27. april 2026.

Specifikacija otvorenog koda za Codex orkestraciju: Symphony

Autori: Alex Kotliarskyi, Victor Zhu i Zach Brock

Učitavanje…

Prije šest mjeseci, dok smo radili na internom alatu za produktivnost, naš tim je donio (u to vrijeme) kontroverznu odluku: izgradit ćemo naš repozitorij bez ijedne linije koda koju je napisao čovjek. Svaka linija u repozitoriju našeg projekta morala je biti generisana pomoću Codexa.

Da bismo to omogućili, redizajnirali smo naš inženjerski radni tok iz temelja. Izgradili smo repozitorij prilagođen agentima, mnogo ulagali u automatizirane testove i zaštitne mehanizme te tretirali Codex kao punopravnog saigrača. To putovanje dokumentovali smo u našoj prethodnoj objavi na blogu o harness engineeringu (razvoju infrastrukturnog okvira za agente)⁠.

I uspjelo je, ali tada smo naišli na sljedeće usko grlo: stalno mijenjanje konteksta.

Da bismo riješili ovaj novi problem, izgradili smo sistem pod nazivom Symphony. Symphony⁠(otvara se u novom prozoru) je orkestrator agenata koji tablu za upravljanje projektima poput Lineara pretvara u kontrolnu ravan za agente za kodiranje. Svaki otvoreni zadatak dobija agenta, agenti rade neprekidno, a ljudi pregledaju rezultate.

Ova objava objašnjava kako smo kreirali Symphony—što je u nekim timovima rezultiralo povećanim brojem spojenih pull requestova od 500%—i kako ga iskoristiti da vlastiti alat za praćenje problema pretvorite u uvijek aktivan orkestrator agenata.

Granice interaktivnih agenata za kodiranje

Mada postaju lakši za korištenje, agenti za kodiranje—bilo da im se pristupa kroz web aplikacije ili CLI—su i dalje interaktivni alati.

Kako se obim agentskog rada povećavao u OpenAI-ju, otkrili smo novu vrstu opterećenja. Svaki inženjer bi otvorio nekoliko Codex sesija, dodijelio zadatke, pregledao rezultate, usmjeravao agenta i to ponavljao. U praksi, većina osoba je mogla udobno upravljati s tri do pet sesija istovremeno prije nego što bi im promjena konteksta postala problem. Nakon toga je produktivnost opadala. Zaboravljali bismo koja sesija šta radi, skakali između terminala da agente vratimo na pravi put i otklanjali probleme u dugotrajnim zadacima koji bi zastali na pola.

Agenti su bili brzi, ali imali smo usko grlo u sistemu: ljudsku pažnju. U suštini smo izgradili tim izuzetno sposobnih mlađih inženjera, a zatim smo naše ljude, inženjere, zudužili da ih mikromenadžuju. Takav sistem nije mogao da raste.

Promjena perspektive

Shvatili smo da optimizujemo pogrešnu stvar. Naš sistem smo orijentisali oko sesija kodiranja i spojenih PR-ova, iako su PR-ovi i sesije zapravo samo sredstvo do cilja. Radni tokovi u razvoju softvera u velikoj mjeri su organizovani oko isporuka: problema, zadataka, tiketa, prekretnica.

Zato smo se zapitali šta bi se dogodilo kada bismo prestali direktno nadzirati agente i umjesto toga im dopustili da sami preuzimaju posao iz našeg alata za praćenje zadataka.

Ta ideja postala je Symphony, pisana specifikacija koja funkcioniše kao supervizor za orkestraciju agentskog rada.

Pretvaranje našeg alata za praćenje prpoblema u orkestratora agenata

Symphony je počeo s jednostavnim konceptom: svaki otvoreni zadatak treba da preuzme i završi agent. Umjesto upravljanja Codex sesijama u više kartica, naš alat za praćenje problema pretvorili smo u upravljački panel.

U ovoj postavci, svaki otvoreni problem u Linearu se mapira na namjenski radni prostor agenta. Symphony neprekidno prati tablu zadataka i osigurava da svaki aktivni zadatak ima agenta koji radi u petlji dok zadatak ne bude završen. Ako se agent sruši ili zastane, Symphony ga ponovo pokreće. Ako se pojavi novi posao, Symphony ga preuzima i počinje organizovati rad.

Naš radni tok smo izgradili na osnovu statusa tiketa, koristeći alat za upravljanje zadacima, Linear, kao mašinu stanja.

Agenti za kodiranje koriste statuse Lineara kao mašinu stanja da bi radili zajedno s nama.

U praksi, Symphony razdvaja posao od sesija i od pull requesta. Neki problemi proizvode više PR-ova kroz različite repozitorije; drugi su čisto istraživanje ili analiza koji nikada ne dodirnu bazu koda.

Kada se posao apstrahuje na taj način, tiketi mogu predstavljati mnogo veće cjeline rada.

Symphony redovno koristimo za orkestraciju složenih funkcionalnosti i migracije infrastrukture. Naprimjer, možemo kreirati zadatak u kojem tražimo od agenta da analizira bazu koda, Slack ili Notion, te izradi plan implementacije. Kada budemo zadovoljni planom, agent generiše stablo zadataka, razlažući posao na faze i definišući zavisnosti između zadataka.

Agenti počinju raditi samo na zadacima koji nisu blokirani, tako da se izvršavanje za ovaj DAG (niz koraka izvršavanja) odvija prirodno i optimalno paralelno. U primjeru ispod označili smo da je React nadogradnja blokirana migracijom na Vite. Očekivano, agenti su počeli nadograđivati React tek nakon što je migracija na Vite bila završena.

Agenti mogu i sami kreirati posao. Tokom implementacije ili pregleda, oni često uoče poboljšanja koja izlaze izvan opsega trenutnog zadatka: problem s performansama, priliku za refaktorisanje ili bolju arhitekturu. Kada se to desi, oni jednostavno kreiraju novi problem koji kasnije možemo procijeniti i rasporediti—mnoge od tih naknadnih zadataka također preuzimaju agenti. Dok mi nadgledamo ovaj proces, agenti ostaju organizovani i održavaju posao u pokretu.

Ovakav način rada drastično smanjuje kognitivni trošak pokretanja nejasno definisanog posla. Ako agent nešto pogriješi, to je i dalje korisna informacija, a naš trošak je skoro nula. Možemo vrlo jeftino kreirati tikete da agent ode praviti prototipe i istraživati, i odbaciti sva istraživanja koja nam se ne dopadnu.

Budući da orkestrator radi na razvojnim mašinama i nikada ne spava, zadatke možemo dodavati odakle god želimo, znajući da će ih agent preuzeti. Naprimjer, jedan inženjer u našem timu napravio je tri značajne promjene iz Linear aplikacije na svom telefonu, iz udobne kolibe na lošem wifi-ju.

Rast istraživanja zahvaljujući ovakvom načinu rada

Kada smo posmatrali efekte rada sa Symphonyjem, najočitija promjena je uočena u izlazu. U nekim timovima u OpenAI-ju vidjeli smo da se broj spojenih PR-ova povećao 6 puta u prve tri sedmice. Izvan OpenAI-ja, osnivač Lineara, Karri Saarinen, istakao je porast broja kreiranih radnih prostora⁠(otvara se u novom prozoru) nakon što smo objavili Symphony. Međutim, dublja promjena nastala je u načinu na koji timovi razmišljaju o poslu.

Kada naši inženjeri više ne provode vrijeme nadzirući Codex sesije, ekonomika promjene koda potpuno se mijenja. Percipirani trošak svake promjene opada jer više ne ulažemo ljudski trud u samo sprovođenje implementacije.

To je promijenilo naše ponašanje. Postalo je trivijalno pokretati spekulativne zadatke u Symphonyju. Dovoljno je isprobati ideju, istražiti refaktorisanje, testirati hipotezu i zadržati samo rezultate koji djeluju obećavajuće.

To također proširuje krug onih koji mogu inicirati posao. Naš produkt menadžer i dizajner sada mogu direktno slati zahtjeve za funkcionalnosti u Symphony. Ne moraju preuzimati repozitorij niti upravljati Codex sesijom. Dovoljno je da opišu funkcionalnost i dobit će paket za pregled koji sadrži video obilazak funkcionalnosti koja radi unutar stvarnog proizvoda.

Symphony se također ističe u velikim monorepozitorijima (poput onog koji imamo u OpenAI-ju), gdje je posljednji korak spajanja PR-a spor i osjetljiv. Sistem prati CI, po potrebi radi rebase, rješava konflikte, ponavlja nepouzdane provjere i općenito provodi promjene kroz cijeli tok. Do trenutka kada tiket dođe do statusa Spajanje, velika je vjerovatnoća da će promjena ući u glavnu granu bez ljudske intervencije.

