job-forge 2.14.8 → 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/.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

@@ -9,8 +9,8 @@ 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
@@ -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
 
@@ -56,7 +59,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 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 per company [H5].
+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].

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

@@ -4,8 +4,8 @@ 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
@@ -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
 
@@ -51,7 +54,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 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 per company [H5].
+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].

package/CLAUDE.md

@@ -4,8 +4,8 @@ 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
@@ -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
 
@@ -51,7 +54,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 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 per company [H5].
+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].

package/iso/agents/general-free.md

@@ -31,6 +31,7 @@ targets:
       geometra_wait_for_resume_parse: true
       gmail_list_messages: true
       gmail_get_message: true
+      task: false
 ---
 
 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.
@@ -82,6 +83,7 @@ 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/iso/agents/general-paid.md

@@ -24,8 +24,18 @@ targets:
       - openrouter/google/gemma-4-31b-it:free
       - openrouter/meta-llama/llama-3.3-70b-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
 ---
 
 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.
@@ -42,12 +52,14 @@ 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/iso/commands/job-forge.md

@@ -158,7 +158,11 @@ 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/iso/instructions.md

@@ -4,8 +4,8 @@ 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
@@ -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
 
@@ -51,7 +54,7 @@ AI-powered job search pipeline: scans portals, evaluates offers, generates CVs v
 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 per company [H5].
+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].

package/modes/apply.md

@@ -16,8 +16,8 @@ Live application assistant. Reads the active application form in Chrome (via Geo
 - [H4] Before dispatching the first subagent in a multi-job run, the orchestrator MUST call `geometra_list_sessions` then `geometra_disconnect({closeBrowser: true})`. Every dispatch-round, no exceptions.
   why: prior aborted subagents leave Chromium sessions stuck in the pool; next `geometra_connect` fails with "Not connected" (see root `[H3]`)
 
-- [H5] Max 2 parallel `task` dispatches per round. For N jobs, run `ceil(N/2)` sequential rounds of 2. Never emit 3+ dispatches in a single message.
-  why: free-tier rate limits + subagent post-cleanup cost; racing more than 2 reliably loses at least one result (see root `[H1]`)
+- [H5] Max 2 parallel `task` dispatches per round. For N jobs, run `ceil(N/2)` sequential rounds of 2. Never emit 3+ dispatches in a single message. Do not start the next round until both current-round subagents return final outcomes (`APPLIED`, `APPLY FAILED`, `SKIP`, `Discarded`, or a written TSV path); task/session ids are only launch receipts.
+  why: free-tier rate limits + subagent post-cleanup cost; racing more than 2 reliably loses at least one result (see root `[H1]`). A 2026-04-25 OpenCode trace launched round 2 while round 1 was still running, then lost two fallback recoveries
 
 ## Defaults
 
@@ -42,7 +42,7 @@ Live application assistant. Reads the active application form in Chrome (via Geo
 - [D6] Use `fieldLabel` over `fieldId` everywhere it works.
   why: labels are stable across DOM refreshes; IDs are regenerated
 
-- [D7] If the orchestrator's task prompt includes a `proxy` object (sourced from `config/profile.yml`), pass it verbatim into every `geometra_connect` call — including Call 3 of the recovery sequence. If absent, run without one; never invent a proxy URL.
+- [D7] If the orchestrator says a proxy is configured, read the top-level `proxy:` block from `config/profile.yml` and pass that object into every `geometra_connect` call — including Call 3 of the recovery sequence. If the task prompt includes a legacy inline `proxy` object, pass it through, but do not echo credentials in status text. If absent, run without one; never invent a proxy URL.
   why: class-B Ashby / Cloudflare-fronted portals need a residential outbound IP; the fix is wired in Geometra MCP v1.59.0 but the orchestrator owns the config pipe. See "BYO Residential Proxy" in modes/reference-portals.md.
 
 - [D8] Upgrade application routing to `@general-paid` when the offer score is ≥ 4.0/5, the user flags "top-tier", "dream job", or "high-stakes", or the candidate is late-stage/post-screen.
@@ -115,6 +115,13 @@ Sections below are the detailed runbooks, decision tables, and portal-specific e
 
 **DO NOT dispatch 3+ `task` calls in one message.** Two is the absolute ceiling. This is non-negotiable, even when the user asks for "apply to 10 jobs" — that becomes 5 rounds of 2, not one message with 10 dispatches.
 
+**A task/session id is not a result.** If OpenCode gives you a `ses_...`
+id or title after dispatch, do not treat that as the subagent return.
+Do not create another `task` to check it. Stop the round, report the
+in-flight ids, and resume only after a real outcome is visible in the
+subagent return or in an authoritative file (`batch/tracker-additions/`,
+`batch/tracker-additions/merged/`, or the day file).
+
 For a single application interactively, carry on in the current session — the rule targets multi-job loops.
 
