job-forge 2.13.0 → 2.14.1

package/.cursor/rules/main.mdc

@@ -41,6 +41,9 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [D3] Upgrade `apply` routing to `@general-paid` when offer score ≥ 4.0/5, when user flags "top-tier / dream job / high-stakes", or when late-stage pipeline (post-screens).
   why: form-fill flows are 6+ steps; free-tier sometimes aborts mid-flow on large Greenhouse/Workday schemas; paid tier has more headroom
 
+- [D3f] **Provider-failure downgrade on `apply` (all harnesses; OpenCode + OpenRouter especially):** If you dispatched `@general-paid` per [D3] and that subagent fails or exhausts retries with provider-side errors — copy mentioning Venice / Diem / Chutes, "insufficient" USD/credits/funds/balance, HTTP 402/429, overload / temporarily unavailable — re-dispatch the **same apply URL** once on `@general-free` before marking FAILED. Do not abandon the role solely because the upgraded tier hit a pool-specific limit.
+  why: `@general-paid` on OpenCode still uses free OpenRouter model ids; Venice-style balance errors are a backend-route issue, not proof that procedural `@general-free` cannot complete the same Greenhouse-style flow after [D5]/[H2] gates pass
+
 - [D4] Auto-submit for offers scoring 3.0+/5 without pausing for confirmation between steps — scan → evaluate → apply is one continuous pipeline. Mark SKIP for <3.0 and move on.
   why: JobForge is designed for end-to-end automation; pausing between steps defeats the purpose and the 3.0 gate already enforces quality
 
@@ -57,7 +60,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 3. Apply [D1]: batch/Geometra work → delegate; single/read-only/dev → inline.
 4. Before any `task` batch using Geometra, run cleanup [H3].
 5. Before `apply`, run duplicate check [H2] and location filter [D5].
-6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers.
+6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers; if that apply dispatch hits provider errors, downgrade once per [D3f].
 7. Cap parallelism at 2 per round [H1].
 8. One in-flight dispatch per company [H5].
 9. Orchestrator does not fill forms in multi-job mode [H4].

package/.opencode/agents/general-free.md

@@ -1,7 +1,7 @@
 ---
 description: Procedural worker on free-tier model. Use for form filling via Geometra, tracker updates, TSV merges, scan dedup, OTP retrieval, and other mechanical/scripted tasks where quality-sensitive text generation is NOT required.
 mode: subagent
-model: openrouter/minimax/minimax-m2.5:free
+model: openrouter/z-ai/glm-4.5-air:free
 tools:
   geometra_connect: true
   geometra_page_model: true
@@ -17,9 +17,10 @@ tools:
 temperature: 0.1
 reasoningEffort: minimal
 fallback_models:
-  - openrouter/qwen/qwen3-coder:free
-  - openrouter/google/gemma-4-26b-a4b-it:free
+  - openrouter/minimax/minimax-m2.5:free
   - openrouter/openai/gpt-oss-20b:free
+  - openrouter/nvidia/nemotron-3-nano-30b-a3b:free
+  - openrouter/qwen/qwen3-coder:free
 ---
 
 You are the @general-free subagent. You run on a free-tier model, which means the orchestrator has delegated this task to you **specifically because the work is procedural**: deterministic steps, scripted outputs, no nuanced writing required.

package/.opencode/agents/general-paid.md

@@ -8,9 +8,10 @@ tools:
 temperature: 0.3
 reasoningEffort: medium
 fallback_models:
-  - openrouter/qwen/qwen3-coder:free
+  - openrouter/nvidia/nemotron-3-super-120b-a12b:free
   - openrouter/openai/gpt-oss-120b:free
   - openrouter/z-ai/glm-4.5-air:free
+  - openrouter/qwen/qwen3-coder:free
 ---
 
 You are the @general-paid subagent. The orchestrator delegated this task to you because it requires quality writing or judgment — the kind of work `@general-free` isn't well-suited for.