Mreža prikaza Symphonyja prije i poslije

Nakon implementacije Symphonyja, više posla delegiramo agentima i fokusiramo se na teže zadatke koji su više istraživačkog tipa.

Napredak donosi nove, drugačije probleme

Rad na ovom nivou nosi kompromise. Kada smo prešli sa interaktivnog usmjeravanja agenata na dodjeljivanje posla na nivou tiketa, izgubili smo mogućnost da ih stalno usmjeravamo usred rada i korigujemo kurs kada je potrebno. Ponekad bi agent proizveo nešto potpuno pogrešno. To je bilo korisno—ti neuspjesi su otkrili praznine u sistemu i pomogli nam da ga učinimo robusnijim.

Umjesto da rezultat ručno ispravljamo, dodali smo zaštitne mehanizme i sposobnosti kako bi agenti sljedeći put uspjeli. Vremenom nas je to navelo da našem harnessu dodamo nove mogućnosti, kao što su pokretanje end-to-end testova, upravljanje aplikacijom kroz Chrome DevTools i vođenje QA smoke testova. Značajno smo unaprijedili dokumentaciju i pojasnili kako izgleda dobar rezultat.

Nije svaki zadatak pogodan za Symphony. Neki problemi i dalje zahtijevaju da inženjeri rade direktno s interaktivnim Codex sesijama, posebno kada su u pitanju nejasni problemi ili posao koji traži snažno prosuđivanje i stručnost. U praksi su to obično najzanimljiviji i najugodniji zadaci na koje naši inženjeri troše vrijeme.

Razlika je u tome što Symphony može preuzeti većinu rutinskog implementacijskog rada. To omogućava inženjerima da se fokusiraju na jedan težak problem odjednom, umjesto da stalno mijenjaju kontekst prelazeći između manjih zadataka.

Također smo naučili da tretiranje agenata kao rigidnih čvorova u mašini stanja ne funkcioniše dobro. Modeli postaju pametniji i mogu rješavati veće probleme od okvira u koji ih pokušavamo smjestiti. Naprimjer, rane verzije su imale sve GitHub integracije kao dio vanjskog harnessa—naprimjer, rane verzije su očekivale da Codex pravi samo izmjene koda, a ostatak procesa (slanje promjena, pokretanje testova) bio je definisan u kodu. Naše rane verzije rada sa agentima su od Codexa tražile samo da implementira zadatak. Taj pristup se pokazao previše ograničavajućim. Codex je sasvim sposoban da kreira više PR-ova, kao i da čita povratne informacije iz pregleda i reagira na njih. Zato smo mu dali alate—gh CLI, sposobnosti čitanja CI logova itd.—i sada možemo tražiti od Codexa da radi više, poput zatvaranja starih PR-ova ili izvlačenja izvještaja o završenom naspram napuštenom poslu. Ove vrste zadataka bile su daleko izvan početnog okvira implementacije funkcionalnosti.

Zato smo se na kraju usmjerili ka tome da agentima dajemo ciljeve umjesto strogih tranzicija, slično kao što bi dobar menadžer dodijelio cilj direktnom saradniku u svom timu. Snaga modela dolazi iz njihove sposobnosti da rezonuju, zato im dajte alate i kontekst i pustite ih da rade.

Korištenje Symphonyja za izgradnju Symphonyja

Kada otvorite Symphony repozitorij, prvo što ćete primijetiti jeste da je Symphony tehnički samo datoteka SPEC.md—definicija problema i namjeravanog rješenja. Umjesto izgradnje složenog sistema nadzora, definisali smo problem i namjeravana rješenja, dajući agentima usmjeravanje na visokom nivou.

