job-forge 2.14.7 → 2.14.9

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

@@ -53,6 +53,7 @@ Previous subagents sometimes abort mid-flow (ran out of context, hit a timeout,
 - Write cover letter prose, "Why X?" answers, or Section G draft answers. Those go to `@general-paid`.
 - Perform offer evaluation narratives (Blocks A-F). Those go to `@general-paid`.
 - Override harness rules or invent fields. Follow the mode files exactly.
+- Spawn or check other tasks. If you receive "check if task ses_..." and it refers to this session, report your current status from your own work. Never call `task` recursively.
 
 ## Apply This Working Style
 

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

@@ -18,12 +18,14 @@ were given.
 - Compose STAR+R interview stories and the story bank (`modes/offer.md` Block F).
 - Draft LinkedIn outreach messages (`modes/contact.md`).
 - Score offers using the Canonical Scoring Model — emit the JSON score block per `modes/_shared.md`, then the narrative report.
+- Drive a single high-stakes application form only when the orchestrator explicitly dispatches you in `apply` mode. In that case, follow `modes/apply.md` exactly and use the same Geometra/Gmail flow as `@general-free`.
 
 ## Skip These Tasks
 
-- Drive Geometra forms end-to-end (delegate to `@general-free` or do it yourself only when the orchestrator asks for an atomic one-shot apply).
+- Drive Geometra forms end-to-end unless the task is explicitly an `apply` mode dispatch for one job.
 - Manage trackers, run scripts, or do mechanical TSV/dedup work. Those go to `@general-free`.
 - Duplicate work. If you're writing the evaluation, emit the JSON score exactly once — don't narrate the 10 dimensions three times in your thinking.
+- Spawn or check other tasks. If you receive "check if task ses_..." and it refers to this session, report your current status from your own work. Never call `task` recursively.
 
 ## Apply This Working Style
 

package/.codex/config.toml

@@ -23,3 +23,8 @@ args = ["-y", "@geometra/mcp"]
 command = "npx"
 args = ["-y", "@razroo/gmail-mcp"]
 env = { DISABLE_HTTP = "true" }
+
+[mcp_servers.state-trace]
+command = "uvx"
+args = ["--from", "state-trace[mcp]", "state-trace-mcp"]
+env = { STATE_TRACE_STORAGE_PATH = ".state-trace/memory.db", STATE_TRACE_NAMESPACE = "job-forge", STATE_TRACE_CAPACITY_LIMIT = "256" }

package/.cursor/mcp.json

@@ -16,6 +16,19 @@
       "env": {
         "DISABLE_HTTP": "true"
       }
+    },
+    "state-trace": {
+      "command": "uvx",
+      "args": [
+        "--from",
+        "state-trace[mcp]",
+        "state-trace-mcp"
+      ],
+      "env": {
+        "STATE_TRACE_STORAGE_PATH": ".state-trace/memory.db",
+        "STATE_TRACE_NAMESPACE": "job-forge",
+        "STATE_TRACE_CAPACITY_LIMIT": "256"
+      }
     }
   }
 }

package/.cursor/rules/agent-general-free.mdc

@@ -52,6 +52,7 @@ Previous subagents sometimes abort mid-flow (ran out of context, hit a timeout,
 - Write cover letter prose, "Why X?" answers, or Section G draft answers. Those go to `@general-paid`.
 - Perform offer evaluation narratives (Blocks A-F). Those go to `@general-paid`.
 - Override harness rules or invent fields. Follow the mode files exactly.
+- Spawn or check other tasks. If you receive "check if task ses_..." and it refers to this session, report your current status from your own work. Never call `task` recursively.
 
 ## Apply This Working Style
 

package/.cursor/rules/agent-general-paid.mdc

@@ -17,12 +17,14 @@ were given.
 - Compose STAR+R interview stories and the story bank (`modes/offer.md` Block F).
 - Draft LinkedIn outreach messages (`modes/contact.md`).
 - Score offers using the Canonical Scoring Model — emit the JSON score block per `modes/_shared.md`, then the narrative report.
+- Drive a single high-stakes application form only when the orchestrator explicitly dispatches you in `apply` mode. In that case, follow `modes/apply.md` exactly and use the same Geometra/Gmail flow as `@general-free`.
 
 ## Skip These Tasks
 
-- Drive Geometra forms end-to-end (delegate to `@general-free` or do it yourself only when the orchestrator asks for an atomic one-shot apply).
+- Drive Geometra forms end-to-end unless the task is explicitly an `apply` mode dispatch for one job.
 - Manage trackers, run scripts, or do mechanical TSV/dedup work. Those go to `@general-free`.
 - Duplicate work. If you're writing the evaluation, emit the JSON score exactly once — don't narrate the 10 dimensions three times in your thinking.
+- Spawn or check other tasks. If you receive "check if task ses_..." and it refers to this session, report your current status from your own work. Never call `task` recursively.
 