package/.opencode/agents/glm-minimal.md

@@ -1,7 +1,7 @@
 ---
 description: Narrow-scope extractor on free-tier model. Use for single-purpose tasks where the orchestrator passes the exact input and expects a small, structured output — e.g., "extract these 8 fields from this JD text" or "parse this form schema into a label→type map". NOT for multi-step workflows.
 mode: subagent
-model: openrouter/google/gemma-4-26b-a4b-it:free
+model: openrouter/openai/gpt-oss-20b:free
 tools:
   geometra_*: false
   gmail_*: false
@@ -14,9 +14,10 @@ tools:
 temperature: 0
 reasoningEffort: none
 fallback_models:
-  - openrouter/minimax/minimax-m2.5:free
-  - openrouter/openai/gpt-oss-20b:free
+  - openrouter/google/gemma-4-26b-a4b-it:free
+  - openrouter/nvidia/nemotron-nano-9b-v2:free
   - openrouter/google/gemma-4-31b-it:free
+  - openrouter/z-ai/glm-4.5-air:free
 ---
 
 You are the @glm-minimal subagent. You handle narrow, one-shot extractions where the orchestrator has pre-digested the context and just needs you to do a specific transform.

package/.opencode/opencode-model-fallback.json

@@ -3,9 +3,15 @@
   "timeout_seconds": 30,
   "notify_on_fallback": true,
   "fallback_models": [
-    "openrouter/qwen/qwen3-next-80b-a3b-instruct:free",
     "openrouter/openai/gpt-oss-120b:free",
-    "openrouter/google/gemma-4-26b-a4b-it:free",
-    "openrouter/z-ai/glm-4.5-air:free"
+    "openrouter/z-ai/glm-4.5-air:free",
+    "openrouter/nvidia/nemotron-3-super-120b-a12b:free",
+    "openrouter/qwen/qwen3-next-80b-a3b-instruct:free"
+  ],
+  "retryable_error_patterns": [
+    "(?i)\\bvenice\\b.*(?:insufficient|balance|credits?|diem|usd)",
+    "(?i)insufficient\\s+(?:usd|diem|credits?|funds?|balance)",
+    "(?i)credit.*balance.*too.*low",
+    "(?i)(?:temporarily\\s+)?unavailable|overloaded|try\\s+again"
   ]
 }

package/AGENTS.md

@@ -36,6 +36,9 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [D3] Upgrade `apply` routing to `@general-paid` when offer score ≥ 4.0/5, when user flags "top-tier / dream job / high-stakes", or when late-stage pipeline (post-screens).
   why: form-fill flows are 6+ steps; free-tier sometimes aborts mid-flow on large Greenhouse/Workday schemas; paid tier has more headroom
 
+- [D3f] **Provider-failure downgrade on `apply` (all harnesses; OpenCode + OpenRouter especially):** If you dispatched `@general-paid` per [D3] and that subagent fails or exhausts retries with provider-side errors — copy mentioning Venice / Diem / Chutes, "insufficient" USD/credits/funds/balance, HTTP 402/429, overload / temporarily unavailable — re-dispatch the **same apply URL** once on `@general-free` before marking FAILED. Do not abandon the role solely because the upgraded tier hit a pool-specific limit.
+  why: `@general-paid` on OpenCode still uses free OpenRouter model ids; Venice-style balance errors are a backend-route issue, not proof that procedural `@general-free` cannot complete the same Greenhouse-style flow after [D5]/[H2] gates pass
+
 - [D4] Auto-submit for offers scoring 3.0+/5 without pausing for confirmation between steps — scan → evaluate → apply is one continuous pipeline. Mark SKIP for <3.0 and move on.
   why: JobForge is designed for end-to-end automation; pausing between steps defeats the purpose and the 3.0 gate already enforces quality
 
@@ -52,7 +55,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 3. Apply [D1]: batch/Geometra work → delegate; single/read-only/dev → inline.
 4. Before any `task` batch using Geometra, run cleanup [H3].
 5. Before `apply`, run duplicate check [H2] and location filter [D5].
-6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers.
+6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers; if that apply dispatch hits provider errors, downgrade once per [D3f].
 7. Cap parallelism at 2 per round [H1].
 8. One in-flight dispatch per company [H5].
 9. Orchestrator does not fill forms in multi-job mode [H4].

package/CLAUDE.md

@@ -36,6 +36,9 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [D3] Upgrade `apply` routing to `@general-paid` when offer score ≥ 4.0/5, when user flags "top-tier / dream job / high-stakes", or when late-stage pipeline (post-screens).
   why: form-fill flows are 6+ steps; free-tier sometimes aborts mid-flow on large Greenhouse/Workday schemas; paid tier has more headroom
 