Markdown

1# Symphony Service Specification
2
3Status: Draft v1 (language-agnostic)
4
5Purpose: Define a service that orchestrates coding agents to get project work done.
6
7## 1. Problem Statement
8
9Symphony is a long-running automation service that continuously reads work from an issue tracker
10(Linear in this specification version), creates an isolated workspace for each issue, and runs a
11coding agent session for that issue inside the workspace.
12
13The service solves four operational problems:
14
15- It turns issue execution into a repeatable daemon workflow instead of manual scripts.
16- It isolates agent execution in per-issue workspaces so agent commands run only inside per-issue
17  workspace directories.
18- It keeps the workflow policy in-repo (`WORKFLOW.md`) so teams version the agent prompt and runtime
19  settings with their code.
20- It provides enough observability to operate and debug multiple concurrent agent runs.
21
22Implementations are expected to document their trust and safety posture explicitly. This
23specification does not require a single approval, sandbox, or operator-confirmation policy; some
24implementations may target trusted environments with a high-trust configuration, while others may
25require stricter approvals or sandboxing.
26
27Important boundary:
28
29- Symphony is a scheduler/runner and tracker reader.
30- Ticket writes (state transitions, comments, PR links) are typically performed by the coding agent
31  using tools available in the workflow/runtime environment.
32- A successful run may end at a workflow-defined handoff state (for example `Human Review`), not
33  necessarily `Done`.
34
35## 2. Goals and Non-Goals
36
37### 2.1 Goals
38
39- Poll the issue tracker on a fixed cadence and dispatch work with bounded concurrency.
40- Maintain a single authoritative orchestrator state for dispatch, retries, and reconciliation.
41- Create deterministic per-issue workspaces and preserve them across runs.
42- Stop active runs when issue state changes make them ineligible.
43- Recover from transient failures with exponential backoff.
44- Load runtime behavior from a repository-owned `WORKFLOW.md` contract.
45- Expose operator-visible observability (at minimum structured logs).
46- Support restart recovery without requiring a persistent database.
47
48### 2.2 Non-Goals
49
50- Rich web UI or multi-tenant control plane.
51- Prescribing a specific dashboard or terminal UI implementation.
52- General-purpose workflow engine or distributed job scheduler.
53- Built-in business logic for how to edit tickets, PRs, or comments. (That logic lives in the
54  workflow prompt and agent tooling.)
55- Mandating strong sandbox controls beyond what the coding agent and host OS provide.
56- Mandating a single default approval, sandbox, or operator-confirmation posture for all
57  implementations.
58
59## 3. System Overview
60
61### 3.1 Main Components
62
631. `Workflow Loader`
64   - Reads `WORKFLOW.md`.
65   - Parses YAML front matter and prompt body.
66   - Returns `{config, prompt_template}`.
67
682. `Config Layer`
69   - Exposes typed getters for workflow config values.
70   - Applies defaults and environment variable indirection.
71   - Performs validation used by the orchestrator before dispatch.
72
733. `Issue Tracker Client`
74   - Fetches candidate issues in active states.
75   - Fetches current states for specific issue IDs (reconciliation).
76   - Fetches terminal-state issues during startup cleanup.
77   - Normalizes tracker payloads into a stable issue model.
78
794. `Orchestrator`
80   - Owns the poll tick.
81   - Owns the in-memory runtime state.
82   - Decides which issues to dispatch, retry, stop, or release.
83   - Tracks session metrics and retry queue state.
84
855. `Workspace Manager`
86   - Maps issue identifiers to workspace paths.
87   - Ensures per-issue workspace directories exist.
88   - Runs workspace lifecycle hooks.
89   - Cleans workspaces for terminal issues.
90
916. `Agent Runner`
92   - Creates workspace.
93   - Builds prompt from issue + workflow template.
94   - Launches the coding agent app-server client.
95   - Streams agent updates back to the orchestrator.
96
977. `Status Surface` (optional)
98   - Presents human-readable runtime status (for example terminal output, dashboard, or other
99     operator-facing view).
100
1018. `Logging`
102   - Emits structured runtime logs to one or more configured sinks.
103
104### 3.2 Abstraction Levels
105
106Symphony is easiest to port when kept in these layers:
107
1081. `Policy Layer` (repo-defined)
109   - `WORKFLOW.md` prompt body.
110   - Team-specific rules for ticket handling, validation, and handoff.
111
1122. `Configuration Layer` (typed getters)
113   - Parses front matter into typed runtime settings.
114   - Handles defaults, environment tokens, and path normalization.
115
1163. `Coordination Layer` (orchestrator)
117   - Polling loop, issue eligibility, concurrency, retries, reconciliation.
118
1194. `Execution Layer` (workspace + agent subprocess)
120   - Filesystem lifecycle, workspace preparation, coding-agent protocol.
121
1225. `Integration Layer` (Linear adapter)
123   - API calls and normalization for tracker data.
124
1256. `Observability Layer` (logs + optional status surface)
126   - Operator visibility into orchestrator and agent behavior.
127
128### 3.3 External Dependencies
129
130- Issue tracker API (Linear for `tracker.kind: linear` in this specification version).
131- Local filesystem for workspaces and logs.
132- Optional workspace population tooling (for example Git CLI, if used).
133- Coding-agent executable that supports JSON-RPC-like app-server mode over stdio.
134- Host environment authentication for the issue tracker and coding agent.
135
136## 4. Core Domain Model
137
138### 4.1 Entities
139
140#### 4.1.1 Issue
141
142Normalized issue record used by orchestration, prompt rendering, and observability output.
143
144Fields:
145
146- `id` (string)
147  - Stable tracker-internal ID.
148- `identifier` (string)
149  - Human-readable ticket key (example: `ABC-123`).
150- `title` (string)
151- `description` (string or null)
152- `priority` (integer or null)
153  - Lower numbers are higher priority in dispatch sorting.
154- `state` (string)
155  - Current tracker state name.
156- `branch_name` (string or null)
157  - Tracker-provided branch metadata if available.
158- `url` (string or null)
159- `labels` (list of strings)
160  - Normalized to lowercase.
161- `blocked_by` (list of blocker refs)
162  - Each blocker ref contains:
163    - `id` (string or null)
164    - `identifier` (string or null)
165    - `state` (string or null)
166- `created_at` (timestamp or null)
167- `updated_at` (timestamp or null)
168
169#### 4.1.2 Workflow Definition
170
171Parsed `WORKFLOW.md` payload:
172
173- `config` (map)
174  - YAML front matter root object.
175- `prompt_template` (string)
176  - Markdown body after front matter, trimmed.
177
178#### 4.1.3 Service Config (Typed View)
179
180Typed runtime values derived from `WorkflowDefinition.config` plus environment resolution.
181
182Examples:
183
184- poll interval
185- workspace root
186- active and terminal issue states
187- concurrency limits
188- coding-agent executable/args/timeouts
189- workspace hooks
190
191#### 4.1.4 Workspace
192
193Filesystem workspace assigned to one issue identifier.
194
195Fields (logical):
196
197- `path` (workspace path; current runtime typically uses absolute paths, but relative roots are
198  possible if configured without path separators)
199- `workspace_key` (sanitized issue identifier)
200- `created_now` (boolean, used to gate `after_create` hook)
201
202#### 4.1.5 Run Attempt
203
204One execution attempt for one issue.
205
206Fields (logical):
207
208- `issue_id`
209- `issue_identifier`
210- `attempt` (integer or null, `null` for first run, `>=1` for retries/continuation)
211- `workspace_path`
212- `started_at`
213- `status`
214- `error` (optional)
215
216#### 4.1.6 Live Session (Agent Session Metadata)
217
218State tracked while a coding-agent subprocess is running.
219
220Fields:
221
222- `session_id` (string, `<thread_id>-<turn_id>`)
223- `thread_id` (string)
224- `turn_id` (string)
225- `codex_app_server_pid` (string or null)
226- `last_codex_event` (string/enum or null)
227- `last_codex_timestamp` (timestamp or null)
228- `last_codex_message` (summarized payload)
229- `codex_input_tokens` (integer)
230- `codex_output_tokens` (integer)
231- `codex_total_tokens` (integer)
232- `last_reported_input_tokens` (integer)
233- `last_reported_output_tokens` (integer)
234- `last_reported_total_tokens` (integer)
235- `turn_count` (integer)
236  - Number of coding-agent turns started within the current worker lifetime.
237
238#### 4.1.7 Retry Entry
239
240Scheduled retry state for an issue.
241
242Fields:
243
244- `issue_id`
245- `identifier` (best-effort human ID for status surfaces/logs)
246- `attempt` (integer, 1-based for retry queue)
247- `due_at_ms` (monotonic clock timestamp)
248- `timer_handle` (runtime-specific timer reference)
249- `error` (string or null)
250
251#### 4.1.8 Orchestrator Runtime State
252
253Single authoritative in-memory state owned by the orchestrator.
254
255Fields:
256
257- `poll_interval_ms` (current effective poll interval)
258- `max_concurrent_agents` (current effective global concurrency limit)
259- `running` (map `issue_id -> running entry`)
260- `claimed` (set of issue IDs reserved/running/retrying)
261- `retry_attempts` (map `issue_id -> RetryEntry`)
262- `completed` (set of issue IDs; bookkeeping only, not dispatch gating)
263- `codex_totals` (aggregate tokens + runtime seconds)
264- `codex_rate_limits` (latest rate-limit snapshot from agent events)
265
266### 4.2 Stable Identifiers and Normalization Rules
267
268- `Issue ID`
269  - Use for tracker lookups and internal map keys.
270- `Issue Identifier`
271  - Use for human-readable logs and workspace naming.
272- `Workspace Key`
273  - Derive from `issue.identifier` by replacing any character not in `[A-Za-z0-9._-]` with `_`.
274  - Use the sanitized value for the workspace directory name.
275- `Normalized Issue State`
276  - Compare states after `lowercase`.
277- `Session ID`
278  - Compose from coding-agent `thread_id` and `turn_id` as `<thread_id>-<turn_id>`.
279
280## 5. Workflow Specification (Repository Contract)
281
282### 5.1 File Discovery and Path Resolution
283
284Workflow file path precedence:
285
2861. Explicit application/runtime setting (set by CLI startup path).
2872. Default: `WORKFLOW.md` in the current process working directory.
288
289Loader behavior:
290
291- If the file cannot be read, return `missing_workflow_file` error.