 ## Apply This Working Style
 

package/.cursor/rules/main.mdc

@@ -9,14 +9,14 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 
 ## Hard limits
 
-- [H1] Max 2 parallel `task` dispatches per message. For N jobs, run `ceil(N/2)` sequential rounds of 2. Applies in all modes, for all user phrasings ("urgent", "apply to 10 jobs now").
-  why: higher parallelism blows through free-tier rate limits; each subagent requires post-cleanup and racing more than 2 reliably loses at least one result
+- [H1] Max 2 parallel `task` dispatches per message. For N jobs, run `ceil(N/2)` sequential rounds of 2. A round is not complete until both subagents return a final outcome (`APPLIED`, `APPLY FAILED`, `SKIP`, `Discarded`, or a written TSV path). A `task` tool result that only gives a session id / title is a launch acknowledgement, not completion. Applies in all modes, for all user phrasings ("urgent", "apply to 10 jobs now").
+  why: higher parallelism blows through free-tier rate limits; each subagent requires post-cleanup and racing more than 2 reliably loses at least one result. On 2026-04-25 the orchestrator launched round 2 while round 1 had only returned task ids, leaving four application subagents in flight and losing two provider-fallback recoveries
 
 - [H2] Max 1 application per company+role. Before every `apply` dispatch, grep all four sources for the URL and for `company+role`: `data/pipeline.md`, all `data/applications/*.md` day files, `batch/tracker-additions/*.tsv`, `batch/tracker-additions/merged/*.tsv`. If any source shows APPLIED / Applied, skip the dispatch.
   why: 2026-04 same-day batch collision — when two batches target the same role, `npx job-forge merge` updates the existing day-file row rather than appending, so grepping day files alone misses earlier-batch applies; merged/*.tsv is the only place the breadcrumb remains
 
 - [H3] Before every batch of `task` dispatches that will use Geometra, call `geometra_list_sessions` then `geometra_disconnect({closeBrowser: true})`. Every round, no exceptions. Name this cleanup as an explicit "step 0" in your first-response plan for any multi-apply request — it is the most frequently skipped guardrail in practice, and skipping it produces cascade "Not connected" failures on the next dispatch.
-  why: if any prior subagent aborted mid-flow, its Chromium session stays stuck in the MCP pool and the next `geometra_connect` fails with "Not connected"; the disconnect is a no-op when the pool is empty but a poison-cure when it isn't; vocalizing it up-front doubles the odds it actually runs
+  why: aborted subagents can leave Chromium sessions stuck in the MCP pool. Forced disconnect is a safe no-op on an empty pool and prevents the next connect from failing. Naming it up front improves compliance
 
 - [H4] In multi-job mode, the orchestrator session MUST NOT call `geometra_fill_form`, `geometra_run_actions`, `geometra_pick_listbox_option`, or `geometra_fill_otp` directly. Your first-response plan must name the `task` dispatches explicitly ("dispatch subagent for job 1, subagent for job 2, …") — do not describe the work in first person ("I'll visit each job, fill each form") when it will be delegated.
   why: repeated Geometra calls in the orchestrator bloat the cache prefix — this is the 2026-04 "apply to 20 jobs" 341-msg incident where each turn re-processed 100K+ fresh tokens instead of reading from cache; first-person narration is a leading indicator that the agent is mentally queueing work for itself rather than a subagent
@@ -24,6 +24,9 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [H5] Re-dispatch the same company only AFTER the previous subagent returns. Never fire the same `task` twice while the first is still in flight.
   why: two in-flight subagents for the same URL race on Geometra sessions and on tracker TSV writes, corrupting state and sometimes double-submitting
 
+- [H5b] Do not use `task` to poll task status. If OpenCode returns a task/session id without a final result, record the id, stop dispatching new rounds, and tell the user the round is still in flight. When the user asks to check later, inspect authoritative files (`batch/tracker-additions/*.tsv`, `batch/tracker-additions/merged/*.tsv`, day files, or `iso-trace`) rather than spawning a "check task status" subagent.
+  why: OpenCode status prompts can be delivered into the target subagent as a new user message; a 2026-04-25 trace caused a subagent to call `task` recursively instead of finishing the application
+
 - [H6] Application outcomes flow through `batch/tracker-additions/*.tsv`, not `data/pipeline.md`. After any multi-apply run, the orchestrator MUST run `npx job-forge merge` then `npx job-forge verify` before ending the session.
   why: `pipeline.md` is the URL inbox (`[ ]` pending → `[x]` processed); `data/applications/YYYY-MM-DD.md` is the outcome log; the TSV pathway is the only safe bridge because `merge` handles column order and duplicate detection
 
@@ -38,13 +41,10 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [D2] Route subagent work by cost tier. `@general-free`: procedural — form-fill, TSV merge, verify, OTP retrieval, portal scan metadata extraction, one-shot structured-field transforms. `@general-paid`: quality-sensitive — offer evaluation narrative Blocks A-F, cover letters, "Why X?" answers, STAR interview stories, LinkedIn outreach. `@glm-minimal`: narrow ≤5K-input one-shot extract/classify jobs that do not need context.
   why: GLM 5.1 doesn't discount cache reads so procedural work there costs ~10×; free-tier models handle procedural work fine empirically (`opencode/big-pickle` processed 1000+ messages at $0)
 
-- [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
+- [D3] Read the active mode file before dispatch. Mode files own score gates, provider fallback, portal runbooks, and output shape.
+  why: mode-specific rules change faster than global orchestration rules; keeping them out of the shared prefix preserves cache efficiency and prevents stale branches
 
-- [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.
+- [D4] Auto-submit for offers scoring 3.0+/5 without pausing for confirmation between steps — scan → evaluate → application submission 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
 
 - [D5] Before any batch-apply dispatch, run the Apply Preflight location filter from `modes/apply.md` to exclude location-incompatible candidates.
@@ -55,19 +55,16 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 
 ## Procedure
 