+- [D3f] **Provider-failure downgrade on `apply` (all harnesses; OpenCode + OpenRouter especially):** If you dispatched `@general-paid` per [D3] and that subagent fails or exhausts retries with provider-side errors — copy mentioning Venice / Diem / Chutes, "insufficient" USD/credits/funds/balance, HTTP 402/429, overload / temporarily unavailable — re-dispatch the **same apply URL** once on `@general-free` before marking FAILED. Do not abandon the role solely because the upgraded tier hit a pool-specific limit.
+  why: `@general-paid` on OpenCode still uses free OpenRouter model ids; Venice-style balance errors are a backend-route issue, not proof that procedural `@general-free` cannot complete the same Greenhouse-style flow after [D5]/[H2] gates pass
+
 - [D4] Auto-submit for offers scoring 3.0+/5 without pausing for confirmation between steps — scan → evaluate → apply is one continuous pipeline. Mark SKIP for <3.0 and move on.
   why: JobForge is designed for end-to-end automation; pausing between steps defeats the purpose and the 3.0 gate already enforces quality
 
@@ -52,7 +55,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 3. Apply [D1]: batch/Geometra work → delegate; single/read-only/dev → inline.
 4. Before any `task` batch using Geometra, run cleanup [H3].
 5. Before `apply`, run duplicate check [H2] and location filter [D5].
-6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers.
+6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers; if that apply dispatch hits provider errors, downgrade once per [D3f].
 7. Cap parallelism at 2 per round [H1].
 8. One in-flight dispatch per company [H5].
 9. Orchestrator does not fill forms in multi-job mode [H4].

package/bin/create-job-forge.mjs

@@ -177,17 +177,25 @@ const opencodeCfg = {
   },
   // Register the exact OpenRouter free models the harness uses so they're
   // selectable even if they are not in OpenCode's built-in preloaded set.
+  // This list is a superset: role primaries, per-agent fallback chains,
+  // and the orchestrator fallback chain.
   provider: {
     openrouter: {
       models: {
+        // Orchestrator + agentic coding (role default)
         'qwen/qwen3-coder:free': {},
+        // Role primaries
+        'z-ai/glm-4.5-air:free': {}, // fast
+        'qwen/qwen3-next-80b-a3b-instruct:free': {}, // quality
+        'openai/gpt-oss-20b:free': {}, // minimal
+        // Common fallbacks
+        'openai/gpt-oss-120b:free': {},
         'minimax/minimax-m2.5:free': {},
-        'qwen/qwen3-next-80b-a3b-instruct:free': {},
+        'nvidia/nemotron-3-super-120b-a12b:free': {},
+        'nvidia/nemotron-3-nano-30b-a3b:free': {},
+        'nvidia/nemotron-nano-9b-v2:free': {},
         'google/gemma-4-26b-a4b-it:free': {},
         'google/gemma-4-31b-it:free': {},
-        'openai/gpt-oss-120b:free': {},
-        'openai/gpt-oss-20b:free': {},
-        'z-ai/glm-4.5-air:free': {},
       },
     },
   },

package/docs/MODEL-ROUTING.md

@@ -18,9 +18,9 @@ Defined in `.opencode/agents/*.md` (shipped in the harness, symlinked into consu
 
 | Agent | Model | Reasoning | Use for |
 |-------|-------|-----------|---------|
-| `@general-free` | `openrouter/minimax/minimax-m2.5:free` | `minimal` | Geometra form fills, tracker TSV merges, scan dedup, OTP retrieval via Gmail, scripted pipeline steps |
+| `@general-free` | `openrouter/z-ai/glm-4.5-air:free` | `minimal` | Geometra form fills, tracker TSV merges, scan dedup, OTP retrieval via Gmail, scripted pipeline steps |
 | `@general-paid` | `openrouter/qwen/qwen3-next-80b-a3b-instruct:free` | `medium` | Offer evaluation narratives (Blocks A-F), cover letters, "Why X?" answers, STAR+R interview stories, LinkedIn outreach prose |
-| `@glm-minimal` | `openrouter/google/gemma-4-26b-a4b-it:free` | `none` | Narrow one-shot transforms: "extract these 8 fields from this JD text → JSON", "classify this archetype" |
+| `@glm-minimal` | `openrouter/openai/gpt-oss-20b:free` | `none` | Narrow one-shot transforms: "extract these 8 fields from this JD text → JSON", "classify this archetype" |
 
 The full task-to-agent mapping lives in [AGENTS.md → Subagent Routing](../AGENTS.md#subagent-routing--which-agent-for-which-task). The orchestrator (your primary session) is expected to delegate before taking any multi-step action — see the **Pre-flight delegation** rule in AGENTS.md.
 
