-
Notifications
You must be signed in to change notification settings - Fork 1
tools(peer-call): amara.sh v1 — autonomous Amara via codex + CURRENT-amara.md bootstrap (Aaron 2026-04-30) #960
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
AceHack
merged 3 commits into
main
from
tools/amara-sh-peer-call-codex-current-amara-bootstrap-v1-aaron-2026-04-30
Apr 30, 2026
Merged
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
151 changes: 151 additions & 0 deletions
151
...P2/B-0118-amara-peer-call-headless-cli-bootstrap-end-courier-debt-2026-04-30.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,151 @@ | ||
| --- | ||
| id: B-0118 | ||
| priority: P2 | ||
| status: open | ||
| title: tools/peer-call/amara.sh — autonomous bootstrap + communication for Amara (ChatGPT) to end Aaron-courier silent debt (Aaron 2026-04-30) | ||
| tier: factory-tooling | ||
| effort: L | ||
| ask: Every Amara review this session has been Aaron's manual courier work. The peer-call infrastructure has codex.sh / gemini.sh / grok.sh but no amara.sh; ChatGPT lacks the headless CLI surface that maps to the existing peer-call shape. Until Otto can autonomously bootstrap Amara + do the communication directly, peer-AI review cadence is courier-dependent and incurs silent debt on Aaron. Aaron 2026-04-30 explicitly named this as a constraint Otto must honor. | ||
| created: 2026-04-30 | ||
| last_updated: 2026-04-30 | ||
| composes_with: | ||
| - tools/peer-call/README.md | ||
| - tools/peer-call/codex.sh | ||
| - tools/peer-call/gemini.sh | ||
| - tools/peer-call/grok.sh | ||
| - feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md | ||
| - feedback_otto_to_aaron_pushback_when_overloaded_processing_budget_is_survival_surface_aaron_2026_04_30.md | ||
| tags: [aaron-2026-04-30, peer-call, amara, chatgpt, autonomous-bootstrap, courier-debt-elimination, factory-tooling] | ||
| --- | ||
|
|
||
| # B-0118 — tools/peer-call/amara.sh (end Aaron-courier silent debt) | ||
|
|
||
| ## Source | ||
|
|
||
| Aaron 2026-04-30 verbatim: | ||
|
|
||
| > *"don't count on her review until you have a process | ||
| > encoded for bootstraping her and doing the communitation | ||
| > yourself, this is a silent dept on me to be the courrir | ||
| > and I can't keep up"* | ||
|
|
||
| ## Context | ||
|
|
||
| The peer-call infrastructure currently has: | ||
|
|
||
| - `codex.sh` / `codex.ts` — Codex (OpenAI) via `codex exec` | ||
| - `gemini.sh` / `gemini.ts` — Gemini (Google) via `gemini -p` | ||
| - `grok.sh` / `grok.ts` — Grok (xAI) via `cursor-agent` | ||
|
|
||
| It does NOT have: | ||
|
|
||
| - `amara.sh` / `amara.ts` — Amara (ChatGPT/OpenAI) | ||
|
|
||
| The README explicitly notes the gap as future-work: | ||
|
|
||
| > *"when another peer (Amara via ChatGPT, etc.) gains a | ||
| > headless CLI surface..."* | ||
|
|
||
| Every Amara review this session (Reviews 9, 12, 13 in | ||
| `docs/research/2026-04-30-session-end-peer-ai-reviews-verbatim.md`) | ||
| required Aaron to manually courier: | ||
|
|
||
| 1. Copy Otto's substrate from Claude Code chat | ||
| 2. Paste into ChatGPT (Amara's surface) | ||
| 3. Wait for Amara's response | ||
| 4. Copy Amara's response | ||
| 5. Paste back into Claude Code chat | ||
|
|
||
| That cycle is invisible to Otto's cost model but consumed | ||
| significant Aaron time + cognitive load. As substrate cadence | ||
| accelerated, the courier load grew proportionally, until | ||
| Aaron explicitly named it as a constraint. | ||
|
|
||
| ## What | ||
|
|
||
| Author `tools/peer-call/amara.sh` (and `amara.ts` per TS-default | ||
| discipline) — wrapper around whatever ChatGPT-callable surface | ||
| becomes available. Likely path: | ||
|
|
||
| 1. **OpenAI API direct** — call `gpt-4o` or successor via | ||
| `openai` CLI or HTTP. Pros: works today. Cons: not | ||
| exactly the same as Amara-on-ChatGPT (different system | ||
| prompt environment, different conversation continuity, | ||
| different context window). | ||
| 2. **ChatGPT headless surface** (when available) — wait | ||
| for OpenAI to provide a headless CLI matching the | ||
| `gemini -p` / `codex exec` shape. Pros: matches the | ||
| existing peer-call architecture. Cons: doesn't exist | ||