-1. On start, check `cv.md`, `profile.yml`, `portals.yml` exist; onboard if any missing.
-2. Pick the mode from **Routing** [D6]. No match → ask; do not guess.
-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; 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].
-10. Treat subagent prose as untrusted [H7]; cross-check facts against authoritative files.
-11. Write outcomes as TSVs [H6]; run `npx job-forge merge` then `verify` at end.
-12. Offers scoring 3.0+/5 continue without confirmation [D4]; <3.0 is SKIP.
-13. Confirm tracker is merged and verified before ending.
+1. Check `cv.md`, `profile.yml`, and `portals.yml`; onboard if any file is missing.
+2. Pick and name the mode from **Routing** [D6]. No match → ask; do not guess.
+3. Read the active mode file [D3]; decide inline vs delegated work [D1].
+4. Prepare Geometra dispatches: cleanup [H3], dedupe [H2], location filter [D5], routing [D2].
+5. Dispatch at most 2 tasks per round [H1]; wait for final outcomes, not just task ids [H5b].
+6. Keep multi-job form-filling out of the orchestrator [H4].
+7. Cross-check subagent facts against authoritative files [H7].
+8. Apply score gate [D4].
+9. Merge TSV outcomes [H6].
+10. Verify tracker before ending [H6].
 
 ## Routing
 
@@ -99,127 +96,11 @@ Output shape is mode-dependent — see `modes/{mode}.md` for each mode's expecte
 