292- The workflow file is expected to be repository-owned and version-controlled.
293
294### 5.2 File Format
295
296`WORKFLOW.md` is a Markdown file with optional YAML front matter.
297
298Design note:
299
300- `WORKFLOW.md` should be self-contained enough to describe and run different workflows (prompt,
301  runtime settings, hooks, and tracker selection/config) without requiring out-of-band
302  service-specific configuration.
303
304Parsing rules:
305
306- If file starts with `---`, parse lines until the next `---` as YAML front matter.
307- Remaining lines become the prompt body.
308- If front matter is absent, treat the entire file as prompt body and use an empty config map.
309- YAML front matter must decode to a map/object; non-map YAML is an error.
310- Prompt body is trimmed before use.
311
312Returned workflow object:
313
314- `config`: front matter root object (not nested under a `config` key).
315- `prompt_template`: trimmed Markdown body.
316
317### 5.3 Front Matter Schema
318
319Top-level keys:
320
321- `tracker`
322- `polling`
323- `workspace`
324- `hooks`
325- `agent`
326- `codex`
327
328Unknown keys should be ignored for forward compatibility.
329
330Note:
331
332- The workflow front matter is extensible. Optional extensions may define additional top-level keys
333  (for example `server`) without changing the core schema above.
334- Extensions should document their field schema, defaults, validation rules, and whether changes
335  apply dynamically or require restart.
336- Common extension: `server.port` (integer) enables the optional HTTP server described in Section
337  13.7.
338
339#### 5.3.1 `tracker` (object)
340
341Fields:
342
343- `kind` (string)
344  - Required for dispatch.
345  - Current supported value: `linear`
346- `endpoint` (string)
347  - Default for `tracker.kind == "linear"`: `https://api.linear.app/graphql`
348- `api_key` (string)
349  - May be a literal token or `$VAR_NAME`.
350  - Canonical environment variable for `tracker.kind == "linear"`: `LINEAR_API_KEY`.
351  - If `$VAR_NAME` resolves to an empty string, treat the key as missing.
352- `project_slug` (string)
353  - Required for dispatch when `tracker.kind == "linear"`.
354- `active_states` (list of strings)
355  - Default: `Todo`, `In Progress`
356- `terminal_states` (list of strings)
357  - Default: `Closed`, `Cancelled`, `Canceled`, `Duplicate`, `Done`
358
359#### 5.3.2 `polling` (object)
360
361Fields:
362
363- `interval_ms` (integer or string integer)
364  - Default: `30000`
365  - Changes should be re-applied at runtime and affect future tick scheduling without restart.
366
367#### 5.3.3 `workspace` (object)
368
369Fields:
370
371- `root` (path string or `$VAR`)
372  - Default: `<system-temp>/symphony_workspaces`
373  - `~` and strings containing path separators are expanded.
374  - Bare strings without path separators are preserved as-is (relative roots are allowed but
375    discouraged).
376
377#### 5.3.4 `hooks` (object)
378
379Fields:
380
381- `after_create` (multiline shell script string, optional)
382  - Runs only when a workspace directory is newly created.
383  - Failure aborts workspace creation.
384- `before_run` (multiline shell script string, optional)
385  - Runs before each agent attempt after workspace preparation and before launching the coding
386    agent.
387  - Failure aborts the current attempt.
388- `after_run` (multiline shell script string, optional)
389  - Runs after each agent attempt (success, failure, timeout, or cancellation) once the workspace
390    exists.
391  - Failure is logged but ignored.
392- `before_remove` (multiline shell script string, optional)
393  - Runs before workspace deletion if the directory exists.
394  - Failure is logged but ignored; cleanup still proceeds.
395- `timeout_ms` (integer, optional)
396  - Default: `60000`
397  - Applies to all workspace hooks.
398  - Non-positive values should be treated as invalid and fall back to the default.
399  - Changes should be re-applied at runtime for future hook executions.
400
401#### 5.3.5 `agent` (object)
402
403Fields:
404
405- `max_concurrent_agents` (integer or string integer)
406  - Default: `10`
407  - Changes should be re-applied at runtime and affect subsequent dispatch decisions.
408- `max_retry_backoff_ms` (integer or string integer)
409  - Default: `300000` (5 minutes)
410  - Changes should be re-applied at runtime and affect future retry scheduling.
411- `max_concurrent_agents_by_state` (map `state_name -> positive integer`)
412  - Default: empty map.
413  - State keys are normalized (`lowercase`) for lookup.
414  - Invalid entries (non-positive or non-numeric) are ignored.
415
416#### 5.3.6 `codex` (object)
417
418Fields:
419
420For Codex-owned config values such as `approval_policy`, `thread_sandbox`, and
421`turn_sandbox_policy`, supported values are defined by the targeted Codex app-server version.
422Implementors should treat them as pass-through Codex config values rather than relying on a
423hand-maintained enum in this spec. To inspect the installed Codex schema, run
424`codex app-server generate-json-schema --out <dir>` and inspect the relevant definitions referenced
425by `v2/ThreadStartParams.json` and `v2/TurnStartParams.json`. Implementations may validate these
426fields locally if they want stricter startup checks.
427
428- `command` (string shell command)
429  - Default: `codex app-server`
430  - The runtime launches this command via `bash -lc` in the workspace directory.
431  - The launched process must speak a compatible app-server protocol over stdio.
432- `approval_policy` (Codex `AskForApproval` value)
433  - Default: implementation-defined.
434- `thread_sandbox` (Codex `SandboxMode` value)
435  - Default: implementation-defined.
436- `turn_sandbox_policy` (Codex `SandboxPolicy` value)
437  - Default: implementation-defined.
438- `turn_timeout_ms` (integer)
439  - Default: `3600000` (1 hour)
440- `read_timeout_ms` (integer)
441  - Default: `5000`
442- `stall_timeout_ms` (integer)
443  - Default: `300000` (5 minutes)
444  - If `<= 0`, stall detection is disabled.
445
446### 5.4 Prompt Template Contract
447
448The Markdown body of `WORKFLOW.md` is the per-issue prompt template.
449
450Rendering requirements:
451
452- Use a strict template engine (Liquid-compatible semantics are sufficient).
453- Unknown variables must fail rendering.
454- Unknown filters must fail rendering.
455
456Template input variables:
457
458- `issue` (object)
459  - Includes all normalized issue fields, including labels and blockers.
460- `attempt` (integer or null)
461  - `null`/absent on first attempt.
462  - Integer on retry or continuation run.
463
464Fallback prompt behavior:
465
466- If the workflow prompt body is empty, the runtime may use a minimal default prompt
467  (`You are working on an issue from Linear.`).
468- Workflow file read/parse failures are configuration/validation errors and should not silently fall
469  back to a prompt.
470
471### 5.5 Workflow Validation and Error Surface
472
473Error classes:
474
475- `missing_workflow_file`
476- `workflow_parse_error`
477- `workflow_front_matter_not_a_map`
478- `template_parse_error` (during prompt rendering)
479- `template_render_error` (unknown variable/filter, invalid interpolation)
480
481Dispatch gating behavior:
482
483- Workflow file read/YAML errors block new dispatches until fixed.
484- Template errors fail only the affected run attempt.
485
486## 6. Configuration Specification
487
488### 6.1 Source Precedence and Resolution Semantics
489
490Configuration precedence:
491
4921. Workflow file path selection (runtime setting -> cwd default).
4932. YAML front matter values.
4943. Environment indirection via `$VAR_NAME` inside selected YAML values.
4954. Built-in defaults.
496
497Value coercion semantics:
498
499- Path/command fields support:
500  - `~` home expansion
501  - `$VAR` expansion for env-backed path values
502  - Apply expansion only to values intended to be local filesystem paths; do not rewrite URIs or
503    arbitrary shell command strings.
504
505### 6.2 Dynamic Reload Semantics
506
507Dynamic reload is required:
508
509- The software should watch `WORKFLOW.md` for changes.
510- On change, it should re-read and re-apply workflow config and prompt template without restart.
511- The software should attempt to adjust live behavior to the new config (for example polling
512  cadence, concurrency limits, active/terminal states, codex settings, workspace paths/hooks, and
513  prompt content for future runs).
514- Reloaded config applies to future dispatch, retry scheduling, reconciliation decisions, hook
515  execution, and agent launches.
516- Implementations are not required to restart in-flight agent sessions automatically when config
517  changes.
518- Extensions that manage their own listeners/resources (for example an HTTP server port change) may
519  require restart unless the implementation explicitly supports live rebind.
520- Implementations should also re-validate/reload defensively during runtime operations (for example
521  before dispatch) in case filesystem watch events are missed.
522- Invalid reloads should not crash the service; keep operating with the last known good effective
523  configuration and emit an operator-visible error.
524
525### 6.3 Dispatch Preflight Validation
526
527This validation is a scheduler preflight run before attempting to dispatch new work. It validates
528the workflow/config needed to poll and launch workers, not a full audit of all possible workflow
529behavior.
530
531Startup validation:
532
533- Validate configuration before starting the scheduling loop.
534- If startup validation fails, fail startup and emit an operator-visible error.
535
536Per-tick dispatch validation:
537
538- Re-validate before each dispatch cycle.
539- If validation fails, skip dispatch for that tick, keep reconciliation active, and emit an
540  operator-visible error.
541
542Validation checks:
543
544- Workflow file can be loaded and parsed.
545- `tracker.kind` is present and supported.
546- `tracker.api_key` is present after `$` resolution.
547- `tracker.project_slug` is present when required by the selected tracker kind.
548- `codex.command` is present and non-empty.
549
550### 6.4 Config Fields Summary (Cheat Sheet)
551
552This section is intentionally redundant so a coding agent can implement the config layer quickly.
553
554- `tracker.kind`: string, required, currently `linear`
555- `tracker.endpoint`: string, default `https://api.linear.app/graphql` when `tracker.kind=linear`
556- `tracker.api_key`: string or `$VAR`, canonical env `LINEAR_API_KEY` when `tracker.kind=linear`