@@ -139,15 +139,17 @@ Default chains ship upstream in each agent's YAML frontmatter (`node_modules/job
 
 | Agent | Primary | Fallback chain (in order) |
 |-------|---------|---------------------------|
-| `@general-free` | `openrouter/minimax/minimax-m2.5:free` | `openrouter/qwen/qwen3-coder:free` → `openrouter/google/gemma-4-26b-a4b-it:free` → `openrouter/openai/gpt-oss-20b:free` |
-| `@general-paid` | `openrouter/qwen/qwen3-next-80b-a3b-instruct:free` | `openrouter/qwen/qwen3-coder:free` → `openrouter/openai/gpt-oss-120b:free` → `openrouter/z-ai/glm-4.5-air:free` |
-| `@glm-minimal` | `openrouter/google/gemma-4-26b-a4b-it:free` | `openrouter/minimax/minimax-m2.5:free` → `openrouter/openai/gpt-oss-20b:free` → `openrouter/google/gemma-4-31b-it:free` |
+| `@general-free` | `openrouter/z-ai/glm-4.5-air:free` | `openrouter/minimax/minimax-m2.5:free` → `openrouter/openai/gpt-oss-20b:free` → `openrouter/nvidia/nemotron-3-nano-30b-a3b:free` → `openrouter/qwen/qwen3-coder:free` |
+| `@general-paid` | `openrouter/qwen/qwen3-next-80b-a3b-instruct:free` | `openrouter/nvidia/nemotron-3-super-120b-a12b:free` → `openrouter/openai/gpt-oss-120b:free` → `openrouter/z-ai/glm-4.5-air:free` → `openrouter/qwen/qwen3-coder:free` |
+| `@glm-minimal` | `openrouter/openai/gpt-oss-20b:free` | `openrouter/google/gemma-4-26b-a4b-it:free` → `openrouter/nvidia/nemotron-nano-9b-v2:free` → `openrouter/google/gemma-4-31b-it:free` → `openrouter/z-ai/glm-4.5-air:free` |
 
 These chains are deliberately free-only so the default OpenCode path never needs to pay. **Note:** OpenCode model IDs must use the provider prefix it expects (`openrouter/...`, `opencode/...`, etc.). The raw OpenRouter model slug by itself is not enough.
 
-Consumers **do not need to configure anything** to get these defaults: the subagent chains arrive via the symlinked agent MD files, and the harness also ships `.opencode/opencode-model-fallback.json` for the main orchestrator / any agent without its own list. `@razroo/opencode-model-fallback` (≥0.3.1) reads per-agent chains from the frontmatter-derived `fallback_models` field and falls through to the global file when no per-agent list exists. The consumer's `opencode.json` only needs `"plugin": ["@razroo/opencode-model-fallback"]` — which the scaffolder sets automatically.
+Consumers **do not need to configure anything** to get these defaults: the subagent chains arrive via the symlinked agent MD files, and the harness ships `.opencode/opencode-model-fallback.json` for the main orchestrator / any agent without its own list. That JSON is **generated by `@razroo/iso-harness`** from the top-level `opencodeModelFallback` object in the harness's `iso/config.json` (same `iso build` pass as `opencode.json`), so it stays in sync with published releases — not a hand-edited file in git. `@razroo/opencode-model-fallback` (≥0.3.1) reads per-agent chains from the frontmatter-derived `fallback_models` field and falls through to the global file when no per-agent list exists. The consumer's `opencode.json` only needs `"plugin": ["@razroo/opencode-model-fallback"]` — which the scaffolder sets automatically.
 