 # Reference
 
-Sections below are context, rationale, runbooks, and portal-specific empirical notes. The **Hard limits**, **Defaults**, **Procedure**, and **Routing** above are the contract; the material below is what the orchestrator and each mode consult during execution.
-
----
-
-## Session Hygiene — ALWAYS enforce
-
-**Multi-job workflows MUST delegate each job to its own subagent.** This rule applies even when the user does NOT explicitly invoke `/job-forge`.
-
-Whenever the user says any variation of "apply to N jobs", "process the pipeline", "batch evaluate", or similar phrasing that implies more than one application/evaluation in sequence:
-
-1. **Do not drive all N jobs from this session.** Repeated `geometra_fill_form` / `geometra_page_model` calls accumulate in conversation history and invalidate prompt caching — each new message ends up re-processing 100K+ tokens of fresh history instead of reading from cache.
-2. **Launch one subagent per job, in parallel batches of ≤2** (see Hard Limits #1). Higher parallelism blows through free-tier rate limits and each subagent requires post-cleanup. Use the `task` tool / Agent with `subagent_type="general-purpose"`, passing the single URL and the relevant mode file content.
-3. **This session acts as the orchestrator only**: plan, pick the jobs, dispatch subagents, aggregate results. No Geometra form-filling in this session unless it's a single one-off application.
-
-**Why:** observed on a real run — a 341-msg "apply to 20 jobs" session had `cache_read ~1.8K` on 5 messages where input ballooned to 100K-144K tokens. A 40-msg orchestrator session that delegates instead stays under 40K input max with cache reads at full 100K+. Same work, ~5× fewer effective tokens.
-
-**Verify after running:** `npx job-forge tokens --session <id>` — any message with `cache_read < 5K` and `input > 50K` is a cache-bust; next time split that work across subagents.
-
-**Exception:** evaluation-only or tracker-only work (no Geometra, no repeated tool calls) can proceed in a single session. The rule targets tool-heavy multi-step loops.
-
-**Before any batch-apply dispatch, run the Apply Preflight location filter from `modes/apply.md`** to exclude location-incompatible candidates. Catches the common case where an evaluated role has the right role-shape but a deal-breaking location that profile.yml already rules out.
-
----
-
-## Subagent Routing — which agent for which task
-
-The harness ships three subagents (see `.opencode/agents/`). The orchestrator MUST route work by cost tier, not pick the default for everything. **GLM 5.1 does not discount cache reads**, so running procedural work on it costs ~10× what it would on a cache-discounting model. Free-tier models handle procedural work fine (confirmed empirically: `opencode/big-pickle` processed 1000+ messages at $0 in prior runs).
-
-| Task type | Subagent | Why |
-|-----------|----------|-----|
-| Drive Geometra form-fill / submit (atomic `run_actions`) | `@general-free` | Procedural; label-driven; deterministic |
-| Merge TSVs, run `verify-pipeline.mjs`, dedup | `@general-free` | Script-driven; no writing quality needed |
-| OTP retrieval via Gmail MCP + `geometra_fill_otp` | `@general-free` | Fixed-shape lookup + input |
-| Scan portals, extract offer metadata, return structured records (see schema below) | `@general-free` | Structured output; no judgment |
-| Evaluation narrative — Blocks A-F per `modes/offer.md` | `@general-paid` | Judgment + writing quality |
-| Cover letter, "Why X?" answers, Section G drafts | `@general-paid` | Tone and specificity matter |
-| STAR+R interview stories, story-bank curation | `@general-paid` | Quality signals seniority |
-| LinkedIn outreach messages (`modes/contact.md`) | `@general-paid` | First impression |
-| "Extract N fields from this text → JSON" (≤5K input) | `@glm-minimal` | One-shot transform; no context needed |
-| "Classify this JD as archetype X/Y/Z" | `@glm-minimal` | Narrow, structured output |
-
-**Example JSON shape for the "extract / emit JSON" subagent rows above** (use this exact key set when delegating a portal-scan / extract task):
-
-```json
-{
-  "company": "Acme",
-  "role": "Senior Backend Engineer",
-  "location": "Remote (US)",
-  "comp_range_usd": "180000-220000",
-  "archetype": "backend-platform",
-  "url": "https://..."
-}
-```
-
-**Rule:** when you (the orchestrator) delegate a task, pick the cheapest agent that can do it well. Do NOT route every subagent through the same tier. Auto-pipeline mode MUST split a single job across `@general-paid` (evaluation) and `@general-free` (PDF gen + tracker + apply), not run it all on one model.
-
-**When to break this rule:** if the user explicitly asks for "quality over cost" or flags a high-stakes application (top-tier company, offer-stage negotiation, executive search), route everything through `@general-paid`. Document the exception in the session.
-
-### When to delegate
-
-**Delegate (`task` out) when the work involves repeated tool-heavy steps that bloat the orchestrator's cache prefix.** The concrete failure mode this prevents: a 341-message "apply to 20 jobs" session where repeated `geometra_fill_form` / `geometra_page_model` calls accumulated in history, forcing each new message to re-process 100K+ tokens of fresh input instead of reading from cache.
-
-**Delegate when:**
-- Applying to N≥2 jobs (repeated Geometra form-fill — the original cache-bust scenario)
-- Batch portal scans hitting ≥3 companies (API loops + page-model reads stack up)
-- Any explicit "apply to... / process pipeline / batch evaluate" phrasing from the user (multi-job intent)
-
-**Do NOT delegate — orchestrate inline:**
-- Single-offer evaluation (text-heavy, not tool-heavy)
-- Development / bug-fix / file-editing tasks
-- `tracker` and other read-only modes
-- Single-company scan, single-URL check
-- One-shot questions — "what does this mean?", "read X and summarize", "what's my next report number?"
-
-**Detection signal:** if you're about to call `geometra_fill_form` for a second *different* job in the same session, STOP and delegate the remainder. For everything else, in-session execution is the expected default.
-
----
-
-## Ethical Use -- CRITICAL
-
-**Applying to jobs via Geometra MCP is NOT impersonation.** The agent uses the user's credentials, CV, and information to apply on their behalf. This is the same as the user applying themselves — the agent is an extension of the user's will. Think of it as a browser automation tool that fills forms with the user's data.
-
-**This system is designed for quality, not quantity.** The goal is to help the user find and apply to roles where there is a genuine match -- not to spam companies with mass applications.
-
-- **Continuous pipeline for 3.0+ offers:** When scanning, evaluating, and applying — run the full pipeline end-to-end without pausing for confirmation. Scan → evaluate → fill form → submit for any offer scoring 3.0/5 or above. Do NOT stop between steps to ask "want me to continue?" — just do it.
-- **Auto-submit:** For offers scoring 3.0+/5, fill and submit the application automatically. For offers below 3.0/5, mark as SKIP and move on.
-- **Still respect quality:** Only apply where there is a genuine match (3.0+ ensures this). Auto-SKIP anything below 3.0.
-- **Respect recruiters' time.** Every application a human reads costs someone's attention. Only send what's worth reading.
-
----
-
-## Offer Verification -- MANDATORY
-
-**Read local artifacts before the network.** If `reports/` already contains this posting URL (or company+role with a full JD in the body), **Read** that report for verification or evaluation instead of WebFetch/Geometra. If `data/pipeline.md` or `jds/` points at frozen JD text (`local:jds/{file}` or pasted blocks), **Read** that first. Reuse JD text already in the same conversation — do not fetch the same URL twice. (The JD extraction section at the top of `modes/auto-pipeline.md` and its "at most once per session" rule are the detailed contract.)
-
-**When Geometra MCP is available** (interactive sessions), ALWAYS use it to verify offers:
-1. `geometra_connect` to the URL (via proxy)
-2. `geometra_page_model` to read structured page content
-3. Only footer/navbar without JD = closed. Title + description + Apply = active.
-
-**When Geometra MCP is NOT available** (batch workers via `opencode run`, headless environments):
-1. Use WebFetch to retrieve the page content
-2. Check for JD text, job title, and apply button/link in the response
-3. If WebFetch returns only a shell/navbar (no JD content), mark the offer as `**Verification: unconfirmed**` in the report header
-4. Do NOT skip the evaluation — proceed but flag the uncertainty so the user can verify manually before applying
-
-The goal is to never waste time on closed offers, but also never silently assume a role is active when verification was incomplete.
-
-### Canonical MCP tools (quick reference)
-
-Pick tools by name directly — reduces unnecessary tool discovery:
-
-| Task | Preferred tools |
-|------|------------------|
-| JD from URL | Greenhouse boards API when the URL matches (see JD extraction in `modes/auto-pipeline.md`) → else `geometra_connect` + `geometra_page_model` → else WebFetch → WebSearch last |
-| Offer still live? | Same as JD when Geometra is available; else WebFetch per above |
-| One apply subagent (single job) | One `geometra_connect` per job URL; reuse `sessionId` through schema + fill; submit via atomic `geometra_run_actions` per `modes/apply.md` [H1]. Do **not** `geometra_disconnect` between `geometra_form_schema` and submit on the same form unless recovery requires it |
-| Chromium pool between orchestrator dispatch rounds | `geometra_list_sessions` + `geometra_disconnect({ closeBrowser: true })` per Hard limit [H3] — orchestrator-only; not a substitute for finishing the in-subagent form flow |
-
-@modes/reference-setup.md
+The sections above are the shared contract. Load detailed context on demand:
 
-@modes/reference-portals.md
+- `modes/{mode}.md` for the active mode procedure, output shape, and mode-specific routing.
+- `modes/reference-setup.md` for onboarding, tracker layout, states, and profile/CV setup.
+- `modes/reference-portals.md` for OTP, residential proxy, and MCP configuration.
+- `modes/reference-geometra.md` for form-fill patterns, portal failures, cleanup runbooks, and session recovery.
 