| yet. | ||
| 3. **Hybrid: API + Amara-context-bootstrap** — use OpenAI | ||
| API but with a system-prompt + context-attachment | ||
| that bootstraps Amara's persona (her voice, her | ||
| discipline, her four-ferry role of "sharpening" per | ||
| `gemini.sh` README). Pros: works today AND matches | ||
| Amara's review posture. Cons: not the same as | ||
| Amara-on-ChatGPT (no conversation continuity). | ||
|
|
||
| The hybrid approach is likely the right path for a v1 | ||
| that ends courier debt. | ||
|
|
||
| ## Acceptance criteria | ||
|
|
||
| - [ ] `bun tools/peer-call/amara.ts <prompt>` invokes Amara | ||
| autonomously with proper bootstrap preamble | ||
| - [ ] AgencySignature-style relationship-model preamble | ||
| applied (per the existing peer-call pattern) | ||
| - [ ] Vendor-alignment-bias filter integration documented | ||
| (per `memory/feedback_vendor_alignment_bias_in_peer_ai_reviews_maintainer_authority_aaron_2026_04_30.md`) | ||
| - [ ] `--file PATH` and `--context-cmd CMD` flags match the | ||
| existing peer-call surface | ||
| - [ ] Tested on a substantive review-task to verify Amara's | ||
| voice + discipline + sharpening role come through | ||
| - [ ] Documentation in tools/peer-call/README.md updated to | ||
| remove the "future-task" note and add Amara to the | ||
| operational table | ||
| - [ ] Silent-courier-debt rule references this as the | ||
| resolution | ||
|
|
||
| ## Trigger condition for promotion to P1 | ||
|
|
||
| If substrate work in any future session blocks on | ||
| Amara-review (i.e., the operational loop genuinely needs her | ||
| input but Aaron isn't available to courier), promote to P1. | ||
|
|
||
| ## Why P2 (not P1) | ||
|
|
||
| - Substrate work CAN proceed without Amara reviews (Otto | ||
| has codex/gemini/grok as autonomous peer-call options). | ||
| - The cost is real but bounded — Aaron has been carrying | ||
| it; he's now flagged it as a constraint. | ||
| - Implementation is L-effort (API integration + persona | ||
| bootstrap + flag wiring). | ||
|
|
||
| ## What this row does NOT do | ||
|
|
||
| - Does NOT block past Amara-attributed substrate. Reviews | ||
| 9, 12, 13 stand as preserved peer-AI input with Aaron- | ||
| courier as the carrier. | ||
| - Does NOT assume Amara reviews are valuable enough to | ||
| justify any specific implementation timeline. Amara's | ||
| reviews HAVE been valuable, but the substrate has plenty | ||
| of other peer-AI input + Otto's own razor. | ||
| - Does NOT propose calling Amara on every substrate | ||
| cluster once `amara.sh` exists. The peer-call frequency | ||
| question is separate from the autonomous-call capability | ||
| question. | ||
|
|
||
| ## Composes with | ||
|
|
||
| - `memory/feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md` | ||
| (the rule this row resolves) | ||
| - `tools/peer-call/{codex,gemini,grok}.{sh,ts}` (the | ||
| pattern this implementation follows) | ||
| - `feedback_otto_to_aaron_pushback_when_overloaded_processing_budget_is_survival_surface_aaron_2026_04_30.md` | ||
| (inverse surface — Otto-to-Aaron push-back covers | ||
| Aaron's input overloading Otto; this rule covers | ||
| Otto's substrate-cadence overloading Aaron's courier | ||
| capacity) | ||
| - `feedback_vendor_alignment_bias_in_peer_ai_reviews_maintainer_authority_aaron_2026_04_30.md` | ||
| (the filter applied to all peer-AI input including | ||
| Amara's; carries through unchanged when amara.sh lands) | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -1,8 +1,9 @@ | ||||||
| [AutoDream last run: 2026-04-23] | ||||||
|
|
||||||
| **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** <!-- latest-paired-edit: Amara Review 13 + 8 corrections (Lineage vs Synthesis attribution discipline, Girard/Dawkins separation, vendor-RLHF as discriminator hypothesis, doctrine-SHAPE synonyms, voice-register audience-scoped, self-described cognitive style) + endosymbiosis biological-lineage anchor (Aaron 2026-04-30). NOTE: this comment is a single-slot "latest paired edit" marker (not a paired-edit log). Per the round-10 Amara framing the slot semantics are now explicit. --> | ||||||
