0000" there would be misleading — label it a subscription instead.
|
# $/token price exists), so a "$0.0000" there would be misleading — label it a subscription instead.
|
||||||
# Metered providers (xai/…) get the real dollar cost opencode computed.
|
# Metered providers (xai-oc/…) get the real dollar cost opencode computed.
|
||||||
case "${MODEL:-}" in
|
case "${MODEL:-}" in
|
||||||
ollama*|*"/ollama"*) COSTF="subscription" ;;
|
ollama*|*"/ollama"*) COSTF="subscription" ;;
|
||||||
*) COSTF=$(awk -v c="$COST" 'BEGIN{printf "$%.4f", c+0}') ;;
|
*) COSTF=$(awk -v c="$COST" 'BEGIN{printf "$%.4f", c+0}') ;;
|
||||||
|
|||||||
@@ -42,18 +42,26 @@ PERM=$(jq -nc --argjson s "$SKILLS" '
|
|||||||
# (gemma4/kimi-k2.7-code/glm-5.2/minimax-m3) + xAI (grok-4.5). The provider `models:` maps are
|
# (gemma4/kimi-k2.7-code/glm-5.2/minimax-m3) + xAI (grok-4.5). The provider `models:` maps are
|
||||||
# DERIVED from agents.json (the single source of truth, shared with route.sh) so every model an
|
# DERIVED from agents.json (the single source of truth, shared with route.sh) so every model an
|
||||||
# agent is routed to is always declared in the provider config. `ollama-cloud/` prefix models go to
|
# agent is routed to is always declared in the provider config. `ollama-cloud/` prefix models go to
|
||||||
# the cloud provider; `ollama/` prefix models go to the local provider; `xai/` prefix models go to
|
# the cloud provider; `ollama/` prefix models go to the local provider; `xai-oc/` prefix models go
|
||||||
# the xAI provider (OpenAI-compatible, https://api.x.ai/v1). No other built-in providers remain.
|
# to our xAI shim (OpenAI-compatible, https://api.x.ai/v1). No other built-in providers remain.
|
||||||
|
#
|
||||||
|
# The provider key is `xai-oc`, NOT `xai` — opencode ships a built-in `xai` entry in its own model
|
||||||
|
# catalog (a real @ai-sdk/xai integration that implements the Responses API). Naming our custom
|
||||||
|
# openai-compatible shim `xai` collides with that catalog entry: opencode's --auto permission-check
|
||||||
|
# path then assumes the catalog's provider (which has `.responses()`) and crashes with
|
||||||
|
# "Z.responses is not a function" on every run once a `permission` block is present (i.e. always in
|
||||||
|
# this pipeline). Confirmed by reproducing locally with the production config shape on opencode
|
||||||
|
# 1.17.13 — renaming the key to `xai-oc` avoids the collision entirely. See issue #118.
|
||||||
# See issue #31.
|
# See issue #31.
|
||||||
AGENTS_JSON="${SCRIPTS:-$(dirname -- "$0")}/agents.json"
|
AGENTS_JSON="${SCRIPTS:-$(dirname -- "$0")}/agents.json"
|
||||||
CLOUD_MODELS=$(jq -r '[.[] | .model | select(startswith("ollama-cloud/")) | sub("^ollama-cloud/";"")] | map({(.):{}}) | add // {}' "$AGENTS_JSON")
|
CLOUD_MODELS=$(jq -r '[.[] | .model | select(startswith("ollama-cloud/")) | sub("^ollama-cloud/";"")] | map({(.):{}}) | add // {}' "$AGENTS_JSON")
|
||||||
LOCAL_MODELS=$(jq -r '[.[] | .model | select(startswith("ollama/")) | sub("^ollama/";"")] | map({(.):{}}) | add // {"ornith:35b":{}}' "$AGENTS_JSON")
|
LOCAL_MODELS=$(jq -r '[.[] | .model | select(startswith("ollama/")) | sub("^ollama/";"")] | map({(.):{}}) | add // {"ornith:35b":{}}' "$AGENTS_JSON")
|
||||||
XAI_MODELS=$(jq -r '[.[] | .model | select(startswith("xai/")) | sub("^xai/";"")] | map({(.):{}}) | add // {}' "$AGENTS_JSON")
|
XAI_MODELS=$(jq -r '[.[] | .model | select(startswith("xai-oc/")) | sub("^xai-oc/";"")] | map({(.):{}}) | add // {}' "$AGENTS_JSON")
|
||||||
jq -n --argjson mcp "$MCP" --argjson perm "$PERM" --argjson cloud "$CLOUD_MODELS" --argjson local "$LOCAL_MODELS" --argjson xai "$XAI_MODELS" --arg url "$OLLAMA_URL" --arg ckey "$OLLAMA_CLOUD_API_KEY" --arg xkey "$XAI_API_KEY" '{
|
jq -n --argjson mcp "$MCP" --argjson perm "$PERM" --argjson cloud "$CLOUD_MODELS" --argjson local "$LOCAL_MODELS" --argjson xai "$XAI_MODELS" --arg url "$OLLAMA_URL" --arg ckey "$OLLAMA_CLOUD_API_KEY" --arg xkey "$XAI_API_KEY" '{
|
||||||
provider: {
|
provider: {
|
||||||
ollama: {npm:"@ai-sdk/openai-compatible", options:{baseURL:($url+"/v1")}, models:$local},
|
ollama: {npm:"@ai-sdk/openai-compatible", options:{baseURL:($url+"/v1")}, models:$local},
|
||||||