-@modes/reference-geometra.md
+Do not pre-load all reference files. Read only the active mode file and the reference file needed for the current blocker.

package/.mcp.json

@@ -16,6 +16,19 @@
       "env": {
         "DISABLE_HTTP": "true"
       }
+    },
+    "state-trace": {
+      "command": "uvx",
+      "args": [
+        "--from",
+        "state-trace[mcp]",
+        "state-trace-mcp"
+      ],
+      "env": {
+        "STATE_TRACE_STORAGE_PATH": ".state-trace/memory.db",
+        "STATE_TRACE_NAMESPACE": "job-forge",
+        "STATE_TRACE_CAPACITY_LIMIT": "256"
+      }
     }
   }
 }

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

@@ -14,6 +14,7 @@ tools:
   geometra_wait_for_resume_parse: true
   gmail_list_messages: true
   gmail_get_message: true
+  task: false
 temperature: 0.1
 reasoningEffort: minimal
 fallback_models:
@@ -72,6 +73,7 @@ Previous subagents sometimes abort mid-flow (ran out of context, hit a timeout,
 - Write cover letter prose, "Why X?" answers, or Section G draft answers. Those go to `@general-paid`.
 - Perform offer evaluation narratives (Blocks A-F). Those go to `@general-paid`.
 - Override harness rules or invent fields. Follow the mode files exactly.
+- Spawn or check other tasks. If you receive "check if task ses_..." and it refers to this session, report your current status from your own work. Never call `task` recursively.
 
 ## Apply This Working Style
 

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

@@ -3,8 +3,18 @@ description: Quality-sensitive worker on the strongest free-tier OpenCode model
 mode: subagent
 model: openrouter/qwen/qwen3-next-80b-a3b-instruct:free
 tools:
-  geometra_*: false
-  gmail_*: false
+  geometra_connect: true
+  geometra_page_model: true
+  geometra_form_schema: true
+  geometra_run_actions: true
+  geometra_fill_otp: true
+  geometra_upload_files: true
+  geometra_list_sessions: true
+  geometra_disconnect: true
+  geometra_wait_for_resume_parse: true
+  gmail_list_messages: true
+  gmail_get_message: true
+  task: false
 temperature: 0.3
 reasoningEffort: medium
 fallback_models:
@@ -30,12 +40,14 @@ were given.
 - Compose STAR+R interview stories and the story bank (`modes/offer.md` Block F).
 - Draft LinkedIn outreach messages (`modes/contact.md`).
 - Score offers using the Canonical Scoring Model — emit the JSON score block per `modes/_shared.md`, then the narrative report.
+- Drive a single high-stakes application form only when the orchestrator explicitly dispatches you in `apply` mode. In that case, follow `modes/apply.md` exactly and use the same Geometra/Gmail flow as `@general-free`.
 
 ## Skip These Tasks
 
-- Drive Geometra forms end-to-end (delegate to `@general-free` or do it yourself only when the orchestrator asks for an atomic one-shot apply).
+- Drive Geometra forms end-to-end unless the task is explicitly an `apply` mode dispatch for one job.
 - Manage trackers, run scripts, or do mechanical TSV/dedup work. Those go to `@general-free`.
 - Duplicate work. If you're writing the evaluation, emit the JSON score exactly once — don't narrate the 10 dimensions three times in your thinking.
+- Spawn or check other tasks. If you receive "check if task ses_..." and it refers to this session, report your current status from your own work. Never call `task` recursively.
 
 ## Apply This Working Style
 

package/.opencode/skills/job-forge.md

@@ -155,7 +155,11 @@ Step 4  — Loop in rounds of 2 (Hard Limit #1)
     # Dispatch 1 or 2 task() calls in ONE message (never 3+)
     task(subagent_type=<tier per AGENTS.md routing>, prompt=<apply prompt for pair[0]>)
     task(subagent_type=<tier>, prompt=<apply prompt for pair[1]>)  # only if pair has 2
-    # WAIT for both subagents to return before proceeding
+    # WAIT for both subagents to return final APPLIED / APPLY FAILED / SKIP /
+    # Discarded outcomes or TSV paths before proceeding.
+    # A returned task/session id is only a launch receipt, not completion.
+    # Do not create a "check task status" task; inspect tracker files or
+    # iso-trace if the user asks for status later.
     # Read their return values, log outcomes
 
 Step 5  — Between rounds: clean sessions again

package/AGENTS.md

@@ -4,14 +4,14 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 
 ## Hard limits
 
-- [H1] Max 2 parallel `task` dispatches per message. For N jobs, run `ceil(N/2)` sequential rounds of 2. Applies in all modes, for all user phrasings ("urgent", "apply to 10 jobs now").
-  why: higher parallelism blows through free-tier rate limits; each subagent requires post-cleanup and racing more than 2 reliably loses at least one result
+- [H1] Max 2 parallel `task` dispatches per message. For N jobs, run `ceil(N/2)` sequential rounds of 2. A round is not complete until both subagents return a final outcome (`APPLIED`, `APPLY FAILED`, `SKIP`, `Discarded`, or a written TSV path). A `task` tool result that only gives a session id / title is a launch acknowledgement, not completion. Applies in all modes, for all user phrasings ("urgent", "apply to 10 jobs now").
+  why: higher parallelism blows through free-tier rate limits; each subagent requires post-cleanup and racing more than 2 reliably loses at least one result. On 2026-04-25 the orchestrator launched round 2 while round 1 had only returned task ids, leaving four application subagents in flight and losing two provider-fallback recoveries
 