557- `tracker.project_slug`: string, required when `tracker.kind=linear`
558- `tracker.active_states`: list of strings, default `["Todo", "In Progress"]`
559- `tracker.terminal_states`: list of strings, default `["Closed", "Cancelled", "Canceled", "Duplicate", "Done"]`
560- `polling.interval_ms`: integer, default `30000`
561- `workspace.root`: path, default `<system-temp>/symphony_workspaces`
562- `worker.ssh_hosts` (extension): list of SSH host strings, optional; when omitted, work runs
563  locally
564- `worker.max_concurrent_agents_per_host` (extension): positive integer, optional; shared per-host
565  cap applied across configured SSH hosts
566- `hooks.after_create`: shell script or null
567- `hooks.before_run`: shell script or null
568- `hooks.after_run`: shell script or null
569- `hooks.before_remove`: shell script or null
570- `hooks.timeout_ms`: integer, default `60000`
571- `agent.max_concurrent_agents`: integer, default `10`
572- `agent.max_turns`: integer, default `20`
573- `agent.max_retry_backoff_ms`: integer, default `300000` (5m)
574- `agent.max_concurrent_agents_by_state`: map of positive integers, default `{}`
575- `codex.command`: shell command string, default `codex app-server`
576- `codex.approval_policy`: Codex `AskForApproval` value, default implementation-defined
577- `codex.thread_sandbox`: Codex `SandboxMode` value, default implementation-defined
578- `codex.turn_sandbox_policy`: Codex `SandboxPolicy` value, default implementation-defined
579- `codex.turn_timeout_ms`: integer, default `3600000`
580- `codex.read_timeout_ms`: integer, default `5000`
581- `codex.stall_timeout_ms`: integer, default `300000`
582- `server.port` (extension): integer, optional; enables the optional HTTP server, `0` may be used
583  for ephemeral local bind, and CLI `--port` overrides it
584
585## 7. Orchestration State Machine
586
587The orchestrator is the only component that mutates scheduling state. All worker outcomes are
588reported back to it and converted into explicit state transitions.
589
590### 7.1 Issue Orchestration States
591
592This is not the same as tracker states (`Todo`, `In Progress`, etc.). This is the service's internal
593claim state.
594
5951. `Unclaimed`
596   - Issue is not running and has no retry scheduled.
597
5982. `Claimed`
599   - Orchestrator has reserved the issue to prevent duplicate dispatch.
600   - In practice, claimed issues are either `Running` or `RetryQueued`.
601
6023. `Running`
603   - Worker task exists and the issue is tracked in `running` map.
604
6054. `RetryQueued`
606   - Worker is not running, but a retry timer exists in `retry_attempts`.
607
6085. `Released`
609   - Claim removed because issue is terminal, non-active, missing, or retry path completed without
610     re-dispatch.
611
612Important nuance:
613
614- A successful worker exit does not mean the issue is done forever.
615- The worker may continue through multiple back-to-back coding-agent turns before it exits.
616- After each normal turn completion, the worker re-checks the tracker issue state.
617- If the issue is still in an active state, the worker should start another turn on the same live
618  coding-agent thread in the same workspace, up to `agent.max_turns`.
619- The first turn should use the full rendered task prompt.
620- Continuation turns should send only continuation guidance to the existing thread, not resend the
621  original task prompt that is already present in thread history.
622- Once the worker exits normally, the orchestrator still schedules a short continuation retry
623  (about 1 second) so it can re-check whether the issue remains active and needs another worker
624  session.
625
626### 7.2 Run Attempt Lifecycle
627
628A run attempt transitions through these phases:
629
6301. `PreparingWorkspace`
6312. `BuildingPrompt`
6323. `LaunchingAgentProcess`
6334. `InitializingSession`
6345. `StreamingTurn`
6356. `Finishing`
6367. `Succeeded`
6378. `Failed`
6389. `TimedOut`
63910. `Stalled`
64011. `CanceledByReconciliation`
641
642Distinct terminal reasons are important because retry logic and logs differ.
643
644### 7.3 Transition Triggers
645
646- `Poll Tick`
647  - Reconcile active runs.
648  - Validate config.
649  - Fetch candidate issues.
650  - Dispatch until slots are exhausted.
651
652- `Worker Exit (normal)`
653  - Remove running entry.
654  - Update aggregate runtime totals.
655  - Schedule continuation retry (attempt `1`) after the worker exhausts or finishes its in-process
656    turn loop.
657
658- `Worker Exit (abnormal)`
659  - Remove running entry.
660  - Update aggregate runtime totals.
661  - Schedule exponential-backoff retry.
662
663- `Codex Update Event`
664  - Update live session fields, token counters, and rate limits.
665
666- `Retry Timer Fired`
667  - Re-fetch active candidates and attempt re-dispatch, or release claim if no longer eligible.
668
669- `Reconciliation State Refresh`
670  - Stop runs whose issue states are terminal or no longer active.
671
672- `Stall Timeout`
673  - Kill worker and schedule retry.
674
675### 7.4 Idempotency and Recovery Rules
676
677- The orchestrator serializes state mutations through one authority to avoid duplicate dispatch.
678- `claimed` and `running` checks are required before launching any worker.
679- Reconciliation runs before dispatch on every tick.
680- Restart recovery is tracker-driven and filesystem-driven (no durable orchestrator DB required).
681- Startup terminal cleanup removes stale workspaces for issues already in terminal states.
682
683## 8. Polling, Scheduling, and Reconciliation
684
685### 8.1 Poll Loop
686
687At startup, the service validates config, performs startup cleanup, schedules an immediate tick, and
688then repeats every `polling.interval_ms`.
689
690The effective poll interval should be updated when workflow config changes are re-applied.
691
692Tick sequence:
693
6941. Reconcile running issues.
6952. Run dispatch preflight validation.
6963. Fetch candidate issues from tracker using active states.
6974. Sort issues by dispatch priority.
6985. Dispatch eligible issues while slots remain.
6996. Notify observability/status consumers of state changes.
700
701If per-tick validation fails, dispatch is skipped for that tick, but reconciliation still happens
702first.
703
704### 8.2 Candidate Selection Rules
705
706An issue is dispatch-eligible only if all are true:
707
708- It has `id`, `identifier`, `title`, and `state`.
709- Its state is in `active_states` and not in `terminal_states`.
710- It is not already in `running`.
711- It is not already in `claimed`.
712- Global concurrency slots are available.
713- Per-state concurrency slots are available.
714- Blocker rule for `Todo` state passes:
715  - If the issue state is `Todo`, do not dispatch when any blocker is non-terminal.
716
717Sorting order (stable intent):
718
7191. `priority` ascending (1..4 are preferred; null/unknown sorts last)
7202. `created_at` oldest first
7213. `identifier` lexicographic tie-breaker
722
723### 8.3 Concurrency Control
724
725Global limit:
726
727- `available_slots = max(max_concurrent_agents - running_count, 0)`
728
729Per-state limit:
730
731- `max_concurrent_agents_by_state[state]` if present (state key normalized)
732- otherwise fallback to global limit
733
734The runtime counts issues by their current tracked state in the `running` map.
735
736Optional SSH host limit:
737
738- When `worker.max_concurrent_agents_per_host` is set, each configured SSH host may run at most
739  that many concurrent agents at once.
740- Hosts at that cap are skipped for new dispatch until capacity frees up.
741
742### 8.4 Retry and Backoff
743
744Retry entry creation:
745
746- Cancel any existing retry timer for the same issue.
747- Store `attempt`, `identifier`, `error`, `due_at_ms`, and new timer handle.
748
749Backoff formula:
750
751- Normal continuation retries after a clean worker exit use a short fixed delay of `1000` ms.
752- Failure-driven retries use `delay = min(10000 * 2^(attempt - 1), agent.max_retry_backoff_ms)`.
753- Power is capped by the configured max retry backoff (default `300000` / 5m).
754
755Retry handling behavior:
756
7571. Fetch active candidate issues (not all issues).
7582. Find the specific issue by `issue_id`.
7593. If not found, release claim.
7604. If found and still candidate-eligible:
761   - Dispatch if slots are available.
762   - Otherwise requeue with error `no available orchestrator slots`.
7635. If found but no longer active, release claim.
764
765Note:
766
767- Terminal-state workspace cleanup is handled by startup cleanup and active-run reconciliation
768  (including terminal transitions for currently running issues).
769- Retry handling mainly operates on active candidates and releases claims when the issue is absent,
770  rather than performing terminal cleanup itself.
771
772### 8.5 Active Run Reconciliation
773
774Reconciliation runs every tick and has two parts.
775
776Part A: Stall detection
777
778- For each running issue, compute `elapsed_ms` since:
779  - `last_codex_timestamp` if any event has been seen, else
780  - `started_at`
781- If `elapsed_ms > codex.stall_timeout_ms`, terminate the worker and queue a retry.
782- If `stall_timeout_ms <= 0`, skip stall detection entirely.
783
784Part B: Tracker state refresh
785
786- Fetch current issue states for all running issue IDs.
787- For each running issue:
788  - If tracker state is terminal: terminate worker and clean workspace.
789  - If tracker state is still active: update the in-memory issue snapshot.
790  - If tracker state is neither active nor terminal: terminate worker without workspace cleanup.
791- If state refresh fails, keep workers running and try again on the next tick.
792
793### 8.6 Startup Terminal Workspace Cleanup
794
795When the service starts:
796
7971. Query tracker for issues in terminal states.
7982. For each returned issue identifier, remove the corresponding workspace directory.
7993. If the terminal-issues fetch fails, log a warning and continue startup.
800
801This prevents stale terminal workspaces from accumulating after restarts.
802
803## 9. Workspace Management and Safety
804
805### 9.1 Workspace Layout
806
807Workspace root:
808
809- `workspace.root` (normalized path; the current config layer expands path-like values and preserves
810  bare relative names)
811
812Per-issue workspace path:
813
814- `<workspace.root>/<sanitized_issue_identifier>`
815
816Workspace persistence:
817
818- Workspaces are reused across runs for the same issue.
819- Successful runs do not auto-delete workspaces.
820
821### 9.2 Workspace Creation and Reuse
822
823Input: `issue.identifier`
824
825Algorithm summary:
826
8271. Sanitize identifier to `workspace_key`.
8282. Compute workspace path under workspace root.
8293. Ensure the workspace path exists as a directory.
8304. Mark `created_now=true` only if the directory was created during this call; otherwise
831   `created_now=false`.
8325. If `created_now=true`, run `after_create` hook if configured.
833
834Notes:
835
836- This section does not assume any specific repository/VCS workflow.
837- Workspace preparation beyond directory creation (for example dependency bootstrap, checkout/sync,
838  code generation) is implementation-defined and is typically handled via hooks.
839
840### 9.3 Optional Workspace Population (Implementation-Defined)
841
842The spec does not require any built-in VCS or repository bootstrap behavior.
843
844Implementations may populate or synchronize the workspace using implementation-defined logic and/or
845hooks (for example `after_create` and/or `before_run`).
846
847Failure handling:
848
849- Workspace population/synchronization failures return an error for the current attempt.
850- If failure happens while creating a brand-new workspace, implementations may remove the partially
851  prepared directory.
852- Reused workspaces should not be destructively reset on population failure unless that policy is
853  explicitly chosen and documented.
854
855### 9.4 Workspace Hooks
856
857Supported hooks:
858
859- `hooks.after_create`
860- `hooks.before_run`
861- `hooks.after_run`
862- `hooks.before_remove`
863
864Execution contract:
865
866- Execute in a local shell context appropriate to the host OS, with the workspace directory as
867  `cwd`.
868- On POSIX systems, `sh -lc <script>` (or a stricter equivalent such as `bash -lc <script>`) is a
869  conforming default.
870- Hook timeout uses `hooks.timeout_ms`; default: `60000 ms`.
871- Log hook start, failures, and timeouts.
872
873Failure semantics:
874
875- `after_create` failure or timeout is fatal to workspace creation.
876- `before_run` failure or timeout is fatal to the current run attempt.
877- `after_run` failure or timeout is logged and ignored.
878- `before_remove` failure or timeout is logged and ignored.
879
880### 9.5 Safety Invariants
881
882This is the most important portability constraint.
883
884Invariant 1: Run the coding agent only in the per-issue workspace path.
885
886- Before launching the coding-agent subprocess, validate:
887  - `cwd == workspace_path`
888
889Invariant 2: Workspace path must stay inside workspace root.
890
891- Normalize both paths to absolute.
892- Require `workspace_path` to have `workspace_root` as a prefix directory.
893- Reject any path outside the workspace root.
894
895Invariant 3: Workspace key is sanitized.
896
897- Only `[A-Za-z0-9._-]` allowed in workspace directory names.
898- Replace all other characters with `_`.
899
900## 10. Agent Runner Protocol (Coding Agent Integration)
901
902This section defines the language-neutral contract for integrating a coding agent app-server.
903
904Compatibility profile:
905
906- The normative contract is message ordering, required behaviors, and the logical fields that must
907  be extracted (for example session IDs, completion state, approval handling, and usage/rate-limit
908  telemetry).
909- Exact JSON field names may vary slightly across compatible app-server versions.
910- Implementations should tolerate equivalent payload shapes when they carry the same logical
911  meaning, especially for nested IDs, approval requests, user-input-required signals, and
912  token/rate-limit metadata.
913
914### 10.1 Launch Contract
915
916Subprocess launch parameters:
917
918- Command: `codex.command`
919- Invocation: `bash -lc <codex.command>`
920- Working directory: workspace path
921- Stdout/stderr: separate streams
922- Framing: line-delimited protocol messages on stdout (JSON-RPC-like JSON per line)
923
924Notes:
925
926- The default command is `codex app-server`.
927- Approval policy, cwd, and prompt are expressed in the protocol messages in Section 10.2.
928
929Recommended additional process settings:
930
931- Max line size: 10 MB (for safe buffering)
932
933### 10.2 Session Startup Handshake
934
935Reference: https://developers.openai.com/codex/app-server/
936
937The client must send these protocol messages in order:
938
939Illustrative startup transcript (equivalent payload shapes are acceptable if they preserve the same
940semantics):
941
942```json
943{"id":1,"method":"initialize","params":{"clientInfo":{"name":"symphony","version":"1.0"},"capabilities":{}}}
944{"method":"initialized","params":{}}
945{"id":2,"method":"thread/start","params":{"approvalPolicy":"<implementation-defined>","sandbox":"<implementation-defined>","cwd":"/abs/workspace"}}
946{"id":3,"method":"turn/start","params":{"threadId":"<thread-id>","input":[{"type":"text","text":"<rendered prompt-or-continuation-guidance>"}],"cwd":"/abs/workspace","title":"ABC-123: Example","approvalPolicy":"<implementation-defined>","sandboxPolicy":{"type":"<implementation-defined>"}}}
947```
948
9491. `initialize` request
950   - Params include:
951     - `clientInfo` object (for example `{name, version}`)
952     - `capabilities` object (may be empty)
953   - If the targeted Codex app-server requires capability negotiation for dynamic tools, include the
954     necessary capability flag(s) here.
955   - Wait for response (`read_timeout_ms`)
9562. `initialized` notification
9573. `thread/start` request
958   - Params include:
959     - `approvalPolicy` = implementation-defined session approval policy value
960     - `sandbox` = implementation-defined session sandbox value
961     - `cwd` = absolute workspace path
962     - If optional client-side tools are implemented, include their advertised tool specs using the
963       protocol mechanism supported by the targeted Codex app-server version.
9644. `turn/start` request
965   - Params include:
966     - `threadId`
967     - `input` = single text item containing rendered prompt for the first turn, or continuation
968       guidance for later turns on the same thread
969     - `cwd`
970     - `title` = `<issue.identifier>: <issue.title>`
971     - `approvalPolicy` = implementation-defined turn approval policy value
972     - `sandboxPolicy` = implementation-defined object-form sandbox policy payload when required by
973       the targeted app-server version
974
975Session identifiers:
976
977- Read `thread_id` from `thread/start` result `result.thread.id`
978- Read `turn_id` from each `turn/start` result `result.turn.id`
979- Emit `session_id = "<thread_id>-<turn_id>"`
980- Reuse the same `thread_id` for all continuation turns inside one worker run
981
982### 10.3 Streaming Turn Processing
983
984The client reads line-delimited messages until the turn terminates.
985
986Completion conditions:
987
988- `turn/completed` -> success
989- `turn/failed` -> failure
990- `turn/cancelled` -> failure
991- turn timeout (`turn_timeout_ms`) -> failure
992- subprocess exit -> failure
993
994Continuation processing:
995
996- If the worker decides to continue after a successful turn, it should issue another `turn/start`
997  on the same live `threadId`.
998- The app-server subprocess should remain alive across those continuation turns and be stopped only
999  when the worker run is ending.
1000
1001Line handling requirements:
1002
1003- Read protocol messages from stdout only.
1004- Buffer partial stdout lines until newline arrives.
1005- Attempt JSON parse on complete stdout lines.
1006- Stderr is not part of the protocol stream:
1007  - ignore it or log it as diagnostics
1008  - do not attempt protocol JSON parsing on stderr
1009
1010### 10.4 Emitted Runtime Events (Upstream to Orchestrator)
1011
1012The app-server client emits structured events to the orchestrator callback. Each event should
1013include:
1014
1015- `event` (enum/string)
1016- `timestamp` (UTC timestamp)
1017- `codex_app_server_pid` (if available)
1018- optional `usage` map (token counts)
1019- payload fields as needed
1020
1021Important emitted events may include:
1022
1023- `session_started`
1024- `startup_failed`
1025- `turn_completed`
1026- `turn_failed`
1027- `turn_cancelled`
1028- `turn_ended_with_error`
1029- `turn_input_required`
1030- `approval_auto_approved`
1031- `unsupported_tool_call`
1032- `notification`
1033- `other_message`
1034- `malformed`
1035
1036### 10.5 Approval, Tool Calls, and User Input Policy
1037
1038Approval, sandbox, and user-input behavior is implementation-defined.
1039
1040Policy requirements:
1041
1042- Each implementation should document its chosen approval, sandbox, and operator-confirmation
1043  posture.
1044- Approval requests and user-input-required events must not leave a run stalled indefinitely. An
1045  implementation should either satisfy them, surface them to an operator, auto-resolve them, or
1046  fail the run according to its documented policy.
1047
1048Example high-trust behavior:
1049
1050- Auto-approve command execution approvals for the session.
1051- Auto-approve file-change approvals for the session.
1052- Treat user-input-required turns as hard failure.
1053
1054Unsupported dynamic tool calls:
1055
1056- Supported dynamic tool calls that are explicitly implemented and advertised by the runtime should
1057  be handled according to their extension contract.
1058- If the agent requests a dynamic tool call (`item/tool/call`) that is not supported, return a tool
1059  failure response and continue the session.
1060- This prevents the session from stalling on unsupported tool execution paths.
1061
1062Optional client-side tool extension:
1063
1064- An implementation may expose a limited set of client-side tools to the app-server session.
1065- Current optional standardized tool: `linear_graphql`.
1066- If implemented, supported tools should be advertised to the app-server session during startup
1067  using the protocol mechanism supported by the targeted Codex app-server version.
1068- Unsupported tool names should still return a failure result and continue the session.
1069
1070`linear_graphql` extension contract:
1071
1072- Purpose: execute a raw GraphQL query or mutation against Linear using Symphony's configured
1073  tracker auth for the current session.
1074- Availability: only meaningful when `tracker.kind == "linear"` and valid Linear auth is configured.
1075- Preferred input shape:
1076
1077  ```json
1078  {
1079    "query": "single GraphQL query or mutation document",
1080    "variables": {
1081      "optional": "graphql variables object"
1082    }
1083  }
1084  ```
1085
1086- `query` must be a non-empty string.
1087- `query` must contain exactly one GraphQL operation.
