docs(autoplan): the 16384 output default applies to both providers; changelog for the wave's integrator fixes

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

autoplan/DRIVER.md

@@ -60,7 +60,7 @@ line yourself; gstack never writes the plan.
 - `gstack-autoplan next --out <dir> --plan <plan.md> [scope flags] [--light] [--spend-cap <usd>] [--max-rounds <n>] [--estimate-usd <n>] [--scaffold]`
   first call: init the run, print PHASE:, SCOPE:, DRIVER: and one ATTEMPT: per voice; --max-rounds caps review rounds per phase (default 2 unattended); an unattended run with --spend-cap (or any unattended Capy run) reserves 5.00 per voice for each attempt, so the cap binds; --estimate-usd <n> sets that reservation and the run keeps it for later phases.
 - `gstack-autoplan run --out <dir> --plan <plan.md> --native-model <id> --outside-model <id> --native-runner api --runner api [--max-tokens <n>] [--spend-cap <usd>]`
-  hosts without subagents: one command calls both models directly (ANTHROPIC_API_KEY, OPENAI_API_KEY) and loops next/submit to the gate; a response cut off at the output limit is reported truncated, so raise --max-tokens (Anthropic default 16384).
+  hosts without subagents: one command calls both models directly (ANTHROPIC_API_KEY, OPENAI_API_KEY) and loops next/submit to the gate; a response cut off at the output limit is reported truncated, so raise --max-tokens (default 16384 for both providers; OpenAI counts reasoning tokens toward it).
 - `gstack-autoplan next --out <dir> [--redispatch <attempt>]`
   later calls: open the next phase or reprint open attempts; never redispatches on its own.
 - `gstack-autoplan submit --out <dir> --phase <p> --voice native|outside --record <file.md> --model <id> [--attempt <id>]`

changelog.d/gsta232-autoplan-wave.md

@@ -5,8 +5,13 @@
 - **DX cap findings carry real titles.** `CAP4` and `CAP6` findings are titled `CAP<n>:<path>:<item> <what fails>`, so the gate shows the problem and not only the item name.
 - **Every open Critical or High finding becomes a gate item.** `a` applies the reviewer's fix to the plan and is recommended. `b` carries it into the build as a blocking task. `rec` and `p1b` apply the fix. An unanswered item keeps the plan as written unless the reply is `p1b`, and a partial reply never locks that choice early. A finding carried with `b` stays open, so a rerun that raises it again asks again.
 - **A spend cap binds on any unattended host.** With `--spend-cap` set and no `--estimate-usd`, each host-subagent attempt reserves the default $5 per voice, on Capy or off it. `next --estimate-usd <n>` sets the reservation for the rest of the run. `run` reserves each API call's priced worst case (prompt size plus the output limit) and settles it at its real token cost, so `--spend-cap 0` refuses before any call.
-- **`gstack-autoplan run` with `--native-runner api --runner api` reaches the gate.** Results are checked as autoplan results, so they bind. A response cut off at the output limit is named `truncated` and interrupts the run instead of binding a partial review. The Anthropic default output limit is 16384 tokens, `--max-tokens <n>` sets it, and an outside result refused at submit leaves the run native-only instead of aborting it.
+- **`gstack-autoplan run` with `--native-runner api --runner api` reaches the gate.** Results are checked as autoplan results, so they bind. A response cut off at the output limit is named `truncated` and interrupts the run instead of binding a partial review. The default output limit is 16384 tokens for both providers (OpenAI counts reasoning tokens toward it), `--max-tokens <n>` sets it, and an outside result refused at submit leaves the run native-only instead of aborting it.
 - **An earlier item-by-item answer carries forward when nothing changed.** When every item on the new gate is carried by origin, the owner's `p1` choice is replayed and their tokens are recorded verbatim as the basis. Any new or changed item still goes to the owner.
+- **A spend cap stays closed when a call fails.** A call cut off at its output limit is settled at what it cost, and a retry with a larger `--max-tokens` is admitted against the cap afresh. A call that timed out or dropped after it was sent is charged its full reservation, because the provider may have billed it. A call refused before anything was sent (no API key, for example) charges nothing, and the rerun reuses its reservation.
+- **A finding you chose to fix stays open until the revised plan is reviewed.** If the reviewer raises it again after a revise that missed it, it comes back to the gate instead of being treated as settled. A withdrawn fix leaves its finding open.
+- **Two findings that only sit near each other are no longer merged.** A user challenge one line away from an unrelated Critical no longer hides the Critical. Findings are merged only when their titles match or the parent says they are the same problem.
+- **A plan gate answered in an agent's own words is not owner approval.** `gstack-ship-receipt` rejects a plan-sha approval citation whose gate was answered with `--words-by agent:<id>`.
+- **A later gate answer replaces the earlier answer's authorship.** When someone else answers again, the earlier answerer's words, `words_by` and carry fields are cleared, so the approval record names who actually answered.
 