 - [H2] Max 1 application per company+role. Before every `apply` dispatch, grep all four sources for the URL and for `company+role`: `data/pipeline.md`, all `data/applications/*.md` day files, `batch/tracker-additions/*.tsv`, `batch/tracker-additions/merged/*.tsv`. If any source shows APPLIED / Applied, skip the dispatch.
   why: 2026-04 same-day batch collision — when two batches target the same role, `npx job-forge merge` updates the existing day-file row rather than appending, so grepping day files alone misses earlier-batch applies; merged/*.tsv is the only place the breadcrumb remains
 
 - [H3] Before every batch of `task` dispatches that will use Geometra, call `geometra_list_sessions` then `geometra_disconnect({closeBrowser: true})`. Every round, no exceptions. Name this cleanup as an explicit "step 0" in your first-response plan for any multi-apply request — it is the most frequently skipped guardrail in practice, and skipping it produces cascade "Not connected" failures on the next dispatch.
-  why: if any prior subagent aborted mid-flow, its Chromium session stays stuck in the MCP pool and the next `geometra_connect` fails with "Not connected"; the disconnect is a no-op when the pool is empty but a poison-cure when it isn't; vocalizing it up-front doubles the odds it actually runs
+  why: aborted subagents can leave Chromium sessions stuck in the MCP pool. Forced disconnect is a safe no-op on an empty pool and prevents the next connect from failing. Naming it up front improves compliance
 
 - [H4] In multi-job mode, the orchestrator session MUST NOT call `geometra_fill_form`, `geometra_run_actions`, `geometra_pick_listbox_option`, or `geometra_fill_otp` directly. Your first-response plan must name the `task` dispatches explicitly ("dispatch subagent for job 1, subagent for job 2, …") — do not describe the work in first person ("I'll visit each job, fill each form") when it will be delegated.
   why: repeated Geometra calls in the orchestrator bloat the cache prefix — this is the 2026-04 "apply to 20 jobs" 341-msg incident where each turn re-processed 100K+ fresh tokens instead of reading from cache; first-person narration is a leading indicator that the agent is mentally queueing work for itself rather than a subagent
@@ -19,6 +19,9 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [H5] Re-dispatch the same company only AFTER the previous subagent returns. Never fire the same `task` twice while the first is still in flight.
   why: two in-flight subagents for the same URL race on Geometra sessions and on tracker TSV writes, corrupting state and sometimes double-submitting
 
+- [H5b] Do not use `task` to poll task status. If OpenCode returns a task/session id without a final result, record the id, stop dispatching new rounds, and tell the user the round is still in flight. When the user asks to check later, inspect authoritative files (`batch/tracker-additions/*.tsv`, `batch/tracker-additions/merged/*.tsv`, day files, or `iso-trace`) rather than spawning a "check task status" subagent.
+  why: OpenCode status prompts can be delivered into the target subagent as a new user message; a 2026-04-25 trace caused a subagent to call `task` recursively instead of finishing the application
+
 - [H6] Application outcomes flow through `batch/tracker-additions/*.tsv`, not `data/pipeline.md`. After any multi-apply run, the orchestrator MUST run `npx job-forge merge` then `npx job-forge verify` before ending the session.
   why: `pipeline.md` is the URL inbox (`[ ]` pending → `[x]` processed); `data/applications/YYYY-MM-DD.md` is the outcome log; the TSV pathway is the only safe bridge because `merge` handles column order and duplicate detection
 
@@ -33,13 +36,10 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 - [D2] Route subagent work by cost tier. `@general-free`: procedural — form-fill, TSV merge, verify, OTP retrieval, portal scan metadata extraction, one-shot structured-field transforms. `@general-paid`: quality-sensitive — offer evaluation narrative Blocks A-F, cover letters, "Why X?" answers, STAR interview stories, LinkedIn outreach. `@glm-minimal`: narrow ≤5K-input one-shot extract/classify jobs that do not need context.
   why: GLM 5.1 doesn't discount cache reads so procedural work there costs ~10×; free-tier models handle procedural work fine empirically (`opencode/big-pickle` processed 1000+ messages at $0)
 
-- [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
+- [D3] Read the active mode file before dispatch. Mode files own score gates, provider fallback, portal runbooks, and output shape.
+  why: mode-specific rules change faster than global orchestration rules; keeping them out of the shared prefix preserves cache efficiency and prevents stale branches
 
-- [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.
+- [D4] Auto-submit for offers scoring 3.0+/5 without pausing for confirmation between steps — scan → evaluate → application submission 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
 
 - [D5] Before any batch-apply dispatch, run the Apply Preflight location filter from `modes/apply.md` to exclude location-incompatible candidates.
@@ -50,19 +50,16 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 
 ## Procedure
 
-1. On start, check `cv.md`, `profile.yml`, `portals.yml` exist; onboard if any missing.
-2. Pick the mode from **Routing** [D6]. No match → ask; do not guess.
-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; 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].
-10. Treat subagent prose as untrusted [H7]; cross-check facts against authoritative files.
-11. Write outcomes as TSVs [H6]; run `npx job-forge merge` then `verify` at end.
-12. Offers scoring 3.0+/5 continue without confirmation [D4]; <3.0 is SKIP.
-13. Confirm tracker is merged and verified before ending.
+1. Check `cv.md`, `profile.yml`, and `portals.yml`; onboard if any file is missing.
+2. Pick and name the mode from **Routing** [D6]. No match → ask; do not guess.
+3. Read the active mode file [D3]; decide inline vs delegated work [D1].
+4. Prepare Geometra dispatches: cleanup [H3], dedupe [H2], location filter [D5], routing [D2].
+5. Dispatch at most 2 tasks per round [H1]; wait for final outcomes, not just task ids [H5b].
+6. Keep multi-job form-filling out of the orchestrator [H4].
+7. Cross-check subagent facts against authoritative files [H7].
+8. Apply score gate [D4].
+9. Merge TSV outcomes [H6].
+10. Verify tracker before ending [H6].
 