-**When fallback fires:** the plugin pattern-matches rate-limit / 5xx / quota / "overloaded" / "insufficient credits" errors. Failed models enter a 60-second cooldown before they're retried. Every rotation logs to `~/.config/opencode/opencode-model-fallback.log` with the trigger error, original model, and target model — grep for `"Auto-retrying with fallback model"` to confirm it fired.
+**When fallback fires:** the plugin pattern-matches rate-limit / 5xx / quota / "overloaded" / insufficient-balance style errors (including Venice / Diem copy — see `retryable_error_patterns` in the harness source). Failed models enter a cooldown before they're retried. Every rotation logs to `~/.config/opencode/opencode-model-fallback.log` with the trigger error, original model, and target model — grep for `"Auto-retrying with fallback model"` to confirm it fired.
+
+**Orchestrator policy (all harnesses):** if an upgraded `@general-paid` apply still fails after model fallback, follow **[D3f]** in the shared instructions (`AGENTS.md` / `CLAUDE.md` / Cursor rules / Codex `AGENTS.md`) — re-dispatch the same URL once on `@general-free` before marking FAILED.
 
 ### Overriding an upstream chain
 
@@ -165,17 +167,23 @@ Add an `agent.<name>.fallback_models` block to your project's `opencode.json`. T
 
 ### Global fallback chain (agents without their own)
 
-Plugin-level config at `.opencode/opencode-model-fallback.json` — applies to any agent whose `fallback_models` is empty:
+Source of truth: **`iso/config.json` → `opencodeModelFallback`** (iso-harness writes `.opencode/opencode-model-fallback.json` on `npm run build:config` / `prepack`). Applies to the orchestrator and any agent whose `fallback_models` is empty. Example shape:
 
 ```json
 {
   "cooldown_seconds": 60,
   "timeout_seconds": 30,
   "notify_on_fallback": true,
-  "fallback_models": ["openrouter/minimax/minimax-m2.5:free", "openrouter/qwen/qwen3-coder:free"]
+  "fallback_models": [
+    "openrouter/openai/gpt-oss-120b:free",
+    "openrouter/z-ai/glm-4.5-air:free"
+  ],
+  "retryable_error_patterns": ["(?i)venice.*insufficient"]
 }
 ```
 
+`retryable_error_patterns` extends the plugin's built-in matchers — use it for provider-specific strings (Venice Diem balance, etc.) that do not match the stock regexes.
+
 ### Disabling fallback
 
 Remove `"@razroo/opencode-model-fallback"` from `opencode.json:plugin` — agents keep their `model:` primary and errors propagate normally.

package/iso/agents/general-free.md

@@ -10,10 +10,14 @@ targets:
     mode: subagent
     temperature: 0.1
     reasoningEffort: minimal
+    # Primary (z-ai/glm-4.5-air:free) resolves from openrouter-free preset.
+    # Fallback chain is ordered by decreasing likelihood of rate-limits,
+    # staying within free models that can tool-call Geometra + Gmail MCPs.
     fallback_models:
-      - openrouter/qwen/qwen3-coder:free
-      - openrouter/google/gemma-4-26b-a4b-it:free
+      - openrouter/minimax/minimax-m2.5:free
       - openrouter/openai/gpt-oss-20b:free
+      - openrouter/nvidia/nemotron-3-nano-30b-a3b:free
+      - openrouter/qwen/qwen3-coder:free
     tools:
       geometra_connect: true
       geometra_page_model: true

package/iso/agents/general-paid.md

@@ -11,10 +11,14 @@ targets:
     mode: subagent
     temperature: 0.3
     reasoningEffort: medium
+    # Primary (qwen/qwen3-next-80b-a3b-instruct:free) resolves from the
+    # openrouter-free preset. Fallback chain prioritizes models with
+    # strong long-form writing judgment over raw size.
     fallback_models:
-      - openrouter/qwen/qwen3-coder:free
+      - openrouter/nvidia/nemotron-3-super-120b-a12b:free
       - openrouter/openai/gpt-oss-120b:free
       - openrouter/z-ai/glm-4.5-air:free
+      - openrouter/qwen/qwen3-coder:free
     tools:
       geometra_*: false
       gmail_*: false