"ollama-cloud": {npm:"@ai-sdk/openai-compatible", options:{baseURL:"https://ollama.com/v1", apiKey:$ckey}, models:$cloud},
|
"ollama-cloud": {npm:"@ai-sdk/openai-compatible", options:{baseURL:"https://ollama.com/v1", apiKey:$ckey}, models:$cloud},
|
||||||
xai: {npm:"@ai-sdk/openai-compatible", options:{baseURL:"https://api.x.ai/v1", apiKey:$xkey}, models:$xai}
|
"xai-oc": {npm:"@ai-sdk/openai-compatible", options:{baseURL:"https://api.x.ai/v1", apiKey:$xkey}, models:$xai}
|
||||||
},
|
},
|
||||||
permission: $perm,
|
permission: $perm,
|
||||||
mcp: $mcp
|
mcp: $mcp
|
||||||
|
|||||||
@@ -10,9 +10,9 @@ Shared **AI dev-team** workflow for Gitea Actions, reusable across repos. It giv
|
|||||||
| `@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. |
|
| `@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`. |
|
| `@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). |
|
| `@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` | `xai/grok-4.5` | yes | pr | `gitea-api` | Tech lead — the hardest problems, architecture, and final calls. |
|
| `@lead` | `xai-oc/grok-4.5` | yes | pr | `gitea-api` | Tech lead — the hardest problems, architecture, and final calls. |
|
||||||
| `@qa` | `ollama-cloud/minimax-m3:cloud` | yes | comment | `gitea-api` | QA / reviewer — reads the PR diff, drives a headless browser (Playwright) to verify behavior; recommendations on the PR, pass/fail verdict on the issue. Never edits code, never merges. |
|
| `@qa` | `ollama-cloud/minimax-m3:cloud` | yes | comment | `gitea-api` | QA / reviewer — reads the PR diff, drives a headless browser (Playwright) to verify behavior; recommendations on the PR, pass/fail verdict on the issue. Never edits code, never merges. |
|
||||||
| `@ops` | `xai/grok-4.5` | no | comment | `gitea-admin` | Gitea operator — administers the instance itself (create orgs/users/repos, labels, secrets, scoped per-user tokens, bootstrap repos). Comments only; never edits code. Confirms before destructive actions. |
|
| `@ops` | `xai-oc/grok-4.5` | no | comment | `gitea-admin` | Gitea operator — administers the instance itself (create orgs/users/repos, labels, secrets, scoped per-user tokens, bootstrap repos). Comments only; never edits code. Confirms before destructive actions. |
|
||||||
| `@intern` | `ollama/ornith:35b` | no | pr | — | Intern — very basic tasks only, routed to the local Ollama model (`ornith:35b`). Text-only, cannot read images. Escalates anything non-trivial to `@junior`, `@senior` or `@lead`. |
|
| `@intern` | `ollama/ornith:35b` | no | pr | — | Intern — very basic tasks only, routed to the local Ollama model (`ornith:35b`). Text-only, cannot read images. Escalates anything non-trivial to `@junior`, `@senior` or `@lead`. |
|
||||||
|
|
||||||
The registry `.gitea/workflows/scripts/agents.json` is the source of truth for this mapping — if you
|
The registry `.gitea/workflows/scripts/agents.json` is the source of truth for this mapping — if you
|
||||||
@@ -111,7 +111,7 @@ points `$SCRIPTS` at it. Keep the workflow and its scripts moving together on `m
|
|||||||
|
|
||||||
| Secret | For |
|
| Secret | For |
|
||||||
|--------|-----|
|
|--------|-----|
|
||||||
| `XAI_API_KEY` | `@lead`, `@ops` (and any other agent switched to a `xai/…` model) |
|
| `XAI_API_KEY` | `@lead`, `@ops` (and any other agent switched to a `xai-oc/…` model) |
|
||||||
| `OLLAMA_URL`, `OLLAMA_CLOUD_API_KEY` | local ornith / Ollama Cloud (gemma4, kimi-k2.7-code, glm-5.2, minimax-m3) |
|
| `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 and comments as itself, and its `gitea-api` skill acts with its own scopes. Scopes: devs + `TOKEN_PM` carry `write:repository` (`@pm` is the only agent that merges, autopilot only); `TOKEN_QA` is `read:repository` + `write:issue` (reviews, never merges). |
|
| `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 and comments as itself, and its `gitea-api` skill acts with its own scopes. Scopes: devs + `TOKEN_PM` carry `write:repository` (`@pm` is the only agent that merges, autopilot only); `TOKEN_QA` is `read:repository` + `write:issue` (reviews, never merges). |
|
||||||
| `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`. |
|
| `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`. |
|
||||||
|
|||||||
Reference in New Issue
Block a user