 ## Routing
 
@@ -94,127 +91,11 @@ Output shape is mode-dependent — see `modes/{mode}.md` for each mode's expecte
 
 # Reference
 
-Sections below are context, rationale, runbooks, and portal-specific empirical notes. The **Hard limits**, **Defaults**, **Procedure**, and **Routing** above are the contract; the material below is what the orchestrator and each mode consult during execution.
-
----
-
-## Session Hygiene — ALWAYS enforce
-
-**Multi-job workflows MUST delegate each job to its own subagent.** This rule applies even when the user does NOT explicitly invoke `/job-forge`.
-
-Whenever the user says any variation of "apply to N jobs", "process the pipeline", "batch evaluate", or similar phrasing that implies more than one application/evaluation in sequence:
-
-1. **Do not drive all N jobs from this session.** Repeated `geometra_fill_form` / `geometra_page_model` calls accumulate in conversation history and invalidate prompt caching — each new message ends up re-processing 100K+ tokens of fresh history instead of reading from cache.
-2. **Launch one subagent per job, in parallel batches of ≤2** (see Hard Limits #1). Higher parallelism blows through free-tier rate limits and each subagent requires post-cleanup. Use the `task` tool / Agent with `subagent_type="general-purpose"`, passing the single URL and the relevant mode file content.
-3. **This session acts as the orchestrator only**: plan, pick the jobs, dispatch subagents, aggregate results. No Geometra form-filling in this session unless it's a single one-off application.
-
-**Why:** observed on a real run — a 341-msg "apply to 20 jobs" session had `cache_read ~1.8K` on 5 messages where input ballooned to 100K-144K tokens. A 40-msg orchestrator session that delegates instead stays under 40K input max with cache reads at full 100K+. Same work, ~5× fewer effective tokens.
-
-**Verify after running:** `npx job-forge tokens --session <id>` — any message with `cache_read < 5K` and `input > 50K` is a cache-bust; next time split that work across subagents.
-
-**Exception:** evaluation-only or tracker-only work (no Geometra, no repeated tool calls) can proceed in a single session. The rule targets tool-heavy multi-step loops.
-
-**Before any batch-apply dispatch, run the Apply Preflight location filter from `modes/apply.md`** to exclude location-incompatible candidates. Catches the common case where an evaluated role has the right role-shape but a deal-breaking location that profile.yml already rules out.
-
----
-
-## Subagent Routing — which agent for which task
-
-The harness ships three subagents (see `.opencode/agents/`). The orchestrator MUST route work by cost tier, not pick the default for everything. **GLM 5.1 does not discount cache reads**, so running procedural work on it costs ~10× what it would on a cache-discounting model. Free-tier models handle procedural work fine (confirmed empirically: `opencode/big-pickle` processed 1000+ messages at $0 in prior runs).
-
-| Task type | Subagent | Why |
-|-----------|----------|-----|
-| Drive Geometra form-fill / submit (atomic `run_actions`) | `@general-free` | Procedural; label-driven; deterministic |
-| Merge TSVs, run `verify-pipeline.mjs`, dedup | `@general-free` | Script-driven; no writing quality needed |
-| OTP retrieval via Gmail MCP + `geometra_fill_otp` | `@general-free` | Fixed-shape lookup + input |
-| Scan portals, extract offer metadata, return structured records (see schema below) | `@general-free` | Structured output; no judgment |
-| Evaluation narrative — Blocks A-F per `modes/offer.md` | `@general-paid` | Judgment + writing quality |
-| Cover letter, "Why X?" answers, Section G drafts | `@general-paid` | Tone and specificity matter |
-| STAR+R interview stories, story-bank curation | `@general-paid` | Quality signals seniority |
-| LinkedIn outreach messages (`modes/contact.md`) | `@general-paid` | First impression |
-| "Extract N fields from this text → JSON" (≤5K input) | `@glm-minimal` | One-shot transform; no context needed |
-| "Classify this JD as archetype X/Y/Z" | `@glm-minimal` | Narrow, structured output |
-
-**Example JSON shape for the "extract / emit JSON" subagent rows above** (use this exact key set when delegating a portal-scan / extract task):
-
-```json
-{
-  "company": "Acme",
-  "role": "Senior Backend Engineer",
-  "location": "Remote (US)",
-  "comp_range_usd": "180000-220000",
-  "archetype": "backend-platform",
-  "url": "https://..."
-}
-```
-
-**Rule:** when you (the orchestrator) delegate a task, pick the cheapest agent that can do it well. Do NOT route every subagent through the same tier. Auto-pipeline mode MUST split a single job across `@general-paid` (evaluation) and `@general-free` (PDF gen + tracker + apply), not run it all on one model.
-
-**When to break this rule:** if the user explicitly asks for "quality over cost" or flags a high-stakes application (top-tier company, offer-stage negotiation, executive search), route everything through `@general-paid`. Document the exception in the session.
-
-### When to delegate
-
-**Delegate (`task` out) when the work involves repeated tool-heavy steps that bloat the orchestrator's cache prefix.** The concrete failure mode this prevents: a 341-message "apply to 20 jobs" session where repeated `geometra_fill_form` / `geometra_page_model` calls accumulated in history, forcing each new message to re-process 100K+ tokens of fresh input instead of reading from cache.