 ### Added
 - **`gstack-autoplan answer --words-by agent:<id>`** records that the words came from the answering agent itself, as `answer_words` and `words_by`, never as `owner_reply`. The default stays `owner`. A later gate never carries those words forward, and `gstack-approvals import` lists that row under the agent, while `--by` names only the rows that hold the owner's words.

docs/troubleshooting.md

@@ -322,7 +322,9 @@ network.
 review ends mid-sentence and its findings may be missing.
 
 **Fix.** Re-run with a larger `--max-tokens` (`gstack-outside-voice run` or
-`gstack-autoplan run`; Anthropic defaults to 16384), or shorten the prompt.
+`gstack-autoplan run`), or shorten the prompt. `gstack-autoplan run` sends a
+default of 16384 to both providers, and OpenAI counts reasoning tokens toward
+it; `gstack-outside-voice run` sends that default to Anthropic only.
 
 **Expected result.** `OUTSIDE_STATUS: completed`.
 

lib/outside-voice-api.ts

@@ -16,7 +16,7 @@ export interface ApiUsage { input_tokens?: number; output_tokens?: number }
 /** `truncated`: the provider stopped at the output token limit (Anthropic `max_tokens`, OpenAI `length`), so the text is cut off. */
 export interface ApiCallResult { text: string; model: string; usage: ApiUsage; provider: 'openai' | 'anthropic'; status: number; truncated: boolean }
 
-/** Anthropic requires max_tokens; a full review needs more than 8192. OpenAI gets a limit only when one is asked for. */
+/** Anthropic requires max_tokens; a full review needs more than 8192. `run` sends this to OpenAI too, where reasoning tokens count toward it. */
 export const DEFAULT_MAX_TOKENS = 16_384;
 /** The api runner's default time limit: five minutes, or about 40 ms per output token the call may write. */
 export const apiTimeoutMs = (maxTokens?: number): number => Math.max(300_000, (maxTokens ?? DEFAULT_MAX_TOKENS) * 40);

scripts/resolvers/autoplan-driver.ts

@@ -18,7 +18,7 @@ import type { ResolverFn } from './types';
 /** One entry per command line the loop runs, as the field-wave plan specifies them. */
 export const AUTOPLAN_DRIVER_COMMANDS: Array<{ cmd: string; does: string }> = [
   { cmd: 'gstack-autoplan next --out <dir> --plan <plan.md> [scope flags] [--light] [--spend-cap <usd>] [--max-rounds <n>] [--estimate-usd <n>] [--scaffold]', does: `first call: init the run, print PHASE:, SCOPE:, DRIVER: and one ATTEMPT: per voice; --max-rounds caps review rounds per phase (default ${DEFAULT_MAX_ROUNDS} unattended); an unattended run with --spend-cap (or any unattended Capy run) reserves ${DEFAULT_HOST_ESTIMATE_USD.toFixed(2)} per voice for each attempt, so the cap binds; --estimate-usd <n> sets that reservation and the run keeps it for later phases` },
-  { cmd: 'gstack-autoplan run --out <dir> --plan <plan.md> --native-model <id> --outside-model <id> --native-runner api --runner api [--max-tokens <n>] [--spend-cap <usd>]', does: 'hosts without subagents: one command calls both models directly (ANTHROPIC_API_KEY, OPENAI_API_KEY) and loops next/submit to the gate; a response cut off at the output limit is reported truncated, so raise --max-tokens (Anthropic default 16384)' },
+  { cmd: 'gstack-autoplan run --out <dir> --plan <plan.md> --native-model <id> --outside-model <id> --native-runner api --runner api [--max-tokens <n>] [--spend-cap <usd>]', does: 'hosts without subagents: one command calls both models directly (ANTHROPIC_API_KEY, OPENAI_API_KEY) and loops next/submit to the gate; a response cut off at the output limit is reported truncated, so raise --max-tokens (default 16384 for both providers; OpenAI counts reasoning tokens toward it)' },
   { cmd: 'gstack-autoplan next --out <dir> [--redispatch <attempt>]', does: 'later calls: open the next phase or reprint open attempts; never redispatches on its own' },
   { cmd: 'gstack-autoplan submit --out <dir> --phase <p> --voice native|outside --record <file.md> --model <id> [--attempt <id>]', does: 'bind a free-form review record (canonical fence, one findings table or list, or `No findings.`)' },
   { cmd: 'gstack-autoplan submit ... --record <file.md> --attest "<reason>" --attempt <id>', does: 'bind a record with no INPUT: line as receipt: attested (a wrong INPUT: always refuses)' },