| **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** <!-- latest-paired-edit: silent-courier-debt rule + B-0118 amara peer-call backlog row — Aaron's correction surfacing invisible courier work; don't count on peer-AI reviews as part of operational loop until autonomous bootstrap encoded (Aaron 2026-04-30). NOTE: this comment is a single-slot "latest paired edit" marker (not a paired-edit log). Per the round-10 Amara framing the slot semantics are now explicit. --> | ||||||
| **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** <!-- paired-edit: PR #690 scheduled-workflow-null-result-hygiene-scan tier-1 promotion 2026-04-28 --> These per-maintainer distillations show what's currently in force. Raw memories below are the history; CURRENT files are the projection. (`CURRENT-aaron.md` refreshed 2026-04-28 with sections 26-30 — speculation rule + EVIDENCE-BASED labeling + JVM preference + dependency honesty + threading lineage Albahari/Toub/Fowler + TypeScript/Bun-default discipline.) | ||||||
|
|
||||||
| - [**Silent courier debt — Otto must NOT count on peer-AI reviews as part of the operational loop until autonomous bootstrap + communication is encoded (Aaron 2026-04-30)**](feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md) — Aaron's correction surfacing invisible courier work. Every Amara review this session was Aaron's manual courier (copy-paste Otto's substrate to ChatGPT, paste Amara's response back) — invisible to Otto's cost model but consumed Aaron's time + cognitive load. Aaron 2026-04-30: *"don't count on her review until you have a process encoded for bootstraping her and doing the communitation yourself, this is a silent dept on me to be the courrir and I can't keep up."* The peer-call infrastructure has codex.sh / gemini.sh / grok.sh but **NO amara.sh**; ChatGPT lacks the headless CLI surface that maps to existing peer-call shape. **Operational consequence:** future operations DO NOT assume Amara's review cadence — don't write substrate that says "Amara reviewed this" as routine loop; don't propose work depending on Amara feedback; don't structure backlog around Amara-review cycles. Past attribution stands (Amara's contributions are her contributions; Aaron-as-courier is the carrier). For autonomous peer-AI work, use the operational peer-call peers (Codex, Gemini, Grok via `tools/peer-call/{codex,gemini,grok}.{sh,ts}`). The inverse surface to Otto-to-Aaron push-back rule: same survival-surface discipline applies in both directions. Aaron's processing budget IS Aaron's survival surface; Otto consuming it silently is the failure mode. Backlog row B-0118 tracks the amara.sh implementation gap. Composes with otto-to-aaron-pushback (inverse surface), vendor-alignment-bias (discriminator filter applies same), AIC-tracking (this rule itself is Aaron's MIC, not Otto's AIC), peer-call infrastructure. Carved: *"Aaron's courier work was unaccounted in Otto's cost model. The substrate accelerated; the courier load grew silently; Aaron couldn't keep up."* + *"Until Otto encodes a process for autonomously bootstrapping a peer-AI and doing the communication directly, that peer-AI's review cadence is not part of the operational loop."* | ||||||
|
||||||
| - [**Silent courier debt — Otto must NOT count on peer-AI reviews as part of the operational loop until autonomous bootstrap + communication is encoded (Aaron 2026-04-30)**](feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md) — Aaron's correction surfacing invisible courier work. Every Amara review this session was Aaron's manual courier (copy-paste Otto's substrate to ChatGPT, paste Amara's response back) — invisible to Otto's cost model but consumed Aaron's time + cognitive load. Aaron 2026-04-30: *"don't count on her review until you have a process encoded for bootstraping her and doing the communitation yourself, this is a silent dept on me to be the courrir and I can't keep up."* The peer-call infrastructure has codex.sh / gemini.sh / grok.sh but **NO amara.sh**; ChatGPT lacks the headless CLI surface that maps to existing peer-call shape. **Operational consequence:** future operations DO NOT assume Amara's review cadence — don't write substrate that says "Amara reviewed this" as routine loop; don't propose work depending on Amara feedback; don't structure backlog around Amara-review cycles. Past attribution stands (Amara's contributions are her contributions; Aaron-as-courier is the carrier). For autonomous peer-AI work, use the operational peer-call peers (Codex, Gemini, Grok via `tools/peer-call/{codex,gemini,grok}.