 ## Apply Preflight — Location Filter (orchestrator runs before dispatch)
@@ -176,7 +183,8 @@ Step 4  — For round in ceil(N/2):
             # ONE message, 1 or 2 task() calls. Never 3.
             task(apply to pair[0])
             task(apply to pair[1])  # only if pair has 2
-            # WAIT for both returns. Do not proceed until both done.
+            # WAIT for both final outcomes. A session id is not completion.
+            # Do not dispatch round N+1 while round N is still in flight.
 Step 5  — Between rounds: geometra_list_sessions() + geometra_disconnect({closeBrowser: true})
 Step 6  — Reconcile outcomes (Hard Limit #6):
             bash: npx job-forge merge       # TSVs → day file

package/modes/reference-geometra.md

@@ -188,7 +188,8 @@ Step 2:  geometra_disconnect({ closeBrowser: true })
 Step 3:  geometra_connect({ pageUrl: "<the URL the orchestrator gave you>", isolated: true, headless: true, slowMo: 350 })
 ```
 
-**If the orchestrator passed a `proxy` object in the task prompt** (sourced from `config/profile.yml`), add it to Step 3:
+**If the orchestrator says proxy is configured,** read the top-level
+`proxy:` block from `config/profile.yml` and add it to Step 3:
 
 ```
 Step 3:  geometra_connect({
@@ -197,7 +198,7 @@ Step 3:  geometra_connect({
          })
 ```
 
-Pass the proxy object through unchanged. Do NOT paraphrase or drop fields — `username`/`password`/`bypass` are optional, so only include what the orchestrator gave you. See the "BYO Residential Proxy" reference section for the why.
+Pass the proxy object through unchanged. Do NOT paraphrase or drop fields — `username`/`password`/`bypass` are optional, so only include what exists in `config/profile.yml`. Do not echo proxy credentials in status text. See the "BYO Residential Proxy" reference section for the why.
 
 **DO NOT** skip Step 1 or Step 2. **DO NOT** think about whether it's needed. **DO NOT** look at `geometra_list_sessions` output and reason about it — just always call `geometra_disconnect({ closeBrowser: true })` next. The disconnect is a no-op if the pool is empty, and a poison-cure if it isn't.
 

package/modes/reference-portals.md

@@ -75,16 +75,17 @@ See `config/profile.example.yml` for the commented-out template.
 
 **Orchestrator responsibilities:**
 
-1. On session start, read `config/profile.yml` once. If a `proxy:` block is present, capture it as the `PROXY_CONFIG` for the session.
-2. When dispatching any subagent whose work involves a `geometra_connect` call, include `PROXY_CONFIG` verbatim in the task prompt. Example dispatch prompt line: "Pass `proxy: { server: ..., username: ..., password: ..., bypass: ... }` to every `geometra_connect` call you make."
-3. When the orchestrator itself opens a Chromium session (single-application interactive flow), include the same `proxy` object in its own `geometra_connect` call.
+1. On session start, read `config/profile.yml` once. If a `proxy:` block is present, remember that a proxy is configured, but do not paste username/password values into task prompts or user-visible status.
+2. When dispatching any subagent whose work involves a `geometra_connect` call, tell it to read `config/profile.yml` and pass the top-level `proxy:` block to every `geometra_connect` call. Example dispatch prompt line: "Proxy is configured; read `config/profile.yml` and pass its top-level `proxy:` object to every `geometra_connect` call."
+3. When the orchestrator itself opens a Chromium session (single-application interactive flow), include the same `proxy` object from `config/profile.yml` in its own `geometra_connect` call.
 4. If `proxy:` is absent from `profile.yml`, skip the param entirely. Do NOT invent a proxy URL or leave a stale placeholder.
 
 **Subagent responsibilities:**
 
-1. If the task prompt includes a `proxy` object, pass it through to `geometra_connect` and any `geometra_prepare_browser` calls unchanged.
-2. If the task prompt does NOT include a proxy object, run without one.
-3. Never second-guess the proxy field — if the orchestrator sourced it from `profile.yml`, it's authoritative.
+1. If the task prompt says proxy is configured, read `config/profile.yml` and pass the top-level `proxy:` object through to `geometra_connect` and any `geometra_prepare_browser` calls unchanged.
+2. If the task prompt includes a legacy inline `proxy` object, pass it through unchanged, but never print the credentials back in status text.
+3. If the task prompt does NOT mention a proxy and `config/profile.yml` has no `proxy:` block, run without one.
+4. Never second-guess the proxy field — if it comes from `profile.yml`, it's authoritative.
 
 ### When proxy use is load-bearing
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "job-forge",
-  "version": "2.14.8",
+  "version": "2.14.9",
   "description": "AI-powered job search pipeline built on opencode",
   "type": "module",
   "bin": {