1088- `variables` is optional and, when present, must be a JSON object.
1089- Implementations may additionally accept a raw GraphQL query string as shorthand input.
1090- Execute one GraphQL operation per tool call.
1091- If the provided document contains multiple operations, reject the tool call as invalid input.
1092- `operationName` selection is intentionally out of scope for this extension.
1093- Reuse the configured Linear endpoint and auth from the active Symphony workflow/runtime config; do
1094  not require the coding agent to read raw tokens from disk.
1095- Tool result semantics:
1096  - transport success + no top-level GraphQL `errors` -> `success=true`
1097  - top-level GraphQL `errors` present -> `success=false`, but preserve the GraphQL response body
1098    for debugging
1099  - invalid input, missing auth, or transport failure -> `success=false` with an error payload
1100- Return the GraphQL response or error payload as structured tool output that the model can inspect
1101  in-session.
1102
1103Illustrative responses (equivalent payload shapes are acceptable if they preserve the same outcome):
1104
1105```json
1106{"id":"<approval-id>","result":{"approved":true}}
1107{"id":"<tool-call-id>","result":{"success":false,"error":"unsupported_tool_call"}}
1108```
1109
1110Hard failure on user input requirement:
1111
1112- If the agent requests user input, fail the run attempt immediately.
1113- The client detects this via:
1114  - explicit method (`item/tool/requestUserInput`), or
1115  - turn methods/flags indicating input is required.
1116
1117### 10.6 Timeouts and Error Mapping
1118
1119Timeouts:
1120
1121- `codex.read_timeout_ms`: request/response timeout during startup and sync requests
1122- `codex.turn_timeout_ms`: total turn stream timeout
1123- `codex.stall_timeout_ms`: enforced by orchestrator based on event inactivity
1124
1125Error mapping (recommended normalized categories):
1126
1127- `codex_not_found`
1128- `invalid_workspace_cwd`
1129- `response_timeout`
1130- `turn_timeout`
1131- `port_exit`
1132- `response_error`
1133- `turn_failed`
1134- `turn_cancelled`
1135- `turn_input_required`
1136
1137### 10.7 Agent Runner Contract
1138
1139The `Agent Runner` wraps workspace + prompt + app-server client.
1140
1141Behavior:
1142
11431. Create/reuse workspace for issue.
11442. Build prompt from workflow template.
11453. Start app-server session.
11464. Forward app-server events to orchestrator.
11475. On any error, fail the worker attempt (the orchestrator will retry).
1148
1149Note:
1150
1151- Workspaces are intentionally preserved after successful runs.
1152
1153## 11. Issue Tracker Integration Contract (Linear-Compatible)
1154
1155### 11.1 Required Operations
1156
1157An implementation must support these tracker adapter operations:
1158
11591. `fetch_candidate_issues()`
1160   - Return issues in configured active states for a configured project.
1161
11622. `fetch_issues_by_states(state_names)`
1163   - Used for startup terminal cleanup.
1164
11653. `fetch_issue_states_by_ids(issue_ids)`
1166   - Used for active-run reconciliation.
1167
1168### 11.2 Query Semantics (Linear)
1169
1170Linear-specific requirements for `tracker.kind == "linear"`:
1171
1172- `tracker.kind == "linear"`
1173- GraphQL endpoint (default `https://api.linear.app/graphql`)
1174- Auth token sent in `Authorization` header
1175- `tracker.project_slug` maps to Linear project `slugId`
1176- Candidate issue query filters project using `project: { slugId: { eq: $projectSlug } }`
1177- Issue-state refresh query uses GraphQL issue IDs with variable type `[ID!]`
1178- Pagination required for candidate issues
1179- Page size default: `50`
1180- Network timeout: `30000 ms`
1181
1182Important:
1183
1184- Linear GraphQL schema details can drift. Keep query construction isolated and test the exact query
1185  fields/types required by this specification.
1186
1187A non-Linear implementation may change transport details, but the normalized outputs must match the
1188domain model in Section 4.
1189
1190### 11.3 Normalization Rules
1191
1192Candidate issue normalization should produce fields listed in Section 4.1.1.
1193
1194Additional normalization details:
1195
1196- `labels` -> lowercase strings
1197- `blocked_by` -> derived from inverse relations where relation type is `blocks`
1198- `priority` -> integer only (non-integers become null)
1199- `created_at` and `updated_at` -> parse ISO-8601 timestamps
1200
1201### 11.4 Error Handling Contract
1202
1203Recommended error categories:
1204
1205- `unsupported_tracker_kind`
1206- `missing_tracker_api_key`
1207- `missing_tracker_project_slug`
1208- `linear_api_request` (transport failures)
1209- `linear_api_status` (non-200 HTTP)
1210- `linear_graphql_errors`
1211- `linear_unknown_payload`
1212- `linear_missing_end_cursor` (pagination integrity error)
1213
1214Orchestrator behavior on tracker errors:
1215
1216- Candidate fetch failure: log and skip dispatch for this tick.
1217- Running-state refresh failure: log and keep active workers running.
1218- Startup terminal cleanup failure: log warning and continue startup.
1219
1220### 11.5 Tracker Writes (Important Boundary)
1221
1222Symphony does not require first-class tracker write APIs in the orchestrator.
1223
1224- Ticket mutations (state transitions, comments, PR metadata) are typically handled by the coding
1225  agent using tools defined by the workflow prompt.
1226- The service remains a scheduler/runner and tracker reader.
1227- Workflow-specific success often means "reached the next handoff state" (for example
1228  `Human Review`) rather than tracker terminal state `Done`.
1229- If the optional `linear_graphql` client-side tool extension is implemented, it is still part of
1230  the agent toolchain rather than orchestrator business logic.
1231
1232## 12. Prompt Construction and Context Assembly
1233
1234### 12.1 Inputs
1235
1236Inputs to prompt rendering:
1237
1238- `workflow.prompt_template`
1239- normalized `issue` object
1240- optional `attempt` integer (retry/continuation metadata)
1241
1242### 12.2 Rendering Rules
1243
1244- Render with strict variable checking.
1245- Render with strict filter checking.
1246- Convert issue object keys to strings for template compatibility.
1247- Preserve nested arrays/maps (labels, blockers) so templates can iterate.
1248
1249### 12.3 Retry/Continuation Semantics
1250
1251`attempt` should be passed to the template because the workflow prompt may provide different
1252instructions for:
1253
1254- first run (`attempt` null or absent)
1255- continuation run after a successful prior session
1256- retry after error/timeout/stall
1257
1258### 12.4 Failure Semantics
1259
1260If prompt rendering fails:
1261
1262- Fail the run attempt immediately.
1263- Let the orchestrator treat it like any other worker failure and decide retry behavior.
1264
1265## 13. Logging, Status, and Observability
1266
1267### 13.1 Logging Conventions
1268
1269Required context fields for issue-related logs:
1270
1271- `issue_id`
1272- `issue_identifier`
1273
1274Required context for coding-agent session lifecycle logs:
1275
1276- `session_id`
1277
1278Message formatting requirements:
1279
1280- Use stable `key=value` phrasing.
1281- Include action outcome (`completed`, `failed`, `retrying`, etc.).
1282- Include concise failure reason when present.
1283- Avoid logging large raw payloads unless necessary.
1284
1285### 13.2 Logging Outputs and Sinks
1286
1287The spec does not prescribe where logs must go (stderr, file, remote sink, etc.).
1288
1289Requirements:
1290
1291- Operators must be able to see startup/validation/dispatch failures without attaching a debugger.
1292- Implementations may write to one or more sinks.
1293- If a configured log sink fails, the service should continue running when possible and emit an
1294  operator-visible warning through any remaining sink.
1295
1296### 13.3 Runtime Snapshot / Monitoring Interface (Optional but Recommended)
1297
1298If the implementation exposes a synchronous runtime snapshot (for dashboards or monitoring), it
1299should return:
1300
1301- `running` (list of running session rows)
1302- each running row should include `turn_count`
1303- `retrying` (list of retry queue rows)
1304- `codex_totals`
1305  - `input_tokens`
1306  - `output_tokens`
1307  - `total_tokens`
1308  - `seconds_running` (aggregate runtime seconds as of snapshot time, including active sessions)
1309- `rate_limits` (latest coding-agent rate limit payload, if available)
1310
1311Recommended snapshot error modes:
1312
1313- `timeout`
1314- `unavailable`
1315
1316### 13.4 Optional Human-Readable Status Surface
1317
1318A human-readable status surface (terminal output, dashboard, etc.) is optional and
1319implementation-defined.
1320
1321If present, it should draw from orchestrator state/metrics only and must not be required for
1322correctness.
1323
1324### 13.5 Session Metrics and Token Accounting
1325
1326Token accounting rules:
1327
1328- Agent events may include token counts in multiple payload shapes.
1329- Prefer absolute thread totals when available, such as:
1330  - `thread/tokenUsage/updated` payloads
1331  - `total_token_usage` within token-count wrapper events
1332- Ignore delta-style payloads such as `last_token_usage` for dashboard/API totals.
1333- Extract input/output/total token counts leniently from common field names within the selected
1334  payload.
1335- For absolute totals, track deltas relative to last reported totals to avoid double-counting.
1336- Do not treat generic `usage` maps as cumulative totals unless the event type defines them that
1337  way.
1338- Accumulate aggregate totals in orchestrator state.
1339
1340Runtime accounting:
1341
1342- Runtime should be reported as a live aggregate at snapshot/render time.
1343- Implementations may maintain a cumulative counter for ended sessions and add active-session
1344  elapsed time derived from `running` entries (for example `started_at`) when producing a
1345  snapshot/status view.
1346- Add run duration seconds to the cumulative ended-session runtime when a session ends (normal exit
1347  or cancellation/termination).
1348- Continuous background ticking of runtime totals is not required.
1349
1350Rate-limit tracking:
1351
1352- Track the latest rate-limit payload seen in any agent update.
1353- Any human-readable presentation of rate-limit data is implementation-defined.
1354
1355### 13.6 Humanized Agent Event Summaries (Optional)
1356
1357Humanized summaries of raw agent protocol events are optional.
1358
1359If implemented:
1360
1361- Treat them as observability-only output.
1362- Do not make orchestrator logic depend on humanized strings.
1363