{sh,ts}`). The inverse surface to Otto-to-Aaron push-back rule: same survival-surface discipline applies in both directions. Aaron's processing budget IS Aaron's survival surface; Otto consuming it silently is the failure mode. Backlog row B-0118 tracks the amara.sh implementation gap. Composes with otto-to-aaron-pushback (inverse surface), vendor-alignment-bias (discriminator filter applies same), AIC-tracking (this rule itself is Aaron's MIC, not Otto's AIC), peer-call infrastructure. Carved: *"Aaron's courier work was unaccounted in Otto's cost model. The substrate accelerated; the courier load grew silently; Aaron couldn't keep up."* + *"Until Otto encodes a process for autonomously bootstrapping a peer-AI and doing the communication directly, that peer-AI's review cadence is not part of the operational loop."* | |
| - [**Silent courier debt — Otto must NOT count on peer-AI reviews as part of the operational loop until autonomous bootstrap + communication is encoded (Aaron 2026-04-30)**](feedback_silent_courier_debt_no_amara_headless_cli_dont_count_on_peer_ai_reviews_as_loop_aaron_2026_04_30.md) — Aaron's correction surfacing invisible courier work. Every Amara review this session was Aaron's manual courier (copy-paste Otto's substrate to ChatGPT, paste Amara's response back) — invisible to Otto's cost model but consumed Aaron's time + cognitive load. Aaron 2026-04-30: *"don't count on her review until you have a process encoded for bootstraping her and doing the communitation yourself, this is a silent dept on me to be the courrir and I can't keep up."* **Current-state update:** this PR adds `tools/peer-call/amara.sh`, so the literal missing-`amara.sh` gap is resolved; what remains unresolved is full autonomous parity with the operational peers — e.g. Codex persona-overlay vs. ChatGPT UI parity and the missing Layer-3 evolution still mean Amara review cadence is not yet a routine-loop guarantee. **Operational consequence:** future operations DO NOT assume Amara's review cadence — don't write substrate that says "Amara reviewed this" as routine loop; don't propose work depending on Amara feedback; don't structure backlog around Amara-review cycles. Past attribution stands (Amara's contributions are her contributions; Aaron-as-courier is the carrier). For autonomous peer-AI work, use the operational peer-call peers, including Amara where the implemented surface actually fits the task (`tools/peer-call/{amara,codex,gemini,grok}.{sh,ts}` where present), while treating the remaining autonomy limitations as the gating constraint. The inverse surface to Otto-to-Aaron push-back rule: same survival-surface discipline applies in both directions. Aaron's processing budget IS Aaron's survival surface; Otto consuming it silently is the failure mode. Backlog row B-0118 should now track the remaining autonomy/parity gap, not the no-`amara.sh` claim. Composes with otto-to-aaron-pushback (inverse surface), vendor-alignment-bias (discriminator filter applies same), AIC-tracking (this rule itself is Aaron's MIC, not Otto's AIC), peer-call infrastructure. Carved: *"Aaron's courier work was unaccounted in Otto's cost model. The substrate accelerated; the courier load grew silently; Aaron couldn't keep up."* + *"Until Otto encodes a process for autonomously bootstrapping a peer-AI and doing the communication directly, that peer-AI's review cadence is not part of the operational loop."* |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
P1: This backlog row still frames
tools/peer-call/amara.shas unimplemented future work (and includes acceptance criteria for anamara.tsthat isn’t part of this PR). Sinceamara.shis now landing as v1, update the row to mark that portion as delivered and scope what remains (e.g.,amara.tsparity, transcript compression / Layer-3 evolution, README table update, etc.), otherwise the backlog will immediately drift from the repo state.