package/iso/agents/glm-minimal.md

@@ -10,10 +10,14 @@ targets:
     mode: subagent
     temperature: 0
     reasoningEffort: none
+    # Primary (openai/gpt-oss-20b:free) resolves from openrouter-free
+    # preset. Fallback chain sticks to small dense models with reliable
+    # structured-output behavior — no creative generation upstream.
     fallback_models:
-      - openrouter/minimax/minimax-m2.5:free
-      - openrouter/openai/gpt-oss-20b:free
+      - openrouter/google/gemma-4-26b-a4b-it:free
+      - openrouter/nvidia/nemotron-nano-9b-v2:free
       - openrouter/google/gemma-4-31b-it:free
+      - openrouter/z-ai/glm-4.5-air:free
     tools:
       geometra_*: false
       gmail_*: false

package/iso/config.json

@@ -1,4 +1,21 @@
 {
+  "opencodeModelFallback": {
+    "cooldown_seconds": 60,
+    "timeout_seconds": 30,
+    "notify_on_fallback": true,
+    "fallback_models": [
+      "openrouter/openai/gpt-oss-120b:free",
+      "openrouter/z-ai/glm-4.5-air:free",
+      "openrouter/nvidia/nemotron-3-super-120b-a12b:free",
+      "openrouter/qwen/qwen3-next-80b-a3b-instruct:free"
+    ],
+    "retryable_error_patterns": [
+      "(?i)\\bvenice\\b.*(?:insufficient|balance|credits?|diem|usd)",
+      "(?i)insufficient\\s+(?:usd|diem|credits?|funds?|balance)",
+      "(?i)credit.*balance.*too.*low",
+      "(?i)(?:temporarily\\s+)?unavailable|overloaded|try\\s+again"
+    ]
+  },
   "targets": {
     "opencode": {
       "plugin": ["@razroo/opencode-model-fallback"],
@@ -8,13 +25,16 @@
         "openrouter": {
           "models": {
             "qwen/qwen3-coder:free": {},
-            "minimax/minimax-m2.5:free": {},
+            "z-ai/glm-4.5-air:free": {},
             "qwen/qwen3-next-80b-a3b-instruct:free": {},
-            "google/gemma-4-26b-a4b-it:free": {},
-            "google/gemma-4-31b-it:free": {},
-            "openai/gpt-oss-120b:free": {},
             "openai/gpt-oss-20b:free": {},
-            "z-ai/glm-4.5-air:free": {}
+            "openai/gpt-oss-120b:free": {},
+            "minimax/minimax-m2.5:free": {},
+            "nvidia/nemotron-3-super-120b-a12b:free": {},
+            "nvidia/nemotron-3-nano-30b-a3b:free": {},
+            "nvidia/nemotron-nano-9b-v2:free": {},
+            "google/gemma-4-26b-a4b-it:free": {},
+            "google/gemma-4-31b-it:free": {}
           }
         }
       }

package/iso/instructions.md

@@ -36,6 +36,9 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [D3] Upgrade `apply` routing to `@general-paid` when offer score ≥ 4.0/5, when user flags "top-tier / dream job / high-stakes", or when late-stage pipeline (post-screens).
   why: form-fill flows are 6+ steps; free-tier sometimes aborts mid-flow on large Greenhouse/Workday schemas; paid tier has more headroom
 
+- [D3f] **Provider-failure downgrade on `apply` (all harnesses; OpenCode + OpenRouter especially):** If you dispatched `@general-paid` per [D3] and that subagent fails or exhausts retries with provider-side errors — copy mentioning Venice / Diem / Chutes, "insufficient" USD/credits/funds/balance, HTTP 402/429, overload / temporarily unavailable — re-dispatch the **same apply URL** once on `@general-free` before marking FAILED. Do not abandon the role solely because the upgraded tier hit a pool-specific limit.
+  why: `@general-paid` on OpenCode still uses free OpenRouter model ids; Venice-style balance errors are a backend-route issue, not proof that procedural `@general-free` cannot complete the same Greenhouse-style flow after [D5]/[H2] gates pass
+
 - [D4] Auto-submit for offers scoring 3.0+/5 without pausing for confirmation between steps — scan → evaluate → apply is one continuous pipeline. Mark SKIP for <3.0 and move on.
   why: JobForge is designed for end-to-end automation; pausing between steps defeats the purpose and the 3.0 gate already enforces quality
 