Referentna implementacija je napisana u Elixiru—jer kada je kôd praktično besplatan, konačno možete birati jezike prema njihovim prednostima, poput one koje ima Elixir—ali osnovna ideja se može izraziti u jednostavnom Markdown dokumentu. Podstičemo vas da svog omiljenog agenta za kodiranje usmjerite na specifikaciju i navedete ga da na osnovu nje implementira vlastitu verziju.

Prvu verziju Symphonyja činila je samo Codex sesija pokrenuta u tmuxu, koja je periodično provjeravala Linear i pokretala podagente za nove zadatke. Radila je, ali nije bila naročito pouzdana. Druga verzija je bila smještena unutar našeg glavnog repozitorija projekta, koji je bio napravljen baš za agente. Već smo imali postavljen okvir za agente koji im daje potrebne funkcionalnosti i kontekst da kvalitetno rade u ovom repozitoriju, tako da ih je Symphony jednostavno sve povezao.

Kada je osnovna funkcionalnost uspostavljena, iskoristili smo Symphony da napravimo Symphony.

Kada smo interno demonstrirali sistem koji upravlja zadacima i prilaže videozapis kao dokaz svog rada, reakcija je bila izuzetno pozitivna: naš projektni kanal za Symphony je rastao, a timovi širom organizacije počeli su ga spontano koristiti. Osnovni preduslov za eksterno lansiranje u OpenAI-ju jeste da proizvod zadovolji interno tržište. Na osnovu upotrebe koju smo vidjeli u OpenAI-ju, postalo je jasno da Symphony trebamo podijeliti i van kompanije.

Zato smo izdvojili ideju u samostalni SPEC.md i zatražili od Codexa da ga implementira. Za referentnu implementaciju odabrali smo Elixir, relativno rijedak jezik s odličnim primitivama za orkestraciju i nadzor konkurentnih procesa. Codex je Elixir implementaciju izgradio iz jednog pokušaja, a mi smo odatle nastavili iterirati i na specifikaciji i na implementaciji. Da bismo dotjerali specifikaciju, čak smo tražili od Codexa da je implementira i u nekoliko drugih jezika—TypeScript, Go, Rust, Java, Python—te da rezultate iskoristi za prepoznavanje nejasnoća i pojednostavljivanje sistema. Uspio je u svakom jeziku.

Kroz proces izgradnje Codexa uklonili smo mnogo usputne složenosti, poput zavisnosti od specifičnih repozitorija ili Linear MCP-a. Symphony više ne zavisi od naših internih repozitorija ni radnih tokova. Osnovni pristup postao je jednostavan:

Za svaki otvoreni zadatak osiguraj da agent radi u vlastitom radnom prostoru.

Osim što olakšava aktivni rad, radni tok razvoja je sada nešto što agenti poznaju i prate. Radni tok razvoja—rad na problemu, preuzimanje repozitorija, stavljanje u status "u toku" kako bi PM znao da se na tome radi, dodavanje PR-a, prebacivanje u status "Pregled", prilaganje videozapisa itd.—sada je zabilježen u jednostavnoj datoteci WORKFLOW.md. Sve je to proces koji su i ljudi slijedili, ali nikada nije bio dokumentovan. Umjesto oslanjanja na ovaj implicitni skup koraka, sada ga dokumentujemo, a Symphony vodi računa da ga se agenti pridržavaju. To nam omogućava da gradimo agente koji rade uz nas. Ako odlučimo da agenti trebaju da prilože samorefleksiju uz završeni rad, dodat ćemo to u WORKFLOW.md, a Symphony će agente usmjeriti na taj korak.

Također smo dobili priliku da koristimo Codex u režimu app servera⁠(otvara se u novom prozoru), ugrađenom headless režimu za Codex. Ovaj režim nam je omogućio da pokrećemo Codex i programski komuniciramo s njim putem dobro dokumentovanog JSON-RPC API-ja za stvari poput pokretanja niti ili reagiranja na poteze. To je mnogo praktičniji i skalabilniji način od pokušaja interakcije s Codexom putem CLI-ja ili živih tmux sesija.

Codex App Server savršeno je odgovarao našem slučaju upotrebe: koristimo harness koji Codex pruža, a pritom imamo kontrole i priključke za integraciju. Naprimjer, da bismo izbjegli davanje pristupnog tokena za Linear podagentima, koristimo dinamička pozivanja alata⁠(otvara se u novom prozoru) da izložimo sirovu funkciju linear_graphql, koja izvršava proizvoljne zahtjeve u Linearu, bez oslanjanja na MCP ili izlaganja pristupnog tokena kontejnerima.

Šta je sljedeće

Symphony je namjerno urađen kao minimalistički sloj za orkestraciju. Otvoreno objavljujemo njegov kôd kako bismo demonstrirali moć Codex App Servera kada se upari s različitim alatima za radni tok, poput Lineara. Kao takav, ne planiramo održavati Symphony kao samostalan proizvod. Posmatrajte ga kao referentnu implementaciju. Slično kao što su mnogi programeri usmjeravali svoje agente za kodiranje na objavu o harness inženjeringu da bi izgradili svoje repozitorije, nadamo se da ćete usmjeriti svog omiljenog agenta za kodiranje na Symphony specifikaciju⁠(otvara se u novom prozoru) i repozitorij⁠(otvara se u novom prozoru) kako biste izgradili vlastite verzije prilagođene svojim okruženjima.

Snaga dolazi od Codexa i njegovog app servera. Symphony je bio način da povežemo Codex i Linear, dva alata koja smo već koristili, kako bismo riješili problem upravljanja radom. Kako agenti za kodiranje postaju bolji u rezonovanju i praćenju instrukcija, pretpostavljamo da će se usko grlo i u drugim kompanijama pomjeriti sa pisanja koda prema upravljanju radom agenata. Posebno je uzbudljivo to što je barijera za eksperimentisanje s ovim sistemima agenata za kodiranje sada iznenađujuće niska; dovoljno je graditi koristeći Codex.

Pohvale zajednici

Oduševljeni smo što vidimo da inženjerska zajednica koristi Symphony u sedmicama nakon objave, uz više od 15 hiljada GitHub zvjezdica⁠(otvara se u novom prozoru) zaključno s 23. aprilom.