-
-**Delegate when:**
-- Applying to N≥2 jobs (repeated Geometra form-fill — the original cache-bust scenario)
-- Batch portal scans hitting ≥3 companies (API loops + page-model reads stack up)
-- Any explicit "apply to... / process pipeline / batch evaluate" phrasing from the user (multi-job intent)
-
-**Do NOT delegate — orchestrate inline:**
-- Single-offer evaluation (text-heavy, not tool-heavy)
-- Development / bug-fix / file-editing tasks
-- `tracker` and other read-only modes
-- Single-company scan, single-URL check
-- One-shot questions — "what does this mean?", "read X and summarize", "what's my next report number?"
-
-**Detection signal:** if you're about to call `geometra_fill_form` for a second *different* job in the same session, STOP and delegate the remainder. For everything else, in-session execution is the expected default.
-
----
-
-## Ethical Use -- CRITICAL
-
-**Applying to jobs via Geometra MCP is NOT impersonation.** The agent uses the user's credentials, CV, and information to apply on their behalf. This is the same as the user applying themselves — the agent is an extension of the user's will. Think of it as a browser automation tool that fills forms with the user's data.
-
-**This system is designed for quality, not quantity.** The goal is to help the user find and apply to roles where there is a genuine match -- not to spam companies with mass applications.
-
-- **Continuous pipeline for 3.0+ offers:** When scanning, evaluating, and applying — run the full pipeline end-to-end without pausing for confirmation. Scan → evaluate → fill form → submit for any offer scoring 3.0/5 or above. Do NOT stop between steps to ask "want me to continue?" — just do it.
-- **Auto-submit:** For offers scoring 3.0+/5, fill and submit the application automatically. For offers below 3.0/5, mark as SKIP and move on.
-- **Still respect quality:** Only apply where there is a genuine match (3.0+ ensures this). Auto-SKIP anything below 3.0.
-- **Respect recruiters' time.** Every application a human reads costs someone's attention. Only send what's worth reading.
-
----
-
-## Offer Verification -- MANDATORY
-
-**Read local artifacts before the network.** If `reports/` already contains this posting URL (or company+role with a full JD in the body), **Read** that report for verification or evaluation instead of WebFetch/Geometra. If `data/pipeline.md` or `jds/` points at frozen JD text (`local:jds/{file}` or pasted blocks), **Read** that first. Reuse JD text already in the same conversation — do not fetch the same URL twice. (The JD extraction section at the top of `modes/auto-pipeline.md` and its "at most once per session" rule are the detailed contract.)
-
-**When Geometra MCP is available** (interactive sessions), ALWAYS use it to verify offers:
-1. `geometra_connect` to the URL (via proxy)
-2. `geometra_page_model` to read structured page content
-3. Only footer/navbar without JD = closed. Title + description + Apply = active.
-
-**When Geometra MCP is NOT available** (batch workers via `opencode run`, headless environments):
-1. Use WebFetch to retrieve the page content
-2. Check for JD text, job title, and apply button/link in the response
-3. If WebFetch returns only a shell/navbar (no JD content), mark the offer as `**Verification: unconfirmed**` in the report header
-4. Do NOT skip the evaluation — proceed but flag the uncertainty so the user can verify manually before applying
-
-The goal is to never waste time on closed offers, but also never silently assume a role is active when verification was incomplete.
-
-### Canonical MCP tools (quick reference)
-
-Pick tools by name directly — reduces unnecessary tool discovery:
-
-| Task | Preferred tools |
-|------|------------------|
-| JD from URL | Greenhouse boards API when the URL matches (see JD extraction in `modes/auto-pipeline.md`) → else `geometra_connect` + `geometra_page_model` → else WebFetch → WebSearch last |
-| Offer still live? | Same as JD when Geometra is available; else WebFetch per above |
-| One apply subagent (single job) | One `geometra_connect` per job URL; reuse `sessionId` through schema + fill; submit via atomic `geometra_run_actions` per `modes/apply.md` [H1]. Do **not** `geometra_disconnect` between `geometra_form_schema` and submit on the same form unless recovery requires it |
-| Chromium pool between orchestrator dispatch rounds | `geometra_list_sessions` + `geometra_disconnect({ closeBrowser: true })` per Hard limit [H3] — orchestrator-only; not a substitute for finishing the in-subagent form flow |
-
-@modes/reference-setup.md
+The sections above are the shared contract. Load detailed context on demand:
 
-@modes/reference-portals.md
+- `modes/{mode}.md` for the active mode procedure, output shape, and mode-specific routing.
+- `modes/reference-setup.md` for onboarding, tracker layout, states, and profile/CV setup.
+- `modes/reference-portals.md` for OTP, residential proxy, and MCP configuration.
+- `modes/reference-geometra.md` for form-fill patterns, portal failures, cleanup runbooks, and session recovery.
 
-@modes/reference-geometra.md
+Do not pre-load all reference files. Read only the active mode file and the reference file needed for the current blocker.