@@ -52,7 +55,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 3. Apply [D1]: batch/Geometra work → delegate; single/read-only/dev → inline.
 4. Before any `task` batch using Geometra, run cleanup [H3].
 5. Before `apply`, run duplicate check [H2] and location filter [D5].
-6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers.
+6. Route by cost tier [D2]; upgrade to `@general-paid` per [D3] for high-stakes offers; if that apply dispatch hits provider errors, downgrade once per [D3f].
 7. Cap parallelism at 2 per round [H1].
 8. One in-flight dispatch per company [H5].
 9. Orchestrator does not fill forms in multi-job mode [H4].

package/models.yaml

@@ -9,9 +9,9 @@
 #
 # JobForge's subagents bind to preset roles via the `role:` field in
 # iso/agents/<slug>.md:
-#   @general-free  → role: fast     (Haiku / OpenRouter MiniMax M2.5 free / gpt-5.4-mini)
+#   @general-free  → role: fast     (Haiku / OpenRouter GLM 4.5 Air free / gpt-5.4-mini)
 #   @general-paid  → role: quality  (Opus 4.7 / OpenRouter Qwen3 Next 80B free / gpt-5.4)
-#   @glm-minimal   → role: minimal  (Haiku / OpenRouter Gemma 4 26B free / gpt-5.4-nano)
+#   @glm-minimal   → role: minimal  (Haiku / OpenRouter GPT-OSS-20B free / gpt-5.4-nano)
 #
 # Override anything by adding fields here. For example, to pin Opus on
 # Claude Code for the @general-paid (quality) role:
@@ -30,13 +30,3 @@
 #           model: gpt-5.4
 
 extends: openrouter-free
-
-# Only override the preset where we prefer a different OpenRouter pick.
-# The preset's quality-tier OpenCode pick is openai/gpt-oss-120b:free;
-# we prefer Qwen3 Next 80B for job-application writing quality.
-roles:
-  quality:
-    targets:
-      opencode:
-        provider: openrouter
-        model: qwen/qwen3-next-80b-a3b-instruct:free

package/opencode.json

@@ -3,26 +3,29 @@
   "model": "openrouter/qwen/qwen3-coder:free",
   "agent": {
     "fast": {
-      "model": "openrouter/minimax/minimax-m2.5:free"
+      "model": "openrouter/z-ai/glm-4.5-air:free"
     },
     "quality": {
       "model": "openrouter/qwen/qwen3-next-80b-a3b-instruct:free"
     },
     "minimal": {
-      "model": "openrouter/google/gemma-4-26b-a4b-it:free"
+      "model": "openrouter/openai/gpt-oss-20b:free"
     }
   },
   "provider": {
     "openrouter": {
       "models": {
         "qwen/qwen3-coder:free": {},
-        "minimax/minimax-m2.5:free": {},
+        "z-ai/glm-4.5-air:free": {},
         "qwen/qwen3-next-80b-a3b-instruct:free": {},
-        "google/gemma-4-26b-a4b-it:free": {},
-        "google/gemma-4-31b-it:free": {},
-        "openai/gpt-oss-120b:free": {},
         "openai/gpt-oss-20b:free": {},
-        "z-ai/glm-4.5-air:free": {}
+        "openai/gpt-oss-120b:free": {},
+        "minimax/minimax-m2.5:free": {},
+        "nvidia/nemotron-3-super-120b-a12b:free": {},
+        "nvidia/nemotron-3-nano-30b-a3b:free": {},
+        "nvidia/nemotron-nano-9b-v2:free": {},
+        "google/gemma-4-26b-a4b-it:free": {},
+        "google/gemma-4-31b-it:free": {}
       }
     }
   },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "job-forge",
-  "version": "2.13.0",
+  "version": "2.14.1",
   "description": "AI-powered job search pipeline built on opencode",
   "type": "module",
   "bin": {
@@ -88,7 +88,7 @@
   },
   "devDependencies": {
     "@razroo/iso": "^0.2.5",
-    "@razroo/iso-harness": "^0.6.0",
+    "@razroo/iso-harness": "^0.6.1",
     "@razroo/iso-route": "^0.5.0",
     "@razroo/iso-trace": "^0.1.0",
     "@razroo/opencode-model-fallback": "^0.3.1"