Marc-André Bombeck f39598f2e7 feat(coach): name a read past the lookback limit on the trail ...

A read whose readings all lie past the lookback limit was reported on its
step as outside_window, and its fetch entry carried no reason, so a client
could not tell an empty window from data the limit keeps out. The step now
carries reason outside_reach and the fetch entry mirrors it. The method
line and the web trail keep the window sentence; the answer names the
limit as before.

2026-11-05 14:12:09 +01:00

..

__tests__

fix(i18n): address the ru review — units, Cyrillic regexes, locale registry

2026-11-02 20:22:03 +00:00

capabilities

perf(ai): read the deletion lock with the usage level, not on its own

2026-10-25 18:54:33 +01:00

coach

feat(coach): name a read past the lookback limit on the trail

2026-11-05 14:12:09 +01:00

prompts

fix(i18n): address the ru review — units, Cyrillic regexes, locale registry

2026-11-02 20:22:03 +00:00

reasoning

fix(ai): keep the reasoning-field day for what a 400 taught

2026-10-29 21:58:40 +01:00

safety

fix(ai): block a negated take, a pause, an increment and a liquid dose

2026-11-04 00:14:56 +01:00

ai-budgets.ts

fix(insights): let slow-model status notes and AI jobs outlast their calls

2026-10-24 11:00:32 +02:00

anthropic-client.ts

Widen the Coach turn budget and keep its rounds on the prompt cache

2026-10-07 22:48:48 +02:00

anthropic-host.ts

refactor(ai): move the stored-key opener and the Anthropic host check out of provider.ts

2026-10-23 17:19:21 +02:00

background-bench.ts

fix(insights): let "Re-run analysis" reach a benched provider

2026-10-25 00:24:51 +02:00

briefing-grounding.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

citation-coverage.ts

feat(i18n): add Russian (ru) locale

2026-11-01 17:11:31 +00:00

codex-client.ts

fix(ai): read a Codex sign-in's memory only under its own account

2026-10-29 21:36:33 +01:00

codex-model-catalog.ts

fix(ai): read a Codex sign-in's memory only under its own account

2026-10-29 21:36:33 +01:00

codex-oauth.ts

fix(ai): serialize Codex refreshes so a lost race never parks a live sign-in

2026-10-21 00:06:21 +02:00

codex-reasoning-wire.ts

refactor(ai): move the Codex reasoning wire into its own module

2026-10-29 19:55:20 +01:00

codex-slug-cache.ts

fix(ai): read a Codex sign-in's memory only under its own account

2026-10-29 21:36:33 +01:00

codex-slug-chain.ts

fix(ai): read a Codex sign-in's memory only under its own account

2026-10-29 21:36:33 +01:00

consent-guard.ts

refactor(ai): define the operator-held providers once

2026-09-26 20:27:53 +02:00

effective-timeout.ts

fix(insights): let slow-model status notes and AI jobs outlast their calls

2026-10-24 11:00:32 +02:00

failure-kind.ts

fix(ai): keep background work off a benched provider and charge failed replies

2026-10-24 20:42:42 +02:00

feedback-attribution.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

insight-interpretation.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

json-dialect.ts

fix(ai): send max_completion_tokens to Azure OpenAI reasoning deployments

2026-10-30 17:08:43 +01:00

json-extract.ts

fix(ai): stop prefilling the assistant turn on Anthropic JSON calls

2026-09-02 10:28:05 +02:00

legacy-payload.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

legacy-private-host-report.ts

fix(security): keep ALLOW_LOCAL_AI_PRIVATE_HOSTS=true for the operator's own AI, deprecated

2026-09-26 20:59:10 +02:00

local-client.ts

fix(ai): send max_completion_tokens to Azure OpenAI reasoning deployments

2026-10-30 17:08:43 +01:00

local-host-allowlist.ts

fix(security): keep ALLOW_LOCAL_AI_PRIVATE_HOSTS=true for the operator's own AI, deprecated

2026-09-26 20:59:10 +02:00

local-reasoning.ts

fix(ai): keep a cut answer from a model never seen reasoning

2026-10-25 00:20:35 +02:00

local-wire.ts

fix(ai): bound one completion call to two requests

2026-10-25 00:11:42 +02:00

medical-references.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

mock-client.ts

feat(ai): reason deterministically in the mock and count reasoning in the chain runner

2026-10-06 19:26:30 +02:00

model-availability.ts

fix(ai): name the real cause of failed briefings and stop retrying what cannot heal

2026-10-08 09:06:09 +02:00

openai-capabilities.ts

fix(ai): learn the max_tokens refusal from the field the request carried

2026-10-30 17:13:09 +01:00

openai-client.ts

fix(ai): learn the max_tokens refusal from the field the request carried

2026-10-30 17:13:09 +01:00

openai-model-family.ts

fix(ai): recognise the gpt-6 model family in every model gate

2026-10-24 10:11:16 +02:00

openai-wire.ts

Widen the Coach turn budget and keep its rounds on the prompt cache

2026-10-07 22:48:48 +02:00

provider-chain.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

provider-egress.ts

refactor(ai): define the operator-held providers once

2026-09-26 20:27:53 +02:00

provider-health-ledger.ts

fix(admin): lift the bench when the operator fixes the shared provider

2026-10-25 00:42:20 +02:00

provider-runner.ts

fix(ai): give background work the High room on a model that always reasons

2026-10-29 09:07:37 +01:00

provider.ts

feat(ai): pick Codex models from the account's live list, per sign-in

2026-10-29 20:17:42 +01:00

reasoning-effort.ts

feat(ai): send a per-entry reasoning effort to Local and gateway providers

2026-10-04 10:42:59 +02:00

request-hops.ts

fix(ai): bound one completion call to two requests

2026-10-25 00:11:42 +02:00

retry-correction.ts

fix(ai): align the corrective retry prompt with the validator that grades the reply

2026-07-19 11:01:57 +02:00

schema.ts

chore: strip planning tags from comments and enable the rule

2026-10-20 09:08:40 +02:00

server-provider-health.ts

refactor(ai): define the operator-held providers once

2026-09-26 20:27:53 +02:00

stored-key.ts

refactor(ai): move the stored-key opener and the Anthropic host check out of provider.ts

2026-10-23 17:19:21 +02:00

types.ts

fix(ai): give background work the High room on a model that always reasons

2026-10-29 09:07:37 +01:00

usage-level.ts

fix(ai-usage): never regenerate more often on frugal than on standard

2026-10-16 05:38:36 +02:00

vision-capability.ts

fix(ai): recognise the gpt-6 model family in every model gate

2026-10-24 10:11:16 +02:00

wire-refusal.ts

fix(ai): send max_completion_tokens to Azure OpenAI reasoning deployments

2026-10-30 17:08:43 +01:00